Al-Based Remoted Sensing Model for Sustainable Landcover Mapping and Monitoring in Smart City Context

Abstract

In recent years, numerous attempts have been documented in the smart city context to make cities and human settlements more inclusive, safe, resilient, and sustainable by combining the power of ICT tools with AI/Machine Learning backed remote sensing technologies. Using remote sensing technologies, this study aims to enhance methodologies for mapping and monitoring changes in terrestrial Landcover resources in Thailand’s Dong Phayayen-Khao Yai National Park. The goal is to investigate and develop a remote sensing technique for classifying terrestrial Landcover by compensating for topographic effects. Changes were detected using the Landsat 5-TM and Landsat 8 OLI satellites, and deviations from solar and terrain were rectified before the satellite imagery was identified using a Random Forest classifier. It improves efficiency in identifying terrestrial forest regions by combining high-level numerical modelling data (Digital Elevation Model: DEM) with it. The results showed that in the Khao Yai National Park area, the extraction of terrestrial Landcover areas using Long-term Landsat satellite photos performed significantly, with an accuracy of 82.05 percent. The goal of this study is to leverage the power of AI to make the best use of a wide range of terrestrial forest resources. This includes the significance of conducting a comprehensive evaluation of legislation governing the management of terrestrial forest resources. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.