Stochastic Environmental Research and Risk Assessment

Published by Springer Nature
Online ISSN: 1436-3259
Learn more about this page
Recent publications
Localization of sampling fields in Aydinli Bay, Marmara Sea and river connections
Box plot of Igeo values of (I) Cr and (II) Ni in Aydinli Bay, Marmara Sea and river connections between 2016–2020. Letters indicate the years (a) 2020, (b) 2019, (c) 2018, (d) 2017, (e) 2016
Box whisker chart of CF of (I) Cr and (II) Ni in Aydinli Bay, Marmara Sea and river connections between 2016–2020. Letters indicate the years (a) 2020, (b) 2019, (c) 2018, (d) 2017, (e) 2016
Article
Industrial activities are a significant source of metals released into the environment, and it is important to understand their impact. Therefore, this study aimed to assess the ecological and human health risks caused by Cr and Ni in sediments from the industrial marine area in Aydinli Bay, Istanbul, Turkey over five years (2016–2020) with its tributaries including the Marmara Sea and river connections. In this process, some physico- and geochemical properties of sediments, and ecological and human health risks caused by Cr and Ni in sediment were evaluated. Between 2016–2020, the mean concentrations of Cr and Ni changed 4.8 ± 1.6–67.6 ± 32.1 µg/g and 6.9 ± 2.0–8.5 ± 2.3 µg/g, 44.5 ± 69.5–211.1 ± 143.2 µg/g and 5.4 ± 3.4–20.5 ± 15.0 µg/g and 9.3 ± 4.8–81.7 ± 60.8 µg/g and 13.6 ± 2.8–19.3 ± 8.8 µg/g in the bay, the Marmara Sea, and river connections, respectively. The statistical results also indicated that the levels of Cr and Ni correlated with pH, organic matters, and inorganic carbon rather than calcium and magnesium. The geoaccumulation risk index of metals in all three sampling areas were categorized as no contamination, except for 2019 and 2020. Moreover, the contamination factors changed in a wide range from low contaminations to high contaminations. Non-carcinogenic and carcinogenic health risks from two exposure pathways (ingestion and dermal contact) were characterized and indicated no adverse heath effect on adults. On the other hand, the results of ecological and health risk assessments also showed that the Cr and Ni contamination was lower in Aydinli Bay compared to the Marmara Sea and the river connections. These results gave a strong indication that ecosystem-based protection, control and management are neccessary in this region.
 
Article
For securing more water resources, traditional solutions including seawater desalination are limited due to high cost and restricted operating conditions. Thus, acoustic stimulation of rainfall is a potential alternative method due to its low cost and convenient operation. Low-frequency acoustic fields can be used to stimulate rainfall through evoking wavy motion of air particles in clouds which will significantly enhance the process of collision coalescence of cloud droplets and lead to their volume increase. Nevertheless, there is still a lack of rational methods to evaluate the effect of acoustic enhancement of rainfall in field experiments. To this end, in this study, nearly two-month field experiments of acoustic rainfall enhancement with 39 trials were carried out by our research team in the Tibetan Plateau. Statistical analysis was applied to evaluate the effect of acoustic wave on precipitation stimulation. The results of average rainfall intensity distribution using ordinary least square analysis disclose that acoustic interference has a considerable effect on rainfall enhancement. Such a rainfall enhancement effect increases significantly along with the increase of rainfall duration which is the index of cloud precipitation potential. For rainfall events with the duration more than two hours, the average rainfall intensity was improved by 72% with the acoustic wave effect at the experiment site. The phenomena are consistent with the fact that clouds with larger precipitation potential contain more cloud droplets which are beneficial to the acoustic coagulation process.
 
Article
Over the past few years, the concentration of fine particulate matter (PM2.5) in Delhi’s atmosphere has progressively increased, resulting in smog episodes and affecting people’s health. Therefore, accurate and reliable forecasting of PM2.5 concentration is essential to guide effective precautions before and during extreme pollution events. In this work, soft computing techniques, including Artificial Neural Network and Gaussian Process Regression are employed to predict PM2.5 concentrations in Delhi. Four models, namely, multi-layer feed-forward neural network (MLFFNN), General regression neural network, Gaussian process regression with ARD squared exponential kernel (GPARD_sqexp) and Gaussian process regression with ARD rational quadratic kernel (GPARD_rat_quad) are built using meteorological and air quality data corresponding to a two-year period (2015–2016). The results of the study suggested that MLFFNN showed the best prediction performance among the four models, with testing correlation coefficient (R) 0.949, Root mean square error 30.193, Nash–Sutcliffe efficiency index 0.892 and Mean absolute error 18.388. Moreover, sensitivity analysis performed to understand the importance of different input variables reported that PM10, wind speed, air quality index and aerodynamic roughness coefficient (Z0) are the most critical parameters influencing MLFFNN model forecasts. On the whole, the work has demonstrated that the artificial neural network model is more capable of dealing with PM2.5 forecasting in Delhi urban area than the Gaussian process regression model.
 
The study area of Khorramabad, Iran
Time series trends of PM2.5 and O3 levels in 2019 and 2020 in Khorramabad, Iran
(left) Correlation between PM2.5 with O3 levels, and (right) relationship between PM2.5/O3 ratio with PM2.5 during 2019 and 2020 across Khorramabad, Iran
(left) Comparative bar between PM2.5 and O3 averages in 2018, 2019 (before COVID-19) with 2020 (during COVID-19), and (right) Cost reduction in fuel consumption in 2018, 2019 (before COVID-19) with 2020 (during COVID-19) across Khorramabad, Iran
Article
The main objectives of this study were to (i) assess variation within fine particles (PM2.5) and tropospheric ozone (O3) time series in Khorramabad (Iran) between 2019 (before) and 2020 (during COVID-19 pandemic); (ii) assess relationship between PM2.5 and O3, the PM2.5/O3 ratio, and energy consumption; and (iii) estimate the health effects of exposure to ambient PM2.5 and O3. From hourly PM2.5 and O3 concentrations, we applied both linear–log and integrated exposure–response functions, city-specific relative risk, and baseline incidence values to estimate the health effects over time. A significant correlation was found between PM2.5 and O3 (r =−0.46 in 2019, r =−0.55 in 2020, p < 0.05).The number of premature deaths for all non-accidental causes (27.5 and 24.6), ischemic heart disease (7.3 and 6.3), chronic obstructive pulmonary disease (17 and 19.2), and lung cancer (9.2 and 6.25) attributed to ambient PM2.5 exposure and for respiratory diseases (4.7 and 5.4) for exposure to O3 above 10 µg m−3 for people older than 30-year-old were obtained in 2019 and 2020. The number of years of life lost declined by 11.6% in 2020 and exposure to PM2.5 reduced the life expectancy by 0.58 and 0.45 years, respectively in 2019 and 2020. Compared to 2019, the restrictive measures associated to COVID-19 pandemic led to reduction in PM2.5 (−25.5%) and an increase of O3 concentration (+ 8.0%) in Khorramabad.
 
Article
Few studies have examined the impact of climate change on groundwater resources worldwide, especially in developing countries. The objective of this study is to review the effects of climate change on groundwater resources in Iran in order to assess the present conditions and challenges and future directions. To this end, the related studies, especially the peer-reviewed national and international articles, were surveyed. Only the responses of 40 aquifers have been estimated toward climate change in Iran, such that a large gap occurs in this perspective. This is in reference to the alluvial aquifers, and even fewer studies have evaluated the impact of climate change on hard-rock and karst groundwater systems despite their being highly vulnerable to the existing stresses. The conducted studies are primarily small-scale, and inadequate research has been conducted on the effect of climate change on aquifers at national and even regional scales. The impact of climate change on groundwater quality and coastal aquifers has not hitherto been adequately assessed. An ever-increasing temperature and ever-decreasing precipitation over the country have been forecasted, resulting in induced stresses on aquifers, including the decline of groundwater level, storage and recharge. If the current managerial approaches are maintained, the failure threshold of most aquifers will certainly be exceeded, making the looming crisis of water in Iran even worse. Finally, it is recommended to reevaluate the groundwater management policies across the country thoroughly and, thence, propose and execute the new adaptation strategies.
 
Article
Can the ensemble smoother with multiple data assimilation be used to predict discharge in an Alpine karst aquifer? The answer is yes, at least, for the Bossea aquifer studied. The ensemble smoother is used to fit a unit hydrograph simultaneously with other parameters in a hydrologic model, such as base flow, infiltration coefficient, or snow melting contribution. The fitting uses observed discharge flow rates, daily precipitations, and temperatures to define the model parameters. The data assimilation approach gives excellent results for fitting individual events. After the analysis of 27 such events, two average models are defined to be used to predict flow discharge from precipitation and temperature, one model for prediction during spring (when snow melting has an impact) and another one during autumn, yielding acceptable results, particularly for the fall rainfall events. The lesser performance for the spring events may indicate that the snow melting approximation needs to be revised. The results also show that the parameterization of the infiltration coefficient needs further exploration. Overall, the main conclusion is that the ensemble smoother could be used to define a characteristic “signature” of a karst aquifer to be used in forecast analyses. The reasons for using the ensemble smoother instead of other stochastic approaches are that it is easy to use and explain and provides an estimation of the uncertainty about the predictions.
 
Article
Climate change has increased the frequency of drought occurrence in various parts of the world. Drought as a complex phenomenon causes severe impacts on ecological and socio-economic status. Short-term and long-term occurrences of drought have made many regions vulnerable globally. This paper makes an attempt to assess drought vulnerability in Godavari Middle Sub-basin of India. Twenty-four site specific socio-economic and environmental factors were identified based on the extensive literature review. Drought frequency was assessed using standardized precipitation index (SPI). These datasets were divided into training (70%) and testing (30%) data. Frequency ratio (FR) model was utilized to establish relationship among drought conditioning factors and drought frequency. Weights obtained from the FR model were used as input to the adaptive neuro-fuzzy inference systems (ANFIS) model. Drought vulnerability results were validated using the testing data and receiver operating characteristic (ROC). The accuracy of ANFIS models for 1-month (0.957), 3-months (0.882), 6-months (0.964) and 12-months (0.938) showed high suitability of ANFIS model for the assessment of drought vulnerability. The findings revealed that very low normalized difference vegetation index (NDVI) and increasing trend of highest maximum and mean maximum temperature were major environmental factors which influenced high drought vulnerability in the sub-basin. High proportion of area under fallow land, high infant mortality rate (IMR) and moderate literacy rate were identified as major socio-economic factors making watersheds vulnerable during short and long-term droughts. Largest area of the sub-basin was found under high vulnerability for 3-months, followed by 6-months and 12-months droughts. Thus, the study calls for policy intervention towards lessening the impact of drought in highly vulnerable watersheds.
 
Article
The Approximate Bayesian Computation (ABC) provides a powerful tool for signature-domain calibration of hydrological models where hydrological signatures are incorporated into calibration objectives. However, the efficiency of ABC relies strongly on the use of a vector of sufficient signatures that can fully represent relevant information in raw data. The application of ABC with randomly chosen signatures can result in inaccurate calibration results. To fill this gap, a hybrid time- and signature-domain Bayesian inference framework for calibration of hydrological models is proposed. In this framework, a set of approximately sufficient signatures is pursued through simultaneous consideration of the information redundancy analysis (IRA) and discriminatory power analysis (DPA) procedures. While the IRA deals with the information redundancy inherent in the pool of available signatures, DPA quantifies the discriminatory power of a given signature as the reliability and sharpness of the associated probabilistic predictions generated by ABC. The verified residual error scheme in time-domain inference is approximated as the probabilistic model in the acceptance test of ABC. The proposed framework is then tested on the Xin’anjiang rainfall-runoff model applied to the Ren River basin (RRB) of China. The use of IRA and DPA provides a probabilistic model prediction statistically equivalent to that of classical time-domain inference in terms of the reliability and sharpness. The comparison to signature-domain inference using the complete set of hydrological signatures further demonstrates the importance of IRA and DPA in improving the quality of Bayesian model calibration in the signature domain and reducing the total predictive uncertainty. The framework makes it practically possible to maintain adequate accuracy of model predictions produced by signature-domain inference, improving the efficiency of ABC in solving the model calibration problems and consequently promotes the use of ABC in signature-domain model calibration.
 
Article
Quantifying the runoff uncertainty influenced by the climate drivers is essential for water resources management. Runoff in the Tarim River Basin (TRB) originated from the ice and snow meltwater is, thus, sensitive to climate change due to its inherent uncertainties. In this paper, a hybrid mathematical model for uncertainty estimation combing the water-heat coupling model, sensitivity coefficient, uncertainty measurement indices, and an improving standard uncertainty method was proposed to quantify the runoff uncertainty influenced by climate drivers in the TRB from 1965 to 2015. The results showed that the runoff uncertainty in the TRB varies at different time scales and bears strong uncertainty in summer and autumn. In addition, runoff is sensitive to climate change, and when the annual precipitation, annual average temperature, and annual potential evapotranspiration factors change by 1%, the annual runoff changes by 2.8857%, 1.6559%, and −1.8857%, respectively, while the contribution rate of temperature to runoff changes gradually increases. When the changes in precipitation and temperature have the fluctuation uncertainties of 5.76–6.96% and 22.26–66.72%, the runoff fluctuation uncertainties influenced by climate drivers in the Hotan River Basin, Yarkand River Basin, Aksu River Basin, and Kaikong River Basin are 14.31%, 15.03%, 18.23%, and 5.93%, respectively. The proposed hybrid mathematical model can provide a quantitative analysis reference for the runoff uncertainty under climate change in inland river basins in the arid region of Northwest China.
 
Article
In the context of “TO CHAIR” project, this work aims to improve the accuracy of short-term forecasts of maximum air temperature obtained from the https://weatherstack.com/ website. The proposed methodology is based on a state-space representation that incorporates the latent process, the state, which is estimated recursively using the Kalman filter. The proposed model linearly and stochastically relates the forecasts from the website (as a covariate) to the observations of the maximum temperature recorded at the study site. The specification of the state-space model is performed using the maximum likelihood method under the assumption of normality of errors, where empirical confidence intervals are presented. In addition, this work also presents a treatment of outliers based on the ratios between the observed maximum temperature and the website forecasts.
 
Article
Thermal bioclimate is a defining factor of agricultural production, ecological condition, public health, and species distribution. This study aimed at assessing the possible changes in the Middle East and North African (MENA) thermal bioclimate for two shared socioeconomic pathways (SSPs), SSP1-1.9 and SSP1-2.6, representing a temperature rise restricted to 1.5 and 2.0°C above the pre-industrial level at the end of the century. Therefore, the study explains the probable least change in bioclimate due to climate change and what might happen for a 0.5°C temperature rise above the 1.5°C addressed by Paris Climate Agreement. A multimodel ensemble of eight global climate models was employed for this purpose. The results indicated a 0.5°C further increase in temperature above the 1.5°C temperature rise threshold would cause a nearly 0.8 to 1.0°C increase in temperature in some parts of MENA, indicating a faster than global average increase in temperature in the region for higher temperature rise scenarios. Climate change would cause a decrease in thermal seasonality by 2-6% over nearly 90% of the study area. The diurnal temperature would decrease by 0.1 to 0.4°C over the entire south, while the annual temperature range would decrease by 0.5 to 1.5°C over a large area in the north. This would cause a decrease in isothermality nearly by 1% over most areas. The area with decreasing isothermality would expand by almost 150% for a further temperature rise by 0.5°C. The results indicate a substantial change in bioclimate in MENA for a minor temperature change.
 
Article
Agricultural droughts are a prime concern for economies worldwide as they negatively impact the productivity of rain-fed crops, employment, and income per capita. In this study, Standard Precipitation Index (SPI) has been used to evaluate different drought indices for Rajasthan of India. In agricultural, hydrological, and meteorological applications such as irrigation scheduling, crop simulation, water budgeting, reservoir operations, and weather forecasting, the accurate estimation of the drought indices such as the Standardized Precipitation Index (SPI) plays an important role. Thus, the present study was conducted to examine the feasibility and effectiveness of the Random Subspace (RSS) model and its hybridization with the M5 Pruning tree (M5P), Random Forest (RF), and Random Tree (RT) to estimate the SPI at 3, 6, and 12 droughts during 2000-2019. Performances of RSS and hybridized algorithms were assessed and compared using performance indicators (i.e., MAE, RMSE, RAE, RRSE, and R 2) and various graphical interpretations. Results indicated that the RSS-M5P provided the most accurate SPI prediction (MAE = 0.497, RMSE = 0.682, RAE = 81.88, RRSE = 87.22, and R 2 = 0.507 for SPI-3; MAE = 0.452, RMSE = 0.717, RAE = 69.76, RRSE = 85.24, and R 2 = 0.402 for SPI-6. And MAE = 0.294, RMSE = 0.377, RAE = 55.79, RRSE = 59.57, and R 2 = 0.783 for SPI-12) compare to RSS alone, RSS-RF, and RSS-RT models for study the drought situation in Jaisalmer Rajasthan. The M5P algorithms have improved the performance of the RSS structure.
 
Article
Effective flood forecasting can significantly prevent losses related to severe floods. However, nonlinear and dynamic flooding processes are difficult to simulate using traditional static networks, necessitating the use of dynamic networks with feedback connections and time delays. In this paper, we introduced a general framework to uniformly describe different dynamic networks, including the focused time delay network (FTDN), layered recurrent network (LRN), and nonlinear autoregressive network with exogenous inputs (NARX) network, which we used to construct 1080 models with six different lead times, ten neuron numbers, and six different time delays to forecast the reservoir inflow in east China. Three hybrid algorithms were utilized for training the models: steepest descent (SD), Broyden–Fletcher–Goldfarb–Shanno (BFGS), and Levenberg–Marquardt (LM) mixing with real-time recurrent learning (RTRL), respectively, which is an online implementation algorithm suitable for real-time flood forecasting. Early stopping was applied to improve model generalizations. In addition to the number of hidden layer neurons, we analyzed the impact of input time delays on the model error. The numerical and experimental results indicated that the training errors of the models exhibited significant change trends with the number of neurons and time delays. The BFGS algorithm demonstrated better stability and convergence than the SD and LM algorithms. For 1–6 h lead times, the NARX-based real-time flood forecasting model achieved the highest accuracy though this advantage is not obvious.
 
Article
Drought is one of the most complex natural hazards. Therefore, precise drought monitoring and forecasting are the biggest tasks for hydrologists and environmentalists. Under grid data structure, this paper provides a new drought index—the adaptive standardized precipitation index (ASPI), for the evolution of drought, inferring its spatio-temporal patterns and detecting trends. The methodology of the proposed index is based mainly on dynamic time warping clustering algorithm and dynamic principal components. Historical simulated precipitation data from the Australian community climate and earth-system simulator model of coupled model intercomparison project 6 of 727 grid points scattered around the Tibet Plateau has been considered. Results show that as the time scale increases, the severe and extreme drought trends have increased significantly. Further, the significant decreasing magnitude in ASPI reveals the persistence of future drought in the Tibet Plateau region. From a data mining point of view, the outcomes associated with this research recommend the endorsement of ASPI for effective and precise drought monitoring under grid data structure.
 
Article
With the frequent recurrence of hydroclimatic hazards, such as rainfall-induced floods and landslides, it is essential to look at the spatio-temporal evolution of rainfall trends and teleconnections of regional rainfall with global climatic indices. The present study is carried out in two climatologically contrasting terrains, the humid regions in the western side of South-Peninsular India (SPI-W) and semi-arid to arid regions in the eastern side of South-Peninsular India (SPI-E). Trends in the rainfall were studied over a long-term (1901–2020) gridded rainfall data, and change points were detected using the Pettitt's test. An expanding-sliding window trend analysis based on Kendall's Taub was carried out to decode the time evolution of rainfall trends and to differentiate consistent gradual monotonic trends from step changes. Two distinct change points were observed in the rainfall, the first in the 1960s and second in 1990s. SPI-E manifested a strong positive trend in the monsoon rainfall after 1990's while SPI-W demonstrated a weakening in rainfall after 1960's. The regionally diverse trends during the recent epochs are evaluated along with IOD (Indian Ocean Dipole) and it was observed that there is a significant increase in co-occurrence of positive rainfall anomaly, positive IOD and positive ENSO (El Niño Southern Oscillation) events after 1990. Increase in positive IOD events could be associated with the changes in the regional rainfall during these recent epochs. The trends in monthly and annual rainfall showed high sensitivity to data periods and data lengths, highlighting the need to perform such comprehensive analysis for the planning of reservoir operations, water management and agricultural activities.
 
Article
Savanna fire has many types: Savanna woody, Savanna vegetation, and grassland. In this paper, Savanna vegetation is studied, characterized by low trees and high grass. It grows in hot and seasonally dry conditions. The Savanna vegetation is described by relating to the environment and climate. Savanna vegetation is considered a metastable mixture of trees and grass and is advanced to explain stability. The Savanna vegetation is modeled with first-order linear differential equations having grass, trees, and sapling (young trees) as components. Furthermore, the model is evaluated numerically by integrating the global search technique Sine-Cosine algorithm and local search technique Interior point algorithm. Comprehensive numerical experiments are conducted to analyze numerical results. To validate solution of proposed technique, Runge-Kutta order four method isolution is taken as a reference solution. The solutions are compared graphically with the results of the reference technique. Performance indicators Mean Absolute Deviation, Root Mean Squared Error, and Error in Nash-Sutcliffe Efficiency are implemented to verify consistency, and multiple independent runs are drawn. Furthermore, the scheme is evaluated through convergence graphs as well.
 
Article
Streamflow simulation in a snow dominated basin is complex due to the presence of a high number of interrelated hydrological processes. This complexity is affected by the delayed responses of the catchment to snow accumulation and snow melting processes. In this study, long short-term memory (LSTM) and artificial neural network (ANN) models were utilized for rainfall–runoff simulation in a snow dominated basin, the Carson River basin in the United States (US). The input structure of the models was determined using the simulated annealing algorithm with a naïve Bayes model from a high dimensional feature space to represent the long-term impacts of historical events (i.e. the hysteresis effect) on current observations. Further, to represent the different responses of the catchment in the model structure, a base flow separation method was included in the simulation framework. The obtained performance indices, root mean square error, percentage bias, Nash–Sutcliffe and Kling–Gupta efficiencies are 0.331 m³ s⁻¹, 13.00%, 0.848, and 0.852 for the ANN model and 0.235 m³ s⁻¹, − 0.80%, 0.923, and 0.934 for the LSTM model, respectively. The proposed methodology was found to be promising for improving the streamflow simulation capability of LSTM and ANN models by only considering precipitation, temperature, and potential evapotranspiration as input variables. Analysing the flow duration curves indicated that the LSTM model is more efficient in representing different flow dynamics within the basin due to embedded cell states. Further, the uncertainty and reliability analyses were conducted by using expanded uncertainty (U95\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$U_{95}$$\end{document}), reliability, and resilience indices. The obtained U95\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$U_{95}$$\end{document}, reliability and resilience indices are 1.78–1.72 m³ s⁻¹, 31.28–66.67% and 11.58–38.27% for the ANN and LSTM models, respectively, showed that the LSTM model produced less uncertainty and is more reliable. However, while lacking a memory component, the proposed methodology significantly contributes to the simulation capability of the ANN model in rainfall–runoff modelling. The results of this study indicated that the proposed methodology could enhance the learning capabilities of machine learning models in rainfall–runoff simulation.
 
Article
An increasing interest in models for multivariate spatio-temporal processes has been noted in the last years. Some of these models are very flexible and can capture both marginal and cross spatial associations amongst the components of the multivariate process. In order to contribute to the statistical analysis of these models, this paper deals with the estimation and prediction of multivariate spatio-temporal processes by using multivariate state-space models. In this context, a multivariate spatio-temporal process is represented through the well-known Wold decomposition. Such an approach allows for an easy implementation of the Kalman filter to estimate linear temporal processes exhibiting both short and long range dependencies, together with a spatial correlation structure. We illustrate, through simulation experiments, that our method offers a good balance between statistical efficiency and computational complexity. Finally, we apply the method for the analysis of a bivariate dataset on average daily temperatures and maximum daily solar radiations from 21 meteorological stations located in a portion of south-central Chile. Supplementary information: The online version contains supplementary material available at 10.1007/s00477-022-02266-3.
 
Article
Flooding is one of the most destructive natural catastrophes that can strike anywhere in the world. With the recent, but frequent catastrophic flood events that occurred in the narrow stretch of land in southern India, sandwiched between the Western Ghats and the Arabian Sea, this study was initiated. The goal of this research is to identify flood-vulnerable zones in this area by making the local self governing bodies as the mapping unit. This study also assessed the predictive accuracy of analytical hierarchy process (AHP) and fuzzy-analytical hierarchy process (F-AHP) models. A total of 20 indicators (nine physical-environmental variables and 11 socio-economic variables) have been considered for the vulnerability modelling. Flood-vulnerability maps, created using remotely sensed satellite data and geographic information systems, was divided into five zones. AHP and F-AHP flood vulnerability models identified 12.29% and 11.81% of the area as very high-vulnerable zones, respectively. The receiver operating characteristic (ROC) curve is used to validate these flood vulnerability maps. The flood vulnerable maps, created using the AHP and F-AHP methods, were found to be outstanding based on the area under the ROC curve (AUC) values. This demonstrates the effectiveness of these two models. The results of AUC for the AHP and F-AHP models were 0.946 and 0.943, respectively, articulating that the AHP model is more efficient than its chosen counterpart in demarcating the flood vulnerable zones. Decision-makers and land-use planners will find the generated vulnerable zone maps useful, particularly in implementing flood mitigation plans.
 
Article
Soil temperature (ST) is one of the vital parameters of soil, which can affect many of the processes occurring in soil. Accurate techniques are therefore needed to know the ST regime at different soil depths. The present study strived to model the daily ST of the Isfahan and Rasht stations, Iran, at four multiple depths (5, 10, 50, 100 cm). To achieve this goal, the standalone gene expression programming (GEP) and support vector machine (SVM) models were applied. In this context, two types of input patterns were taken into consideration including weather parameters- and lagged ST data-based patterns. Additionally, two different pre-processing methods comprising of entropy and τ-Kendall were utilized to discern the most important weather parameters under the weather parameters-based patterns. It was found that both the employed pre-processing techniques introduced various input combinations as the most important weather parameters. In general, entropy-based GEP and SVM models slightly presented higher accuracy compared to the τ-Kendall-based standalone models at different depths. Then, wavelet (W)-based coupled models were proposed by hybridizing the W theory on the GEP and SVM in order to develop the hybrid W-GEP and W-SVM approaches. The outcomes demonstrated that the implemented coupled models outperformed the single GEP and SVM in modeling the ST of various depths under both the defined input patterns.
 
Pandemics and uncertainty (1996Q1–2021Q3)
Source: Author’s own calculation based on WPUI (2020) and Ahir (2018). The World Pandemic Uncertainty Index (WPUI) is the simple average of WPUI of 143 countries
Quantile-on-Quantile (QQ) estimations of the slope coefficient α1 (θ, τ) Impact of Pandemic Uncertainty (PUN) on CO2 Emissions (CO2)
Checking the Robustness of the QQ Approach by Comparing QR and QQ Regression Estimations
Article
The recent COVD-19 pandemic has been a major shock, affecting various macroeconomic indicators, including the environmental quality. The question of how the pandemics-related uncertainty will affect the environment is of paramount importance. The study analyzes the asymmetric impact of pandemic uncertainty on CO2 emissions in top-10 polluted economies (China, USA, India, Russia, Germany, Japan, Iran, South Korea, Indonesia, and Saudi Arabia). Taking panel data from 1996 to 2018, a unique technique, 'Quantile-on-Quantile (QQ)', is employed. CO2 emissions are used as an indicator of environmental quality. The outcomes define how the quantiles of pandemic uncertainty impact the quantiles of carbon emissions asymmetrically by providing an effective paradigm for comprehending the overall dependence framework. The outcomes reveal that pandemic uncertainty promotes environmental quality by lowering CO2 emissions in our sample countries at various quantiles. However, Japan shows mixed findings. The effect of PUN on CO2 is substantially larger in India, Germany, and South Korea and lower in Russia and Saudi Arabia. Furthermore, the magnitude of asymmetry in the pandemic uncertainty-CO2 emissions association differs by economy, emphasizing that government must pay particular caution and prudence when adopting pandemics-related uncertainty and environmental quality policies.
 
Article
Due to the importance of the forest fire susceptibility zonation for proper management of this environmental hazard, this study presents two different hybrids of artificial neural network (ANN) for spatial analysis of forest fire in northern Iran. To this end, ant colony optimization (ACO) and biogeography-based optimization (BBO) evolutionary algorithms are synthesized with ANN to optimize its computational parameters. In this work, slope aspect, elevation, land use, wind speed, soil type, plan curvature, temperature, distance to river, distance from road, distance from village, slope degree, topographic wetness index, annual mean evaporation, annual mean rainfall, and normalized difference vegetation index are considered as the forest fire ignition factors. Notably, the frequency ratio model is used to demonstrate the spatial interaction between the forest fire and ignition factors. The findings showed that the BBO and ACO could improve the accuracy of the ANN from 81.3% to 84.0 and 83.9%, respectively. Moreover, the ranking results (obtained by applying mean square error, area under the curve, and mean absolute error indices) revealed the superiority of the BBO-ANN.
 
Article
With wind power providing an increasing amount of electricity worldwide, the quantification of its spatio-temporal variations and the related uncertainty is crucial for energy planners and policy-makers. Here, we propose a methodological framework which (1) uses machine learning to reconstruct a spatio-temporal field of wind speed on a regular grid from spatially irregularly distributed measurements and (2) transforms the wind speed to wind power estimates. Estimates of both model and prediction uncertainties, and of their propagation after transforming wind speed to power, are provided without any assumptions on data distributions. The methodology is applied to study hourly wind power potential on a grid of $$250\times 250$$ 250 × 250 m $$^{2}$$ 2 for turbines of 100 m hub height in Switzerland, generating the first dataset of its type for the country. We show that the average annual power generation per turbine is 4.4 GWh. Results suggest that around 12,000 wind turbines could be installed on all 19,617 km $$^{2}$$ 2 of available area in Switzerland resulting in a maximum technical wind potential of 53 TWh. To achieve the Swiss expansion goals of wind power for 2050, around 1000 turbines would be sufficient, corresponding to only 8% of the maximum estimated potential.
 
Article
Increased greenhouse gas concentration in the atmosphere has led to significant climate warming and changes in precipitation and temperature characteristics. These trends, which are expected to continue, will affect water infrastructure and raise the need to update associated planning and design policies. The potential effects of climate change can be addressed, in part, by incorporating outputs of climate model projections into statistical assessments to develop the Intensity Duration Frequency (IDF) curves used in engineering design and analysis. The results of climate model projections are available at fixed temporal and spatial resolutions. Model results often need to be downscaled from a coarser to a finer grid spacing (spatial downscaling) and/or from a larger to a smaller time-step (temporal downscaling). Machine Learning (ML) models are among the methods used for spatial and temporal downscaling of climate model outputs. These methods are more frequently used for spatial downscaling; fewer studies explore temporal downscaling. In this study, multiple ML models are evaluated to temporally downscale precipitation time-series (available at 3-h time steps) generated by several regional climate models of the North American Regional Climate Change Assessment Program (NARCCAP) under a high-carbon-emission projection. The temporally downscaled time-series for 2-h, 1-h, 30-min, and 15-min durations are intended for subsequent statistical analysis to generate current- and future-climate IDF curves for Maryland. In this study, the behavior of the ML models is explored by assessing performance in predicting large target response quantities, identifying systematic trends in errors, investigating input/output relationships using response functions, and leveraging conventional performance metrics.
 
Article
This paper investigates the effects of climate change on the hydrological and meteorological parameters of the Navrood Watershed (a Caspian Hyrcanian forest watershed) in the north of Iran. Outputs of seven CMIP6 GCMs (Tmin, Tmax, and precipitation) under two scenarios, SSP2-4.5 and SSP5-8.5, were utilized. This study considered the historical period (1994–2014), the near future (2025–2049), the middle future (2050–2074), and the far future (2075–2099). The EDCDFm and MBA methods were used for bias correction of the outputs of GCMs and combining GCMs, respectively. The LARS-WG model was used for statistical downscaling. the runoff was calculated by the IHACRES model. Based on the results, the annual Tmin under SSP2-4.5 and SSP5-8.5 will increase as much as 1.04 °C and 1.25 °C in the near future, 1.55 °C and 2.48 °C in the middle future, and 2.09 °C and 4.11 °C in the far future, respectively. The annual Tmax under SSP2-4.5 and SSP5-8.5 will increase as much as 1.59 °C and 1.38 °C in the near future, 1.98 °C and 3.02 °C in the middle future, and 2.58 °C and 4.94 °C in the far future, respectively. The annual precipitation (PCP) under SSP2-4.5 and SSP5-8.5 will increase as much as 6.81% and 7.11% in the near future, 6.15% and 4.43% in the middle future, and 8.63% and 6.58% in the far future, respectively. Finally, the annual runoff under SSP2-4.5 and SSP5-8.5 will increase as much as 16.3% and 15.4% in the near future, 14.8% and 10.6% in the middle future, and 19.2% and 15.1% in the far future, respectively.
 
Article
Accurate forecasting of wind speed (WS) data plays a crucial role in planning and operating wind power generation. Nowadays, the importance of WS predictions overgrows with the increased integration of wind energy into the electricity market. This work proposes machine learning algorithms to forecast a one-hour ahead short-term WS. Forecasting models were developed based on past time-series wind speeds to estimate the future values. Adaptive Neuro-Fuzzy Inference System (ANFIS) with Fuzzy c-means, ANFIS with Grid Partition, ANFIS with Subtractive Clustering and Long Short-Term Memory (LSTM) neural network were developed for this purpose. Three measurement stations in the Marmara and Mediterranean Regions of Turkey were selected as the study locations. According to the hourly WS prediction, the LSTM neural network based on the deep learning approach gave the best result in all stations and among all models applied. Mean Absolute Error values in the testing process were obtained to be 0.8638, 0.9603 and 0.5977 m/s, and Root Mean Square Error values were found to be 1.2193, 1.2573 and 0.7531 m/s from the LSTM neural network model for measuring stations MS1, MS2, and MS3, respectively. In addition, the analyzes revealed that the best correlation coefficient (R) results among the algorithms in the test processes were obtained to be 0.9498, 0.9147, and 0.8897 for the MS1, MS2, and MS3 measurement stations, respectively. In this regard, it is shown that the LSTM method gave high sensitive results and mainly provided greater performance than the ANFIS models for one hour-ahead WS estimations.
 
Article
The occurrence and intensity of climatic and hydrologic extreme events, as indicators of climate change, are increasing in most parts of arid and semi-arid regions, including Ardabil province, Iran. Recent studies have revealed the need for the multidimensional assessment of flood disasters in this area. Consequently, this present study was conducted to provide comprehensive information on the flood vulnerability of 26 watersheds in Ardabil province. Here, six components, including meteorological, hydrological, physical-environmental, social, economic, and countermeasures, were computed at a watershed scale based on 19 different criteria. Finally, the flood vulnerability index (FVI) for each watershed was calculated. The results revealed the need for different management approaches for flood hotspots based on the vulnerability to the six components studied. The integrated FVI showed that 46.97%, 33.63%, 18.10%, 1.20%, and 0.10% of the province have very high, high, medium, low, and very low flood vulnerability, respectively. The spatial mapping also revealed that all study areas were under flood stress, except small parts in central, east, and north. The preliminary version of the flood vulnerability atlas is presented, which estimates the flood disaster risk throughout the province. In addition, the developed regional framework in this study also allows for more comprehensive and extensive dataset analysis.
 
Article
We propose a general methodology to characterize a non-stationary random process that can be used for simulating random realizations that keep the probabilistic behavior of the original time series. The probability distribution of the process is assumed to be a piecewise function defined by several weighted parametric probability models. The weights are obtained analytically by ensuring that the probability density function is well defined and that it is continuous at the common endpoints. Any number of subintervals and continuous probability models can be chosen. The distribution is assumed to vary periodically in time over a predefined time interval by defining the model parameters and the common endpoints as truncated generalized Fourier series. The coefficients of the expansions are obtained with the maximum likelihood method. Different sets of orthogonal basis functions are tested. The method is applied to three time series with different particularities. Firstly, it is shown its good behavior to capture the high variability of the precipitation projected at a semiarid location of Spain for the present century. Secondly, for the Wolf sunspot number time series, the Schwabe cycle and time variations close to the 7.5 and 17 years are analyzed along a 22-year cycle. Finally, the method is applied to a bivariate time series that contains (1) freshwater discharges at the last regulation point of a dam located in a semiarid zone in Andalucía (Spain) which is influenced not only by the climate variability but also by management decisions and (2) the salinity at the mouth of the river. For this case, the analysis, that was combined with a vectorial autoregressive model, focus on the assessment of the goodness of the methodology to replicate the statistical features of the original series. In particular, it is found that it reproduces the marginal and joint distributions and the duration of sojourns above/below given thresholds.
 
Article
After standard seawalls have been built successfully, fishery ports become the structures most easily damaged during a typhoon. Estimating the risk of fishery ports against typhoons would be useful for identifying weaknesses and implementing corrective measures to protect fishing boats from a typhoon. This study describes a versatile methodology for conducting this type of quantitative assessment at fishery ports. The Dongsha fishery port in Zhejiang Province was selected as a case study to test the results derived from a high-precision Hydrodynamic Flexible Mesh model coupled with the Spectral Wave model. First, typhoon characteristics were assessed based on historical typhoons in the study area, and then, the wind, tide, storm surge, and waves were modeled and tide-surge interactions were investigated. Through comparisons of the destructive parameters from the typhoon assessment with the design and structural parameters of the fishery port, the level of the Dongsha fishery port against typhoons was determined to be 12, and the main weaknesses of the port’s defenses were found to be located near feature points T2, T3, T8, and T15. The results obtained demonstrate that the proposed methodology can be used to acquire valuable information on the risk of fishery ports against typhoons.
 
Article
Simultaneous identification of the location and release history of pollutant sources in river networks is an ill-posed and complicated problem, particularly in the case of multiple sources with time-varying release patterns. This study presents an innovative method for solving this problem using minimum observational data. To do so, a procedure is proposed in which, the number and the suspected reaches to the existence of pollutant sources are determined. This is done by defining two different types of monitoring stations with an adaptive arrangement in addition to real-time data collection and reliable flow and transport mathematical models. In the next step, the sources’ location and their release history are identified by solving the inverse source problem employing a geostatistical approach. Different scenarios are discussed for different conditions of number, release history and location of pollutant sources in the river network. Results indicated the capability of the proposed method in identifying the characteristics of the sources in complicated cases. Hence, it can be effectively used for the comprehensive monitoring of river networks for different purposes.
 
Article
In the higher latitudes of the northern hemisphere, ice jam related flooding can result in millions of dollars of property damages, loss of human life and adverse impacts on ecology. Since ice-jam formation mechanism is stochastic and depends on numerous unpredictable hydraulic and river ice factors, ice-jam associated flood forecasting is a very challenging task. A stochastic modelling framework was developed to forecast real-time ice jam flood severity along the transborder (New Brunswick/Maine) Saint John River of North America during the spring breakup 2021. Modélisation environnementale communautaire—surface hydrology (MESH), a semi-distributed physically-based land-surface hydrological modelling system was used to acquire a 10-day flow forecast. A Monte-Carlo analysis (MOCA) framework was applied to simulate hundreds of possible ice-jam scenarios for the model domain from Fort Kent to Grand Falls using a hydrodynamic river ice model, RIVICE. First, a 10-day outlook was simulated to provide insight on the severity of ice jam flooding during spring breakup. Then, 3-day forecasts were modelled to provide longitudinal profiles of exceedance probabilities of ice jam flood staging along the river during the ice-cover breakup. Overall, results show that the stochastic approach performed well to estimate maximum probable ice-jam backwater level elevations for the spring 2021 breakup season.
 
Article
The Great Plains Low-Level Jet (GPLLJ) system consists of very strong winds in the lower troposphere that transport a huge amount of moisture from the Gulf of Mexico to the American Great Plains. This paper aims to study the extremes of the Transported Moisture (TM) from the GPLLJ source region to the jet domain; and, for low and high TM, to analyze the extremal dependence between the upper tail of the precipitation in the GPLLJ sink region and the lower tail of the tropospheric stability in that region, which is known as tropospheric instability. The declustered extremes of TM were analyzed using Peaks Over Threshold (POT). A non-stationary Exponential model was fitted to the cluster maxima. Estimated return levels show that the extremes of TM are expected to decrease in the future. This is meteorologically congruent with the known displacement of the western edge of the North Atlantic Subtropical High, which controls atmospheric circulation in the North Atlantic, and to a higher scale with the change of phase from negative to positive of the Atlantic Multidecadal Oscillation. Bilogistic and Logistic models were fitted to the extremes of (tropospheric instability, precipitation) for low and high TM, respectively. The extremal dependence between tropospheric instability and precipitation proves to be stronger in the case of high TM. This confirms that dynamical instability is the most important parameter for achieving high values of precipitation once there is a mechanism that allows the continuous supply of large amounts of moisture, such as the derived from a low-level jet system.
 
Article
Forecasting drought is essential for water resource management when policymakers encounter a water shortage and high demand. This research utilizes the Bayesian averaging model (BMA) based on multiple hybrid artificial neural network models including ANN- water strider algorithm (WSA), ANN-particle swarm optimization (ANN-PSO), ANN-salp swarm algorithm (ANN-SSA), and ANN-sine cosine algorithm (ANN-SCA) to forecast standardized precipitation index as one of the most important indices of drought. The models were used to forecast Standardized Precipitation Index (SPI) SPI (1), SPI (3), SPI (6), and SPI (12) in the Wadi Ouahrane basin of Algeria. The WSA, SSA, SCA, and PSO were applied to set model parameters of the ANN model. The inputs were lagged El Niño–Southern Oscillation (ENSO), Pacific decadal oscillation (PDO), North Atlantic oscillation index (NAO), and southern oscillation index (SOI). The gamma test was integrated with WSA to identify the best input scenario for forecasting drought. The BMA for forecasting SPI (1) improved the MAE attained by the ANN-WSA, ANN-SSA, ANN-SCA, ANN-PSO, and ANN models 26, 33, 38, 42, and 46%, respectively in the testing level. The MAE of BMA for forecasting SPI (6) was 40, 42, 46, 48, and 62% lower than those of ANN-WSA, ANN-SSA, ANN-SCA, ANN-PSO, and ANN-PSO. Also, the BMA and ANN-WSA had the best accuracy among other models for forecasting SPI (6) and SPI (12). This study indicated that the WSA, SSA, SCA, and PSO improved the accuracy of the ANN models for forecasting drought.
 
Results of grouped analyses by sex and age on the association between a 10 μg/m³ increases in the average concentration of O3-8 h and daily outpatient visits for urticaria
Shows the season-stratified results from a single-day lag and a multi-day cumulative lag
Article
Although mounting evidence suggests that short-term exposure to ozone increases the risk of respiratory disease, cardiovascular disease and mortality, there are few studies comparing the effects of ozone in relation to urticaria in China. To evaluate the risks for urticaria exacerbations related to ambient ozone measured as 1-h maximum (O3-1 h max), maximum 8-h (O3-8 h max) and 24-h average (O3-24 h avg) concentrations. We calculated three metrics of ozone, 1-h maximum, maximum 8-h and 24-h average based on the hourly data. Generalized additive models with Poisson regression incorporating natural spline functions were used to investigate short-term effects on urticaria associated with ambient ozone pollution in Lanzhou, China, using 5 years of daily data (2013–2017). We also examined the association by sex, age and season. In all-year analyses, a 10 μg/m³ increase in daily average, O3-1 h max, O3-8 h max and O3-24 h avg at lag2 corresponded to an increase of 0.58%(95%CI: 0.26, 0.90), 0.82% (95%CI: 0.47, 1.16) and 2.17% (95%CI: 1.17, 2.79), respectively. The elderly populations and females were susceptible to O3, and the associations between ozone and urticaria appeared to be more evident during warm season than in the cold season. In conclusion, these results indicated that ozone, as a widespread pollutant, affects outpatient visits for urticaria in Lanzhou.
 
Geographic distribution of the weather stations considered in this research. Analysed stations are shown by crosses
Example of a regression analysis of the maximum rainfall intensity and wind speed regarding the considered duration, obtained from data series of various recording intervals
Implementation examples of the proposed approach, obtaining the extreme values of rainfall intensity for different recording intervals at the Santiago EOAS station (Santiago de Compostela, Galicia, Spain)
Implementation examples of the proposed approach, obtaining the extreme values of wind speed for different recording intervals at the Santiago EOAS station (Santiago de Compostela, Galicia, Spain)
Article
A wide variety of engineering applications requires the use of maximum values of rainfall intensity and wind speed related to short recording intervals, which can often only be estimated from available less exhaustive records. Given that many locations lack exhaustive climatic records that would allow accurate empirical correlations between different recording intervals to be identified, generic equations are often used to estimate these extreme values. The accuracy of these generic estimates is especially important in fields such as the study of wind-driven rain, in which both climatic variables are combined to characterise the phenomenon. This work assesses the reliability and functionality of some of these most widespread generic equations, analysing climatic datasets gathered since 2008 in 109 weather stations in Spain and the Netherlands. Considering multiple recording intervals at each location, it is verified that most of these generic estimations, used especially in the study of wind-driven rain, have functional limitations and can cause significant errors when characterising both variables for subdaily intervals and extreme conditions. Finally, an alternative approach is proposed to accurately extrapolate extreme values of both variables related to any subdaily recording interval in a functional manner and from any available records.
 
Article
Knutson et al. (BAMS 101:E303–E322, 2020) combined results from many studies to produce distributions of how tropical cyclone frequency and average intensity may change in the future. These distributions can be applied to risk models by using them to simulate multiple realisations of possible changes in future storm climate. Ideally the simulations would be performed to maintain consistency between the changes in frequency and average intensity, but it is not obvious how to do that, or whether it is even possible. Considering North Atlantic cyclones, we test three methods for simulating from Knutson et al. and find two that are consistent and one that is not. Using the best of the methods we find that there are no future scenarios in which weak storms increase in frequency while very intense storms decrease in frequency. We then apply changes in frequency and average intensity to a risk model for annual maximum intensity. After integrating over the uncertainty, we find that on a conditional basis all storms become more intense under climate change, and that the annual probability of the most intense storms increases by 19%. Annual maximum intensity decreases at intermediate levels of intensity as a result of the non-linear propagation of uncertainty. We also show that the changes in risk implied by the Knutson et al. results cannot be well approximated if the propagation of uncertainty is ignored. Future work should involve updating these results with tropical cyclone projections from the latest high-resolution climate models.
 
Article
Drought imposes severe, long-term effects on global environments and ecosystems. A better understanding of how long it takes a region to recover to pre-drought conditions after drought is essential for addressing future ecology risks. In this study, drought-related variables were obtained using remote sensing and reanalysis products for 2003 to 2016. The meteorological drought index [standardized precipitation evapotranspiration index (SPEI)] and agricultural drought index [vegetation condition index (VCI)] were employed to estimate drought duration time (DDT) and drought recovery time (DRT). To the basin’s west, decreasing rainfall and increasing potential evapotranspiration led to decreasing SPEI. On the east side, decreasing soil moisture from each depth effects vegetation condition, which results in a decreasing gross primary productivity and VCI. Extreme meteorological drought events are likely to occur in the basin’s northeastern and middle western areas, while the southern basin is more likely to suffer from extreme agricultural drought events. The mean SPEI-based DDT (2.45 months) was smaller than the VCI-based DDT (2.97 months); the average SPEI-based DRT (2.02 months) was larger than the VCI-based DRT (1.63 months). Most of the area needs 1 or 2 months to recover from drought except for the basin’s northwestern area, where the DRT is more than 8 months. DDT is the most important parameter in determining DRT. These results provide useful information about regional drought recovery that will help local governments looking to mitigate potential environmental risks and formulate appropriate agricultural policies in Lake Victoria Basin.
 
Article
Accomplishing the objectives of optimal and sustainable management in the agricultural sector is increasingly getting complicated, which includes increasing the sustainable productivity of water and energy resources, ensuring food security, decreasing contaminations from fertilizers and chemical pesticides, and environmental destruction. The present research deals with designing the relationships between the water-energy-food nexus approach with economic and environmental objectives to accomplish the aforementioned objectives. Hence, a multi-objective programming model was developed to maximize the water-energy-food nexus index and farmers' gross margin, minimize the use of chemical fertilizers (nitrogen and phosphate), and minimize the use of chemical pesticides (herbicides) by considering the balancing constraint to groundwater resources. Afterward, the proposed multi-objective model was solved using the augmented ε-constraint method, and then the total of strong and efficient Pareto solutions was extracted. Then, the best solution was chosen using the TOPSIS method and assigning a weight of equal importance to the desired objectives. The irrigation network of Jiroft plain in Kerman province in Iran was chosen as the study area to implement such a system. The obtained results indicated that the optimal and sustainable management in the agriculture sector can be hopeful using the proposed approach in the current research. On the other hand, the results revealed that despite considering the economic objective in the proposed system, the farmers' profits can be significantly decreased. Thus, the realization of optimal and sustainable management in the agricultural sector is not possible without the implementation of policies for increasing the economic incentive of farmers.
 
Article
Climate change has caused a rise in temperature extremes, particularly heatwaves, in recent decades. Physical-empirical models are developed in this study using two classical machine learning algorithms, namely decision tree (DT) and random forests, and a novel hybrid technique consists of Ada-Boost Regression and decision tree (ABR-DT) for forecasting annual heatwave days (HWDs) of Iran from synoptic predictors. The daily temperature data of Princeton Meteorological Forcing were extracted for 27 points to estimate the annual number of HWDs, and the National Centers for Environmental Prediction reanalysis data were used as predictors. The major synoptic variables were extracted for four pressure levels (e.g., 300, 500, 850, and 1000 hPa) and three monthly time lags. The Principal Component Analysis was employed to reduce the diverse predictors and their features to the most optimal structure. The grid point-based performance evaluation revealed the superiority of ABR-DT, which showed a correlation coefficient (CC) of 0.860 and meant absolute error (MAE) of 6.929, using only specific humidity and wind component as predictors. The spatial performance indices over eight different climate regions of Iran also showed the better performance of ABR-DT, which improved the CC and MAE of its two alternatives up to 185 and 19%. The study identified the optimal parameter combination as the predictors of heatwaves by examining the effects of numerous weather components. The results proved the proposed hybrid forecasting approach's effectiveness in predicting heatwave days, a devastating hazard, for many regions.
 
Spatial location of the samples
The overall flowchart of this study
Spatial distribution of available trace elements in soils estimated by the Bayesian maximum entropy (BME) technique
Spatial prediction error difference maps between cokriging and Bayesian maximum entropy
Article
Trace elements are essential nutrients for plant growth. An accurate prediction of soil available trace elements is necessary for scientifically based fertilization and soil environmental protection. In total, 670 surface soil samples were collected across the study area to analyze the relationship between soil properties and available trace elements (Cu, Zn, Fe, Mn, B, and Mo). Moreover, the Bayesian maximum entropy (BME) technique was employed to predict the spatial distribution of the trace elements by combining soil property information as auxiliary data. In addition, the prediction accuracy of the BME technique was compared with that of the conventional cokriging (CK) method. The results showed that soil macronutrients, especially organic matter, available P, available K and slow-release K, were significantly correlated with the content of the available trace elements. Soil texture also had great influences on trace elements and was generally represented as clay > heavy loam > medium loam > light loam. The BME technique combined with auxiliary soil property information (both categorical and numerical) performed better than the traditional CK technique, which was supported by the smaller MAE and RMSE and higher R² from the ten-fold cross validation. By mapping the spatial prediction error difference between the BME and CK methods across the study area, in comparison to the CK method, the BME technique provided consistently more accurate spatial predictions of trace element concentrations. In conclusion, with the advantages of combining categorical and numerical auxiliary data, the BME technique is a suitable spatial prediction method, and the results obtained in local regions could provide an important reference for the scientific application of microfertilizers.
 
Article
Once the safety of a biomass gasification unit is threatened, the leakage of syngas may result, which will have a great impact on humans, the environment, property and society. This study proposes a method for the risk assessment of biomass gasification units that integrates the DEMATEL-ISM with the CM-TOPSIS methods. The risk assessment process is divided into two stages. In the first stage, a directed hierarchical structure describing the relationships among accident factors can be obtained by using the DEMATEL-ISM method. The centrality, total degree and clustering coefficient are introduced to determine the weights of accident factors. The weight calculation results not only provide objectivity but also reflect the interrelationships among accident factors. In the second stage, CM-TOPSIS is used to calculate and prioritize the risks of accident factors. The results of risk values calculated by TOPSIS integrate the fuzziness and randomness of the assessment results of the CM, which can reduce the uncertainty of the results. More importantly, for high-risk factors, the directed hierarchical structure obtained in the first stage can be used to analyse the transmission routes of accident factors that lead to their occurrence. Finally, a case study and a comparative analysis are conducted to prove the effectiveness and applicability of the proposed method. The results show that pump and flow control valve failures are the highest risk accident factors. Moreover, the transmission routes that cause pump failure are determined and analysed for the purpose of safe production.
 
Article
Isotope techniques are most frequently used when hydrochemical analysis are insufficient to determine the origin and quality of groundwater and reveal seawater intrusion into groundwater along coastlines. In this study, the potential of the multilayer perceptron, adaptive neuro-fuzzy inference system, generalized regression neural networks, radial basis neural networks, classification and regression tree, Gaussian process regression, multiple linear regression analysis, and support vector machines were compared using known hydrochemical properties of waters for estimating deuterium (δD) and oxygen-18 (δ¹⁸O) isotopes in groundwater of the Bafra plain, Northern Turkey. The data were divided into training (70%) and testing (30%) sets. Cluster analysis was performed to decrease the number of input variables. The data on electrical conductivity, chloride, magnesium, and sulfate were introduced into the models after examining different combinations of these variables in the studied models. The determination coefficient (R²), mean absolute error (MAE), and root mean square error (RMSE) were used to evaluate the performances of the models. In addition, visualization techniques (Taylor diagram and heat maps) were prepared to assess the similarities between the measured and estimated δD and δ¹⁸O values. The R², RMSE, and MAE for δ¹⁸O (0.98, 0.31 and 0.20‰, respectively), and δD (0.95, 2.85 and 1.89‰, respectively) values for the testing datasets revealed that the performance accuracy of multilayer perceptron is the best among the applied models tested. Therefore, the study suggests using data-driven methods, multilayer perceptron in this case, when lacking appropriate laboratory isotope analysis or facing high laboratory analysis costs.
 
Article
Accurate forecasting of soil moisture (SM) is crucial for managing the irrigation demands effectively. The dynamics of SM is largely controlled by interaction between land and atmosphere. As an alternate to physics based models, the machine learning based tools have been shown to yield better accuracy in forecasting SM. However, the complexity in the process that controls SM at largely varying scale (from small size porous media to continental level climate) influence the forecast to have uncertainty. Hence, this paper aims at developing a modelling framework for forecasting daily SM up to 5 days lead time along with associated uncertainty. In this modeling, the uncertainty in initial point estimates of artificial neural network (ANN) parameters are re-estimated in a probabilistic framework using Particle filter. In order to reduce the high dimensionality of such problems, most sensitive parameters of the ANN model were identified through Sobol’s sensitivity analysis. The SM and weather data collected from the R.J. Cook Agronomy Farm experimental field near Pullman, Washington, USA were used to demonstrate the proposed method. The overall results of the models were highly encouraging in terms of having a Nash-Sutcliffe efficiency of more than 0.90 in calibration and validation. Further, the parametric uncertainty of ANN model parameters have helped quantifying the uncertainty in the SM forecast and found within acceptable limits. The proposed framework, in turn, helped providing useful information when the models are used in decision making supported with associated uncertainty information.
 
Article
Landslides are one of the most destructive natural phenomena in the world, which occur mostly in mountainous areas and cause damage to the economic sectors, agricultural lands, residential areas and infrastructures of any country, and also threaten the lives and property of human beings. Therefore, landslide susceptibility mapping (LSM) can play a critical role in identifying prone areas and reducing the damage caused by landslides in each area. In the present study, deep learning algorithms including convolutional neural network (CNN) and long short-term memory (LSTM) were used to identify landslide prone areas in Ardabil province, Iran. Then 312 landslide locations were identified and randomly divided into train and test datasets, and according to previous studies and environmental conditions in the study area, twelve factors affecting the occurrence of landslides were selected. The ratio of the importance of each influential factor in landslide occurrence was obtained through information gain ranking filter method and it was found that land-use and profile curvature had the highest and lowest impacts, respectively. Afterwards, LSMs were generated using CNN and LSTM algorithms. In the next step, the performance of the models was evaluated based on the area under curve (AUC) value of receiver operating characteristics curve and the root mean square error (RMSE) method. The AUC values for CNN and LSTM models were 0.821 and 0.832, respectively. Furthermore, the RMSE values in the CNN model for each of the training and testing dataset were 0.121 and 0.132, respectively. The RMSE values in the LSTM model for each of the training and testing dataset were 0.185 and 0.188, respectively. Therefore, it can be concluded that LSTM performance is slightly better than CNN; but in general, both models have close performance and the accuracy of both models is acceptable.
 
Total number of positive WNV cases by sampling season
(a) Occupancy and (b) detection probabilities for PHUs Ottawa (OTT), Sudbury (SUD), Toronto (TOR), and Windsor-Essex (WEC) in 2016. Solid lines are posterior medians, and bands are ninety-five percent credible intervals. (c) Lagged mean temperature and (d) Culex proportion are influential occupancy and detection covariates
Posterior medians for occupancy probabilities in Ontario on the 34th epiweek of 2016. The inset map juxtaposes southern Ontario relative to northern Ontario
Posterior medians for detection probabilities in Ontario on the 34th epiweek of 2016. Detection was missing when no surveys were done. The inset map juxtaposes southern Ontario relative to northern Ontario
Areal covariate corresponding to the first SRE. Negative (positive) values are in blue (red). The inset map juxtaposes southern Ontario relative to northern Ontario
Article
Occupancy models determine the true presence or absence of a species by adjusting for imperfect detection in surveys. They often assume that species presences can be detected only if sites are occupied during a sampling season. We extended these models to estimate occupancy rates that vary throughout a sampling season as well as account for spatial dependence among sites. For these methods, we constructed a fast Gibbs sampler with the Pólya-Gamma augmentation strategy to conduct inference on covariate effects. We applied these methods to evaluate how environmental conditions and surveillance practices are associated with the presence of West Nile virus in mosquito traps across Ontario, Canada from 2002 to 2017. We found that urban land cover and warm temperatures drove viral occupancy, whereas viral testing on pools with higher proportions of Culex mosquitoes was more likely to result in a positive test for West Nile virus. Models with time-varying occupancy effects achieved much lower Watanabe-Akaike information criteria than models without such effects. Our final model had strong predictive performance on test data that included some of the most extreme seasons, demonstrating the promise of these methods in the study of pathogens spread by mosquito vectors.
 
Article
As a primary input in meteorology, the accuracy of solar radiation simulations affects hydrological, climatological, and agricultural studies and sustainable development practices and plans. With the advent of machine learning models and their proven capabilities in modelling the hydro-meteorological phenomena, it is necessary to find the best model suitable for each phenomenon. Models performance depends upon their structure and the input data set. Therefore, some well-known and newest machine learning models with different inputs are tested here for solar radiation simulation in Illinois, USA. The data mining models of Support Vector Machine (SVM), Gene Expression Programming (GEP), Long Short-Term Memory (LSTM), and their combination with the wavelet transformation building a total of six model structures are applied to five data sets to examine their suitability for solar radiation simulation. The five input data sets (SCN_1 to SCN_5) are based on five readily accessible parameters, namely extraterrestrial radiation (Ra), maximum and minimum air temperature (Tmin, Tmax), corrected clear-sky solar irradiation (ICSKY), and Day of Year (DOY). The LSTM outperformed other models, consulting the performance measures of RMSE, SI, MAE, SSRMSE, and SSMAE. Of the different input data sets, in general, SCN_4 was the best input scenario for predicting global daily solar radiation using Ra, Tmax, Tmin, and DOY variables. Overall, six machine learning based models showed acceptable performances for estimating solar radiation, with the LSTM machine learning technique being the most recommended.
 
Article
Pressure reducing valves (PRVs) are widely used to regulate pressures in the supply and distribution parts of water networks, by reducing the upstream pressure to a set outlet pressure (i.e., downstream of the PRV), usually referred to as set point. As all types of mechanical equipment, PRVs may exhibit malfunctions affecting pressure regulation, such as high frequency fluctuations around the set point and/or prolonged systematic deviations from the set point, allowing their detection to be approached in a statistical context. In this study, we develop a statistical framework for detection of PRV malfunctions in water supply and water distribution networks, which uses: (a) the root mean squared error as a proper statistical metric for monitoring the performance of PRVs by detecting individual malfunctions in high-resolution pressure time series, and (b) the hazard function concept to identify a proper duration of sequential events from (a) to issue alerts. The suggested methodology is implemented using pressure data at 1-min temporal resolution from pressure management area Diagora of the water distribution network of the city of Patras in Greece, for the 3-year period from 01/Jan./2017 to 31/Dec./2019. The obtained results show that the developed statistical approach effectively detects major PRV malfunctions as the issuance of alerts agrees well with the reported repair dates by the Municipal Enterprise of Water Supply and Sewerage of the City of Patras, allowing it to be used for operational purposes, while making it suitable for possible extensions to continuous monitoring and fault diagnosis of other types of mechanical equipment.
 
Article
For effective water resource management, water budgeting, and optimal release discharge from a reservoir, the accurate prediction of daily inflow is critical. An attempt has been made using artificial intelligence (AI) techniques to enhance water management efficiency in the Haditha-dam reservoir. This case study occasionally suffers from severe drought events and thus causes significant water shortages as well as stopping hydroelectric power stations for several months. Four different approaches were employed for inflow forecasting, namely multiple linear regression (MLR), random forest (RF), extreme learning machine (ELM), and regularized extreme learning machine (RELM). Autocorrelation function (ACF) and partial autocorrelation function (PACF) were used to select the best-lagged variables. The obtained results revealed the superiority of the RELM model compared to other forecast models. The proposed model (RELM) yielded higher prediction accuracy, and its prediction records were similar to the actual values. Moreover, the adopted model achieved a higher correlation of coefficient value (R = 0.955). The regularization approach effectively enhanced the prediction capacity and the generalization ability of the proposed model. On the other hand, the RF model's performance capacity was poor compared to other comparable models due to the overfitting issue. Moreover, the results showed that the PACF (partial autocorrelation function) gave more accurate and realistic predictors than ACF (autocorrelation function) because of its ability to cope with a sudden temporal variation of inflow time series. Overall, the RELM approach provided higher adequacy and tighter confidence in forecasting daily inflow even in noisy data and severe climatic conditions.
 
Article
At the beginning of 2022 the global daily count of new cases of COVID-19 exceeded 3.2 million, a tripling of the historical peak value reported between the initial outbreak of the pandemic and the end of 2021. Aerosol transmission through interpersonal contact is the main cause of the disease’s spread, although control measures have been put in place to reduce contact opportunities. Mobility pattern is a basic mechanism for understanding how people gather at a location and how long they stay there. Due to the inherent dependencies in disease transmission, models for associating mobility data with confirmed cases need to be individually designed for different regions and time periods. In this paper, we propose an autoregressive count data model under the framework of a generalized linear model to illustrate a process of model specification and selection. By evaluating a 14-day-ahead prediction from Sweden, the results showed that for a dense population region, using mobility data with a lag of 8 days is the most reliable way of predicting the number of confirmed cases in relative numbers at a high coverage rate. It is sufficient for both of the autoregressive terms, studied variable and conditional expectation, to take one day back. For sparsely populated regions, a lag of 10 days produced the lowest error in absolute value for the predictions, where weekly periodicity on the studied variable is recommended for use. Interventions were further included to identify the most relevant mobility categories. Statistical features were also presented to verify the model assumptions.
 
Article
Fine particulate matter (PM2.5) concentrations pollution is one of serious environmental issues. It is necessary for PM2.5 concentrations estimation because the existing PM2.5 ground monitoring stations are relatively sparse and cannot obtain continuous PM2.5 concentrations over a large area. Several studies have been applied aerosol optical depth (AOD) to PM2.5 concentrations estimation. However, the missing of the AOD data does not improve the accuracy of PM2.5 estimations. Therefore, we need a filling technique to fill the AOD data. The purpose of this study is to deal with the missing AOD data using machine learning interpolation techniques and to estimate the PM2.5 concentrations at 1 km resolution by adding auxiliary factors to fit the relationship between AOD data and PM2.5 data. We used a long short-term memory network (LSTM), model to fit the filled AOD data. We estimated PM2.5 values based on the meteorological conditions and the AOD data at the station, and we also established the temporal and spatial relationships of PM2.5. Overall, the method is suitable for PM2.5 estimations with R² = 0.75. We conducted experiments at existing stations in Beijing. The results of the study demonstrate the validity of gap-filling AOD data for PM2.5 estimations, with PM2.5 distributions being higher in the south and lower in the north.
 
Top-cited authors
Jan Franklin Adamowski
  • McGill University
Rahim Barzegar
  • McGill University
Ravinesh Deo
  • University of Southern Queensland 
Asghar Asghari Moghaddam
  • University of Tabriz
Jyotir Moy Chatterjee
  • Lord Buddha Education Foundation Kathmandu Nepal