Improving the prediction of wildfire susceptibility on Hawai'i Island, Hawai'i, using explainable hybrid machine learning models.

This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawai'i Island, Hawai'i. 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 Hawai'i 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.

Spatial modeling of geogenic indoor radon distribution in Chungcheongnam-do, South Korea using enhanced machine learning algorithms.

Prolonged inhalation of indoor radon and its progenies lead to severe health problems for housing occupants; therefore, housing developments in radon-prone areas are of great concern to local municipalities. Areas with high potential for radon exposure must be identified to implement cost-effective radon mitigation plans successfully or to prevent the construction of unsafe buildings. In this study, an indoor radon potential map of Chungcheongnam-do, South Korea, was generated using a group method of data handling (GMDH) algorithm based on local soil properties, geogenic, geochemical, as well as topographic factors. To optimally tune the hyper-parameters of GMDH and enhance the prediction accuracy of modelling radon distribution, the GMDH model was integrated with two metaheuristic optimization algorithms, namely the bat (BA) and cuckoo optimization (COA) algorithms. The goodness-of-fit and predictive performance of the models was quantified using the area under the receiver operating characteristic (ROC) curve (AUC), mean squared error (MSE), root mean square error (RMSE), and standard deviation (StD). The results indicated that the GMDH-COA model outperformed the other models in the training (AUC = 0.852, MSE = 0.058, RMSE = 0.242, StD = 0.242) and testing (AUC = 0.844, MSE = 0.060, RMSE = 0.246, StD = 0.0242) phases. Additionally, using metaheuristic optimization algorithms improved the predictive ability of the GMDH. The GMDH-COA model showed that approximately 7 % of the total area of Chungcheongnam-do consists of very high radon-prone areas. The information gain ratio method was used to assess the predictive ability of considered factors. As expected, soil properties and local geology significantly affected the spatial distribution of radon potential levels. The radon potential map produced in this study represents the first stage of identifying areas where large proportions of residential buildings are expected to experience significant radon levels due to high concentrations of natural radioisotopes in rocks and derived soils beneath building foundations. The generated map assists local authorities to develop urban plans more wisely towards region with less radon concentrations.

Radon potential mapping in Jangsu-gun, South Korea using probabilistic and deep learning algorithms.

The adverse health effects associated with the inhalation and ingestion of naturally occurring radon gas produced during the uranium decay chain mean that there is a need to identify high-risk areas. This study detected radon-prone areas using a geographic information system (GIS)-based probabilistic and machine learning methods, including the frequency ratio (FR) model and a convolutional neural network (CNN). Ten influencing factors, namely elevation, slope, the topographic wetness index (TWI), valley depth, fault density, lithology, and the average soil copper (Cu), calcium oxide (Cao), ferric oxide (Fe2O3), and lead (Pb) concentrations, were analyzed. In total, 27 rock samples with high activity concentration index values were divided randomly into training and validation datasets (70:30 ratio) to train the models. Areas were categorized as very high, high, moderate, low, and very low radon areas. According to the models, approximately 40% of the study area was classified as very high or high risk. Finally, the radon potential maps were validated using the area under the receiver operating characteristic curve (AUC) analysis. This showed that the CNN algorithm was superior to the FR method; for the former, AUC values of 0.844 and 0.840 were obtained using the training and validation datasets, respectively. However, both algorithms had high predictive power. Slope, lithology, and TWI were the best predictors of radon-affected areas. These results provide new information regarding the spatial distribution of radon, and could inform the development of new residential areas. Radon screening is important to reduce public exposure to high levels of naturally occurring radiation.

Convolutional neural network (CNN) with metaheuristic optimization algorithms for landslide susceptibility mapping in Icheon, South Korea.

Landslides are a geological hazard that can pose a serious threat to human health and the environment of highlands or mountain slopes. Landslide susceptibility mapping is an essential tool for predicting and mitigating landslides. This study aimed to investigate the application of deep learning algorithms based on convolutional neural networks (CNNs) with metaheuristic optimization algorithms, namely the grey wolf optimizer (GWO) and imperialist competitive algorithm (ICA), to landslide susceptibility mapping. The study area was Icheon City, South Korea, for which an accurate landslide inventory dataset was available. The landslide inventory map was prepared and randomly divided into datasets of 70% for training and 30% for validation. Additionally, 18 landslide-related factors, including geo-environmental and topo-hydrological factors, were considered as predictive variables. The models were compared using area under the curve (AUC) values in receiver operating characteristic (ROC) curve analysis. The validation results showed that optimized models based on CNN-GWO (AUC = 0.876, RMSE = 0.08) and CNN-ICA (AUC = 0.852, RMSE = 0.09) outperformed the standalone CNN model (AUC = 0.847, RMSE = 0.12). Nevertheless, the CNN model outperformed previous research that used a machine learning algorithm alone. Thus, the deep learning algorithm with optimization algorithms proposed in this study can generate more suitable models for landslide susceptibility mapping in the study area due to its improved accuracy.

Development of novel hybridized models for urban flood susceptibility mapping.

Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.

Spatial prediction of landslide susceptibility using hybrid support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) with various metaheuristic algorithms.

Landslides are natural and sometimes quasi-natural hazards that are destructive to natural resources and cause loss of human life every year. Hence, preparing susceptibility maps for landslide monitoring is essential to minimizing their negative effects. The main aim of the current research was to develop landslide susceptibility maps for Icheon Township, South Korea, using hybrid Machin learning and metaheuristic algorithms, that is, the bee algorithm (Bee), the adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), and the grey wolf optimizer (GWO), and to compare their predictive accuracy. Based on identified landslide locations, an inventory map was prepared and divided into training and validation data sets (70%/30%). the predicated model outcomes were validated with root mean square error (RMSE), and area under receiver operating characteristic curve (AUC), and pairwise comparison values for the ANFIS, ANFIS-Bee, ANFIS-GWO, SVR, SVR-Bee, and SVR-GWO models were obtained. The area under the curve was obtained with the training and validation data sets. Based on the training data sets, AUC of 80%, 83%, 83%, 69%, 81%, and 80% were obtained for the SVR, SVR-GWO, SVR-Bee, ANFIS, ANFIS-GWO, and ANFIS-Bee models, respectively. For the validation data sets, values of 79%, 82%, 82%, 68%, 79%, and 79%, respectively, were obtained. The SVR-GWO and SVR-Bee models were the most predictive models in terms of constructing the exceptionally focused landslide susceptibility map, with little spatial variation in the highly susceptible classes. Furthermore, the MSE, RMSE, and pairwise comparisons indicated that the SVR-GWO and SVR-Bee models were superior models for this study township. In addition, ANFIS individually was not superior to the ensembles of ANFIS-GWO and ANFIS-Bee for landslide assessment. These landslide susceptibility maps provide a platform for land use planning with an eye toward sustainable development of infrastructure and damage reduction for Icheon Township.

Capability and robustness of novel hybridized models used for drought hazard modeling in southeast Queensland, Australia.

Widespread detrimental and long-lasting droughts are having catastrophic impacts around the globe. Researchers, organizations, and policy makers need to work together to obtain precise information, enabling timely and accurate decision making to mitigate drought impacts. In this study, a spatial modeling approach based on an adaptive neuro-fuzzy inference system (ANFIS) and several metaheuristic optimizations (ANFIS-BA, ANFIS-GA, ANFIS-ICA, ANFIS-PSO) was developed to predict the spatial occurrence of drought in a region in southeastern Queensland, Australia. In this approach, data describing the distribution of eight drought-contributing factors were prepared for input into the models to serve as independent variables. Relative departures of rainfall (RDR) and relative departures of soil moisture (RDSM) were analyzed to identify locations where drought conditions have occurred. The set of locations in the study area identified as having experienced drought conditions was randomly divided into two groups, 70% were used for training and 30% for validation. The models employed these data to generate maps that predict the locations that would be expected to experience drought. The prediction accuracy of the model-produced drought maps was scrutinized with two evaluation metrics: area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). The results demonstrate that the hybridized models (ANFIS-BA (AUCmean = 83.7%, RMSEmean = 0.236), ANFIS-GA (AUCmean = 81.62%, RMSEmean = 0.247), ANFIS-ICA (AUCmean = 82.12%, RMSEmean = 0.247), and ANFIS-PSO (AUCmean = 81.42%, RMSEmean = 0.255)) yield better predictive performance than the standalone ANFIS model (AUCmean = 71.8%, RMSEmean = 0.344). Furthermore, sensitivity analyses indicated that plant-available water capacity, the percentage of soil comprised of sand, and mean annual precipitation were the most important predictors of drought hazard. The versatility of the new approach for spatial drought modeling and the capacity of ANFIS model hybridization to improve model performance suggests great potential to assist decision makers in their formulations of drought risk, recovery, and response management, and in the development of contingency plans.

Flood susceptibility mapping in Dingnan County (China) using adaptive neuro-fuzzy inference system with biogeography based optimization and imperialistic competitive algorithm.

Flooding is one of the most significant environmental challenges and can easily cause fatal incidents and economic losses. Flood reduction is costly and time-consuming task; so it is necessary to accurately detect flood susceptible areas. This work presents an effective flood susceptibility mapping framework by involving an adaptive neuro-fuzzy inference system (ANFIS) with two metaheuristic methods of biogeography based optimization (BBO) and imperialistic competitive algorithm (ICA). A total of 13 flood influencing factors, including slope, altitude, aspect, curvature, topographic wetness index, stream power index, sediment transport index, distance to river, landuse, normalized difference vegetation index, lithology, rainfall and soil type, were used in the proposed framework for spatial modeling and Dingnan County in China was selected for the application of the proposed methods due to data availability. There are 115 flood occurrences in the study area which were randomly separated into training (70% of the total) and verification (30%) sets. To perform the proposed framework, the step-wise weight assessment ratio analysis algorithm is first used to evaluate the correlation between influencing factors and floods. Then, two ensemble methods of ANFIS-BBO and ANFIS-ICA are constructed for spatial prediction and producing flood susceptibility maps. Finally, these resultant maps are assessed in terms of several statistical and error measures, including receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), root-mean-square error (RMSE). The experimental results demonstrated that the two ensemble methods were more effective than ANFIS in the study area. For instance, the predictive AUC values of 0.8407, 0.9045 and 0.9044 were achieved by the methods of ANFIS, ANFIS-BBO and ANFIS-ICA, respectively. Moreover, the RMSE values for ANFIS, ANFIS-BBO and ANFIS-ICA using the verification set were 0.3100, 0.2730 and 0.2700, respectively. In addition, as regards ANFIS-BBO and ANFIS-ICA, a total areas of 39.30% and 35.39% were classified as highly susceptible to flooding. Therefore, the proposed ensemble framework can be used for flood susceptibility mapping in other sites with similar geo-environmental characteristics for taking measures to manage and prevent flood damages.

Multi-hazard probability assessment and mapping in Iran.

Several areas of Iran are prone to numerous natural hazards. An effective multi-hazard risk reduction requires analysis of the individual hazards and their interplay. This research develops a multi-hazard probability map for three hazards (i.e. landslides, floods, and earthquakes) for the management of hazard-prone areas in Lorestan Province, Iran, using anew ensemble model named SWARA-ANFIS-GWO. First, based on flood and landslide occurrence maps, hazard-prone areas were identified and sub-divided into two subsets.70% of these locations were randomly chosen to be used for the construction of susceptibility maps, while the remaining 30% of the instances were used to assess the accuracy of the models. Then, eleven factors relating to terrain and land use were selected for the preparation of landslide and flood susceptibility maps. An earthquake map was prepared based on a probabilistic seismic hazard analysis (PSHA). The SWARA method was implemented for weighting contributing factors and evaluating spatial relationships between the three hazards and predisposing factors. Subsequently, the ANFIS approach was used to acquire weights for each value while using a gray Wolf metaheuristic algorithm. Finally, all weight values were further assessed using the MATLAB software. The predicated results from the models were validated with ROC (rate of change) curves. The resulting AUCs (area under the curve) of the validation data indicated accuracies of 84% and 80% for floods and landslides, respectively, and 87% and 82.6%for flood and landslides based on the training data, respectively. Finally, the flood, landslide, and earthquake maps were combined to create a multi-hazard probability map of the Lorestan Province. This multi-hazard map serves as a valuable tool for land use planning and sustainable infrastructure development for the Lorestan Province.

A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran).

In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811).

Novel Hybrid Evolutionary Algorithms for Spatial Prediction of Floods.

Adaptive neuro-fuzzy inference system (ANFIS) includes two novel GIS-based ensemble artificial intelligence approaches called imperialistic competitive algorithm (ICA) and firefly algorithm (FA). This combination could result in ANFIS-ICA and ANFIS-FA models, which were applied to flood spatial modelling and its mapping in the Haraz watershed in Northern Province of Mazandaran, Iran. Ten influential factors including slope angle, elevation, stream power index (SPI), curvature, topographic wetness index (TWI), lithology, rainfall, land use, stream density, and the distance to river were selected for flood modelling. The validity of the models was assessed using statistical error-indices (RMSE and MSE), statistical tests (Friedman and Wilcoxon signed-rank tests), and the area under the curve (AUC) of success. The prediction accuracy of the models was compared to some new state-of-the-art sophisticated machine learning techniques that had previously been successfully tested in the study area. The results confirmed the goodness of fit and appropriate prediction accuracy of the two ensemble models. However, the ANFIS-ICA model (AUC = 0.947) had a better performance in comparison to the Bagging-LMT (AUC = 0.940), BLR (AUC = 0.936), LMT (AUC = 0.934), ANFIS-FA (AUC = 0.917), LR (AUC = 0.885) and RF (AUC = 0.806) models. Therefore, the ANFIS-ICA model can be introduced as a promising method for the sustainable management of flood-prone areas.

Land Subsidence Susceptibility Mapping in South Korea Using Machine Learning Algorithms.

In this study, land subsidence susceptibility was assessed for a study area in South Korea by using four machine learning models including Bayesian Logistic Regression (BLR), Support Vector Machine (SVM), Logistic Model Tree (LMT) and Alternate Decision Tree (ADTree). Eight conditioning factors were distinguished as the most important affecting factors on land subsidence of Jeong-am area, including slope angle, distance to drift, drift density, geology, distance to lineament, lineament density, land use and rock-mass rating (RMR) were applied to modelling. About 24 previously occurred land subsidence were surveyed and used as training dataset (70% of data) and validation dataset (30% of data) in the modelling process. Each studied model generated a land subsidence susceptibility map (LSSM). The maps were verified using several appropriate tools including statistical indices, the area under the receiver operating characteristic (AUROC) and success rate (SR) and prediction rate (PR) curves. The results of this study indicated that the BLR model produced LSSM with higher acceptable accuracy and reliability compared to the other applied models, even though the other models also had reasonable results.

GIS-based groundwater potential analysis using novel ensemble weights-of-evidence with logistic regression and functional tree models.

The aim of the current study was to produce groundwater spring potential maps using novel ensemble weights-of-evidence (WoE) with logistic regression (LR) and functional tree (FT) models. First, a total of 66 springs were identified by field surveys, out of which 70% of the spring locations were used for training the models and 30% of the spring locations were employed for the validation process. Second, a total of 14 affecting factors including aspect, altitude, slope, plan curvature, profile curvature, stream power index (SPI), topographic wetness index (TWI), sediment transport index (STI), lithology, normalized difference vegetation index (NDVI), land use, soil, distance to roads, and distance to streams was used to analyze the spatial relationship between these affecting factors and spring occurrences. Multicollinearity analysis and feature selection of the correlation attribute evaluation (CAE) method were employed to optimize the affecting factors. Subsequently, the novel ensembles of the WoE, LR, and FT models were constructed using the training dataset. Finally, the receiver operating characteristic (ROC) curves, standard error, confidence interval (CI) at 95%, and significance level P were employed to validate and compare the performance of three models. Overall, all three models performed well for groundwater spring potential evaluation. The prediction capability of the FT model, with the highest AUC values, the smallest standard errors, the narrowest CIs, and the smallest P values for the training and validation datasets, is better compared to those of other models. The groundwater spring potential maps can be adopted for the management of water resources and land use by planners and engineers.

Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution.

Floods are among Earth's most common natural hazards, and they cause major economic losses and seriously affect peoples' lives and health. This paper addresses the development of a flood susceptibility assessment that uses intelligent techniques and GIS. An adaptive neuro-fuzzy inference system (ANFIS) was coupled with a genetic algorithm and differential evolution for flood spatial modelling. The model considers thirteen hydrologic, morphologic and lithologic parameters for the flood susceptibility assessment, and Hengfeng County in China was chosen for the application of the model due to data availability and the 195 total flood events. The flood locations were randomly divided into two subsets, namely, training (70% of the total) and testing (30%). The Step-wise Weight Assessment Ratio Analysis (SWARA) approach was used to assess the relation between the floods and influencing parameters. Subsequently, two data mining techniques were combined with the ANFIS model, including the ANFIS-Genetic Algorithm and the ANFIS-Differential Evolution, to be used for flood spatial modelling and zonation. The flood susceptibility maps were produced, and their robustness was checked using the Receiver Operating Characteristic (ROC) curve. The results showed that the area under the curve (AUC) for all models was >0.80. The highest AUC value was for the ANFIS-DE model (0.852), followed by ANFIS-GA (0.849). According to the RMSE and MSE methods, the ANFIS-DE hybrid model is more suitable for flood susceptibility mapping in the study area. The proposed method is adaptable and can easily be applied in other sites for flood management and prevention.