Saeid Janizadeh’s research while affiliated with University of Hawaiʻi at Mānoa and other places

In this article, we aim at the prediction of possible locations of already defunct historical objects with a defensive function (HODFs) in Slovakia, which have not been found and documented so far, using three machine learning methods. Specifically, we used the support vector machine, k-nearest neighbors, and random forest algorithms, which were trained based on the following five factors influencing the possible occurrence of HODFs: elevation, distance from a river, distance from a settlement, lithological rock type, and type of representative geoecosystems. Training and testing datasets were based on a database of already documented 605 HODFs, which were divided into 70% of training samples and 30% of testing samples. All of the three models reached the AUC-ROC value over 0.74 based on the testing dataset. The best performance was recorded by the random forest predictive model with the AUC-ROC value equal to 0.79. The results of the random forest model were also validated with the recently documented HODFs via the archeological research. Supplementary Information The online version contains supplementary material available at 10.1038/s41598-024-82290-1.

This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawaiʻi Island, Hawaiʻi. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms-Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA)-were employed to map areas susceptible to wildfire. To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWO-XGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics-sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs)-were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on Hawaiʻi Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWO-XGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOA-XGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors. The wildfire susceptibility maps generated in this study can be used by local authorities for wildfire management and fire suppression activity.

In this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, and Bayesian) were applied to predict forest fire hazard in the Chalus Rood watershed in the Mazandaran Province, Iran. Data from 108 historical forest fire events collected through field surveys were applied as the basis of the analysis. About 70% of the data were used for training the models, while the remaining 30% was used for testing. A total of 14 environmental, climatic, and vegetation variables were used as input features to the models to predict forest fire probability. After conducting a multicollinearity test on the independent variables, the GLM and the ensemble models were applied for modeling. The efficiency of the models was evaluated using receiver operating characteristic (ROC) curve parameters. Results from the validation process, based on the area under the ROC curve (AUC), showed that the GLM, PLS-GLM, boosted-GLM, Bagging-GLM, and Bayesian-GLM models had efficiencies of 0.79, 0.75, 0.81, 0.84, and 0.85, respectively. The results indicated that all ensemble methods, except the PLS algorithm, improved the performance of the GLM model in modeling forest fire hazards in the Chalus Rood watershed, with the Bayesian algorithm being the most efficient method among them.

The objective of this research is to examine the possible impacts of climate change on landslide susceptibility in Iran. To accomplish this, 15 independent variables including 11 static variables, and 4 climatic dynamic variables that can affect landslide susceptibility were applied to predict landslide susceptibility from 3903 landslide susceptibility locations. These data points were separated into two phases for training and testing. Phase 6 of the Coupled Model Intercomparison Project (CMIP6) downscaled the data and enabled the combination of nine global climate models (GCMs) under shared socio-economic pathways (SSPs) to examine the impacts of climate change. The combination of demographic (SSP) and climatic (representative concentration pathways) scenarios were used (e.g., SSP1-2.6 and SSP5-8.5 were used to predict precipitation impacts resulting from climate change at four future dates – 2030, 2050, 2070, and 2090. The machine learning algorithms extreme gradient boosting (XGBoost) and random forest (RF) were employed to model and map landslide susceptibility. The area under curve (AUC) results generated with the testing (validation) phase demonstrates that the predictive power is suitable. The RF model produced the best results (AUC= 0.95). The XGBoost model was not as robust (AUC= 0.93). The investigation of how climate change effects on landslide susceptibility in Iran revealed that climate change should cause shifts in the ranges of susceptibility at different times. The RF model using CMIP SSP1-2.6 predicted the proportion of sites with very-high susceptibility in 2030, 2050, 2070, and 2090 would be 11.45, 11.42, 11.55, and 11.38%. The proportion of sites with high susceptibility would be 15.93, 16.03, 15.79, and 15.95%. And sites with moderate susceptibility will comprise 21.54, 20.92, 21.41, and 20.92%. With the CMIP SSP5-8.5 model, the percentages of locations with very-high susceptibility would be 11.59, 11.70, 11.88, and 12.17%.

This study presents the performance of stand-alone and novel hybrid models combining the feed-forward neural network (FFNN) and extreme gradient boosting (XGB) with the genetic algorithm (GA) optimization to determine the riverine flood potential at a local spatial scale, which is represented by the Gidra river basin, Slovakia. Eleven flood factors and a robust flood inventory database, consisting of 10,000 flood and non-flood locations, were used. Using the FFNN, XGB, GA-FFNN and GA-XGB models, 16.5%, 11.0%, 17.1%, and 12.3% of the studied basin, respectively, is characterized with high to very high riverine flood potential. The applied models resulted in very high accuracy, that is, AUC = 0.93 in case of the FFNN stand-alone model and AUC = 0.96 in case of the XGB stand-alone model. The GA algorithm was able to raise the value of AUC for the hybrid GA-FFNN and GA-XGB models to 0.94 and 0.97, respectively. The results of this study can be useful, especially, for the identification of the areas with the highest potential for riverine floods within the next updating of the Preliminary Flood Risk Assessment, which is being carried out based on the EU Floods Directive.

With advances in remote-sensing technology and higher-quality products, the field of spectral indices has experienced a sizeable progressive evolution. These spectral indices computed by using different brands of remote-sensing products and applying additive, subtractive, or normalizing operations, have been and are being devised to detect diverse objects in various spheres of our planet. For instance, there are spectral indices that detect and delineate plant leaf moisture, that biome comes under biosphere, at distinctive spatial scales. There are other indices that are used to extract elements from the lithosphere like iron oxide content, or to show clay mineral content, etc. Similarly, there are spectral indices to detect various elements which constitute other spheres of our planet. In this work, we have used the Web of Science (WoS) database from 1999 to 2022 and searched for only English language research journals, book chapters, books, and scientific reports. We found 2227 documents in all the categories to perform a systematic, scientometric review regarding spectral indices used for the identification of elements constituting various objects of the five different spheres. The primary objective of this chapter is to present a systematic and scientometric review of spectral indices used for quantification of different elements of all the spheres of our planet relating to lithosphere, hydrosphere, atmosphere, biosphere, and anthroposphere, across remote-sensing platforms and sensors. The study also examines the rationale of spectral indices across the ever-advancing remote-sensing platform and sensors, and their future challenges, and investigates the challenges and prospects of this domain of study. This study will be useful for acquainting new researchers with the use spectral indices for their specific objectives.