Impact of climate change on future flood susceptibility projections under shared socioeconomic pathway scenarios in South Asia using artificial intelligence algorithms.

This study investigated the impact of climate change on flood susceptibility in six South Asian countries Afghanistan, Bangladesh, Bhutan, Bharat (India), Nepal, and Pakistan-under two distinct Shared Socioeconomic Pathway (SSP) scenarios: SSP1-2.6 and SSP5-5.8, for 2041-2060 and 2081-2100. To predict flood susceptibility, we employed three artificial intelligence (AI) algorithms: the K-nearest neighbor (KNN), conditional inference random forest (CIRF), and regularized random forest (RRF). Predictions were based on data from 2452 historical flood events, alongside climatic variables measured over monthly, seasonal, and annual timeframes. The innovative aspect of this research is the emphasis on using climatic variables across these progressively condensed timeframes, specifically addressing eight precipitation factors. The performance evaluation, employing the area under the receiver operating characteristic curve (AUC) metric, identified the RRF model as the most accurate, with the highest AUC of 0.94 during the testing phase, followed by the CIRF (AUC = 0.91) and the KNN (AUC = 0.86). An analysis of variable importance highlighted the substantial role of certain climatic factors, namely precipitation in the warmest quarter, annual precipitation, and precipitation during the wettest month, in the modeling of flood susceptibility in South Asia. The resultant flood susceptibility maps demonstrated the influence of climate change scenarios on susceptibility classifications, signalling a dynamic landscape of flood-prone areas over time. The findings revealed variable trends under different climate change scenarios and periods, with marked differences in the percentage of areas classified as having high and very high flood susceptibility. Overall, this study advances our understanding of how climate change affects flood susceptibility in South Asia and offers an essential tool for assessing and managing flood risks in the region.

Sustainable extraction and conservation of soil resources: New insights through Natural Gamma-ray Spectrometry based Proximal Sensing Method.

Soil is one the most extracted natural raw materials. The vast expanses of fertile alluvial soils of the Indo Gangetic Plains have long remained as abundant soil resource pool for brick manufacturing and construction sectors. Unmonitored continuous removal of soil is reported to cause depletion of soil reserves, loss of soil fertility and affect crop yield. Excavation and removal of soil from isolated patches of land creates low lying and elevated degraded areas which disrupts normal crop cultivation pattern. Natural gamma-ray spectrometry (NGS) can be used as a non-destructive and rapid geophysical sensing method, for identification and delineation of areas with suitable soils. During this work brick kiln areas were visited to understand soil's availability and extraction pattern. NGS measurements of samples from soil profiles were carried out to find if gamma-ray intensities varied with soil clay content. Soil texture and plasticity of the same samples were obtained following standard testing procedures. Winkler and Plasticity charts were used to assess suitability of the soils. A strong linear relationship between gamma-ray potassium (K) intensity and clay contents of soil profile samples (R2 = 0.88) was observed. NGS based devices can be used to scan soil samples rapidly and log shallow depth boreholes in grid sampling design. The gathered spectral gamma-ray data can be then used to predict and generate high resolution 3D models of soil properties, based on which resource areas of suitable soils can be delineated for long term soil extraction without affecting cultivated areas. This will help in delineating areas restricted for soil extraction, which will not only make soil mining sustainable but also address soil conservation by setting aside large cultivated fertile soil areas untouched. Adopting NGS methods will prevent unsystematic removal of fertile soil and creation of degraded lands. This will ultimately result in efficient soil resource management.

Natural gamma-ray spectrometry as a rapid sensing method for detecting variations in soil shrinking and cracking behaviour: An application case study.

Soils which develop desiccation cracks after drying are unsuitable for the making of earthenware. The present work was carried out to demonstrate the use of Natural Gamma-ray Spectrometry (NGS) as a rapid sensing method to detect the variation of cracking behaviour and types of clay dominant in soil using samples collected from the study region. Natural gamma-ray intensities due to potassium (K) and equivalent thorium (eTh) radioisotopes present in soil were recorded using an NGS device. Circular soil cakes of set diameter were sun-dried to find shrinking and cracking variations. Other tests included measurement of particle size distribution, Atterberg indices, basic soil physico-chemical properties, exchangeable cation contents using ICP-OES and XRD identification of clays. 6 soil varieties were identified from the distribution of data points in the binary plots of gamma-ray potassium (GR-K) and thorium (GR-eTh) counts per sec (C/s). Variation of GR-K was observed to be wider (2.14 C/s to 2.54 C/s) than GR-eTh (0.44 C/s to 0.63 C/s). The measured GR-K counts reflect changes in illite content. The soils displayed 3 categories of shrinking and cracking behaviour. The soil variety which displayed maximum mild shrinkage without fine desiccation cracks on the set surface area has the highest GR-K counts. The soil shrinking and cracking variations were not clearly defined by the classification based on the texture and plasticity chart, though the latter indicated dominant smectites. A strong linear relationship between GR-K and exchangeable K (R2 = 0.84) indicates K+ contribution mainly from illite and dominance of other clay types in outliers. Higher levels of polyvalent cations known for binding clay aggregates were observed in the non-cracking soils. Concomitant higher GR-K levels indicate that shrinking soils lacking fine desiccation cracks are associated with fluvial sediments of the recent past with parental mica. This research concludes that NGS-based portable devices can be used for rapid sensing of soils to detect variation in shrinking and cracking behaviour and dominant clay type and thus can be used for identification of soil suitable for earthenware making.

Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India.

This study is an attempt to quantitatively test and compare novel advanced-machine learning algorithms in terms of their performance in achieving the goal of predicting flood susceptible areas in a low altitudinal range, sub-tropical floodplain environmental setting, like that prevailing in the Middle Ganga Plain (MGP), India. This part of the Ganga floodplain region, which under the influence of undergoing active tectonic regime related subsidence, is the hotbed of annual flood disaster. This makes the region one of the best natural laboratories to test the flood susceptibility models for establishing a universalization of such models in low relief highly flood prone areas. Based on highly sophisticated flood inventory archived for this region, and 12 flood conditioning factors viz. annual rainfall, soil type, stream density, distance from stream, distance from road, Topographic Wetness Index (TWI), altitude, slope aspect, slope, curvature, land use/land cover, and geomorphology, an advanced novel hybrid model Adaptive Neuro Fuzzy Inference System (ANFIS), and three metaheuristic models-based ensembles with ANFIS namely ANFIS-GA (Genetic Algorithm), ANFIS-DE (Differential Evolution), and ANFIS-PSO (Particle Swarm Optimization), have been applied for zonation of the flood susceptible areas. The flood inventory dataset, prepared by collected flood samples, were apportioned into 70:30 classes to prepare training and validation datasets. One independent validation method, the Area-Under Receiver Operating Characteristic (AUROC) Curve, and other 11 cut-off-dependent model evaluation metrices have helped to conclude that the ANIFS-GA has outperformed other three models with highest success rate AUC = 0.922 and prediction rate AUC = 0.924. The accuracy was also found to be highest for ANFIS-GA during training (0.886) & validation (0.883). Better performance of ANIFS-GA than the individual models as well as some ensemble models suggests and warrants further study in this topoclimatic environment using other classes of susceptibility models. This will further help establishing a benchmark model with capability of highest accuracy and sensitivity performance in the similar topographic and climatic setting taking assumption of the quality of input parameters as constant.