Deep Learning and Remote Sensing for Agricultural Land Use Monitoring: A Spatio-Multitemporal Analysis of Rice Field Conversion using Optical Satellite Images

Rice is a staple food for over half of the global population, making its production crucial for food security, especially in Indonesia, the world's third-largest rice consumer. Population growth and urban expansion have led to agricultural land conversion, necessitating efficient monitoring methods. Traditional approaches, such as area sample frameworks and tile surveys, are costly and time-consuming, prompting the need for remote sensing and deep learning solutions. This study utilizes medium-resolution Sentinel-1, Sentinel-2, and Landsat-8 optical satellite imagery from 2013 and 2021 to analyze land cover changes in West Bandung and Purwakarta Regencies, key agricultural regions in Indonesia. A deep learning model is developed to classify land cover, validated through ground-truth evaluation, and applied to assess spatio-multitemporal land use conversion, paddy field estimation, and conversion rates. Results show that deep learning models effectively classify land cover with high accuracy, revealing significant agricultural land loss due to urban expansion. This research contributes to artificial intelligence (AI)-driven land monitoring, particularly in tropical regions, and supports policymakers in sustainable food agriculture land management. The findings highlight the potential of integrating remote sensing and deep learning for cost-effective agricultural monitoring, ensuring food security and sustainable land use. Future research should explore higher-resolution imagery and advanced AI techniques to enhance predictive accuracy and decision-making.