APPLICATION OF GIS AND REMOTE SENSING IN MAPPING AGROFORESTRY SYSTEMS AND HORTICULTURAL PRODUCTIVITY

Abstract

The integration of Geographic Information Systems (GIS), Remote Sensing (RS), and Artificial Intelligence (AI) has revolutionized the mapping, monitoring, and management of complex agroforestry systems and horticultural production. This paper presents a comprehensive review of advanced geospatial frameworks that address the challenges of structural heterogeneity, tree-crop interactions, biomass estimation, and resource optimization in multifunctional landscapes. Key technologies discussed include spectral unmixing for mixed-pixel problems, multi-criteria decision making (MCDM) for land suitability mapping, vegetation indices (NDVI, EVI, NDRE, etc.) for crop health and phenology monitoring, machine learning algorithms for above-ground biomass and carbon stock estimation, thermal remote sensing for precision irrigation, and UAV-LiDAR combined with digital aerial photogrammetry for 3D canopy architecture and individual tree phenotyping. The study highlights the role of digital Monitoring, Reporting, and Verification (MRV) systems in carbon credit generation and emphasizes how these geospatial tools enhance biodiversity, soil health, water-use efficiency, and climate resilience. Despite existing barriers such as spatial resolution limitations in smallholder systems, emerging hyperspectral satellite missions and hybrid physics-informed models promise greater precision and scalability. This geospatial approach supports data-driven decision-making for sustainable food security and environmental conservation amid growing global population and climate pressures.