This paper couples an adaptive neuro-fuzzy inference system (ANFIS), with two heuristic-based computation methods namely biogeography-based optimization (BBO) and BAT algorithm (BA) with GIS to map flood susceptibility in a region of Iran. These algorithms have been used for flood modelling, infrequently. A total of 287 flood locations were randomly categorized into training (70%; 201 floods), and validation (30%; 86 floods) datasets for modelling process and evaluation. The Step-wise Weight Assessment Ratio Analysis (SWARA) technique was applied to evaluate the role of nine dominant factors on flood occurrence. The results of using the ANFIS and the artificial intelligence ensemble algorithms were three flood susceptibility maps. Results indicated that the ANFIS-BBO had the highest accuracy in comparison with the ANFIS and ANFIS-BA models in flood modelling. In addition, BBO algorithm showed its great potential by considering higher accuracy and lower computational time, in mapping and assessment of flood susceptibility.

In this study, groundwater springs potentiality maps were prepared using a novel integrated model, support vector regression (SVR) with genetic algorithm (GA), for the Jerash and Ajloun region, Jordan.The conditioning factors such as altitude, aspect, slope angle, plan curvature, stream power index, topographic wetness index, length of slope, distance from drainage network, lithology, distance from faults, land use and normalised difference vegetation index were considered to map the groundwater spring potentiality. GA was used for two purposes. First, GA was used to optimize the hyper-parameters of the radial basis function (RBF) kernel of SVR model. Second, GA in combination with SVR was used as feature selection (FS).The results of these models were compared with common grid search (GS) method used in most of the studies. The GS method was employed to calculate the parameters related to the SVR model and also hyper-parameters of RBF kernel. The results show optimum values of the kernels in the SVR model and selecting the optimal features which have the most contribution in modeling were the major steps in modeling and also in achieving a desirable precision level.

Flooding is a recurrent hazard occurring worldwide, resulting in severe losses. The preparation of a flood susceptibility map is a non-structural approach to flood management before its occurrence. With recent advances in artificial intelligence, achieving a high-accuracy model for flood susceptibility mapping (FSM) is challenging. Therefore, in this study, various artificial intelligence approaches have been utilized to achieve optimal accuracy in flood susceptibility modeling to address this challenge. By incorporating the grey wolf optimizer (GWO) metaheuristic algorithm into various models—including recurrent neural networks (RNNs), support vector regression (SVR), and extreme gradient boosting (XGBoost)—the objective of this modeling is to generate flood susceptibility maps and evaluate the variation in model performance. The tropical Manimala River Basin in India, severely battered by flooding in the past, has been selected as the test site. This modeling utilized 15 conditioning factors such as aspect, enhanced built-up and bareness index (EBBI), slope, elevation, geomorphology, normalized difference water index (NDWI), plan curvature, profile curvature, soil adjusted vegetation index (SAVI), stream density, soil texture, stream power index (SPI), terrain ruggedness index (TRI), land use/land cover (LULC) and topographic wetness index (TWI). Thus, six susceptibility maps are produced by applying the RNN, SVR, XGBoost, RNN-GWO, SVR-GWO, and XGBoost-GWO models. All six models exhibited outstanding (AUC above 0.90) performance, and the performance ranks in the following order: RNN-GWO (AUC: 0.968) > XGBoost-GWO (AUC: 0.961) > SVR-GWO (AUC: 0.960) > RNN (AUC: 0.956) > XGBoost (AUC: 0.953) > SVR (AUC: 0.948). It was discovered that the hybrid GWO optimization algorithm improved the performance of three models. The RNN-GWO-based flood susceptibility map shows that 8.05% of the MRB is very susceptible to floods. The modeling found that the SPI, geomorphology, LULC, stream density, and TWI are the top five influential conditioning factors.

Fires are one of the most destructive forces in natural ecosystems. This study aims to develop and compare four hybrid models using two well-known machine learning models, support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS), as well as two meta-heuristic models, the whale optimization algorithm (WOA) and simulated annealing (SA) to map wildland fires in Jerash Province, Jordan. For modeling, 109 fire locations were used along with 14 relevant factors, including elevation, slope, aspect, land use, normalized difference vegetation index (NDVI), rainfall, temperature, wind speed, solar radiation, soil texture, topographic wetness index (TWI), distance to drainage, and population density, as the variables affecting the fire occurrence. The area under the receiver operating characteristic (AUROC) was used to evaluate the accuracy of the models. The findings indicated that SVR-based hybrid models yielded a higher AUROC value (0.965 and 0.949) than the ANFIS-based hybrid models (0.904 and 0.894, respectively). Wildland fire susceptibility maps can play a major role in shaping firefighting tactics.

Classification and Regression Tree (CART) is one of the well-known and widely-used machine learning and data mining models that has been used in various fields. Despite the high level of interpretability of this model, its results usually are less accurate than other models. However, this model offers high interpretability that makes it an attractive and appropriate model for decision makers. To address the low accuracy of the CART model, this paper developed two new and enhanced CART-based algorithms which can provide both high interpretability and high accuracy for flood susceptibility mapping. In the developed models, various hyperparameters of the CART were explicitly tuned using the genetic algorithm (GA) and grid search (GS) methods. Eleven variables and 222 flood locations were used in Sardabroud watershed in Iran for modeling. The locations were split into a training dataset (147 locations) and a validation dataset (74 locations). The results showed area under the receiver operating characteristic curve (AUROC) values of 0.884, 0.927 and 0.908 respectively for the CART, CART-GS and CART-GA models in validation run. According to this study, the GA and GS were successful in the tuning of hyperparameters for the CART. The results show that the developed models can produce the output that satisfies both accuracy and interpretability criteria.

The study aims to evaluate the long-term accuracy of global precipitation (Climate Prediction Center (CPC) and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks – Climate Data Record (PERSIANN-CDR)) along with raingauge datasets at multiple temporal scales in the Vu Gia Thu Bon basin, Vietnam. Since there are few rainfall stations in this basin, it is important to validate multisource data for multiple purposes. This is the first time that a lumped hydrological model (i.e. Probability Distributed Moisture (PDM)) has been used for this basin. Various statistical indicators, including the correlation coefficient, mean absolute error (MAE), root mean square error (RMSE), percent bias (BIAS) and Taylor diagram, were used to evaluate the applicability of the global precipitation data and the PDM model. The precipitation datasets showed a good correlation with the raingauge rainfall data. In contrast, CPC underestimates while PERSIANN-CDR overestimates the raingauge rainfall. In general, PERSIANN-CDR performed slightly better than CPC. The daily streamflow simulation driven by PDM and all data sources underestimates the actual flow.