Stream Power Index Research Articles

Assessment of land degradation susceptibility within the Shaqlawa subregion of Northern Iraq-Kurdistan Region via synergistic application of remotely acquired datasets and advanced predictive models.

Land degradation (LD) is the decline in a land's functional capacity and productive potential, which includes various anthropogenic and natural drivers. This study focuses on three primary manifestations of LD including soil erosion, landslides, and rockfalls, which are the most prevalent in the Shaqlawa district. A set of 22 LD conditioning factors, encompassing curvature, lithology, aspect, river density, soil type, lineament density, river distance, elevation, road distance, length slope (LS), land use land cover (LULC), stream power index (SPI), valley depth, profile curvature, slope, solar radiation, road density, lineament distance, rainfall, topographic wetness index (TWI), plan curvature, and normalized difference vegetation index (NDVI), were integrated into the analysis. Variance inflation factors (VIF) and tolerance (TOL) values from linear regression indicate that most LD factors have acceptable levels of multicollinearity. The Information Gain Ratio (IGR) identified key variables TWI, NDVI, and lithology-as pivotal factors for predicting LD. Additionally, the study evaluated degradation factors using various machine learning (ML) algorithms, including random forest (RF), Naive Bayes, logistic regression, rotation forest, forest penalized attributes (FPA), and Fisher's Linear discriminant analysis (FLDA). This facilitated categorizing the study area into five susceptibility categories. The FLDA model categorized the highest area under very high degradation risk at 26.72%, emphasizing the varied insights each algorithm brought to characterizing the degradation risk. Additionally, the receiver operating characteristic curves (ROC) were employed for model validation, identifying RF as the most successful model in the training dataset with an area under the curve (AUC) of 0.882, while FLDA outperformed in the testing dataset with an AUC of 0.883. The identified LD-prone areas will help land-use planners and emergency management officials apply effective mitigation strategies for similar terrains.

Exploring a GIS-based analytic hierarchy process for spatial flood risk assessment in Egypt: a case study of the Damietta branch

Floods are the most common and costly disasters worldwide, while spatial flood risk assessment is still challenging due to fewer observations and method limitations. In this study, the flood risk zonation in the Nile districts of the Damietta branch, Egypt, is delineated and assessed by integrating remote sensing with a geographic information system, and an analytical hierarchy process (AHP). Twelve thematic layers (elevation, slope, normalized difference vegetation index, topographic wetness index, modified normalized difference water index, topographic positioning index, stream power index, modified Fournier index, drainage density, distance to the river, sediment transport index, and lithology) are used for producing flood susceptibility zonation (FSZ) and six parameters (total population, distance to hospital, land use/land cover, population density, road density, and distance to road) are utilized for producing flood vulnerability zonation. Multicollinearity analysis is applied to identify highly correlated independent variables. Sensitivity studies have been used to assess the effectiveness of the AHP model. The results indicate that the high and very high flood risk classes cover 21.40% and 8.26% of the area, respectively. In 14.07%, 27.01%, and 29.26% of the research area, respectively, flood risk zones classified as very low, low, and moderate are found. Finally, FSZ is validated using the receiver operating characteristics curve and area under curve (AUC) analysis. A higher AUC value (0.741) in the validation findings demonstrated the validity of this AHP approach. The results of this study will help planners, hydrologists, and managers of water resources manage areas that are susceptible to flooding and reduce potential harm.

Flash flood prediction modeling in the hilly regions of Southeastern Bangladesh: A machine learning attempt on present and future climate scenarios

Flash floods are highly destructive, and their frequency and intensity are expected to escalate due to climatic changes. This study thus investigated flash flood susceptibility (FFS) by applying machine learning algorithms and climate projection to predict both present and future hazard scenarios in the southeastern hilly regions of Bangladesh. To predict FFS, we evaluated twelve flood-influencing variables: elevation (EL), slope (SL), aspect (AS), drainage density (DD), distance to stream (DS), topography roughness index (TRI), stream power index (SPI), topographic wetness index (TWI), soil permeability (SP), precipitation (PR), land use and land cover (LULC) and normalized difference vegetation index (NDVI). Earth observation data, field surveys, and past flood records were used to create a detailed flood inventory. Among the machine learning models tested, the random forest (RF) algorithm outperformed others, including support vector machine (SVC), logistic regression (LR), and extreme gradient boosting (XGBoost), and was subsequently used for flood susceptibility mapping based on future precipitation projections under two Sixth Coupled model intercomparison project (CMIP6) climate change scenarios: SSP1-2.6 and SSP5-8.5. Our findings indicated that the areas at high to very high risk of flooding are projected to increase significantly under both the SSP1-2.6 and SSP5-8.5 scenarios. Initially, around 38 % of the studied region had high to very high flood susceptibility, but this is expected to rise to 40–42 % over the projected time periods. These spatial delineations of flood-prone areas can provide guidance for developing effective mitigation and adaptation strategies to address the adverse impacts of flash flooding in the hilly river basins of Bangladesh.

Flood Susceptibility Mapping Using Analytic Hierarchy Process and Geographic Information System in Baitarani Basin of Odisha, India

Baitarani, the 6th largest river basin in Odisha, eastern India, faces water related challenges in its catchments. As one of the most frequent environmental disasters, floods are consistently cited in hotspots of the eastern region in India. Hence, in this study, flood susceptibility maps were generated for Baitarani River basin by using analytical hierarchy process technique and geographic information system. Eleven thematic maps of topographic ruggedness index, topographic wetness index, stream power index, elevation, lithology, soil, slope, drainage density, distance from drainage network, land use/land cover and normalized difference vegetation index were prepared for flood vulnerability mapping. The themes were assigned suitable weights depending on relative influence of each of the themes on flood risk. The results indicated that 87% of the basin falls under intermediate flood susceptibility zone, while 10% is classified under high flood hazard zone. Areas in the lower elevation catchment, particularly those with flat topography near the coastline, were identified as being highly susceptible to flooding. The impacts of severe flooding in the basin are most pronounced in specific blocks in Jajpur district (Jajpur, Dasarathpur, and Korei blocks), Bhadrak district (Dhamnagar and Bhandaripokhari blocks), and Anandapur block in the Keonjhar district of Odisha. Additionally, changes in land use/land cover during 1995-2020 revealed 8% decline in agricultural land and 13.93% increase in fallow land in the area. The outcomes of this research can help researchers, planners and managers in managing natural resources, find locations that could be vulnerable to flooding, and lessen the damage.

Geospatial Intelligence for Landslide Susceptibility and Risk Analysis: Insights from NH31A and East Sikkim Himalaya Settlements

Slope instability is a serious concern in the Sikkim Himalayas. The town and numerous road segments along National Highway 31A were ravaged by multiple landslides that occurred in the nearby region. A bivariate statistical method known as frequency ratio (FR), information value (IV), and certainty factor (CF) analysis was employed in this work to examine landslide risk assessment (LRA) and landslide susceptibility zonation (LSZ) maps in the Rorachu watershed. This study represents the first comprehensive analysis of landslide risk in the populated areas of East Sikkim and along NH31A, offering a deeper understanding of the risks involved and contributing to the enhancement of local resilience against landslide hazards. A total of 153 different landslide locations were mapped using Google Earth and GIS software; 30% (46) of these locations were used to validate the models, and 70% of these (107) served as training data for the FR, IV, and CF models. The thirteen landslide causative factors (geology, soil, elevations, slope, curvature, drainage density (DD), road density (RD), rainfall, normalized difference vegetation index (NDVI), land use land cover (LULC), topographic position index (TPI), stream power index (SPI), and topographic wetness index (TWI)) were extracted from a spatial database for LSZ mapping. Landslides were most prevalent on slopes (35° to 50°), heights (2,500–4,100 m), and rainfall (2000–2,500 mm and 3,000–3,300 mm). The area under the curves (AUC) for the FR, IV, and CF models are 0.925 (92.50%), 0.846 (84.60%), and 0.868 (86.20%), respectively. The prediction rates are shown by the AUCs for the FR, IV, and CF models, which are 0.828 (82.8%), 0.750 (%), and 0.836 (83.60%), respectively. According to the landslide risk assessment (LRA), the FR (20.75%), IV (40.91%) and CF (18.78%) models showed high risk on Highway 31A, while the FR (9.05%), IV (38.59%) and CF (20.90%) models showed high risk in densely populated areas. These landslide risk and vulnerability maps can be used to develop land use planning strategies that can save lives and are useful for planners and mitigation measures. Special attention should be paid to urbanization, highway construction, and deforestation.

Machine learning and deep learning-based landslide susceptibility mapping using geospatial techniques in Wayanad, Kerala state, India

Landslide susceptibility mapping is vital for disaster management and sustainable land-use planning. This research was conducted in Wayanad, Kerala, India, to identify landslide susceptible zones. The study used large geospatial datasets, such as elevation, slope, aspect, curvature, stream power index, topographic wetness index, land use and land cover, rainfall, flow accumulation, geology, and geomorphology. It is followed by the application of various machine learning and deep learning models such as the support vector machine, artificial neural networks, logistic regression, random forest, gradient boosting machine, recurrent neural networks long short-term memory, and deep neural network models to map the landslide susceptible zones. The model was trained and validated using the landslide inventory map, which contains 298 sites of landslides. The random forest model, with 97 % accuracy, performed best. It is possible to effectively mitigate landslides and plan long-term land use by identifying hazardous zones within the study region.

Landslide susceptibility zonation mapping using geospatial technologies and multi criteria evaluation techniques in the upper Didessa sub-basin, Southwest Ethiopia

ABSTRACT Landslides have a profound impact on landscape geology, resulting in extensive devastation and loss of human lives. Mapping landslide susceptibility is crucial for effective land use planning in mountainous country like Ethiopia. This study was conducted in the upper Didessa sub-basin, southwestern parts of Ethiopia using Geographic Information System (GIS) and multi criteria evaluation (MCE) technique. This study employed a blend of primary data, encompassing field surveys and interviews with experts, as well as secondary data derived from diverse source, such as remote sensing data, digital soil maps, and geological maps. A total of eleven critical factors were employed to assess the triggers of landslides. These factors include slope, aspect, drainage density, topographic wetness index (TWI), stream power index (SPI), topographic ruggedness index (TRI), hypsometric integral, lithology, land use land cover (LULC), soil texture, and distance from roads. The analytical hierarchy process (AHP) method was used to determine the significance of each indicator through pairwise comparison matrix. The study area was categorized into different zones based on the susceptibility to landslides, namely very high, high, moderate, low, and very low. Results revealed that cultivated land had the highest likelihood of experiencing landslides, with a total of nine incidents out of 25, followed by built-up areas with seven landslides. Conversely, dense forests, sparse forests, and grazing land experienced a lower likelihood of landslides. Out of the 11 factors contributing to landslides, 24% of the surveyed region was deemed to have a moderate susceptibility, with 12% and 6% falling into the categories of high and very high susceptibility to landslides, respectively. The findings of this research provide important information for policymakers to develop efficient measures for preventing and reducing the risks of landslides.

Using algorithmic game theory to improve supervised machine learning: A novel applicability approach in flood susceptibility mapping.

This study was carried out with the aim of applying Condorcet and Borda scoring algorithms based on Game Theory (GT) to determine flood points and Flood Susceptibility Mapping (FSM) based on Machine Learning Algorithms (MLA) including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in the Cheshmeh-Kileh watershed, Iran. Therefore, first, FS conditioning factors including Aspect (As), Elevation (El), Euclidean distance (Euc), Forest (F), NDVI, Precipitation (P), Plan Curvature (PlC), Profile Curvature (PrC), Residential (Re), Rangeland (Rl), Slope (Sl), Stream Power Index (SPI), Topographic Position Index (TPI), and Topographic Wetness Index (TWI) were quantified in each Sub-Watershed (SW). Based on this, flood and non-flood points were identified based on both GT algorithms. In the following, MLAs including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) were used for the distributional mapping of FS. Finally, based on optimal conjunct approaches, FS maps were presented in the study watershed. Based on the results, among the conjunct algorithms in FS classification, RF-Condorcet and RF-Borda models were selected as the most optimal MLA-GT hybrid models. The upstream SWs were highly susceptible. Also, the effectiveness of NDVI and forest conditioning factors in each classification approach was high. The similarity of SW prioritization based on Condorcet algorithm with RF-Condorcet algorithm was about 86.70%. Meanwhile, the degree of similarity in RF-Borda conjunct algorithm was around 73.33%. These results showed that Condorcet algorithm had an optimal classification compared to Borda scoring algorithm.

Improving the identification of pollution source areas with catchment-resolution sensitivity analysis

The significant impacts of total nitrogen (TN) and total phosphorus (TP) on riverine ecosystems underscores the critical need to identify the primary nutrient source areas in watersheds. This study aims to unravel the influences of terrain and land use types on mean monthly TN (TNM) and mean monthly TP (TPM) export across varying catchment resolutions in the Qiantang River Watershed of China. The findings of this study illuminated the critical role of topography in understanding nutrient dynamics, wielding a profound influence over water flow patterns and nutrient dispersion. Both land slope and Stream Power Index (SPI) displayed substantial negative correlations (r < −0.6) with TNM and TPM concentrations, whereas the Topographic Wetness Index (TWI) showed positive correlations with the nutrient indexes. In addition to terrain characteristics, impervious land surfaces had a positive correlation with nutrient concentrations, while grassland and forest areas exhibited negative correlations. Results further underscored the substantial influence of catchment resolution on correlations between watershed properties and riverine nutrient concentrations. It was imperative to choose an effective catchment resolution in watershed delineation – not too coarse, nor too fine – to accurately capture the topographic and land use impacts on nutrient dynamics. With the most appropriate catchment size (Catchment 700 km2), the critical pollution source areas for TN and TP pollution were identified, and thus could be used to guide future pollution reduction efforts. The study not only highlights the importance of identifying an appropriate catchment size for water pollution, but also emphasizes the necessity of effectively extracting critical pollution source areas to mitigate water nutrient pollution and increase the ecological integrity of the Qiantang River Watershed.

Utilizing geodetectors to identify conditioning factors for gully erosion risk in the black soil region of northeast China

In the black soil region of Northeast China, the issue of gully erosion persists as a significant threat, resulting in extensive damage to farmland, severe degradation of the black soil, and decreased productivity. It is therefore of utmost importance to accurately identify areas that are susceptible to gully erosion to effectively prevent and control its negative impact. This study tried to utilize geographical detectors (geodetectors) as a means to identify the factors that contribute to the distribution of gullies and assess the risk of gully erosion (GER) in five catchments within the region, with areas ranging from approximately 80 km2–200 km2. By employing the geodetectors method, fourteen geo-environmental factors were analyzed, including topographic attributes (such as aspect, catchment area, convergence index, elevation, plan curvature, profile curvature, slope length, slope, stream power index, and topographic wetness index), channel network distance, vegetation index (NDVI and EVI), as well as land use/land cover (LULC). The modeling of GER was conducted using the random forest algorithm (RFA). Out of the fourteen examined geo-environmental factors, only a subset, comprising less than or equal to 50%, demonstrated a significant (p < 0.05) influence on the spatial distribution of gullies. These selected factors were sufficient in assessing GER, with LULC (mean q-value = 0.270) and elevation (mean q-value = 0.113) identified as the two most important factors. Furthermore, the RFA exhibited satisfactory performance across all catchments, achieving AUC values ranging from 0.712 to 0.933 (mean = 0.863) in predicting GER. Overall, the catchment areas were classified into high, moderate, low, and very low-risk levels, representing 9.67%–15.95%, 19.28%–26.08%, 24.59%–30.55%, and 30.54%–39.08% of the total area, respectively. Importantly, a significant positive linear relationship (r2 = 0.722, p < 0.05) was observed between the proportion of cropland area and the occurrence of high-level GER. Although the primary risk levels were categorized as low and very low, the proportion of high-risk levels exceeded the existing gully coverage (0.34%–3.69%). These findings highlight the substantial potential for gully erosion and underscore the necessity for intensified efforts in the prevention and control of gully erosion within the black soil region of Northeast China.

Understanding the mechanism of gully erosion in the alpine region through an interpretable machine learning approach

In the alpine region, climate warming has led to the retreat of glaciers, snow cover, and permafrost. This has intensified water cycling, soil erosion, and increased the occurrence of natural disasters in the alpine region. This study investigated the Lhasa River Basin in the southern Tibetan Plateau, serving as a representative case study of a typical alpine basin, with a specific focus on gully erosion. Based on field investigations and interpretation using high-resolution satellite remote sensing images, the Random Forest (RF) algorithm was applied to evaluate gully erosion susceptibility on watershed level. The Shapley Additive Interpretation method was then used to interpret the RF model and gain deeper insights into the influencing variables of gully erosion. The results showed that the RF model achieved an area under the receiver operating characteristic (AUC) accuracy of 0.99 and 0.98 for the training and testing datasets, respectively, indicating an outstanding performance of the model. The resulting susceptibility map based on the RF model shows that areas with moderate and higher levels of gully erosion susceptibility are covering 50 % of the basin. The model interpretation results indicated that elevation, slope, permafrost, rainstorm, silt loam topsoil, human activity, stream power, and vegetation were the explaining variables with the highest importance for gully erosion occurrence. Different variables are characterized by specific thresholds promoting gully erosion such as: i) elevations higher than 4950 m, ii) slopes steeper than 13.5°, iii) extreme rainstorms longer than 11 days per year, iv) silt loam topsoil, v) presence of permafrost, vi) stream power index higher than 1.2, and vii) normalized difference vegetation index (NDVI) lower than 0.25. Our findings provide the scientific basis to improve soil erosion control in such highly vulnerable alpine area.

Enhancing the Performance of Machine Learning and Deep Learning-Based Flood Susceptibility Models by Integrating Grey Wolf Optimizer (GWO) Algorithm

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) &gt; XGBoost-GWO (AUC: 0.961) &gt; SVR-GWO (AUC: 0.960) &gt; RNN (AUC: 0.956) &gt; XGBoost (AUC: 0.953) &gt; 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.

Spatio-temporal modeling of lake's ecosystem and dynamism in response to changing environment: a case study of L. Ol Bolossat in Kenya.

Lakes' ecosystems are vulnerable to environmental dynamisms prompted by natural processes and anthropogenic activities happening in catchment areas. The present study aimed at modeling the response of Lake Ol Bolossat ecosystem in Kenya to changing environment between 1992 to 2022 and its future scenario in 2030. The study used temperature, stream power index, rainfall, land use land cover, normalized difference vegetation index, slope, and topographic wetness index as datasets. A GIS-ensemble modeling approach coupling the analytical hierarchical process and principal component analysis was used to simulate the lake's extents between 1992 and 2022. Cellular Automata-Markov chain analysis was used to predict the lake extent in 2030. The results revealed that between 1992 and 2002, the lake extent shrunk by about 18%; between 2002 and 2012, the lake extent increased by about 13.58%; and between 2012 and 2022, the lake expanded by about 26%. The spatial-temporal changes exhibited that the lake has been changing haphazardly depending on prevailing climatic conditions and anthropogenic activities. The comparison between the simulated and predicted lake extents in 2022 produced Kno, Klocation, KlocationStrata, K standard, and average index values of 0.80, 0.81, 1.0, 0.74, and 0.84, respectively, which ascertained good performance of generated prediction probability matrices. The predicted results exhibited there would be an increase in lake extent by about 13% by the year 2030. The research findings provide baseline information which would assist in protecting and conserving the Lake Ol Bolossat ecosystem which is very crucial in promoting tourism activities and provision of water for domestic and commercial use in the region.

Enhancing Landslide Prediction Through Advanced Transformer-Based Models: Integrating SAR Imagery and Environmental Data

Landslides, a significant natural hazard driven predominantly by rainfall infiltration, pose a continuous threat to the terrain, buildings, and ecosystem of Caiazzo, located in southern Italy (Caserta). This research undertakes a novel approach to predict and understand the complex patterns of landslide deformations in this region. Our study leverages the advanced capabilities of COSMO-SkyMed satellite imagery, integrating a comprehensive dataset that includes factors such as elevation, slope, Topographic Wetness Index, Stream Power Index, geology, flow direction, curvature, Normalized Difference Vegetation Index, and several other relevant indices. We employ Transformer-based models, renowned for their effectiveness in capturing long-range dependencies within sequential data. The Transformer models in our study are adept at analyzing the temporal sequences of environmental factors and their intricate interactions, thereby offering a more nuanced understanding of the temporal patterns leading to landslides. These Transformer models are designed to process the entire sequence of satellite data obtained by the Coherent Pixels - Temporal Phase Coherence within the SUBSOFT package to ensure data integrity and precision, encompassing 132 images in ascending geometry and 143 in descending geometry, spanning from 2013 to 2021. By doing so, they efficiently identify critical patterns and dependencies over time, such as the interplay between rainfall events and subsequent soil and vegetation changes. The models are fine-tuned to our specific dataset, ensuring high precision and accuracy in landslide deformation prediction. Our evaluation metrics, including Mean Absolute Error, Root Mean Square Error, and R^2 score, demonstrate the superior performance of the Transformer-based approach, with significant improvements over the conventional Deep Learning model. The visual correlation of our predictions with actual landslide occurrences further corroborates the effectiveness of this method. This transformative approach not only enhances our understanding and predictive capability for landslides in Caiazzo but also sets a benchmark for landslide prediction in geologically vulnerable regions worldwide.

Evaluation of potentially susceptible flooding areas leveraging geospatial technology with multicriteria decision analysis in Edo State, Nigeria

Floods have claimed lives and devastated societal and ecological systems. Because of their catastrophic tendency and the financial and fatalities they cause, floods have become more and more significant on a global scale in recent years. In Edo State, Nigeria, flooding is a frequent threat that happens annually and seriously damages both lives and property. While the potential of flooding cannot entirely be eliminated, geospatial-based technologies can greatly lessen its effects. In Nigeria's flood-prone Edo State, the study's objectives are to identify inundated places and provide nuanced mapping of the flood risk. To facilitate the determination of the flood risk index (FRI), the study's fundamental flood-predictive features were determined by taking into consideration elevation, slope, distance from the river, rainfall intensity, land use/land cover, soil texture, topographic roughness index, topographic wetness index, normalized difference vegetation index (NDVI), runoff coefficient, aspect, drainage capacity, flow accumulation, the sediment transport index, and the stream power index. The significance of each predictive factor in the analytic hierarchy procedure (AHP) was determined by gathering expert views and perspectives from public entities. A flood threat map was created by processing the gathered data using the AHP and the ArcGIS 10.5 framework. The multicollinearity (MC) estimation was applied to assess the model's predictability. The results of the FRI showed that there were high and extremely severe flood risk zones that affected roughly 26 and 9% of the area, respectively. Flood risks have been identified as predominant in the Edo south region of the study area, which is characterized by low elevation and slope, high drainage capacity, distance from the river, topographic wetness, and index. It showed that the model's resultant vulnerability to flooding maps agreed with past flood occurrences that were previously experienced in the research area, demonstrating the technique's efficacy in locating and mapping locations plagued by flooding. Linear regression (R2) analysis was further conducted on the FRI to evaluate the scientific reliability of the utilized methodology; this shows 0.816 (81.6%) dependability. Consequently, frequent and long-lasting implementation of flooding predictions, warning systems, and mitigation strategies may be achieved.

Forecasting of flash flood susceptibility mapping using random forest regression model and geographic information systems

Flash floods, rapid and devastating inundations of water, are increasingly linked to the intensifying effects of climate change, posing significant challenges for both vulnerable communities and sustainable environmental management. The primary goal of this research is to investigate and predict a Flood Susceptibility Map (FSM) for the Ibaraki prefecture in Japan. This research utilizes a Random Forest (RF) regression model and GIS, incorporating 11 environmental variables (involving elevation, slope, aspect, distance to stream, distance to river, distance to road, land cover, topographic wetness index, stream power index, and plan and profile curvature), alongside a dataset comprising 224 instances of flooded and non-flooded locations. The data was randomly classified into a 70 % training set for model development, with the remaining 30 % used for model validation through Receiver Operating Characteristics (ROC) curve analysis. The resulting map indicated that approximately two-thirds of the prefecture as exhibiting low to very low flood susceptibility, while approximately one-fifth of the region is categorized as high to very high flood susceptibility. Furthermore, the RF model achieved a noteworthy validation with an area under the ROC curve of 99.56 %. Ultimately, this FSM serves as a crucial tool for policymakers in guiding appropriate spatial planning and flood mitigation strategies.

Environmental thresholds for plant species richness of black alder (Alnus glutinosa) forests in Central Europe

The diversity of vascular plants in temperate floodplain forests varies between biogeographical regions of Europe. Our study aims to identify the key environmental drivers of plant species richness in forests dominated by black alder (Alnus glutinosa) in Central Europe with four regions: Pannonian lowland, Matricum as the southern part of the Western Carpathians, High Western Carpathians and Polish Plain. We analysed plant species richness and quantified 15 environmental characteristics (soil, climatic and landscape characteristics) in 140 vegetation plots (35 per region). We used model-based regression trees to test the influence of predictors on the richness of both native and alien species. The regression tree analysis identified eight significant variables controlling species richness in three regions and all bioregions together but found no significant predictor in Matricum. The analysis of the joint dataset indicates that native plant richness was controlled by the effects of catchment slope, soil reaction and precipitation of the warmest quarter. In contrast, the richness of alien species was influenced by the precipitation of the warmest quarter, soil phosphorous and temperature. The species richness of native plants in the High Western Carpathians was driven by soil reaction and the presence of artificial surfaces around the plots, while the richness trend in the Pannonain lowland was determined by annual temperature. Alien richness was affected by the proportion of agricultural areas in the High Western Carpathians, by the stream power index in the Polish Plain and by soil reaction in the Pannonian lowland. The explanatory power of the tree models ranged from 22 to 36%. Our results suggest that the predictability of the richness patterns is contingent upon the specific regions, which differ in the length of environmental gradients.

Google Earth Engine and Machine Learning for Flash Flood Exposure Mapping—Case Study: Tetouan, Morocco

Recently, the earth’s climate has changed considerably, leading to several hazards, including flash floods (FFs). This study aims to introduce an innovative approach to mapping and identifying FF exposure in the city of Tetouan, Morocco. To address this problem, the study uses different machine learning methods applied to remote sensing imagery within the Google Earth Engine (GEE) platform. To achieve this, the first phase of this study was to map land use and land cover (LULC) using Random Forest (RF), a Support Vector Machine (SVM), and Classification and Regression Trees (CART). By comparing the results of five composite methods (mode, maximum, minimum, mean, and median) based on Sentinel images, LULC was generated for each method. In the second phase, the precise LULC was used as a related factor to others (Stream Power Index (SPI), Topographic Position Index (TPI), Slope, Profile Curvature, Plan Curvature, Aspect, Elevation, and Topographic Wetness Index (TWI)). In addition to 2024 non-flood and flood points to predict and detect FF susceptibility, 70% of the dataset was used to train the model by comparing different algorithms (RF, SVM, Logistic Regression (LR), Multilayer Perceptron (MLP), and Naive Bayes (NB)); the rest of the dataset (30%) was used for evaluation. Model performance was evaluated by five-fold cross-validation to assess the model’s ability on new data using metrics such as precision, score, kappa index, recall, and the receiver operating characteristic (ROC) curve. In the third phase, the high FF susceptibility areas were analyzed for two-way validation with inundated areas generated from Sentinel-1 SAR imagery with coherent change detection (CDD). Finally, the validated inundation map was intersected with the LULC areas and population density for FF exposure and assessment. The initial results of this study in terms of LULC mapping showed that the most appropriate method in this research region is the use of an SVM trained on a mean composite. Similarly, the results of the FF susceptibility assessment showed that the RF algorithm performed best with an accuracy of 96%. In the final analysis, the FF exposure map showed that 2465 hectares were affected and 198,913 inhabitants were at risk. In conclusion, the proposed approach not only allows us to assess the impact of FF in this study area but also provides a versatile approach that can be applied in different regions around the world and can help decision-makers plan FF mitigation strategies.

Spatiotemporal distribution of mangrove along the Egyptian Red Sea coast and analysis of hydrological impact on growth patterns

AbstractThis study presents an in-depth spatiotemporal analysis of mangrove ecosystems along Egypt’s Red Sea coast, utilizing satellite imagery and GIS to examine changes from 2003 to 2022. We evaluate the effects of hydrological factors, specifically rainfall and runoff -presented by Stream Power Index-, on mangrove growth patterns. Results indicate a significant increase in mangrove areas, with a notable annual growth rate, despite a reduction in a specific region. This research highlights the integral role of catchment area runoff (R2 = 0.735, R = 0.857, P-value = 0.003 &lt; 0.05, CV = 70.26%), rather than direct rainfall, in mangrove expansion, contributing to the understanding of mangrove resilience and informing sustainable coastal management strategies. The study bridges a significant research gap by mapping decadal mangrove changes, offering insights into the dynamics affecting these crucial ecosystems.

Flood susceptibility modeling by integrating tree‐based regression with metaheuristic algorithm, BWO

AbstractFloods are becoming more widely acknowledged as a common occurrence of nature's dangers on a global scale. Although forecasting models primarily focus on timely warnings, models aimed at evaluating dangerous zones can play a vital role in shaping policies for adaptation, mitigation, and reducing the risk of disasters. Using machine learning techniques including hybrid black widow optimization (BWO) with XGBoost, LGBoost, and AdaBoost. We generate a flood susceptibility map for considered region of lower mahanadi basin (LMB). This study examines the effectiveness of these machine learning models in assessing and mapping flood susceptibility, while also providing suggestions for future research in this area. Flood susceptibility model was developed using 13 variables: Altitude, Aspect, Curvature, Distance from river, Drainage Density, Stream Power Index (SPI), Sediment Transport Index (STI), Rainfall intensity, Land Use Land Cover (LULC), Topographic Wetness Index (TWI), Terrain Roughness Index (TRI), Normalized Difference Vegetation Index (NDVI), and slope. Additionally, flood inventory data were incorporated into the model. Dataset was divided into a 70% portion for training model and a 30% portion for validating model. To assess the performance of the model, several evaluation metrics were employed, including receiver operating characteristic (ROC) curve and other performance indices. Evaluation of flood susceptibility mapping, using ROC curve method in combination with flood density yielded strong and reliable results for various models. BWO‐XGBoost achieved a score of 0.889, BWO‐LGBoost achieved a score of 0.937, and BWO‐ADABoost achieved a score of 0.904. These scores indicate effectiveness of these models in accurately predicting flood susceptibility in the study area. A comparison was made with commonly used methods in flood susceptibility assessment to evaluate the efficiency of proposed models. It was found that having a first‐class and enlightening database is crucial for accurately classifying flood types in flood susceptibility mapping. This aspect greatly contributes to improving the overall performance of the model. Among the evaluated methods, the hybrid model BWO‐LGBoost demonstrated better performance compared with others, indicating its effectiveness in accurately predicting flood susceptibility.