Application of GIS and Remote Sensing to Study the Change Detection in Similipal Reserve Forest using Machine Learning

Abstract

This research paper explores how Geographic Information Systems (GIS), remote sensing techniques, also machine learning algorithms apply to detect change in the Similipal Reserve Forest. The primary objectives involve analysing spatial together with temporal variations within vegetation cover as well as assessing fluctuations for water body dynamics inside of the forest area. The study integrates GIS data with remote sensing data because it uses regression analysis to measure trends during this period. Spectral indices from satellite imagery are specifically used in assessing vegetation density changes. In contrast, water indices are employed for analysis of variations in water bodies. Important shifts in water body extent and vegetation cover emerge from the study. These alterations do indicate dynamic ecological processes within the Similipal Reserve Forest. The paper underscores that in order to conserve the forest’s ecological integrity and also biodiversity, monitor and manage with effectiveness continuously. Furthermore, the research recommends that future studies integrate advanced machine learning algorithms for improved accuracy and efficient change detection. This study adds knowledge in a general way to the increasing application of GIS, remote sensing, and machine learning when it comes to ecological research plus natural resource management.