Search

Abstract 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.

Abstract This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.

Abstract Groundwater is a primary source of drinking water for billions worldwide. It plays a crucial role in irrigation, domestic, and industrial uses, and significantly contributes to drought resilience in various regions. However, excessive groundwater discharge has left many areas vulnerable to potable water shortages. Therefore, assessing groundwater potential zones (GWPZ) is essential for implementing sustainable management practices to ensure the availability of groundwater for present and future generations. This study aims to delineate areas with high groundwater potential in the Bankura district of West Bengal using four machine learning methods: Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), and Voting Ensemble (VE). The models used 161 data points, comprising 70% of the training dataset, to identify significant correlations between the presence and absence of groundwater in the region. Among the methods, Random Forest (RF) and Extreme Gradient Boosting (XGBoost) proved to be the most effective in mapping groundwater potential, suggesting their applicability in other regions with similar hydrogeological conditions. The performance metrics for RF are very good with a precision of 0.919, recall of 0.971, F1-score of 0.944, and accuracy of 0.943. This indicates a strong capability to accurately predict groundwater zones with minimal false positives and negatives. Adaptive Boosting (AdaBoost) demonstrated comparable performance across all metrics (precision: 0.919, recall: 0.971, F1-score: 0.944, accuracy: 0.943), highlighting its effectiveness in predicting groundwater potential areas accurately; whereas, Extreme Gradient Boosting (XGBoost) outperformed the other models slightly, with higher values in all metrics: precision (0.944), recall (0.971), F1-score (0.958), and accuracy (0.957), suggesting a more refined model performance. The Voting Ensemble (VE) approach also showed enhanced performance, mirroring XGBoost's metrics (precision: 0.944, recall: 0.971, F1-score: 0.958, accuracy: 0.957). This indicates that combining the strengths of individual models leads to better predictions. The groundwater potentiality zoning across the Bankura district varied significantly, with areas of very low potentiality accounting for 41.81% and very high potentiality at 24.35%. The uncertainty in predictions ranged from 0.0 to 0.75 across the study area, reflecting the variability in groundwater availability and the need for targeted management strategies. In summary, this study highlights the critical need for assessing and managing groundwater resources effectively using advanced machine learning techniques. The findings provide a foundation for better groundwater management practices, ensuring sustainable use and conservation in Bankura district and beyond.

Abstract The snowline exhibits significant seasonal shifts upward and downward, reflecting the ever-changing dynamics of the seasons and being influenced by climate variations, which can vary annually. These fluctuations profoundly impact the cryosphere, biota, and ecosystem processes in high mountain regions. Despite the critical role of snowline variations, comprehensive information on how actual climate variability affects snow cover trends in the central mountain range of the western Himalayas is scarce. In the 'Pindari' region of the Uttarakhand district, India, which is part of the Himalayas, these challenges are exacerbated by the unchecked growth of anthropogenic activities and the broader impacts of climate change. This study analyses snowline variations in the Pindari glacial region from 1972 to 2018. The findings revealed that the snowline elevation significantly shifted upward between 1972 and 2018. Notably, this research revealed a decrease in snow-covered areas of approximately 5.01 km2 over the course of 46 years. This decrease is attributed to a direct response to the increasing number of high-temperature events that occurred during this extended period. This study emphasizes the urgent need for conservation measures in the study region and similar high mountains to combat global warming and safeguard the snowline, which serves as a visible proxy indicator to safeguard high-altitude Himalayan glaciers.

Abstract Groundwater resources are essential for drinking water, irrigation, and the economy mainly in semiarid environments where rainfall is limited. Currently, unpredictable rainfall due to climate change and pollution on the Earth’s surface directly affects groundwater resources. In this area, most people depend on groundwater resources for irrigation and drinking purposes, and every summer, most of the area depends on groundwater in a semiarid environment. Hence, we selected two popular methods, the analytical hierarchy process (AHP) and multiple influence factor (MIF) methods, which can be applied to map groundwater potential zones. Nine thematic layers, such as land use and land cover (LULC), geomorphology, soil, drainage density, slope, lineament density, elevation, groundwater level, and geology maps, were selected for this study using remote sensing and geographic information system (GIS) techniques. These layers are integrated in ArcGIS 10.5 software with the help of the AHP and MIF methods. The map of the groundwater potential zones in the study area revealed four classes, i.e., poor, moderate, good, and very good, based on the AHP and MF methods. The groundwater potential zone area is 241.50 (ha) Poor, 285.64 (ha) moderate, 408.31 (ha) good, and 92.75 (ha) very good using the AHP method. Similarly, the MIF method revealed that the groundwater potential classes were divided into four classes: 351.29 (ha) poor, 511.18 (ha), moderate, 123.95 (ha) good, and 41.78 (ha) very good. The results were compared to determine which methods are best for planning water and land resource development in specific areas that have basaltic rock and drought conditions. Both groundwater potential zone maps were validated with water yield data. The receiver operating characteristic (ROC) curve and area under the curve (AUC) model results are found to be 0.80 (good) and 0.93 (excellent) using the MIF and AHP methods, respectively; hence, the AHP method is best for delineation of groundwater potential zone maps and groundwater resource planning. The present study’s framework and the results will be valuable for improving the efficiency of irrigation, conserving rainwater and maintaining the ecosystem in India.

Abstract Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes.

Realizing the intricate relationships between drought, vegetation dynamics, and climate change is essential for sustainable resource management. Although temperature and rainfall patterns are the primary determinants of these fluctuations, human activity also plays a significant role. Recent decades have witnessed significant climate change events, particularly in peninsular India. Analyzing these year-by-year variations in rainfall and temperature is essential for informed decision-making. This knowledge can guide the development of innovative adaptation strategies to ensure sustainable livelihoods in the region. This study utilizes the Google Earth Engine platform to analyze yearly climate data and relevant geographical indices from 2003 to 2023 across Peninsular India. The analysis reveals a statistically significant increase in mean annual rainfall (0.262 mm/year) alongside a slight rise in regional land surface temperature (LST) trends (0.102 °C/year). However, yearly average anomaly values for LST also show an upward trend, rising from 2.56 in 2003 to 3.23 in 2023. This suggests a potential shift in rainfall patterns, with potential consequences for water availability. Rising temperatures coupled with altered rainfall patterns can lead to water scarcity, especially in regions reliant on rain-fed agriculture. This has a direct impact on crop yields and overall agricultural productivity. Despite rising temperatures, the analysis using drought indices suggests a decline in average annual drought severity across Peninsular India, with values decreasing from 0.33 in 2003 to 2.70 in 2023. Interestingly, we found a strong positive association between rainfall and vegetation indices, while rainfall and LST exhibited a negative correlation. Interestingly, while rainfall and LST exhibited a negative correlation, a strong positive association was found between rainfall and vegetation indices. These comprehensive findings hold significant potential for informing future climate projections and promoting sustainable development in peninsular India through evidence-based applications.

Study region: Prahova river basin located in the central-southern region of Romania. Study focus: This study aims to assess the susceptibility to flooding by using state-of-the-art machine learning and optimization procedures. To achieve this goal, we employed ten flood-related variables as independent variables in our machine learning models. These variables include slope angle, convergence index, distance from the river, elevation, plan curvature, hydrological soil group, lithology, topographic wetness index, rainfall, and land use. We used 158 flood locations as dependent variables in the training of four hybrid models: Deep Learning Neural Network-Statistical Index (DLNN-SI), Particle Swarm Optimization-Deep Learning Neural Network-Statistical Index (PSO-DLNN-SI), Support Vector Machine-Statistical Index (SVM-SI), and Particle Swarm Optimization-Support Vector Machine-Statistical Index (PSO-SVM-SI). Utilizing the Statistical Index method, we calculated coefficients for each flood predictor class or category. New hydrological insights for the region: The PSO-DLNN-SI model demonstrated the best performance, achieving an AUC-ROC curve of 0.952. It's worth noting that the application of the PSO algorithm significantly enhanced the model's performance. Additionally, it's crucial to highlight that approximately 25 % of the study region exhibits a high to very high susceptibility to flood events. Taking into account the very precise results of the models applied in the present study, we can state that from a hydrological point of view, the current research contributes to a better understanding of the intensity with which floods can affect the different areas of the Prahova river basin.

Modelling at the basin scale offers crucial insights for policymakers as they make decisions regarding the optimal utilization of water resources. This study employed the MIKE HYDRO Basin model to analyse water demand and supply dynamics in the Parvati Basin of Rajasthan, India, for the period 2005–2020. The MIKE11 NAM model showcased strong alignment between simulated and observed runoff during both the calibration (NSE = 0.79, PBIAS = −2%, R2 = 0.79, RMSE = 4.95, RSR = 0.5, and KGE = 0.84) and validation (NSE = 0.67, PBIAS = −12.4%, R2 = 0.68, RMSE = 8.3, RSR = 0.62, and KGE = 0.67) phases. The MIKE HYDRO Basin model also exhibited excellent agreement between observed and simulated reservoir water levels, with R2, NSE, RMSE, PBIAS, RSR, and KGE values of 0.86, 0.81, 3.87, −2.30%, 0.43, and 0.88, respectively. The MIKE HYDRO Basin model was employed to create six distinct scenarios, considering conveyance efficiency, irrigation method, and conjunctive water use, to assess irrigation demands and deficits within the basin. In the initial simulation, featuring a conveyance efficiency of 45%, flood irrigation, and no groundwater utilization, the average water demand and deficit throughout the study period were estimated as 43.15 MCM and 3.45 MCM, respectively, resulting in a sustainability index of 0.506. Enhancing conveyance efficiency to 75% under flood irrigation and 5% conjunctive use could elevate the sustainability index to 0.92. Transitioning to sprinkler irrigation and a lift irrigation system could raise the system’s sustainability index to 1. These developed models hold promise for real-time reservoir operation and irrigation planning across diverse climatic conditions and varying cropping patterns.

AbstractChoosing appropriate locations for built-up growth while maintaining natural balance has become necessary for sustainable urban planning. To this end, two multi-criteria decision-making (MCDM) approaches—the multi-influencing factor (MIF) and the analytical hierarchy process (AHP)—have been applied in this work. The MIF model results show that 23.546% of the study region was very highly suitable for newly built-up areas, and 18.786% was restricted for urban settlement, whereas, in the AHP model, 28.907% of the area was highly suitable, 17.619% was restricted for urban settlement. Finally, the dependability and efficiency of the two models used for the study area were assessed through the receiver operating curve (ROC) and area under curve (AUC) analysis. The comparative analysis demonstrates that the MIF approach (AUC 0.817) is more suitable and reliable than the AHP (AUC 0.783). The present work provides new insights to integrate GIS tools with MCDM for practical urban land suitability assessment.