<![CDATA[This study aims to develop an integrated model for food crop productivity by combining natural sciences, remote sensing technology, and Nias local wisdom in South Nias Regency, Indonesia. The agricultural sector in this region faces challenges such as low productivity, soil fertility variability, and limited access to modern agricultural monitoring systems. To address these issues, a mixed-methods approach was applied, integrating quantitative geospatial analysis and qualitative ethnographic data. Remote sensing data from Sentinel-2 and Landsat satellites were used to extract vegetation indices (NDVI) for assessing crop health and spatial productivity patterns. Soil parameters and climatic variables from natural sciences were incorporated to explain biophysical factors influencing crop growth. In addition, local wisdom practices such as organic farming, mixed cropping, and traditional planting systems were quantified into a Local Wisdom Index (LWI). The data were analyzed using Geographic Information Systems and machine learning models to generate a predictive productivity map. The results show that the integrated model significantly improves prediction accuracy compared to single-source approaches, with strong spatial consistency between vegetation health, soil fertility, and traditional farming practices. This study demonstrates that combining scientific data, geospatial technology, and indigenous knowledge provides a more holistic and sustainable framework for agricultural productivity modeling in tropical rural regions.]]>
Copyrights © 2026
