Raghu Babu Kottala

Landslides are among the most destructive natural hazards in the Western Ghats region of Kerala, driven by complex interactions between geological, hydrological, and anthropogenic factors. This study aims to generate a high-resolution Landslide Susceptibility Level Map (LSLM) using a machine learning (ML)-based Random Forest (RF) model integrated with Geographic Information Systems (GIS). A total of 231 historical landslide locations obtained from the Bhukosh portal were used as reference data. Eight predictive factors—Stream Order, Drainage Density, Slope, Aspect, Geology, Land Use/Land Cover (LULC), Normalized Difference Vegetation Index (NDVI), and Moisture Stress Index (MSI)—were derived from remote sensing and ancillary datasets, preprocessed, and reclassified for model input. The RF model was trained and validated using a 50:50 split of landslide and non-landslide points, with variable importance values derived to weight each predictive factor of the raster layer in ArcGIS. The resulting Landslide Susceptibility Index (LSI) was reclassified into five susceptibility zones: Very Low, Low, Moderate, High, and Very High. Results indicate that approximately 17.82% of the study area falls under high to very high susceptibility, predominantly in the steep, weathered, and high rainfall zones of the Western Ghats. Validation using Area Under the Curve–Receiver Operating Characteristic (AUC-ROC) analysis yielded an accuracy of 0.890, demonstrating excellent model performance. The output LSM provides valuable spatial insights for planners, disaster managers, and policymakers, enabling targeted mitigation strategies and sustainable land-use planning in landslide-prone regions.

Title of the Article: A QGIS-based study to understand the relationship between Land Surface Temperature and Greenness in Urban Areas. Name of the Reviewer: Prof. K. Raghu Babu, Dept. of Geology, Yogi Vemana University, Kadapa, A.P., India. Abstrac...

The research objective is to assess the Mahi River basin, morphometric parameters, and structurally controlled morphological terrains about the topsoil grain size index (TGSI), based on satellite data including Landsat 8 OLI/TIRS and SRTM-DEM data, using ArcGIS processing software. According to morphometric analysis, the Mahi River basin has an area of 28,844.2 km² and is a drainage basin of the 8^th order. In the sub-basin (SB8), bifurcation ratio reveals structural and geomorphological disorder, and high sinuosity causes significant meandering. These positive dependency factors, such as drainage density (Dd) and stream frequency (Sf), are increasing in SB7, SB8, SB12, and SB13, which results in high permeability, strong runoff, a flat topography, and a gentle slope. TGSI has been performed to analyze the geomorphological features of the structurally controlled Mahi River. The Landsat 8 OLI/TIRS has been utilized for the TGSI analysis, and SRTM-DEM has been utilized for the extraction of structurally controlled lineaments of the river basin. The resultant structurally controlled terrains have been cross-verified based on the DN reflectance of TGSI and the lineament type in the river basin for the morphometry. The results of the TGSI reveal that the minimum and maximum values are -0.1324 and 0.4207; the dominant type of terrain is pediment pediplain complex (PPC), having the TGSI range 0.1322 to 0.4207 with the fracture-type structural dominance with an area of 56.7% of the total area. The results reveal that the structural linear features in the Mahi catchment consist of structural deformed bodies such as faults, fractures, and ridge plains. Thus, it can be observed from the findings that remote sensing data (SRTM-DEM) combined with GIS methodology prove to be an effective tool in morphometric analysis and TGSI data could be utilized in the future for basin management and other hydrological studies.

The process of determining whether a specific portion of land is suitable for a specific purpose is known as land suitability analysis (LSA). In order to promote sustainable development in semi-arid regions, the objective of this study is to analyse, evaluate, and identify the land for green growth based on topography, climate, and soil characteristics. Twelve thematic maps are prepared by using remote sensing satellite data. The Landsat 8 OLI/TIRS is used for the preparation of the thematic maps like land use land cover (LULC), normalized difference vegetation index (NDVI), top soil grain size index (TGSI), and geomorphology (GM), and DEM data is used for the preparation slope, and drainage density (DD). The collateral data is used to prepare geology and soil thematic maps. From the field work, we have collected soil samples for the compulsory physicochemical parameters such as soil EC and soil N-P-K which were taken into consideration and prepared thematic maps. The analytical hierarchy process (AHP) was used to generate the LSA of the research region, by assigning the appropriate weights to each criterion and sub-criterion for the thematic maps. Geographic information systems (GIS) and the multicriteria decision-making (MCDM) approach were used in the study’s methodology. The LSA of the study area has been categories in to four types, i.e., highly suitable, moderately suitable, marginally suitable, and not suitable. The results revealed that 421.31 sq.km (40.09%) is not suitable for agriculture green growth in the study region, whereas 89.58 sq.km (8.52%) is moderately suitable, 267.66 sq.km (25.47%) is marginally suitable, and 266.54 sq.km (25.36%) is highly suitable. Accuracy assessment has validated the LSA map’s accuracy (AA). The AA of LSA is 84.22%, which demonstrates a strong connection with the actual data. The research’s results could be helpful in locating productive agricultural areas in various parts of the world. The decision-making AHP tool paired with GIS provides a novel method.

Land degradation (LD) and desertification are serious ecological, environmental, and social-economic threats in the world, and there is a demanding need to develop accountable and reproducible techniques to assess them at different scales. This study assesses LD and desertification with the help of remote sensing (RS) and geographical information system (GIS) in the study region for the period past 29 years, i.e., from 1990 to 2019. The severity of LD and desertification was assessed quantitatively by collecting twelve soil samples in the study region and analyzing the eleven soil physico-chemical parameters and these values have made correlated with digital number (DN) values with LANDSAT 8 OLI/TIRS satellite image. The land cover analysis of LANDSAT imagery revealed that the water body slightly increased from 0.29% in 1990 to 0.46% in 2019, and built-up-land increased from 2.87% in 1990 to 5.31% in 2019. Vegetation decreased from 52.03% in 1990 to 28.57%. Fallow land, degraded land, and desertified lands increased at alarming rates, respectively 13.71% to 26.35, 18.57% to 22.31%, and 12.53% to 17.00%. It is also established that the multi-temporal analysis of change detection data can provide a sophisticated measure of ecosystem health and variation, and that, over the last 29 years, considerable progress has been made in the respective research.