@canaraengineering.in
Assistant Professor-Department of CSE
Canara Engineering college
Academician with 10 years of teaching experience in different engineering colleges and 1.8 years of research experience at Manipal Institute of Technology, Manipal. Area of interests include Satellite image processing, remote sensing, machine learning and deep learning techniques.
M.Tech in CSE
Artificial Intelligence, Computer Science, Multidisciplinary, Computer Vision and Pattern Recognition
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Babitha Ganesh, Shweta Vincent, Sameena Pathan, and Silvia Raquel Garcia Benitez
Springer Science and Business Media LLC
AbstractA landslide susceptibility map (LSM) assists in reducing the danger of landslides by locating the landslide-prone locations within the designated area. One of the locations that are prone to landslides in India's Western Ghats of which Goa is a part. This article presents the LSMs prepared for the state of Goa using four standard machine learning algorithms, namely Logistic Regression (LR ), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and Random Forest (RF). In order to create LSMs, a 78-point landslide inventory, as well as 14 landslide conditioning factors, has been used, including slope, elevation, aspect, total curvature, plan curvature, profile curvature, yearly rainfall, Stream Power Index, Topographic Wetness Index, distance to road, depth to bedrock/soil depth, soil type, lithology, and land use land cover. The most pertinent features for the models' construction have been chosen using the Pearson correlation coefficient test and the Random Forest method. The presence of landslides is shown to be strongly influenced by the distance to road, slope of the terrain, and the annual rainfall. The LSMs generated were classified into five levels ranging from very low susceptibility level to very high susceptible. The prediction accuracy, precision, recall, F1-score, area under the ROC (AUC-ROC), and True Skill Statistics (TSS) have been used to analyse and compare the LSMs created using various methodologies. All of these algorithms perform pretty well, as evidenced by the overall accuracy scores of 81.90% for LR, 83.33% for SVM, 81.94% for KNN, and 86.11% for RF. SVM and RF are the better approaches for forecasting landslide vulnerability in the research area, according to TSS data. The maximum AUC-ROC of 86% was achieved by the RF algorithm. The results of performance metrics lead to the conclusion that the tree-based RF approach is most appropriate for producing LSM for the state of Goa. The results of this study indicate that more landslide-prone areas can be found in the Sattari, Dharbandora, Sanguem, and Canacona regions of Goa.
Shweta Vincent, Babitha Ganesh, Sameena Pathan, Vishwajeet Kulkarni, Parth Sirohi, Tushar Agarwal, and Silvia Raquel Garcia Benitez
IEEE
This article presents a light-weight ANN model for the creation of a landslide susceptibility map (LSM) for the district of Idukki in the South Indian state of Kerala. The landslide conditioning factors (LCF) considered for the creation, training, validation and testing of the LSM are elevation, slope, aspect, curvature, topographic wetness index (TWI), stream power index (SPI), rainfall, topographic ruggedness index (TRI), geology, soil type and land use and land cover. The Frequency Ratio (FR) analysis has been carried out on the LCFs and those having the highest Predictive Rate (PR) have been determined as aspect, slope, rainfall and soil type. Once the LSM is created, it is tested using landslide and non-landslide points using the proposed ANN model which yields an accuracy of 83.5%. Future scope in this work is to improve the accuracy of the model by using metaheuristic algorithms for optimization of weights of the ANN model.
Babitha Ganesh, Shweta Vincent, Sameena Pathan, and Silvia Raquel Garcia Benitez
IOP Publishing
Abstract The loss of natural resources has been linked to rapid and invasive urbanization, which in turn worsens the local environment’s scenery and conditions. Preparation of a land use land cover(LULC) map is one of the methods to observe the changes in the geological structure of the study area. The LULU map gives an idea of changes that are occurring during the specified period which will in turn helps in suggesting the measures to be taken to prevent the chances of natural disasters that might occur because of these changes. This study uses a collection of LANDSAT images to evaluate changes in LULC in the Shimoga district for the years 2010, 2015, and 2020. For the classification and creation of LULC maps for the chosen periods, a supervised technique using a Maximum Likelihood Classifier(MLC) has been used. Waterbodies, urban areas, forest areas, and agricultural land have been recognized as the main classes of LULC. The overall accuracy of these maps has been evaluated while taking into account ground facts from Google Earth Pro. The overall accuracy for classification obtained is 85.03% for 2010, 85.27% for 2015, and 85.61% for 2020. The classifier created using LANDSAT scenes and the MLC approach performs well for the research area, as seen by the Kappa index values of 0.8, 0.8, and 0.81 for the years 2010, 2015, and 2020, respectively. The study’s findings indicate that over ten years, the proportion of built-up areas has expanded from 2.8% to 5.4%. When a 2.49% increase occurs in just 10 years, it is necessary to be concerned given the rise of only 1.6% over the previous 40 years. It can also be observed that the proportion of agricultural land has expanded while the fraction of forests has diminished in the study area. The findings of this study are useful in determining that LULC changes are one of the causes of natural disasters including landslides, floods, and forest fires.
Babitha Ganesh, S. Vincent, Sameena Pathan and Silvia Raquel Garcia Benitez
Babitha, Shweta Vincent, Sameena Pathan, and Silvia Raquel Garcia Benitez
IEEE
Around the world, landslides are the natural disasters that cause the most devastation and fatalities. By identifying the landslide prone locations in a chosen research area, Landslide Susceptibility Mapping (LSM) assists in reducing the danger of landslides. This article presents the LSM prepared for the state of Goa using Weight of Evidence (WoE) statistical method. Establishing the dimensional relationship linking the historical landslide locations of the research region and the various topographical, hydrological, and geological conditioning elements is necessary for the preparation of LSM utilizing the weight of evidence technique. Information about the 78 historical landslides in the research area was gathered from the publicly accessible Bhukosh portal. Ten landslide conditioning factors have been determined for the research area: slope, elevation, total curvature, plan curvature, profile curvature, yearly rainfall, Stream Power Index (SPI), Topographic Wetness Index (TWI), distance to road, and aspect. The WoE model's input data is values of these thematic variables pertaining to past landslide locations. 20% of this data has been set aside for validating the model's predictive power. The Landslide Susceptibility Index (LSI) is created based on the weights assigned by the WoE algorithm to each causative element. The final map of landslide susceptibility has been classed into susceptibility categories viz., very high, high, moderate, low, and very low. It is found that, the eastern and southern portion of Goa includes localities with more chances of having landslide. Area under the ROC curve is utilized to validate this susceptibility map. This model's validation outcome revealed testing accuracy of 71%. The finding of this study helps in identifying the landslide prone locations of the region of interest.