ArticlePDF Available

Groundwater Level Fluctuations in Coastal Aquifer: Using Artificial Neural Networks to Predict the Impacts of Climatical CMIP6 Scenarios


Abstract and Figures

Groundwater resources play a crucial role in supplying water for domestic, industrial, and agricultural use. In this study ACCESS-CM2, HadGEM3-GC31-LL, and NESM3 were selected for validation from Coupled Model Intercomparison Project Phase 6 (CMIP6). In the following, the feedforward neural network was employed to predict monthly groundwater level (GWL) based on the emission scenarios of the sixth IPCC report (SSP2-4.5 and SSp5-8.5) for the next two decades (2021–2040) in the Sari-Neka coastal aquifer near the Caspian Sea, Iran. In this regard, the monthly maximum and minimum temperature, precipitation, and water table of previous month from four piezometers from 2000 to 2019 were used as input variables to forecast GWL. The evaluation of the three GCM models demonstrated that the ACCESS-CM2 provided the best values of the R² and RMSE with observation parameters. The results of r, R², RMSE, and MAE were evaluated for the model and indicated good performance of the model. The results also illustrated that under such mentioned scenarios, the mean monthly temperature would rise approximately from 0.1–1.2 °C. In addition, the mean monthly precipitation is likely to witness changes from -10% to 78% in the next two decades. As a result, this seems to lead to improvement and recharge of groundwater level for the near future. The results can help managers and policymakers to identify adaptation strategies more precisely for basins with similar climates.
Content may be subject to copyright.
Water Resources Management
1 3
Groundwater Level Fluctuations inCoastal Aquifer: Using
Artificial Neural Networks toPredict theImpacts ofClimatical
CMIP6 Scenarios
AdibRoshani1 · MehdiHamidi1
Received: 3 March 2022 / Accepted: 25 May 2022
© The Author(s), under exclusive licence to Springer Nature B.V. 2022
Groundwater resources play a crucial role in supplying water for domestic, industrial, and
agricultural use. In this study ACCESS-CM2, HadGEM3-GC31-LL, and NESM3 were
selected for validation from Coupled Model Intercomparison Project Phase 6 (CMIP6). In
the following, the feedforward neural network was employed to predict monthly ground-
water level (GWL) based on the emission scenarios of the sixth IPCC report (SSP2-4.5
and SSp5-8.5) for the next two decades (2021–2040) in the Sari-Neka coastal aquifer near
the Caspian Sea, Iran. In this regard, the monthly maximum and minimum temperature,
precipitation, and water table of previous month from four piezometers from 2000 to 2019
were used as input variables to forecast GWL. The evaluation of the three GCM models
demonstrated that the ACCESS-CM2 provided the best values of the R2 and RMSE with
observation parameters. The results of r, R2, RMSE, and MAE were evaluated for the
model and indicated good performance of the model. The results also illustrated that under
such mentioned scenarios, the mean monthly temperature would rise approximately from
0.1–1.2°C. In addition, the mean monthly precipitation is likely to witness changes from
-10% to 78% in the next two decades. As a result, this seems to lead to improvement and
recharge of groundwater level for the near future. The results can help managers and poli-
cymakers to identify adaptation strategies more precisely for basins with similar climates.
Keywords CMIP6· Groundwater level· Artificial neural network· LARS-WG· Sari-Neka
1 Introduction
According to studies by the Intergovernmental Panel on Climate Change (IPCC), the short-
age of water resources is expected to become a major challenge in many regions of Asia,
as the demand for water is increasing due to the rise in population and standards of living
(IPCC 2014). Given the strong dependence of the Asian economy on agriculture, about 80%
of groundwater in Asia is used for this purpose. The groundwater level in coastal aquifers
* Mehdi Hamidi
1 Department ofCivil Engineering, Babol Noshirvani University ofTechnology, Babol, Iran
A.Roshani, M.Hamidi
1 3
can be influenced by population growth (Alimohammadi etal. 2020), High quality of life
(Mirdashtvan etal. 2021), tides, rising sea level, increased salinity, uncontrolled withdrawal,
and reduced recharge (Hamidi and Sabbagh-Yazdi 2008; Natarajan and Sudheer 2020;
Nasiri etal. 2021). As an arid and semi-arid country in Western Asia, Iran has a shoreline of
750km on the Caspian Sea and about 2250km on the Persian Gulf and the Gulf of Oman,
and numerous islands and estuaries. As a result, it has earned the title of a coastal country.
As of the latest census, about 22% of Iran’s population inhabit coastal lines. These regions
play a significant role in the economic growth of a developing society, in terms of both agri-
culture and industry. Moreover, they can greatly contribute to the gross domestic product of
a country. The critical role played by groundwater in this economic growth necessitates the
awareness and management of changes in groundwater levels. Researchers have employed
theoretical and observation models to investigate prospective climate conditions. Models of
global climate change (GCMs) are primary tools for predicting the trend of changing climate
change through different scenarios of greenhouse gas emissions (Ouhamdouch and Bahir
2017). General circulation models (GCMs) are some of the most authoritative theoretical
models that are based on physics (O’Neill etal. 2017). However, they have certain disadvan-
tages, such as their large scale. Nonetheless, they can be converted to small scales through
techniques termed “downscaling methods”, (Hewitson and Crane 1996; Wilby and Wigley
1997; Guo and Wang 2016; Theodossiou 2016). One of the most well-known and useful
downscaling models is the Long Ashton Research Station-Weather Generator (LARS-WG)
developed by Semenov and Barrow (Semenov etal. 1998). Its input data include minimum
temperature, maximum temperature, precipitation, and sunshine hours or solar radiation on
a daily scale. The model is capable of simulating climatic parameters for future decades
based on various scenarios and GCMs. The models in Coupled Model Intercomparison Pro-
ject Phase 6 (CMIP6) have produced the latest simulations of the past, present, and future
climates for a better understanding of climate change. These new models boast considerable
improvements over those used in CMIP5, including a higher resolution and better physics
(Priestley etal. 2020; Xin etal. 2020). Various researchers have simulated climatic param-
eters using the LARS-WG model and confirmed the results (Hassan etal. 2014; Sha etal.
2019; Bayatvarkeshi etal. 2020). Most previous research has used CMIP3 or CMIP5 out-
puts for this purpose. In this regard, it is necessary to simulate and evaluate the impact of
the latest versions of CMIPs on climatic parameters and natural resources. In this study, the
impact of updating CMIPs was investigated on groundwater levels.
In recent years, international climatologists and economists have created a wide range
of new pathway scenarios. They have described changes in climates and international com-
munities in terms of population, economy, and greenhouse gas (GHG) emissions. The lat-
est is named Shared Socio-economic Pathways (SSP), divided into five categories, from
SSP1 to SSP5. These scenarios are displayed in the form of SSPx-y, where x represents
SSP, and y denotes the radiative forcing (w/m2) in 2100 (O’Neill etal. 2017; Gupta etal.
The artificial neural network (ANN) is known as an estimator whose effectiveness has
been verified in previous research, being utilized in numerous scientific fields in recent
years (Yoon et al. 2011; Shen 2018; Rajaee et al. 2019). The applications of ANN in
hydrology include the prediction of nonlinear phenomena, such as rainfall-runoff, evapo-
transpiration, dam volume evaluation, streamlines, and water and rain quality modeling
(Taormina etal. 2012; Zhao et al. 2020; Roy et al. 2020; Di Nunno and Granata 2020;
Chen etal. 2020; Derbela and Nouiri 2020). One of the most important challenges in fore-
casting groundwater levels using ANN has been the selection of input data. Daily, weekly,
or monthly temperature and precipitation have been the major driving factors in the impact
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
of climate change on water resources in the literature. (Yoon etal. 2011; Maharjan et al.
2021). Moghaddam etal. (2019) used monthly evaporation, average temperature, aquifer
discharge and recharge, and aquifer level to evaluate the performance of ANN, Bayes-
ian network (BN), and MODFLOW in the simulation of a 12-year period work. Hasda
etal. (2020) employed the neural network (NN) to forecast weekly levels of groundwater,
52weeks in advance. The studies by Chang etal. 2015; Ghazi etal. 2021; and Sharma etal.
2021 investigated the impact of climate change using the output of CMIP3 and CMIP5 cli-
mate models and various scenarios on variations in groundwater levels.
Various organizations have cooperated to use groups of climate model outputs to stand-
ardize the design of GCMs and the distribution of simulated models. These models have
recently become a crucial element in guiding global research on climates (Thorne etal.
2017). The rapid growth in population and industry has had diverse effects on the manner
of GHG emissions. Since new emission scenarios are introduced every couple of years, it
seems necessary to be up-to-date on the latest trends in climate change. The most common
aim of climate studies is to determine the changes in the weather of the region under study.
To this end, the present study attempted to evaluate the best available models (CMIP6)
for the specified basin. The main objective of the CMIP6 is to determine how the struc-
ture of the earth responds to different forces in relation to the origins and consequences of
organized models, climate change quantification, and scenario uncertainty. The number of
vertical layers in all CMIP6 models has increased compared to those in CMIP5 models.
An advantage of this increase is a more accurate simulation in the stratosphere, in addition
to a significant increase in the number of investigated prospective scenarios. The new sce-
narios added to CMIP6 are SSP1-1.9, SSP4-3.4, and SSP3-7.0. In addition, the 4 scenarios
SSP1-2.6, SSP2-4.5, SSP4-6.0, and SSP5-8.5 have updated RCP2.6, RCP4.5, RCP6.0, and
RCP8.5 scenarios in CMIP5, respectively (Eyring etal. 2016; Li etal. 2020; Gupta etal.
The new CMIP6 models are enhanced in terms of horizontal resolution and better rep-
resentation of synoptic processes (Di Luca et al. 2020; Nie et al. 2020; Srivastava etal.
2020), which will lead to more reasonable results in climate studies. As a result, CMIP6
simulations of climates are more reliable than before, and this makes investigation to better
understand future climates necessary. In this regard, the main aim of this study was to: (1)
determine the performance of three CMIP6 GCMs and select the best ones; (2) assess the
impact of climate change and forecast monthly groundwater depths of the coastal Sari-Neka
aquifer in Iran by FNN under the latest scenarios codified by the Intergovernmental Panel on
Climate Change (IPCC) (SSP2-4.5, SSP5-8.5) for near future (2021–2040) decades.
2 Materials andMethods
For the purpose of assessing the potential impact of climate change on groundwater lev-
els in the Sari-Neka aquifer, GCM models were used. Firstly, three CMIP6 GCM models
(ACCESS-CM2, HadGEM3-GC31-LL, and NESM3) were selected and compared with
observation data. In the following, temperature and precipitation were simulated under
two scenarios (SSP2-4.5 and SSP5-8.5) for the near future (2021 to 2040) by LARS-WG.
Monthly datasets, maximum and minimum temperature, precipitation, and groundwater
level in the previous month were used for the input of the ANN model, with the groundwa-
ter level being simulated for two next decades (2021–2040). How the research was carried
out is shown in Fig.1.
A.Roshani, M.Hamidi
1 3
2.1 Study Area
Sari-Neka region, a basin which is located by the Caspian Sea between 35° 56 36° 52’ N
and 52° 43 54° 44’ E, was selected as a case study in Mazandaran province (Fig.2). It is
divided into mountainous parts, hills, and flat plains, mainly covered by alluvial sediments
from a geomorphological view. The climate there is regarded as generally Mediterranean
and semi-humid by the DeMartonne’s Method. This region covers an area of about 6938.5
km2, of which an area of 977.87 km2 is devoted to plains, while the rest is highland (5877.8
km2). The highest elevation in the area is 3836m, with the lowest point being -27m (Nasiri
Downscaling &
Simula n
Temperature & Precipitan
in dailyscale
Calibrateby Q-test
Select climatemodel
Select SSPscenarios
SSP2-4.5 & SSP5-8.5
Simulate Temperature &
precipitanfor future
observaon wells
Defineinput and
target parameters
Change of parameters fortraining
1. Number of hidden layers
2. Number of neurons in hidden layer
3. Transfer func n
Training andtes ng ANN
depthfor future period
Fig. 1 flowchart of the current study
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
etal. 2021). Annual average rainfall fluctuated between 400–1000mm from 2000 to 2019.
The most humid months there are October and November, and the annual mean maximum
and minimum temperatures are 23 and 13 Celsius, with January and August being the cold-
est and the warmest months respectively. On plains, the groundwater flows from the south
to the north. Most of the study area consists of limestone structures, which are the princi-
pal sources of groundwater supply through groundwater fronts. East and south portions of
the basin predominantly contain geological Jurassic formations that provide surface and
groundwater recharge, as well as snow accumulation in the basin (Nasiri etal. 2021). Land
types are diverse in the study region, including farmland (rice fields and citrus gardens),
residential areas, rangeland, forests, and water bodies. Piezometric wells, which are 0 to
31.1m deep, are situated within this aquifer (Sahour etal. 2020).
Fig. 2 Location of the study area in the map of Iran and the location of piezometer wells in the aquifer
A.Roshani, M.Hamidi
1 3
2.2 Date Collection
Different datasets were prepared for this study, identified as:
1- Maximum temperature, minimum temperature, and precipitation data of historical and
future period for three models ACCESS-CM2, HadGEM3-GC31-LL, and NESM3 under
CMIP6 report from IPCC based on SSP2-4.5 and also SSP5-8.5 scenarios were received
for downscaling from https:// clima te4im pact. eu.
2- Maximum and minimum temperatures, and precipitation for the observation period
(2000–2019) were provided from the meteorological organization of Mazandaran prov-
ince on a daily scale.
3- Data on groundwater level fluctuations in 68 piezometers (2000–2019) were provided
from the regional water organization of Mazandaran province on a monthly scale.
2.3 Climate Models andEmissions Scenarios
In this study, the outputs of the three climate models from CMIP6 were received from the
mentioned databases, and the data of the region were extracted using ArcGis10.8. To this
end, the ACCESS-CM2, HadGEM3-GC31-LL, and NESM3 models were used. The pre-
cipitation, maximum temperature, and minimum temperature of these models are shown
in Table1. The SSP2-4.5 and SSP5-8.5 scenarios used in this study were called the mid-
dle of the road and fossil-fueled development—taking the highway, respectively. Their
specifications are summarized in Table2. These scenarios were used due to the following
reasons: (1) the SSP2-4.5 and SSP-5–8.5 were utilized for the vulnerabilities to climate
change and its consequences (Warnatzsch and Reay 2019); (2) since SSP1-2.6, which is an
update of RCP2.6, is absent in some models, a comparison between the models becomes
2.4 Downscaling
Presently, GCM outputs are not directly employed in hydrological models due to their reso-
lution inability and lack of sufficient spatial and temporal certainty (Semenov and Barrow
1997). The model employed in this research was LARS-WG6, the initial version of which
was introduced by Racsko et al. (1991), to address the issues of the Markov chain, which
was frequently used to model precipitation, and was later upgraded by Semenov and Barrow.
As a generator, LARS-WG produces climatic parameters, such as maximum temperature,
minimum temperature, precipitation, and solar radiation on a daily basis for any period of
time according to a set of semi-empirical distributions (Roshan etal. 2013). Even though this
model is not a weather forecast tool, it is a means to generate an artificial weather time series
that statistically resembles observation data.
The delta change factor (DCF) technique was utilized to generate the Atmosphere–Ocean
General Circulation Model (AOGCM) climate change scenario. This method calculates
the maximum and minimum temperature difference and the precipitation ratio of the pro-
spective and base periods in the studied region’s model according to Eqs.1, 2, and 3. The
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
Table 1 List of CMIP6 models that have been used in this study (Priestley etal. 2020)
Model name Institution Resolution Processing Simulated scenarios
ACCESS-CM2 CSIRO-ARCCSS; Commonwealth Scientific and Industrial Research
Organization, and Bureau of Meteorology, Australia
192*145 r1i1p1f1 SSP2-4.5
HadGEM3-GC31-LL MOHC; Met Office Hadley Center, United Kingdom 192*144 r1i1p1f1 SSP2-4.5
NESM3 NUIST; Nanjing University of Information Science and Technology, China 192*96 r1i1p1f1 SSP2-4.5
A.Roshani, M.Hamidi
1 3
Table 2 Summary of assumptions regarding demographic and human development elements of SSP2 and SSP5 (O’Neill etal. 2017)
SSP element SSP2 SSP5
Development Medium, uneven Rapid
Carbon intensity Medium High
Energy tech change Some investment in renewables but
continued reliance on fossil fuels
Directed toward fossil fuels; alternative sources not actively pursued
Economy & lifestyle
Growth (per capita) Medium, uneven High
Globalization Semi-open globalized economy Strongly globalized, increasingly connected
Consumption & Diet Material-intensive
consumption, medium meat consumption
Materialism, status consumption, tourism,
mobility, meat-rich diets
Policies & institutions
Relatively weak Effective in pursuit of development goals, more limited for envt. goals
Environmental Policy Concern for local pollutants but only
moderate success in implementation
Focus on local environment with obvious benefits to
well-being, little concern with global problems
Policy orientation Weak focus on sustainability Toward development, free markets, human capita
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
base and prospective periods were assumed to be 2000–2019 and 2021–2040, respectively
(Semenov and Barrow 1997).
In the above equations,
, and
represent the monthly climate change sce-
narios of precipitation, minimum temperature, and maximum temperature, respectively.
denotes the 20-year precipitation average simulated by the AOGCM models for
the prospective period, and
represents the same for the base period (2000–2019
in this study). the explanations provided for the minimum and maximum temperature are
correct. Two files were created to generate climatic data in the LARS-WG model and to
downscale the GCM data for future periods. The first file describes past climatic behavior,
while the other contains climate change scenarios. The model was calibrated in the first
step and then verified using statistical tests and a comparison of the graphs.
2.5 Clustering ofObservation Well
Clustering is an unsupervised learning technique in which samples are categorized into
similar groups with identical features. A common clustering method is the K-means, intro-
duced by MacQueen in 1967 (MacQueen 1967), in which the number of clusters is pre-
determined. The number of clusters was validated using the common Elbow index, deter-
mined by Eq. (4) (Brusco and Steinley 2007). Since there were 68 piezometers in this
basin, clustering was performed to avoid over-complication of the model. The geographical
coordinates and groundwater levels of the piezometers were used for clustering.
is the set of observations in the Kth and
is the mean of variable
in cluster
. In this technique, the number of clusters is directly related to the Within-Cluster Sum
of Square (WCSS), which is the sum of the squared distance between each point and the
centroid in a cluster. The vertical axis represents WCSS, with the horizontal axis showing
the number of clusters. In this index, the number of clusters, K, begins from 1 and grows
to where the value of WCSS remains almost constant, being the largest in the first cluster.
2.6 Artificial Neural Network (ANN)
Artificial neural networks (ANN) are typically based on human nervous systems. In hydro-
logical contexts, these heuristics are particularly appropriate for predicting and forecasting
variables because they are capable of modeling nonlinear, nonstationary, and nongaussian
processes. NNs are trained to recognize data patterns until a minimum acceptable error is
found between the ANN predicted data and the observation data. NNs are mostly divided
Min =TMin
Max =TMax
xiv xvk
A.Roshani, M.Hamidi
1 3
into three general layers. The input layer is responsible for receiving data, the output layer
contains forecast information, and the middle layer performs the necessary calculations
(Maier and Dandy 1997; Daliakopoulos etal. 2005; Moghaddam etal. 2019). The inputs are
multiplied by synaptic weights and delivered to the first hidden layer. In the hidden units, the
weighted sum of inputs is transformed by a nonlinear activation function (Taormina etal.
ANNs are either feedforward or recurrent. The present research utilized feedforward
NNs and the sigmoid activation function. The Levenberg–Marquardt algorithm was
employed to train the NN (Daliakopoulos etal. 2005; Derbela and Nouiri 2020). In feed-
forward networks, the input enters from the left, and the output exits from the right. The
number of input and output neurons are determined by the number of parameters in the
network and is typically determined by the nature of the problem (Emamgholizadeh etal.
2014). and those of the hidden layer are determined via trial and error. The hidden layer is
tasked with linking the input and output layers. Using this layer, the NN can extract nonlin-
ear relationships from the data input to the model.
Training is aimed at reaching a state where the network is capable of correctly respond-
ing to training data in addition to similar non-training data. NN learning is either super-
vised or unsupervised, with the former being used in the present study. In this approach,
training is mostly performed using sample vectors of pairs, such that a specific output
vector is assigned to each input vector. As these vectors are presented to the network, the
weights are corrected according to the learning algorithm. The present research minimum
and maximum temperature, precipitation in the current month, and groundwater level in
the previous month were used as the input data. In addition, groundwater level in the cur-
rent month was employed as the output data (Coppola etal. 2005; Chitsazan etal. 2015;
Moghaddam etal. 2019).
2.7 Performance Criteria
Statistical methods for assessing the error between observated and predicted data were
used in terms of correlation coefficients (r), coefficients of determination (R2), Mean Abso-
lute Error (MAE), and Root Mean Squared Error (RMSE).
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
where n is the total number of measured data,
are the predicted and observed value,
respectively, and
are the average value of the measured data (Natarajan and Sudheer
3 Result andDiscussion
3.1 CMIP6 Models Validation
In the first step, the performances of the NESM3, HadGEM3-GC31-LL, and ACCESS-
CM2 of the CMIP6 models with respect to the observation data were evaluated in order to
determine the best model for studying climate change in the area. To this end, the
ficient of determination and the root-mean-square error (RSME) were used for the min-
imum and maximum temperature and precipitation parameters. According to the results
presented in Table3, the ACCESS-CM2 model showed the smallest RMSE at the mini-
mum and maximum temperatures and the best precipitation performance in both statistical
tests. This indicated the superiority of this model over the other two in simulating the area
under study. Therefore, it was selected for investigating climate change in the research step.
This step involved a forecast of the meteorological data by the ACCESS-CM2 model
under the climate change scenarios SSP2-4.5 and SSP5-8.5. Additionally, the 2000–2019
climatic data were utilized for the LARS-WG model’s base period, and forecast was made
for the subsequent two decades (2021–2040). Using the Site Analysis functionality of the
LARS-WG model, calibration and verification were performed simultaneously using two
datasets including daily observation data and the geographic information of the research
station. The performance of LARS-WG was evaluated by the K-S, t, and F statistical tests.
The K-S test was conducted to test the equality of the seasonal distributions of the wet and
dry series, the daily distribution of precipitation, and the daily distribution of minimum and
maximum temperature. The F-test was performed to test the equality in the standard devia-
tion of monthly precipitation. The t-test was aimed at testing the equality of the monthly
average of precipitation and the monthly average of the maximum and minimum daily
Table 3 Statistical comparison of AOGCM models to select the best model
Statistical test Models AOGCM
Maximum temperature
0.97 0.96 0.98
RMSE (°C) 4.09 6.32 5.19
Minimum temperature
0.98 0.95 0.98
RMSE (°C) 5.55 8.38 5.75
0.95 0.94 0.94
RMSE (mm) 2.29 2.51 2.70
A.Roshani, M.Hamidi
1 3
temperature. Based on the P-value calculated in all tests, there was no significant difference
between the simulated and observation values at a significance level of 5%. According to
Table4, the LARS-WG model exhibited acceptable consistency between the simulated and
observation series of monthly climate data (Nover etal. 2016; Adnan etal. 2019). How-
ever, the same results were erroneous and unreliable on a daily scale. In addition, the larg-
est error corresponded to the simulated precipitation in January. The largest precipitation
error might be due to the large variation in precipitation (Hassan etal. 2014) and compared
to changes in temperature, changes in precipitation are more uncertain (Msowoya etal.
2016). Given the results of the model, the maximum temperature was simulated better than
the other two parameters, providing higher accuracy (Bayatvarkeshi etal. 2020). Although
there has been no complete correlation between the models and observations to date, the
lack of such correlation is not a barrier to using climate models. Climate models are not
used to predict specific weather events, but to predict a trend in climate change over time
(Warnatzsch and Reay 2019). Based on simulated and observational values of climatic
parameters, Table4 presents a statistical comparison. As can be seen, the overall statistical
evaluation of the ACCESS-CM2 model provided an acceptable result.
3.2 Future Climate Modeling
Figure 3 displays a comparison of the average minimum and maximum temperatures of
the base period and the average monthly temperature for both SSP2-4.5 and SSP5-8.5 sce-
narios during the 2021–2040 period. As shown, the minimum and maximum temperatures
increased over the months due to climate change. Therefore, minimum and maximum tem-
peratures are expected to rise by 0.20°C to 1.3°C over the next two decades. The largest
increase in minimum temperature corresponded to SSP5-8.5 with a 1.3°C in November,
and the smallest increase was in February (0.2 °C), corresponding to SSP5-8.5. For the
maximum temperature, a similar method was followed, and the results indicated that the
Table 4 K-S test daily distribution of observation and simulated data
Month Minimum temperature Maximum temperature Precipitation
Evaluation K-S P-value Evaluation K-S P-value Evaluation K-S P-value
January * 0.105 0.999 * 0.053 1.000 * 0.138 0.971
February * 0.053 1.000 * 0.106 0.999 * 0.060 1.000
march * 0.053 1.000 * 0.053 1.000 * 0.048 1.000
April * 0.053 1.000 * 0.010 1.000 * 0.054 1.000
May * 0.053 1.000 * 0.053 1.000 * 0.105 0.999
June * 0.053 1.000 * 0.106 0.999 * 0.078 1.000
July * 0.053 1.000 * 0.053 1.000 * 0.062 1.000
August * 0.106 0.999 * 0.053 1.000 * 0.107 0.999
September * 0.053 1.000 * 0.053 1.000 * 0.089 1.000
October * 0.053 1.000 * 0.053 1.000 * 0.081 1.000
November * 0.053 1.000 * 0.053 1.000 * 0.067 1.000
December * 0.053 1.000 * 0.053 1.000 * 0.067 1.000
*not statistically significant
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
most significant changes in the base period would occur in April under SSP5-8.5, while the
smallest changes would occur in October under SSP2-4.5. The results of the present study
are in good agreement with previous research by (Al-Maktoumi etal. 2018; Shahvari etal.
2019; Maghsood etal. 2019). In general, it can be said that the average air temperature in
this basin is on the rise. The rise in temperature could be caused by the unstable and rapid
industrial development that is taking place in this area.
The average monthly precipitation during the base period and the forecast period
(2021–2040) for both scenarios is displayed in Fig.3. Except for February, May, June,
Fig. 3 Comparison of Minimum and maximum temperature average and precipitation of base (2000–2019)
and future (2021–2040) under 2 scenarios SSP2-4.5 and SSP5-8.5: (a) minimum temperature, (b) maxi-
mum temperature, (c) precipitation
A.Roshani, M.Hamidi
1 3
and September, the results show an increase in precipitation for the rest of the months. As
compared to the base period, the highest increase corresponded to the SSP5-8.5 scenario
at 41mm in October. On the other hand, the smallest increase corresponded to Septem-
ber at 6.3 mm under SSP2-4.5. In this regard, as predicted, the precipitation in the two
upcoming decades will vary between -12% and 78%, with an overall increase from 2000
to 2040, (Abiodun etal. 2017; Konapala etal. 2020; Tabari 2020). In addition, the results
of Zhang etal. (2016) who studied three different GCMs under the RCP2.6, RCP4.5 and
RCP8.5 scenarios indicated that precipitation in the RCP2.6 and RCP4.5 scenarios would
increase gradually and continuously, but the increase in precipitation in future decades
under RCP8.5 is likely to be remarkable.
The highest-precipitation month during the observation period was November, but it
changed to October due to climate change in both scenarios. On the other hand, August
tends to remain the warmest month in the two coming decades. The results also indicated
the highest rise in precipitation in the winter and fall, while the largest absolute increase
corresponded to July and August during the summer, which agreed with the results of
Sha etal. (2019). Based on the findings, precipitation is also expected to increase in both
scenarios. According to IPCC, a rise in temperature intensifies the groundwater cycle and
increases evaporation. In turn, an increase in evaporation leads to frequent and strong
storms and may further humidify humid regions and dry out dryer regions. In this regard,
Boudiaf etal. (2020) reported a rise in temperature and precipitation in the coastal Medi-
terranean regions. Climate change has contributed to atmospheric warming and resulted in
stronger precipitation. Research carried out by Araya-Osses etal. (2020) indicated that an
increase in precipitation could lead to a higher snow potential in the heights, but a change
in the form of precipitation, for example stronger precipitation was encountered during the
same period due to higher temperatures.
3.3 Clustering
The Elbow index was used in this work to determine the optimal number of clusters. The
outcome of the clustering is displayed in Fig.4. The results indicated a significant differ-
ence in WCSS in the first four clusters. However, this difference became negligible from
K = 4 onward and hence four clusters were considered for the region under study. The loca-
tions of the four clusters and the four piezometers are shown in Fig.5.
Fig. 4 Clustering by Elbow method
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
3.4 Groundwater Modeling
The groundwater level of the Sari-Neka basin under climate change during the 2021–2040
period was predicted in MATLAB using ANN. For this purpose, the data were divided
into training, validation, and testing data, with 75% of them being assigned to training,
and 15% to each of validation and testing. Since an important point in ANN is the num-
ber of neurons in the hidden layer, the trial and error resulted in an optimal number of
eight neurons in the present work. In the first step, the model was trained to simulate the
groundwater level during the observation period. It was then used to predict the prospec-
tive groundwater level. To develop the ANN model, maximum and minimum temperature
and precipitation in the current month and groundwater levels in the previous months were
used. Furthermore, the groundwater level in the current month was used for the output of
the ANN model. The performance assessment of the constructed model was conducted
for each cluster of piezometers over the 2000–2019 period, and the results are shown in
Table5. In all four piezometers, the results indicated that network performance was accept-
able (Chitsazan etal. 2015; Sun etal. 2016; Derbela and Nouiri 2020).
On the other hand, previous research results demonstrated that the three available obser-
vation data inputs (groundwater level, temperature, and precipitation or evaporation) were
sufficient to construct a high-performance ANN (Daliakopoulos etal. 2005; Szidarovszky
etal. 2007; Mohanty etal. 2010; Chang etal. 2015; Ghazi etal. 2021).
In order to better comprehend the results predicted by the ANN, the Taylor diagram
was used, (Fig. 6). The horizontal and vertical axes represent the observation data and
the standard deviation, respectively. The points approach the hypotenuse which indicates
that the standard deviation of the predicted data was close to that of the observation data,
Table 5 Performance of the
artificial neural network based
on Correlation coefficient (r),
coefficient of determination
(R.2), root mean square error
(RMSE) and Mean absolute error
cluster well
P1 692,838 4,058,999 0.835 0.697 0.324 0.233
P2 697,350 4,075,550 0.929 0.864 0.360 0.253
P3 686,501 4,048,865 0.860 0.739 0.878 0.639
P4 688,031 4,074,145 0.895 0.802 0.339 0.237
Fig. 5 Clustering and positioning of groundwater observation wells (P1-P4) on the Sari-Neka region
A.Roshani, M.Hamidi
1 3
confirming that the model was performing properly. In addition, the correlation coefficient
was on the main hypotenuse and measured the performance of the model on a 0–1 basis,
where a value close to 1 indicated the good performance of the model.
The observation groundwater level in all of the piezometers, except for the 4th one,
increased, illustrating an improvement in the groundwater depth. Also, the groundwater
depth at all of the piezometers showed a gradual decrease in the coming two decades
due to climate change (Chang etal. 2015). As seen from the observation trend of the
four piezometers in Fig.7, the depth of groundwater in the basin under study exhibited
an increasing trend from about 2012 onward. However, a decreasing trend in depth due
to climate change was observed for the coming two decades, except in the fourth pie-
zometer under SSP2-4.5. As discussed, due to the higher precipitation in SSP5-8.5 than
SSP2-4.5, the groundwater level was expected to be higher in SSP5-8.5. Additionally,
the largest change observed in the depth of groundwater was associated with piezometer
P2 in SSP5-8.5. The results of previous research demonstrated an increase in groundwa-
ter levels under climate change (Ligotin etal. 2010; Chang etal. 2015). Therefore, from
the results, it can be concluded that the groundwater level will improve in the future due
Fig. 6 Performance of the artificial neural network based on Taylor diagram
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
to the influence of climatic parameters, such as temperature and precipitation. Neverthe-
less, other factors, such as industrial and economic developments, population growth,
and migration, may adversely affect the availability of water resources.
4 Conclusions
Awareness of the changes in the groundwater level can make a remarkable contribution to
water resource management. In the present research, three models of the CMIP6 GCMs
were selected, and based on the model with the most adaptation to observation data, the
groundwater level under two scenarios was simulated for the coastal Sari-Neka aquifer.
In the first step, a comparison of the CMIP6 GCMs with observed data was performed in
order to determine how well they would reproduce weather parameters over the basin and
Fig. 7 Groundwater level predicted under climate scenarios (SSP2-4.5 & SSP5-8.5) for 2021–2040
A.Roshani, M.Hamidi
1 3
as a result the best model was selected for the area. Subsequently, the ACCESS-CM2 model
was selected, and the weather parameters (temperature and precipitation) under scenarios
(SSP2-4.5 and SSP5-8.5) were simulated by LARS-WG for the coming two decades. The
results have indicated that the selected model is an improvement over the previous ones,
i.e., ACCESS 1.0 and ACCESS 1.3 (Williams etal. 2018; Bodman etal. 2020). The results
indicated that the precipitation fluctuated between -10% and 78% and average temperature
(0.1–1.2 °C) would increase, which agrees with other research results in this field (Tan
etal. 2017; Anjum etal. 2019; Yan etal. 2019). Variations in precipitation throughout the
months of the year can make events such as floods and droughts more frequent. Therefore,
efficient strategies should be undertaken to address these issues. In the second step, the 68
piezometers were clustered based on geographical coordinates and groundwater level and
evaluated using the Elbow method. This resulted in four piezometer clusters. The Sigmoid
activation function and the Levenberg–Marquardt algorithm were employed to construct
the ANN model. The number of neurons in the hidden layer was determined using trial
and error that resulted in eight neurons. The groundwater depth was predicted under the
two mentioned scenarios (SSP2-4.5 & SSP5-8.5) for future, 2021–2040 period. The results
indicated that the groundwater depth of the Sari-Neka basin is likely to decrease with a
gentle slope.
Author Contribution Adib Roshani: Conceptualization and design of the study, Acquisition of data, Analy-
sis and/or interpretation of data, Methodology, Software, Validation, and Drafting the manuscript. Mehdi
Hamidi: Conceptualization and design of the study, Acquisition of data, Analysis and/or interpretation of
data, Methodology, Software, Validation, Revising the manuscript critically for important intellectual con-
tent, Approval of the version of the manuscript to be published, Project administration, and Supervision.
Funding The authors have not received support from any organization for the submitted work.
Data Availability All GCM models are available online from: https:// clima te4im pact. eu
Code Availability ANN is commercial codes.
Ethical Approval Authors agreed to the ethical approval needed to publish this manuscript.
Consent to Participate The authors declare their consent to participate in this work.
Consent to Publish The authors declare their consent of the publication of this manuscript by “Water
Resources Management” journal.
Conflicts of Interest The authors declare that they have no conflict of interest.
Abiodun BJ, Adegoke J, Abatan AA, Ibe CA, Egbebiyi TS, Engelbrecht F, Pinto I (2017) Potential
impacts of climate change on extreme precipitation over four African coastal cities. Clim Change
Adnan RM, Liang Z, Trajkovic S, Zounemat-Kermani M, Li B, Kisi O (2019) Daily streamflow prediction
using optimally pruned extreme learning machine. J Hydrol 577:123981
Alimohammadi H, Massah Bavani AR, Roozbahani A (2020) Mitigating the impacts of climate change on
the performance of multi-purpose reservoirs by changing the operation policy from SOP to MLDR.
Water Resour Manage 34(4):1495–1516
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
Al-Maktoumi A, Zekri S, El-Rawy M, Abdalla O, Al-Wardy M, Al-Rawas G, Charabi Y (2018) Assessment
of the impact of climate change on coastal aquifers in Oman. Arab J Geosci 11(17). https:// doi. org/ 10.
1007/ s12517- 018- 3858-y
Anjum MN, Ding Y, Shangguan D (2019) Simulation of the projected climate change impacts on the river
flow regimes under CMIP5 RCP scenarios in the westerlies dominated belt, northern Pakistan. Atmos
Res 227:233–248
Araya-Osses D, Casanueva A, Román-Figueroa C, Uribe JM, Paneque M (2020) Climate change pro-
jections of temperature and precipitation in Chile based on statistical downscaling. Clim Dyn
Bayatvarkeshi M, Zhang B, Fasihi R, Adnan RM, Kisi O, Yuan X (2020) Investigation into the effects of
climate change on reference evapotranspiration using the HadCM3 and LARS-WG. Water 12(3):666
Bodman RW, Karoly DJ, Dix MR, Harman IN, Srbinovsky J, Dobrohotoff PB, Mackallah C (2020) Evalu-
ation of CMIP6 AMIP climate simulations with the ACCESS-AM2 model. J Southern Hemisphere
Earth Syst Sci 70(1):166–179
Boudiaf B, Dabanli I, Boutaghane H, Şen Z (2020) Temperature and precipitation risk assessment under
climate change effect in northeast Algeria. Earth Syst Environ 4(1):1–14
Brusco MJ, Steinley D (2007) A comparison of heuristic procedures for minimum within-cluster sums of
squares partitioning. Psychometrika 72(4):583–600
Chang J, Wang G, Mao T (2015) Simulation and prediction of suprapermafrost groundwater level variation
in response to climate change using a neural network model. J Hydrol 529:1211–1220
Chen Y, Song L, Liu Y, Yang L, Li D (2020) A review of the artificial neural network models for water
quality prediction. Appl Sci 10(17):5776
Chitsazan M, Rahmani G, Neyamadpour A (2015) Forecasting groundwater level by artificial neural net-
works as an alternative approach to groundwater modeling. J Geol Soc India 85(1):98–106
Coppola EA Jr, Rana AJ, Poulton MM, Szidarovszky F, Uhl VW (2005) A neural network model for pre-
dicting aquifer water level elevations. Groundwater 43(2):231–241
Daliakopoulos IN, Coulibaly P, Tsanis IK (2005) Groundwater level forecasting using artificial neural net-
works. J Hydrol 309(1–4):229–240
Derbela M, Nouiri I (2020) Intelligent approach to predict future groundwater level based on artificial neural
networks (ANN). Euro-Mediterranean J Environ Integration 5(3):1–11
Di Luca A, Pitman AJ, de Elía R (2020) Decomposing temperature extremes errors in CMIP5 and CMIP6
models. Geophys Res Lett 47(14):e2020GL088031
Di Nunno F, Granata F (2020) Groundwater level prediction in Apulia region (Southern Italy) using NARX
neural network. Environ Res 190:110062
Emamgholizadeh S, Moslemi K, Karami G (2014) Prediction the groundwater level of bastam plain (Iran)
by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Water Resour
Manage 28(15):5433–5446
Eyring V, Bony S, Meehl GA, Senior CA, Stevens B, Stouffer RJ, Taylor KE (2016) Overview of the
Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization.
Geosci Model Devel 9(5):1937–1958
Ghazi B, Jeihouni E, Kalantari Z (2021) Predicting groundwater level fluctuations under climate change
scenarios for Tasuj plain. Iran Arabian J Geosci 14(2):1–12
Guo D, Wang H (2016) Comparison of a very-fine-resolution GCM with RCM dynamical downscaling in
simulating climate in China. Adv Atmos Sci 33(5):559–570
Gupta V, Singh V, Jain MK (2020) Assessment of precipitation extremes in India during the 21st century
under SSP1–1.9 mitigation scenarios of CMIP6 GCMs. J Hydrol 590:125422
Hamidi M, Sabbagh-Yazdi SR (2008) Modeling of 2D density-dependent flow and transport in porous
media using finite volume method. Comput Fluids 37(8):1047–1055
Hasda R, Rahaman MF, Jahan CS, Molla KI, Mazumder QH (2020) Climatic data analysis for groundwater
level simulation in drought prone Barind Tract, Bangladesh: Modelling approach using artificial neural
network. Groundw Sustain Dev 10:100361
Hassan Z, Shamsudin S, Harun S (2014) Application of SDSM and LARS-WG for simulating and downs-
caling of rainfall and temperature. Theoret Appl Climatol 116(1):243–257
Hewitson BC, Crane RG (1996) Climate downscaling: techniques and application. Climate Res 7(2):85–95
IPCC (2014) Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the
Fifth Assessment Report of the Intergovernmental Panel on Climate Change. In: Core Writing Team,
Pachauri RK, Meyer LA (eds). IPCC, Geneva, Switzerland, p 151
Konapala G, Mishra AK, Wada Y, Mann ME (2020) Climate change will affect global water availability
through compounding changes in seasonal precipitation and evaporation. Nat Commun 11(1):1–10
A.Roshani, M.Hamidi
1 3
Li SY, Miao LJ, Jiang ZH, Wang GJ, Gnyawali KR, Zhang J, Zhang H, Fang K, He Y, Li C (2020) Pro-
jected drought conditions in Northwest China with CMIP6 models under combined SSPs and RCPs for
2015–2099. Adv Clim Chang Res 11(3):210–217
Ligotin VA, Savichev OG, Makushin JV (2010) The long-term changes of seasonal and annual levels and
temperature of ground waters of the top hydro dynamical zone in Tomsk area. Geoecology 13(1):23–
29 (in Russian)
MacQueen J (1967) Some methods for classification and analysis of multivariate observations. Proc Fifth
Berkeley Symp Math Stat Probab 1(14):281–297
Maghsood FF, Moradi H, Massah Bavani AR, Panahi M, Berndtsson R, Hashemi H (2019) Climate change
impact on flood frequency and source area in Northern Iran under CMIP5 scenarios. Water 11(2):273.
https:// doi. org/ 10. 3390/ w1102 0273
Maharjan M, Aryal A, Talchabhadel R, Thapa BR (2021) Impact of Climate Change on the Streamflow
Modulated by Changes in Precipitation and Temperature in the North Latitude Watershed of Nepal.
Hydrology 8(3):117
Maier HR, Dandy GC (1997) Determining inputs for neural network models of multivariate time series.
Comput Aided Civil Infrastruct Eng 12(5):353–368
Mirdashtvan M, Najafinejad A, Malekian A, Sa’doddin A (2021) Sustainable water supply and demand
management in semi-arid regions: optimizing water resources allocation based on RCPs scenarios.
Water Resour Manage 35(15):5307–5324
Moghaddam HK, Moghaddam HK, Kivi ZR, Bahreinimotlagh M, Alizadeh MJ (2019) Developing com-
parative mathematic models, BN and ANN for forecasting of groundwater levels. Groundw Sustain
Dev 9:100237
Mohanty S, Jha MK, Kumar A, Sudheer KP (2010) Artificial neural network modeling for groundwater
level forecasting in a river island of eastern India. Water Resour Manage 24(9):1845–1865
Msowoya K, Madani K, Davtalab R, Mirchi A, Lund JR (2016) Climate change impacts on maize produc-
tion in the warm heart of Africa. Water Resour Manage 30(14):5299–5312
Nasiri M, Moghaddam HK, Hamidi M (2021) Development of multi-criteria decision making methods for
reduction of seawater intrusion in coastal aquifers using SEAWAT code. J Contam Hydrol 242:103848
Natarajan N, Sudheer C (2020) Groundwater level forecasting using soft computing techniques. Neural Comput
Appl 32(12):7691–7708
Nie S, Fu S, Cao W, Jia X (2020) Comparison of monthly air and land surface temperature extremes simu-
lated using CMIP5 and CMIP6 versions of the Beijing Climate Center climate model. Theoret Appl
Climatol 140(1):487–502
Nover DM, Witt JW, Butcher JB, Johnson TE, Weaver CP (2016) The effects of downscaling method on
the variability of simulated watershed response to climate change in five US basins. Earth Interact
O’Neill BC, Kriegler E, Ebi KL, Kemp-Benedict E, Riahi K, Rothman DS, van Ruijven BJ, van Vuuren DP,
Birkmann J, Kok K, Levy M (2017) The roads ahead: Narratives for shared socioeconomic pathways
describing world futures in the 21st century. Glob Environ Chang 42:169–180
Ouhamdouch S, Bahir M (2017) Climate change impact on future rainfall and temperature in semi-arid
areas (Essaouira Basin, Morocco). Environ Process 4(4):975–990
Priestley MD, Ackerley D, Catto JL, Hodges KI, McDonald RE, Lee RW (2020) An Overview of the Extrat-
ropical Storm Tracks in CMIP6 Historical Simulations. J Clim 33(15):6315–6343
Racsko P, Szeidl L, Semenov M (1991) A serial approach to local stochastic weather models. Ecol Model
Rajaee T, Ebrahimi H, Nourani V (2019) A review of the artificial intelligence methods in groundwater
level modeling. J Hydrol 572:336–351
Roshan G, Ghanghermeh A, Nasrabadi T, Meimandi JB (2013) Effect of global warming on inten-
sity and frequency curves of precipitation, case study of Northwestern Iran. Water Resour Manage
Roy DK, Barzegar R, Quilty J, Adamowski J (2020) Using ensembles of adaptive neuro-fuzzy inference
system and optimization algorithms to predict reference evapotranspiration in subtropical climatic
zones. J Hydrol 591:125509
Sahour H, Gholami V, Vazifedan M (2020) A comparative analysis of statistical and machine learning
techniques for mapping the spatial distribution of groundwater salinity in a coastal aquifer. J Hydrol
Semenov MA, Barrow EM (1997) Use of a stochastic weather generator in the development of climate
change scenarios. Clim Change 35(4):397–414
Semenov MA, Brooks RJ, Barrow EM, Richardson CW (1998) Comparison of the WGEN and LARS-WG
stochastic weather generators for diverse climates. Clim Res 10:95–107. https:// doi. org/ 10. 3354/ cr010 095
Groundwater Level Fluctuations inCoastal Aquifer: Using…
1 3
Sha J, Li X, Wang ZL (2019) Estimation of future climate change in cold weather areas with the LARS-WG
model under CMIP5 scenarios. Theoret Appl Climatol 137(3):3027–3039
Shahvari N, Khalilian S, Mosavi SH, Mortazavi SA (2019) Assessing climate change impacts on water
resources and crop yield: a case study of Varamin plain basin Iran. Environ Monit Assess 191(3).
https:// doi. org/ 10. 1007/ s10661- 019- 7266-x
Sharma P, Madane D, Bhakar SR (2021) Monthly streamflow forecasting using artificial intelligence
approach: a case study in a semi-arid region of India. Arab J Geosci 14(22):1–10
Shen C (2018) A transdisciplinary review of deep learning research and its relevance for water resources
scientists. Water Resour Res 54(11):8558–8593
Srivastava A, Grotjahn R, Ullrich PA (2020) Evaluation of historical CMIP6 model simulations of extreme
precipitation over contiguous US regions. Weather Clim Extrem 29:100268
Sun Y, Wendi D, Kim DE, Liong SY (2016) Technical note: Application of artificial neural networks in
groundwater table forecasting – a case study in a Singapore swamp forest. Hydrol Earth Syst Sci
20(4):1405–1412. https:// doi. org/ 10. 5194/ hess- 20- 1405- 2016
Szidarovszky F, Coppola EA Jr, Long J, Hall AD, Poulton MM (2007) A hybrid artificial neural network-
numerical model for ground water problems. Groundwater 45(5):590–600
Tabari H (2020) Climate change impact on flood and extreme precipitation increases with water availability.
Sci Rep 10(1):1–10
Tan ML, Yusop Z, Chua VP, Chan NW (2017) Climate change impacts under CMIP5 RCP scenarios on
water resources of the Kelantan River Basin, Malaysia. Atmos Res 189:1–10
Taormina R, Chau KW, Sethi R (2012) Artificial neural network simulation of hourly groundwater levels in
a coastal aquifer system of the Venice lagoon. Eng Appl Artif Intell 25(8):1670–1676
Theodossiou N (2016) Assessing the impacts of climate change on the sustainability of groundwater aqui-
fers. Application in Moudania Aquifer in N. Greece. Environ Process 3(4):1045–1061
Thorne KM, Elliott-Fisk DL, Freeman CM, Bui TV, Powelson KW, Janousek CN, Buffington KJ, Takekawa
JY (2017) Are coastal managers ready for climate change? A case study from estuaries along the
Pacific coast of the United States. Ocean Coast Manag 143:38–50
Warnatzsch EA, Reay DS (2019) Temperature and precipitation change in Malawi: Evaluation of CORDEX-
Africa climate simulations for climate change impact assessments and adaptation planning. Sci Total
Environ 654:378–392
Wilby RL, Wigley TM (1997) Downscaling general circulation model output: a review of methods and limi-
tations. Prog Phys Geogr 21(4):530–548
Williams KD, Copsey D, Blockley EW, BodasSalcedo A, Calvert D, Comer R, Davis P, Graham T, Hewitt
HT, Hill R, Hyder P (2018) The Met Office global coupled model 3.0 and 3.1 (GC3. 0 and GC3. 1)
configurations. J Adv Model Earth Syst 10(2):357–380
Xin X, Wu T, Zhang J, Yao J, Fang Y (2020) Comparison of CMIP6 and CMIP5 simulations of precipita-
tion in China and the East Asian summer monsoon. Int J Climatol 40(15):6423–6440
Yan T, Bai J, Arsenio T, Liu J, Shen Z (2019) Future climate change impacts on streamflow and nitro-
gen exports based on CMIP5 projection in the Miyun Reservoir Basin. China Ecohydrol Hydrobiol
Yoon H, Jun SC, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural net-
works and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol
Zhang Y, You Q, Chen C, Ge J (2016) Impacts of climate change on streamflows under RCP scenarios: A
case study in Xin River Basin, China. Atmos Res 178:521–534
Zhao L, Dai T, Qiao Z, Sun P, Hao J, Yang Y (2020) Application of artificial intelligence to wastewater
treatment: a bibliometric analysis and systematic review of technology, economy, management, and
wastewater reuse. Process Saf Environ Prot 133:169–182
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and
institutional affiliations.
... Taylor diagrams were also employed to understand better the results predicted with observed data (Fig. 5). In the diagram, the horizontal axis illustrates the observation data, while the vertical axis shows the standard deviation (Roshani and Hamidi, 2022). It confirms that the model is performing properly when the points approach the hypotenuse, indicating that the standard deviation of the predicted data is near that of the observation data. ...
Full-text available
Awareness about the impact of climate change on the change rate of dust phenomenon has become a crucial problem due to public health, climate, and air quality. It has been recognized that the Tigris- Euphrates alluvial plain is the main source of dust storms in the Middle East and southwest Asia. In this work, the effects of different variables, including minimum temperature (Tmin), maximum temperature (Tmax), precipitation (Pr), mean wind speed (MWS), humidity (H), and vegetation (Veg) on dust activity are investigated, and Aerosol optical depth (AOD) was predicted by Long Short-Term Memory (LSTM) from 2021 to 2040. HadGEM3-GC was selected to generate the climatic patterns under Shared Socioeconomic Pathways (SSP2-4.5 and SSP5-8.5) scenarios until 2040. The Long Ashton Research Station Weather Generator (LARS-WG 6) software was used to downscale the General Circulation model (GCM). Moreover, Mann-Kendall and Sen's slope tests are utilized to assess a significant trend. Tmax, Tmin, Pr, and Veg were determined to predict AOD that had a highly close relationship with AOD (r=0.865, R2=0.752, RMSE=0.079, and MAE=0.065). The results indicated that AOD would rise gradually in two upcoming decades with 10.5% and 15.2% related to base period (2000-2020) under two scenarios. Understanding of dust phenomenon of future prospective could help policymakers to provide a better situation of air quality.
... In recent years, machine learning algorithms have been used more and more widely and with better results. A neural network model was used to predict the future climate of the Iranian Caspian Sea for the next 20 years under the RCP4.5 and RCP8.5 emission scenarios with more simulation accuracy [21]. LARS-WG was utilized to predict future (2015-2044) climate variables in central Iran, and an artificial neural network was used to establish the relationship between climate variables and snow water equivalents during the baseline period to predict future snow water equivalents [22]. ...
Full-text available
Climate is closely related to human life, food security and ecosystems. Forecasting future climate provides important information for agricultural production, water resources management and so on. In this paper, historical climate data from 1962–2001 was used at three sites in Tianjin Baodi, Tianjin and Tanggu districts as baseline and the model parameters were calibrated by the Long Ashton Research Station Weather Generator (LARS-WG). 2m-temperatures in 2011–2020 were verified under two scenarios, representative concentration pathway (RCP) 4.5 and RCP8.5 in different atmospheric circulation models with optimal minimum 2m-temperatures at the three sites. From 2031–2050, Tianjin will be using more moderate minimum 2m-temperatures in future simulations. Support vector machines (SVM) were used to optimize the simulated data to obtain more accurate future maximum and minimum 2m-temperatures for the three sites. The results showed that the determinant coefficient of LARS-WG simulation was 0.8 and SVM optimized determinant coefficient was 0.9 which greatly improved the prediction accuracy. The minimum and maximum future 2m-temperatures optimized under European Community Earth System Model (EC-EARTH) were relatively low and the same future 2m-temperatures optimized under Hadley Centre Global Environment Model Earth System (Had-GEM2-ES4) were high especially in the RCP8.5 scenario which simulated 2051–2070 climate. The SVM optimization showed that the maximum and minimum 2m-temperatures were in general agreement with the original simulation values.
... Although the LARS-WG 6.0 software was implemented to downscale the GCM models with the AR5 scenarios, the practical guide of this model characterizes its general application in modeling with the outputs of the GCM models (Semenov and Barrow 2002). This method was used in similar studies conducted by Roshani and Hamidi (2022) and Sha et al. (2021). This study used the outputs of the GCM models with the AR6 scenarios. ...
Full-text available
The main necessity of sustainable water resource management is an accurate estimation of the water demands. Therefore, all the factors affecting water demand in different sectors should be considered. Based on recent investigations, climate change has impacted the hydrologic system and subsequently the water demands. Thus, this study attempts to identify the potential impacts of climate change on the water resources management scenarios in the future horizons at the Moghan Plain, northwest of Iran. These scenarios will be compared and afterward, their impacts on water demands will be determined. For this purpose, the Water Evaluation and Planning (WEAP) model was employed to simulate the water basin resources system for 2021–2040, 2041–2060, and 2061–2080 future periods. Additionally, nine scenarios for water resources management were developed in the WEAP model by considering the impacts of climate change. The climate change scenarios were based on a combination of different Global Climate Models (GCMs) outputs for the climate change scenarios SSP245 and SSP585. Although all the agricultural water demands of the basin were fully met under the different climate changes scenarios, the external driving forces, i.e., the development of agricultural farms and the supply of environmental flow requirements, and their impacts on the region have shown the necessity of investigating and examining the adaptation scenarios in this region to provide the necessary water resources for agriculture. Furthermore, the maximum increase and decrease of the required water demands respectively were observed in the scenarios of external control, increasing area of the irrigated agriculture by up to 29.4%, and adaptation scenario of upgrading irrigation systems and increasing irrigation efficiency by up to 18.28% on the climate change scenario SSP585. The outcomes of this study will help decision-makers regarding the prioritization of climate change adaptation strategies toward more sustainable water resources management schemes.
Full-text available
The main objective of this paper is to analyze the impact of climate change on water resources management and groundwater quantity and quality in the coastal agricultural Almyros Basin, in Greece. Intensive groundwater abstractions for irrigation and nitrogen fertilization for crop production maximization, have caused a large water deficit, nitrate pollution, as well as seawater intrusion in the Almyros aquifer system. Multi-model climate projections for Representative Concentration Pathways (RCPs 4.5 and 8.5) from the Med-CORDEX database for precipitation and temperature have been used to evaluate the impacts of climate change on the study area. The multi-model climate projections have been bias-corrected with Delta, Delta change of Mean and Variance, Quantile Delta Change, Quantile Empirical Mapping, and Quantile Gamma Mapping methods, and statistically tested to find the best GCM/RCM multi-model ensemble. Simulation of coastal water resources has been performed using an Integrated Modelling System (IMS) that contains connected models of surface hydrology (UTHBAL), groundwater hydrology (MODFLOW), nitrate leaching/crop growth (REPIC), nitrate pollution (MT3DMS), and seawater intrusion (SEAWAT). The results indicate that the best climate multi-model ensemble consists of three (3) climate models for both RCP4.5 and RCP8.5 using the Quantile Empirical Mapping bias-correction method. The IMS was applied for historical and future periods with observed and simulated meteorological inputs (e.g. precipitation and temperature) and various irrigation and agronomic scenarios and water storage works development (i.e. reservoirs). The results indicate that at least deficit irrigation and deficit irrigation along with rain-fed cultivation schemes, combined with or without the development and operation of reservoirs, should be applied to overcome the degradation of groundwater quality and quantity in the study basin. Based on the findings of this work, the water resources management should be adaptive to tackle the water resources problems of the Almyros Basin.
The inclusion of new strategies is crucial to achieve the different targets of the sustainable development goals for the guarantee of supply in the different cities and reduction the consumption of non-renewable resources. The development of these strategies implies the improvement of the sustainability indicators and green rating systems of the city. This research proposes a decarbonisation strategy, which includes different optimization procedures based on a self-calibration process according to recorded flow values over time. These stages are integrated into one tool to define the best making decision in the management of the supply system, analysing whether self-consumption of energy is feasible. It was applied on the Bahamas. The application of the strategy enabled the decrease of the annual consumption of energy equal to 32%. The self-consumption could represent 30% of the consumed energy of the pump station. The making decision to define the best operation strategy, establishing a Levelized Cost of Energy around 0.12 €/kWh when the feasibility of using photovoltaic systems combined with micro hydropower was done. It implies the reduction of 40% of the tCO2 emission, getting a cost of carbon abatement values around 400 €/tCO2 for different discount rates and scenarios.
Full-text available
Climate as one of the key factors in water resources management affects the amount of water in the hydrological cycle, which subsequently impacts the level of water availability. Considering the challenges that the South Alborz Region, Iran is currently facing in supplying water for various consumers; in this study, the climate change adaptation scenarios are investigated for sustainable water supply and demand. This study uses a procedure in which five different adaptation approaches, under RCPs scenarios, were established using the WEAP model to assess the impacts of various adaptation strategies on increasing the balance between water supply and demand over current and 2020s accounts. The findings suggest an imbalance between supply and demand in the current situation with the greatest imbalance in domestic use while the minimum in the industrial sector. The results of assessing adaptive scenarios show that various scenarios have different effects on balancing the water supply and demand by different consumers; on the other hand, the scenarios that directly affect domestic water demand have the greatest effect on minimizing the gap between supply and demand in the region; therefore, the options for decreasing the population demand along with diminishing the losses in the domestic water distribution network are the most effective alternatives for balancing supply and demand under all of the climate scenarios. The findings of this research indicate that adaptive management with the focus on restricting demand helps actively management of water resources in the regions with scarce water resources.
Full-text available
It is unambiguous that climate change alters the intensity and frequency of precipitation and temperature distribution at the global and local levels. The rate of change in temperature in the northern latitudes is higher than the worldwide average. The annual distribution of the precipitation over the Himalayas in the northern latitude shows substantial spatial and temporal heterogeneity. The precipitation and temperature are the major driving factors that impact the streamflow and water availability in the basin, illustrating the importance of the research on the impact of climate change on streamflow attributed by varying precipitation and temperature in the Thuli Bheri river basin (TBRB). Multiple climate models were used to project and evaluate the precipitation and temperature distribution changes in temporal and spatial domains. To analyze the potential impact of climate change on the streamflow in the basin, the Soil and Water Assessment Tool (SWAT) hydrological model was used. The climate projection was carried out in the three future time windows. The result shows that the precipitation fluctuates between approximately-12% to +50%, the maximum temperature varies between-7% to +7%, and the minimum temperature rises from +0.7% to +5% under intermediate and high emission scenarios. In contrast, the streamflow in the basin varies from-40% to +85%. Thus, there is a significant trend in the temperature increment and precipitation reduction in the basin. Further, the relationship between precipitation and temperature with streamflow shows a substantial dependency between them. The variability in the precipitation and streamflow is well represented by the water yield in the basin, which plays an important role in the sustainability of the water-related projects in the basin and downstream to it. This also helps quantify the amount of water available for hydropower generation, agricultural production, and balancing the water ecosystem in the TBRB.
Full-text available
Coastal aquifers world-wide are being confronted with several major challenges, such as overextraction of groundwater, climate change impacts, contamination by wastewater, and saltwater intrusion into water resources. Climate change induced alteration of the hydrological cycle is one of the main threats to future accessibility of water resources. Effective prediction of possible impacts of climate change on groundwater reserves, a crucial water resource, could be of great importance for sustainable water management. In a comparative study, artificial neural network (ANN), least square support vector machine (LSSVM), and nonlinear autoregressive network with exogenous inputs (NARX) models was applied to evaluate possible impacts of three representative concentration pathways (RCP) climate change scenarios (RCP2.6, RCP4.5, RCP8.5) on groundwater levels in Tasuj Plain, Iran. Four general circulation models (GCM) was used to predict temperature and precipitation values for the future period 2022–2050 and found that future temperature increased, while the amount of precipitation decreased. To improve the accuracy of three models in groundwater level prediction, db4 wavelet transform was applied. The results indicated that the Wavelet-NARX approach gave the best accuracy in forecasting groundwater level in the study area. In all cases, prediction indicated that groundwater level in all representative wells would decline in future.
Full-text available
Northwest China is one of the most arid regions in the world and has experienced intriguing climate warming and humidification. Nonetheless , future climate conditions in Northwest China still remain uncertain. In this study, we applied an ensemble of the 12 latest model simulations of the Coupled Model Intercomparison Project Phase 6 (CMIP6) to assess future drought conditions until 2099 in Northwest China, as inferred from the Palmer Drought Severity Index (PDSI). Future drought conditions were projected under three climate change scenarios through the combination of shared socioeconomic pathways (SSPs) and representative concentration pathways (RCPs), namely, SSP126 (SSP1 þ RCP2.6, a green development pathway), SSP245 (SSP2 þ RCP4.5, an intermediate development pathway), and SSP585 (SSP5 þ RCP8.5, a high development pathway). For 2015e2099, drought severity showed no trend under SSP126, in contrast, for the SSP245 and SSP585 scenarios, a rapid increase during 2015e2099 was observed, especially under SSP585. We also found that the drought frequency in Northwest China under SSP585 was generally lower than that under SSP126 and SSP245, although the drought duration under SSP585 tended to be longer. These findings suggest the green development pathway in drought mitigation and adaptation strategies in Northwest China, an arid and agricultural region along the Silk Road.
Full-text available
The most recent version of the ACCESS-AM2 atmosphere-only climate model is introduced with results from the CMIP6 Atmospheric Model Intercomparison Project (AMIP) experiments configured with two land-surface models: CABLE and JULES. AMIP simulations are required as part of the CMIP6 core experiments. They are forced by prescribed time-varying observed sea surface temperature and sea-ice variations as well as variations in natural and anthropogenic external forcings. We evaluate the performance of the two configurations using three historical realisations for each. Model biases are estimated both globally and for the Australian region. The model shows close agreement with observed interannual variations of global-mean temperature across the latitude range 65°N–65°S. This is also true for the land-only temperature for 65°N–65°S, and a more stringent test of the model is driven by specified observed sea surface temperatures. Patterns of mean precipitation are simulated reasonably well, although there are biases in the amount and distribution of precipitation, typical of longstanding problems in representing this aspect of the climate. Selected features of the atmospheric circulation are discussed, including air temperatures and wind speeds. For the Australian region, in addition to examining the climatological patterns of temperature and precipitation, important drivers of climate variability are reviewed: El Niño-Southern Oscillation, the Indian Ocean Dipole and the Southern Annular Mode. In general, the correlation patterns for precipitation simulated by ACCESS-AM2 are somewhat weaker than in observations, although the ensemble means show better agreement than individual ensemble members. Overall, the two different land-surface schemes perform similarly. ACCESS-AM2 has reduced root mean square errors for both temperature and precipitation of around 15–20% at the global scale compared to the older CMIP5 versions of the model: ACCESS 1.0 and ACCESS 1.3.
Full-text available
Water quality prediction plays an important role in environmental monitoring, ecosystem sustainability, and aquaculture. Traditional prediction methods cannot capture the nonlinear and non-stationarity of water quality well. In recent years, the rapid development of artificial neural networks (ANNs) has made them a hotspot in water quality prediction. We have conducted extensive investigation and analysis on ANN-based water quality prediction from three aspects, namely feedforward, recurrent, and hybrid architectures. Based on 151 papers published from 2008 to 2019, 23 types of water quality variables were highlighted. The variables were primarily collected by the sensor, followed by specialist experimental equipment, such as a UV-visible photometer, as there is no mature sensor for measurement at present. Five different output strategies, namely Univariate-Input-Itself-Output, Univariate-Input-Other-Output, Multivariate-Input-Other(multi), Multivariate-Input-Itself-Other-Output, and Multivariate-Input-Itself-Other (multi)-Output, are summarized. From results of the review, it can be concluded that the ANN models are capable of dealing with different modeling problems in rivers, lakes, reservoirs, wastewater treatment plants (WWTPs), groundwater, ponds, and streams. The results of many of the review articles are useful to researchers in prediction and similar fields. Several new architectures presented in the study, such as recurrent and hybrid structures, are able to improve the modeling quality of future development.
Accurate and reliable streamflow forecasting is paramount in the field of water resource planning and management, especially in semi-arid regions. However, streamflow time series are highly complex and non-linear in nature; traditional or physical-based models may fail to capture the complexity and maintain the robustness of the datasets. Therefore, the present study aims to improve the forecasting accuracy and reduce the uncertainty in the datasets by using the data-driven approach such as artificial neural network (ANN) that can efficiently handle the non-linearity in the large and complex hydrological data. This study method includes two steps: i.e., first to develop the ANN models using different combinations of inputs such as rainfall, temperature, and streamflow lag by one or two and then to validate the developed models to forecast the streamflow by using a total of four performance evaluation indices such as correlation coefficient (R), root mean square error (RMSE), modified Nash-Sutcliff efficiency (MNSE), and modified index of agreement (MIA). The proposed method is demonstrated in Jakham reservoir located in Pratapgarh district, Rajasthan, India, for improving the accuracy of monthly streamflow forecasting over a 40-year period (1975–2015). We found that increasing the number of input parameters improves the accuracy of the model and enhance its performance. According to the results, the ANN models 5 and 6 (M5 and M6) showed significant variation in the performance evaluation criteria. This clearly indicates that ANN model with an input combination of lag one or two streamflow (i.e., model M5 and M6) is performed better when compared to a model that incorporates only monthly rainfall and monthly lag one or two rainfall as inputs. Overall, the application of ANN models M5 and M6 (with lag one and two streamflow as an input) can forecast monthly streamflow forecasting with better accuracy.
Unplanned pumping of groundwater in the past two decades has caused many regional problems and tensions, leading to seawater intrusion into coastal aquifers. The main objective of this paper is the use of a Multi-Criteria Decision-Making (MCDM) approach combining with numerical simulation for reducing seawater intrusion in the Tajan coastal aquifer located on the southern seashores of the Caspian Sea, Iran, taking into account economic, social, and environmental issues. The MODFLOW code was used to simulate the groundwater flow. MT3DMS and SEAWAT codes were used to simulate the solute transport and seawater intrusion. A 10-year period from 2010 to 2020 was simulated for evaluating the current conditions and forecasting the future conditions of the aquifer. The results indicated an increase in the extent of seawater intrusion. To assess the proposed eleven curative solutions, the economic, social, and environmental criteria such as efficiency of applying of curative solutions in improvement of the aquifer's water level and efficiency of applying of curative solutions on reduction in the extent of the seawater intrusion were weighted using the Analytic Hierarchy Process (AHP) method. The results of the AHP method showed that the criterion of efficiency of applying of curative solutions in improvement of the aquifer's water level with the weight of 0.311 was the most important one. Three multi-criteria decision making methods namely, Simple Additive Weighting (SAW), Technique for Order Performance by Similarity (TOPSIS), and VIse Kriterijumska Optimizacija kompromisno Resenje (VIKOR) were utilized to select the best curative solution. The solution of 10% reduction of pumping rate and the construction of Gelvard dam in the SAW and TOPSIS methods and the solution of 3% reduction of pumping rate and the construction of Gelvard dam in the VIKOR method ranked first. Combined techniques namely, the Rank Average Method, Borda's Method, and Copeland's Method were used to develop a consensus on prioritizing curative solutions for the Tajan Aquifer. The results of these techniques showed that the solution of 10% reduction in pumping rate along with the construction of the Gelvard dam was the best. The results of simulating this solution demonstrated a 1.91 m improvement in the groundwater level of the aquifer in the MODFLOW code and a 361.5-m recede in seawater intrusion length along the coast in the SEAWAT code.
To depict hydrogeological variables and understand the physical processes taking place in a complex hydrogeological system, artificial neural networks (ANNs) are widely used as a good alternative approach to tedious numerical models. The aim of this study was to predict the dynamic fluctuations in piezometric levels in Nebhana aquifers (NE Tunisia) using ANNs. A correlation analysis carried out between piezometry, evapotranspiration and rainfall during the period 2000 to 2018 revealed that piezometric levels were influenced by monthly rainfall, evapotranspiration and initial water table level. These informative variables were used as input variables to train the ANN to predict future monthly water table levels for four hydrogeological systems. The minimal and maximal computed relative errors were 0.01 and 19.00%, respectively; root mean square error (RMSE) varied between 0.41 and 2.06; the determination coefficient (R2) ranged between 0.93 and 0.99; and the Nash–Sutcliffe (NASH) efficiency coefficient ranged from 85.32 to 97.82%. To test the generalization capacity of the developed ANN models, we used the ANNs to predict monthly piezometric levels for the period September 2016 to August 2018. The results were satisfactory for all piezometers. Indeed, the minimal and maximal computed RE were − 12.00 and 0.03%, respectively; RMSE was between 0.44 and 1.74; R2 varied between 0.95 and 0.98; the NASH coefficient ranged from 60.00 to 98.99%. These models developed in this study can be adopted for future groundwater level prediction to accurately estimate trends in piezometric levels as well as water pumping costs.
Accurate prediction of reference evapotranspiration (ET0) is essential for efficient planning and management of limited water resources through proper irrigation scheduling. The FAO-56 Penman-Monteith approach to ET0 estimation was adopted to compute ET0 from data obtained in a subtropical climatic region in Bangladesh. Quantified ET0 values along with the meteorological variables for two other Stations located in south Florida, USA, were directly obtained from the USGS website. A commonly used machine learning algorithm, Adaptive Neuro Fuzzy Inference System (ANFIS), was employed to predict daily ET0 using regional meteorological data (e.g., daily maximum and minimum air temperatures, wind speed, relative humidity, sensible heat flux, latent heat and sunshine duration). Four optimization algorithms were employed to tune ANFIS, resulting in hybrid models: Biogeography-based Optimization (BBO-ANFIS), Firefly Algorithm (FA-ANFIS), Particle Swarm Optimization (PSO-ANFIS), and Teaching-Learning-based Optimization (TLBO-ANFIS). These models’ performances were compared with the standard ANFIS model with parameters tuned using an Integrated Least Squares and Backpropagation Gradient Descent (LSGD) algorithm. Decision theories were applied to assess the accuracy of the predictions as well as to rank prediction models based on eight statistical indices. Results indicated that FA-ANFIS resulted in the most accurate ET0 predictions. In the next stage, ensembles of these prediction models were compared to determine whether the ensemble models resulted in more reliable predictions than the standalone models. To develop each ensemble, three decision theories were applied: Shannon’s Entropy, Coefficient of Variation, and Grey Relational Analysis. All three ensemble approaches provided similar results, showing ensemble prediction methods to perform better than most individual models.