Seed Cell Area Index Research Articles

Flood Susceptibility Mapping Using Information Fusion Paradigm Integrated with Decision Trees

Accurate estimation of flood-damaged zones in a watershed is prominent in guiding a framework for developing sustainable strategies. For these purposes, several flood conditioning factor values at flooded and non-flooded points are extracted, and those points are analyzed using decision tree algorithms and eight novel information fusion techniques to get more reliable flood susceptibility mapping. The belief function values of flood susceptibility values at leaf nodes of the tree are fused by several techniques named Dempster-Shafer (DS), Fuzzy Gamma Overlay (FGO), Hesitant Fuzzy Weighted Averaging (HFWA), Hesitant Fuzzy Weighted Geometric (HFWG), Hesitant Fuzzy Weighted Ordered Averaging (HFWOA), HFWOG, Closeness coefficient (Cc) using Euclidean and Manhattan distances. The flood susceptibility values are extracted from the generated maps and are validated by receiver operating characteristics (ROC) curve parameters, and the seed cell area index (SCAI) of classified flood levels. The area under ROC (AUROC) values of training process are 0.997 for DS, HFWA, HFWOA, and Cc-Euclidean, 0.996 for Cc-Manhattan, 0.995 for FGO and 0.994 for HFWG and HFWOG. The AUROC values of the testing process are 0.951 for DS, HFWA, HFWOA, Cc-Euclidean, and Cc-Manhattan, 0.945 for FGO, 0.943 for HFWG, and 0.941 for HFWOG. True Skill Statistics values are 0.962 and 0.870 for training and testing processes. Although these techniques present excellent performance, the SCAI values versus flood susceptibility classes are fitted to assess the prediction capabilities of the techniques further. HFWA and HFWOG have the first- and second-best performances on the estimations. Hence, information fusion paradigm can be employed to combine flood conditioning factors based on a robust classification method to get reliable predictions of flood potential levels and utilize them for land use and construction planning and management.

Application of genetic algorithm in optimization parallel ensemble-based machine learning algorithms to flood susceptibility mapping using radar satellite imagery

Floods are the natural disaster that occurs most frequently due to the weather and causes the most widespread destruction. The purpose of the proposed research is to analyze flood susceptibility mapping (FSM) in the Sulaymaniyah province of Iraq. This study employed a genetic algorithm (GA) to fine-tune parallel ensemble-based machine learning algorithms (random forest (RF) and bootstrap aggregation (Bagging)). Four machine learning algorithms (RF, Bagging, RF-GA, and Bagging-GA) were used to build FSM in the study area. To provide inputs into parallel ensemble-based machine learning algorithms, we gathered and processed data from meteorological (Rainfall), satellite image (flood inventory, normalized difference vegetation index (NDVI), aspect, land cover, altitude, stream power index (SPI), plan curvature, topographic wetness index (TWI), slope) and geographic sources (geology). For this research, Sentinel-1 synthetic aperture radar (SAR) satellite images were utilized to locate flooded areas and create an inventory map of floods. To train and validate the model, we employed 70 % and 30 % of 160 selected flood locations, respectively. Multicollinearity, frequency ratio (FR), and Geodetector methods were used for data preprocessing. Four metrics were utilized to assess the FSM performance: the root mean square error (RMSE), the area under the receiver-operator characteristic curve (AUC-ROC), the Taylor diagram, and the seed cell area index (SCAI). The results exhibited that all the suggested models have high accuracy of prediction, but the performance of Bagging-GA (RMSE (Train = 0.1793, Test = 0.4543)) was slightly better than RF-GA (RMSE (Train = 0.1803, Test = 0.4563)), Bagging (RMSE (Train = 0.2191, Test = 0.4566)), and RF (RMSE (Train = 0.2529, Test = 0.4724)). According to the ROC index, the Bagging-GA model (AUC = 0.935) was the most accurate in flood susceptibility modeling, followed by the RF-GA (AUC = 0.904), the Bagging (AUC = 0.872), and the RF (AUC = 0.847) models. The study's identification of high-risk flood zones and the most significant factors contributing to flooding make it a helpful resource for flood management.

An objective absence data sampling method for landslide susceptibility mapping

The accuracy and quality of the landslide susceptibility map depend on the available landslide locations and the sampling strategy for absence data (non-landslide locations). In this study, we propose an objective method to determine the critical value for sampling absence data based on Mahalanobis distances (MD). We demonstrate this method on landslide susceptibility mapping of three subdistricts (Upazilas) of the Rangamati district, Bangladesh, and compare the results with the landslide susceptibility map produced based on the slope-based absence data sampling method. Using the 15 landslide causal factors, including slope, aspect, and plan curvature, we first determine the critical value of 23.69 based on the Chi-square distribution with 14 degrees of freedom. This critical value was then used to determine the sampling space for 261 random absence data. In comparison, we chose another set of the absence data based on a slope threshold of < 3°. The landslide susceptibility maps were then generated using the random forest model. The Receiver Operating Characteristic (ROC) curves and the Kappa index were used for accuracy assessment, while the Seed Cell Area Index (SCAI) was used for consistency assessment. The landslide susceptibility map produced using our proposed method has relatively high model fitting (0.87), prediction (0.85), and Kappa values (0.77). Even though the landslide susceptibility map produced by the slope-based sampling also has relatively high accuracy, the SCAI values suggest lower consistency. Furthermore, slope-based sampling is highly subjective; therefore, we recommend using MD -based absence data sampling for landslide susceptibility mapping.

Application of novel hybrid model for land subsidence susceptibility mapping

Land subsidence (LS) is one of the challenging geo‐hazards in several regions of the world that is mainly caused by the overexploitation of groundwater and subsequent collapse of underground cavities. The prediction of LS is difficult due to limitations in monitoring, proper surveys, and knowledge related to the functioning and behaviour of the phenomenon. The application of remote sensing (RS) and global positioning system (GPS) for the proper location identification of LS in the ground and its implementation in susceptibility mapping can help to better constrain this geohazard. However, proper LS susceptibility maps to identify LS prone areas and to mitigate this problem in a way are generally lacking. Several methodologies have been developed for preparing LS susceptibility maps through RS techniques coupled with statistical and machine learning (ML) algorithms. Furthermore, different regions have unique natural and anthropogenic causes for the occurrence of LS, such as subsidence due to groundwater over‐exploitation, road construction, consolidation of alluvial soil, mining activities, and so forth, resulting in severe economic losses. The LS susceptibility mapping (LSSM) can help to prevent natural and human catastrophes and reduce the economic damages. ML techniques are becoming increasingly proficient at modelling such occurrences and have wide application in LSSM. This study compares the performances of single and hybrid ML models to predict and map the susceptible areas prone to LS. A combination of several algorithms helps to improve the overall results. In order to achieve this, the gradient‐boosting machine‐evolutionary genetic algorithm (GBM‐EG) was adopted in this study for LS assessment and compared to three algorithms, namely random forest, artificial neural networks, and alternating decision tree, that stand as commonly used benchmarks. This case study on LSSM was carried out in the Abozidabad watershed, Isfahan Province, Iran, and a total of 155 LS locations were identified by using GPS. Measures of 12 conditioning factors were compiled for each of the sites. These data were input into the models in five different training‐to‐validation configurations of sample ratios: D1 (90%:10%), D2 (80%:20%), D3 (70%:30%), D4 (60%:40%), and D5 (50%:50%). The performance of the algorithms were evaluated with the receiver operating characteristic curve and seed cell area index (SCAI). The results show that the best area under curve value (0.989) and SCAI value were achieved by the GBM‐EG hybrid model in an 80:20 ratio. The results demonstrate that LSSMs can be effectively produced to support planning and land use for management decisions.

Assessment of landslide susceptibility, exposure, vulnerability, and risk in shahpur valley, eastern hindu kush

This study assessed landslide susceptibility in Shahpur valley, situated in the eastern Hindu Kush. Here, landslides are recurrent phenomena that disrupt the natural environment, and almost every year, they cause huge property damages and human losses. These damages are expected to escalate in the study area due to the high rate of deforestation in the region, population growth, agricultural expansion, and infrastructural development on the slopes. Landslide susceptibility was assessed by applying “weight of evidence” (WoE) and “information value” (IV) models. For this, the past landslide areas were identified and mapped on the SPOT5 satellite image and were verified from frequent field visits to remove the ambiguities from the initial inventory. Seven landslide contributing factors including surface geology, fault lines, slope aspect and gradient, land use, and proximity to roads and streams were identified based on indigenous knowledge and studied scientific literature. The relationship of landslide occurrence with contributing factors was calculated using WoE and IV models. The susceptibility maps were generated based on both the WoE and IV models. The results showed that the very high susceptible zone covered an area of 14.49% and 12.84% according to the WoE and IV models, respectively. Finally, the resultant maps were validated using the success and prediction rate curves, seed cell area index (SCAI), and R-index approaches. The success rate curve validated the results at 80.34% for WoE and 80.13% for the IV model. The calculated prediction rate for both WoE and IV was 83.34 and 85.13%, respectively. The SCAI results showed similar performance of both models in landslide susceptibility mapping. The result shows that the R-index value for the very high LS zone was 29.64% in the WoE model, and it was 31.21% for the IV model. Based on the elements at risk, a landslide vulnerability map was prepared that showed high vulnerability to landslide hazards in the lower parts of the valley. Similarly, the hazard and vulnerability maps were combined, and the risk map of the study area was generated. According to the landslide risk map, 5.5% of the study area was under high risk, while 2% of the area was in a very high-risk zone. It was found from the analysis that for assessing landslide susceptibility, both the models are suitable and applicable in the Hindu Kush region.

Spatiotemporal assessment of landslide susceptibility in Southern Sichuan, China using SA-DBN, PSO-DBN and SSA-DBN models compared with DBN model

Landslide is one of the most serious geo-hazards, and the landslide susceptibility assessment (LSA) is an existing effective method to efficiently mitigate the loss caused by landslides. This study develops the improved deep belief network (DBN) models by selecting the optimal model hyperparameter to improve the accuracy of LSA. Evaluation factors of the LSA are selected from fifteen influencing factors by chi-square test, multicollinearity test and out-of-bag error. 30% data of the study area are selected randomly as the training data to assess the landslide susceptibility of each grid in the study area. The spatial LSA is then obtained by integrating the DBN models with three optimization algorithms, namely the simulated annealing (SA), particle swarm optimization (PSO) and sparrow search algorithm (SSA). The assessment results obtained using DBN and improved DBN models are thus compared and verified using the receiver operating characteristic (ROC) curve and seed cell area index. It shows that the three improved DBN models outperform the DBN model, which demonstrates the ability of optimization algorithms to improve model performance, and the SSA-DBN model achieves the highest assessment accuracy, followed by the PSO-DBN and SA-DBN models. Meanwhile, the effective rainfall model and peak ground acceleration are respectively employed to evaluate the impact of two inducing factors, namely the rainfall and earthquake, and the temporal LSA is thus obtained. The spatiotemporal LSA map is then generated by coupling the optimal spatial LSA map and temporal LSA map. Therefore, the present study further explores the proposed improved methods and offers instructions for spatiotemporal LSA.

Multi-Hazard Susceptibility Assessment Using the Analytical Hierarchy Process and Frequency Ratio Techniques in the Northwest Himalayas, Pakistan

Globally, natural hazards have become more destructive in recent times because of rapid urban development and exposure. Consequently, significant human life loss, the damage to property and infrastructure, and the collapse of the environment directed the attention of geoscientists to control the consequences and risk management in relation to geo-hazards. In this research, an effort was made to produce a compound map, geo-visualizing the susceptibility of multi-hazards, to select suitable sites for sustainable future development and other economic activities in the region. Muzaffarabad District was chosen as a case research area due to the high magnitude of hydro-meteorological and geological hazards. On the one hand, both selected geo-hazard inventories were developed using the field survey and remote sensing data. The subjective and objective weight of all the causative factors and their classes were calculated using the assembled geospatial techniques, such as the Analytical Hierarchy Process (AHP) and Frequency Ratio (FR) in the Geographic Information System (GIS). The results reveal that the most suitable areas are distributed in the southern and northwestern parts, which can be used for future sustainable development and other economic activities. In contrast, the eastern and western regions, including Muzaffarabad City, are within high and very susceptibility zones. Finally, more than 50% of the land area is located in very low and low susceptibility zones. The validation of the proposed model was checked by using three different techniques: the Receiver Operative Characteristic (ROC) curve, Seed Cell Area Index (SCAI), and Frequency Ratio (FR). Both ROCs, the Success Rate Curve (SRC) and the Predictive Rate Curve (PRC), showed the goodness of fit for both the selected geo-hazards: landslides (81.3%) and floods (93.2%), at 80.1% and 91.7%, respectively. All the validation techniques showed good fitness for both the individual and multi-hazard maps. The proposed model sets a baseline for policy implementation for all the stakeholders to minimize the risk and sustainable future development in areas of high frequent geo-hazards.

Evaluation of machine learning, information theory and multi-criteria decision analysis methods for flood susceptibility mapping under varying spatial scale of analyses

The annual average economic losses due to various natural disasters are increasing exponentially across the globe and have reached a mark of US$239.2 billion per year between the period 2000–2019. In India, due to flood hazards, approximately 6.5 million people were affected and the total economic damages were approximately US$3 billion per year between 1990 and 2019. This study proposes to compare and evaluate the performance of the Support Vector Machine (SVM), Shannon's Entropy (SE), and Analytical Hierarchy Process (AHP) methods in the preparation of flood susceptibility mapping and assess their contextual suitability. The study has been carried out in coastal districts of West Bengal, India namely, South 24 Parganas and East Midnapur. Nine flood conditioning factors were identified and used as input parameters for the study. Each flood susceptibility map was subdivided into four categories where 27.29% of the study area were categorized as highly susceptible, while 39.45% of area were categorized as moderately susceptible to flood hazards. The Receiver Operating Characteristic (ROC) curve and the Seed Cell Area Index (SCAI) were applied for accuracy assessment and validation of the selected models. AUC values for ROC curves showed that the performance of the SVM model is better than that of the AHP and SE methods. Moreover, Hot Spots analyses for identification of high flood susceptible clusters revealed that the SVM model was far superior when compared to the other two models. The factors selected for assessment of flood susceptibility in AHP and SE models could not respond to the changing scale of analyses and hence produced significant erroneous outcomes. Hence, the SVM model evolved as the most versatile method in this comparison.

Flood Susceptibility Modeling in a Subtropical Humid Low-Relief Alluvial Plain Environment: Application of Novel Ensemble Machine Learning Approach

This study has developed a new ensemble model and tested another ensemble model for flood susceptibility mapping in the Middle Ganga Plain (MGP). The results of these two models have been quantitatively compared for performance analysis in zoning flood susceptible areas of low altitudinal range, humid subtropical fluvial floodplain environment of the Middle Ganga Plain (MGP). This part of the MGP, which is in the central Ganga River Basin (GRB), is experiencing worse floods in the changing climatic scenario causing an increased level of loss of life and property. The MGP experiencing monsoonal subtropical humid climate, active tectonics induced ground subsidence, increasing population, and shifting landuse/landcover trends and pattern, is the best natural laboratory to test all the susceptibility prediction genre of models to achieve the choice of best performing model with the constant number of input parameters for this type of topoclimatic environmental setting. This will help in achieving the goal of model universality, i.e., finding out the best performing susceptibility prediction model for this type of topoclimatic setting with the similar number and type of input variables. Based on the highly accurate flood inventory and using 12 flood predictors (FPs) (selected using field experience of the study area and literature survey), two machine learning (ML) ensemble models developed by bagging frequency ratio (FR) and evidential belief function (EBF) with classification and regression tree (CART), CART-FR and CART-EBF, were applied for flood susceptibility zonation mapping. Flood and non-flood points randomly generated using flood inventory have been apportioned in 70:30 ratio for training and validation of the ensembles. Based on the evaluation performance using threshold-independent evaluation statistic, area under receiver operating characteristic (AUROC) curve, 14 threshold-dependent evaluation metrices, and seed cell area index (SCAI) meant for assessing different aspects of ensembles, the study suggests that CART-EBF (AUCSR = 0.843; AUCPR = 0.819) was a better performant than CART-FR (AUCSR = 0.828; AUCPR = 0.802). The variability in performances of these novel-advanced ensembles and their comparison with results of other published models espouse the need of testing these as well as other genres of susceptibility models in other topoclimatic environments also. Results of this study are important for natural hazard managers and can be used to compute the damages through risk analysis.

Evaluating novel hybrid models based on GIS for snow avalanche susceptibility mapping: A comparative study

Snow avalanches cause economic losses in many parts of the world, especially in mountainous areas. Due to its changing climates and the complex topography of mountainous regions in Iran, avalanches are significant problems. Therefore, modeling snow avalanches to predict them is essential for sustainable and safe development, appropriate infrastructure, planning for residential development, and loss prevention. This study assesses the performances of multi-criteria decision-making models and machine-learning hybrid models for snow avalanche susceptibility mapping in northwestern Iran's Sirvan watershed based on the weight of analytic network process, weighted linear combination, and frequency ratio. Using multicollinearity analysis and Pearson correlation, eleven snow avalanche conditioning factors were deemed appropriate for use. The areas under the curve (AUC), root mean square error (RMSE), seed cell area index, and snow avalanche relative index were used to validate snow avalanche susceptibility maps. The results showed that all hybrid models performed very well for the determination of the susceptibility of locations to avalanching. Based on the results of the validation analyses, the analytic network process-frequency ratio hybrid model was best among the models (AUC = 0.941, RMSE = 0.3). The resulting maps provide strong evidence to guide efforts to prevent the exposure to snow avalanches in the Sirvan watershed, and these hybrid models can be tested in other regions affected by snow avalanches.

Hybrid Models Incorporating Bivariate Statistics and Machine Learning Methods for Flash Flood Susceptibility Assessment Based on Remote Sensing Datasets

Flash floods are considered to be one of the most destructive natural hazards, and they are difficult to accurately model and predict. In this study, three hybrid models were proposed, evaluated, and used for flood susceptibility prediction in the Dadu River Basin. These three hybrid models integrate a bivariate statistical method of the fuzzy membership value (FMV) and three machine learning methods of support vector machine (SVM), classification and regression trees (CART), and convolutional neural network (CNN). Firstly, a geospatial database was prepared comprising nine flood conditioning factors, 485 flood locations, and 485 non-flood locations. Then, the database was used to train and test the three hybrid models. Subsequently, the receiver operating characteristic (ROC) curve, seed cell area index (SCAI), and classification accuracy were used to evaluate the performances of the models. The results reveal the following: (1) The ROC curve highlights the fact that the CNN-FMV hybrid model had the best fitting and prediction performance, and the area under the curve (AUC) values of the success rate and the prediction rate were 0.935 and 0.912, respectively. (2) Based on the results of the three model performance evaluation methods, all three hybrid models had better prediction capabilities than their respective single machine learning models. Compared with their single machine learning models, the AUC values of the SVM-FMV, CART-FMV, and CNN-FMV were 0.032, 0.005, and 0.055 higher; their SCAI values were 0.05, 0.03, and 0.02 lower; and their classification accuracies were 4.48%, 1.38%, and 5.86% higher, respectively. (3) Based on the results of the flood susceptibility indices, between 13.21% and 22.03% of the study area was characterized by high and very high flood susceptibilities. The three hybrid models proposed in this study, especially CNN-FMV, have a high potential for application in flood susceptibility assessment in specific areas in future studies.

Evaluating underlying causative factors for earthquake-induced landslides and landslide susceptibility mapping in Upper Indrawati Watershed, Nepal

The main objective of this study is to understand the overall impact of earthquake in upper Indrawati Watershed, located in the high mountainous region of Nepal. Hence, we have assessed the relationship between the co-seismic landslide and underlying causative factors as well as performed landslide susceptibility mapping (LSM) to identify the landslide susceptible zone in the study area. We assessed the landslides distribution in terms of density, number, and area within 85 classes of 13 causal factors including slope, aspect, elevation, formation, land cover, distance to road and river, soil type, total curvature, seismic intensity, topographic wetness index, distance to fault, and flow accumulation. The earthquake-induced landslide is clustered in Northern region of the study area, which is dominated by steep rocky slope, forested land, and low human density. Among the causal factors, 'slope' showed positive correlation for landslide occurrence. Increase in slope in the study area also escalates the landslide distribution, with highest density at 43%, landslide number at 4.34/km2, and landslide area abundance at 2.97% in a slope class (> 50°). We used logistic regression (LR) for LSM integrating with geographic information system. LR analysis depicts that land cover is the best predictor followed by slope and distance to fault with higher positive coefficient values. LSM was validated by assessing the correctly classified landslides under susceptibility categories using area under curve (AUC) and seed cell area index (SCAI). The LSM approach showed good accuracy with respective AUC values for success rate and prediction rate of 0.843 and 0.832. Similarly, the decreasing SCAI value from very low to very high susceptibility categories advise satisfactory accuracy of the LSM approach.

Spatiotemporal Landslide Susceptibility Mapping Incorporating the Effects of Heavy Rainfall: A Case Study of the Heavy Rainfall in August 2021 in Kitakyushu, Fukuoka, Japan

Landslide represents an increasing menace causing huge casualties and economic losses, and rainfall is a predominant factor inducing landslides. Landslide susceptibility assessment (LSA) is a commonly used and effective method to prevent landslide risk, however, the LSA does not analyze the impact of the rainfall on landslides which is significant and non-negligible. Therefore, the spatiotemporal LSA considering the inducing effect of rainfall is proposed to improve accuracy and applicability. In this study, the influencing factors are selected using the chi-square test, out-of-bag error and multicollinearity test. The spatial LSA are thus obtained using the random forest (RF) model, deep belief networks model and support vector machine, and compared using receiver operating characteristic curve and seed cell area index to determine the optimal assessment result. According to the heavy rainfall characteristics in the study area, the rainfall period is divided into four stages, and the effective rainfall model is employed to generate the rainfall impact (RI) maps of the four stages. The spatiotemporal LSAs are obtained by coupling the optimal spatial LSA and various RI maps and verified using the landslide warning map. The results demonstrate that the optimal spatiotemporal LSA is obtained using the spatial LSA of the RF model and temporal LSA of the rainfall data in the peak stage. It can predict the area where rainfall-induced landslides are likely to occur and prevent landslide risk.

Spatial modeling of snow avalanche susceptibility using hybrid and ensemble machine learning techniques

In this study, snow avalanche susceptibility maps of Uzungöl Basin, which is a special environmental protected zone located in Eastern Black Sea Basin of Turkeywere conducted. For this, the belief function values of snow avalanche conditioning factors extracted from snow avalanche inventory data exploring geographical information system software were used. Classes of snow avalanche conditioning factors based on J48, random tree (RT), random forest (RF), and AdaBoost M1, Bagging, Real AdaBoost, and Random Subspace ensemble models of J48, RT, and RF models were implemented. Then snow avalanche susceptibility maps of each model were generated based on the combination rule of Dempster-Shafer theory. The model predictions were validated using a receiver operating characteristics curve, seed cell area index, and statistical tests. AdaBoost M1 ensemble of RT model was found to be the best performing results. However, ensemble models did not improve the prediction results unexpectedly. It can be expected that findings of this study will lead to the implementation of dynamic snow avalanche modeling studies on avalanche paths highlighted in the prepared maps, planning of land-use change projections, controlling snow avalanche movement, and mitigating the risks of loss of life and possible snow avalanches.

The Predictive Capability of a Novel Ensemble Tree-Based Algorithm for Assessing Groundwater Potential

Understanding the potential groundwater resource distribution is critical for sustainable groundwater development, conservation, and management strategies. This study analyzes and maps the groundwater potential in Busan Metropolitan City, South Korea, using random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGB) methods. Fourteen groundwater conditioning factors were evaluated for their contribution to groundwater potential assessment using an elastic net. Curvature, the stream power index, the distance from drainage, lineament density, and fault density were excluded from the subsequent analysis, while nine other factors were used to create groundwater potential maps (GMPs) using the RF, GBM, and XGB models. The accuracy of the resultant GPMs was tested using receiver operating characteristic curves and the seed cell area index, and the results were compared. The analysis showed that the three models used in this study satisfactorily predicted the spatial distribution of groundwater in the study area. In particular, the XGB model showed the highest prediction accuracy (0.818), followed by the GBM (0.802) and the RF models (0.794). The XGB model, which is the most recently developed technique, was found to best contribute to improving the accuracy of the GPMs. These results contribute to the establishment of a sustainable management plan for groundwater resources in the study area.

A Novel Hybrid Method for Landslide Susceptibility Mapping-Based GeoDetector and Machine Learning Cluster: A Case of Xiaojin County, China

Landslide susceptibility mapping (LSM) could be an effective way to prevent landslide hazards and mitigate losses. The choice of conditional factors is crucial to the results of LSM, and the selection of models also plays an important role. In this study, a hybrid method including GeoDetector and machine learning cluster was developed to provide a new perspective on how to address these two issues. We defined redundant factors by quantitatively analyzing the single impact and interactive impact of the factors, which was analyzed by GeoDetector, the effect of this step was examined using mean absolute error (MAE). The machine learning cluster contains four models (artificial neural network (ANN), Bayesian network (BN), logistic regression (LR), and support vector machines (SVM)) and automatically selects the best one for generating LSM. The receiver operating characteristic (ROC) curve, prediction accuracy, and the seed cell area index (SCAI) methods were used to evaluate these methods. The results show that the SVM model had the best performance in the machine learning cluster with the area under the ROC curve of 0.928 and with an accuracy of 83.86%. Therefore, SVM was chosen as the assessment model to map the landslide susceptibility of the study area. The landslide susceptibility map demonstrated fit with landslide inventory, indicated the hybrid method is effective in screening landslide influences and assessing landslide susceptibility.

Hazard Mapping of the Rainfall–Landslides Disaster Chain Based on GeoDetector and Bayesian Network Models in Shuicheng County, China

Landslides are among the most frequent natural hazards in the world. Rainfall is an important triggering factor for landslides and is responsible for topples, slides, and debris flows—three of the most important types of landslides. However, several previous relevant research studies covered general landslides and neglected the rainfall–topples–slides–debris flows disaster chain. Since landslide hazard mapping (LHM) is a critical tool for disaster prevention and mitigation, this study aimed to build a GeoDetector and Bayesian network (BN) model framework for LHM in Shuicheng County, China, to address these geohazards. The GeoDetector model will be used to screen factors, eliminate redundant information, and discuss the interaction between elements, while the BN model will be used for constructing a causality disaster chain network to determine the probability and risk level of the three types of landslides. The practicability of the BN model was confirmed by error rate and scoring rules validation. The prediction accuracy results were tested using overall accuracy, Matthews correlation coefficient, relative operating characteristics curve, and seed cell area index. The proposed framework is demonstrated to be sufficiently accurate to construct the complex LHM. In summary, the combination of the GeoDetector and BN model is very promising for spatial prediction of landslides.

Investigating the Effect of Cross-Modeling in Landslide Susceptibility Mapping

To mitigate the negative effects of landslide occurrence, there is a need for effective landslide susceptibility mapping (LSM). The fundamental source for LSM is landslide inventory. Unfortunately, there are still areas where landslide inventories are not generated due to financial or reachability constraints. Considering this led to the following research question: can we model landslide susceptibility in an area for which landslide inventory is not available but where such is available for surrounding areas? To answer this question, we performed cross-modeling by using various strategies for landslide susceptibility. Namely, landslide susceptibility was cross-modeled by using two adjacent regions (“Łososina” and “Gródek”) separated by the Rożnów Lake and Dunajec River. Thus, 46% and 54% of the total detected landslides were used for the LSM in “Łososina” and “Gródek” model, respectively. Various topographical, geological, hydrological and environmental landslide-conditioning factors (LCFs) were created. These LCFs were generated on the basis of the Digital Elevation Model (DEM), Sentinel-2A data, a digitized geological and soil suitability map, precipitation, the road network and the Różnów lake shapefile. For LSM, we applied the Frequency Ratio (FR) and Landslide Susceptibility Index (LSI) methods. Five zones showing various landslide susceptibilities were generated via Natural Jenks. The Seed Cell Area Index (SCAI) and Relative Landslide Density Index were used for model validation. Even when the SCAI indicated extremely high values for “very low” susceptibility classes and very small values for “very high” susceptibility classes in the training and validation areas, the accuracy of the LSM in the validation areas was significantly lower. In the “Łososina” model, 90% and 57% of the landslides fell into the “high” and “very high” susceptibility zones in the training and validation areas, respectively. In the “Gródek” model, 86% and 46% of the landslides fell into the “high” and “very high” susceptibility zones in the training and validation areas, respectively. Moreover, the comparison between these two models was performed. Discrepancies between these two models exist in the areas of critical geological structures (thrust and fault proximity), and the reliability for such susceptibility zones can be low (2–3 susceptibility zone difference). However, such areas cover only 11% of the analyzed area; thus, we can conclude that in remaining regions (89%), LSM generated by the inventory for the surrounding area can be useful. Therefore, the low reliability of such a map in areas of critical geological structures should be borne in mind.

Assessing subsidence susceptibility to coal mining using frequency ratio, statistical index and Mamdani fuzzy models: evidence from Raniganj coalfield, India

Raniganj, an important coalfield in India, is susceptible to mining subsidence, ejection of toxicants in the environment and huge subsurface destruction. Mining with opencast method poses a great risk to the surrounding areas of this coalfield. Anthropogenic and natural activities have caused ground movement leading to subsidence in Raniganj coalfield. Existing knowledge on subsidence susceptibility to coal mining in Raniganj coalfield is scant. The study makes an attempt to analyze mining subsidence susceptibility in Raniganj coalfield using site-specific parameters. We first prepared subsidence inventory map to identify old subsidence locations and to construct the model. It was later utilized for validating the models. Fifteen site-specific parameters related to subsidence were chosen to analyze coal mining subsidence. Frequency ratio (Fr), statistical index (SI) and Mamdani fuzzy (Mf) models were utilized to assess their effectiveness in preparing susceptibility map. Findings of the study revealed very high susceptibility in the central part, high susceptibility in north-western part and moderate susceptibility in the eastern part of Raniganj coalfield. Low and very low susceptibility was found in those parts having largest area under vegetation and water bodies. The models were validated through ROC curve, seed cell area index (SCAI) and spatially agreed area approach. Mamdani fuzzy model with highest success rate (87%) and prediction accuracy (85%) was found the best fit model for analyzing mining subsidence susceptibility. The framework of the methodology will be instructive for analyzing susceptibility at different geographical locations.

Novel Ensemble Approaches of Machine Learning Techniques in Modeling the Gully Erosion Susceptibility

Gully erosion has become one of the major environmental issues, due to the severity of its impact in many parts of the world. Gully erosion directly and indirectly affects agriculture and infrastructural development. The Golestan Dam basin, where soil erosion and degradation are very severe problems, was selected as the study area. This research maps gully erosion susceptibility (GES) by integrating four models: maximum entropy (MaxEnt), artificial neural network (ANN), support vector machine (SVM), and general linear model (GLM). Of 1042 gully locations, 729 (70%) and 313 (30%) gully locations were used for modeling and validation purposes, respectively. Fourteen effective gully erosion conditioning factors (GECFs) were selected for spatial gully erosion modeling. Tolerance and variance inflation factors (VIFs) were used to examine the collinearity among the GECFs. The random forest (RF) model was used to assess factors’ effectiveness and significance in gully erosion modeling. An ensemble of techniques can provide more accurate results than can single, standalone models. Therefore, we compared two-, three-, and four-model ensembles (ANN-SVM, GLM-ANN, GLM-MaxEnt, GLM-SVM, MaxEnt-ANN, MaxEnt-SVM, ANN-SVM-GLM, GLM-MaxEnt-ANN, GLM-MaxEnt-SVM, MaxEnt-ANN-SVM and GLM-ANN-SVM-MaxEnt) for GES modeling. The susceptibility zones of the GESMs were classified as very-low, low, medium, high, and very-high using Jenks’ natural break classification method (NBM). Subsequently, the receiver operating characteristics (ROC) curve and the seed cell area index (SCAI) methods measured the reliability of the models. The success rate curve (SRC) and predication rate curve (PRC) and their area under the curve (AUC) values were obtained from the GES maps. The results show that the ANN model combined with two and three models are more accurate than the other combinations, but the ANN-SVM model had the highest accuracy. The rank of the others from best to worst accuracy is GLM, MaxEnt, SVM, GLM-ANN, GLM-MaxEnt, GLM-SVM, MaxEnt-ANN, MaxEnt-SVM, GLM-ANN-SVM-MaxEnt, GLM-MaxEnt-ANN, GLM-MaxEnt-SVM and MaxEnt-ANN-SVM. The resulting gully erosion susceptibility models (GESMs) are efficient and powerful and could be used to improve soil and water conservation and management.