Utilizing Machine Learning Algorithms to Predict Accuracy of the Index of Relative Tectonic Activity (IRTA), Dhansiri (North) River Basin in India and Bhutan

A river tries to maintain a dynamic equilibrium state by adjusting different controlling factors. A significant change in one of the controlling factors will dictate modifications in the others to re-establish the equilibrium in a river system. A river basin may indicate active tectonic movements more precisely than the best space-based geodetic techniques. Morphometric analyses, with the help of DEM and GIS often generates insights into the tectonic activities of an area. The Dhansiri (North) River basin lies on the north bank of the Brahmaputra and on the northern part of the Dhansiri-Kopili fault, which is tectonically active at different times. This paper analyses the impact of relative tectonics on drainage pattern development in the basin based on various morphometric parameters of linear (stream length ratio, bifurcation ratio), areal (form factor, basin elongation ratio), and relief (relief ratio, ruggedness number) aspects. Eleven well-known ML algorithms,namely, Logistic Regression (LR), K Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Gaussian Naive Bayes (GNB) classifier, Neural Network (NN), Extra Tree Classifier (ET), Ada Boost Classifier (AB), Gradient Boosting Classifier (GB), XG Boost Classifier (XGB) is used to model the spatial distribution of relative tectonic activity.These algorithms were executed in Python to assess prediction accuracy using standard metrics like accuracy, precision, recall, and F1 score. The assessment utilized widely used libraries such as sci-kit-learn and TensorFlow to implement and test the algorithms, benefiting from their comprehensive model evaluation and performance assessment tools. The SVM, ET, DT, and GNB techniques had the best performance, achieving an accuracy of 82.60 percent as per the modeling results.The Dhansiri (North) is a sixth-seven-ordered basin characterized by a dendritic drainage pattern. Notably,the spatial prediction of morphometric parameters with ML is potentially competent for regional analyses of neotectonics.