Answers are grounded in this paper and cite their sources.
Currently, the urbanisation, population growth of cites, and environmental ecosystem degradation are major effect for changing the Land Use and Land Cover (LULC) pattern on the earth surface. These changes have been significant impacts on the environmental systems and sustainable land resource management. Systematic monitoring of LULC is essential for proper planning and management of land resources by using geospatial and modeling approaches. This paper mainly focuses on the accurate change detection and LULC mapping of 2016 and 2024 using Google Earth Engine (GEE) platform, classifers models and satellite database. The main aim of this study is to analyse the change of LULC classes from one category to another between 2016 and 2024 in the Ajmer district of Rajasthan state, India. The primary objective is to develop machine learning (ML) classifier models for the accurate mapping and monitoring of LULC classes and their changes during 2016 and 2024 period. In this view, the Classification and Regression Trees (SMILE CART) and Random Forest (RF) models have been developed and implemented to both years of satellite datasets, which are identifying four major LULC classes such as Water Bodies, Vegetation Cover, Urban Land, and Waste Land during 2016 and 2024. Both models were precise prepare the LULC mapping of both years, and their performance was compared for the years 2016 and 2024. The CART model reached the moderate classification performance for LULC mapping in both years. These model results of training accuracy showing little increased from 80.01% (2016) to 81.28% (2024), while testing accuracy better from 70.50% to 75.99%. The overall accuracy is indicating the slightly higher from 77.16% to 79.51%, which is indicating better perform the model on 2024 satellite datasets. The RF model constantly outperformed compared with CART model, which is indicating better classification accuracy. The RF model training accuracy continued very higher at 98.70% (2016) and 97.85% (2024), while testing accuracy enhanced slightly from 78.56% to 79.02%. The performance of RF model results are 92.75% & 92.49% during 2016 and 2024, checking the strength, stability, and higher classficiation performance of the RF model for LULC mapping and long-term urban growth monitoring. These results can support evidence-based city planning, land-use plan preparation, smart city, groundwater and sustainable infrastructure development by given consistent remote sensing information for appropriate decision-making and resource distribution.
No takes yet. Share an insight, caveat, or question.
Sharma et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: