Normalized Difference Vegetation Index for Rice Mapping and Estimation of Rice Area and Yield in Sudan Ecology of Nigeria

Rice is a vital crop for global food security, and remote monitoring and mapping are crucial for detecting crop stress and estimating cultivated areas and outputs. This study employed Normalized Difference Vegetation Index (NDVI) and supervised image classification to assess crop health and map rice-growing areas in three Nigerian states (Kano, Kaduna and Katsina). The research analyzed satellite imagery from Sentinel and Landsat missions during the 2022 growing season. NDVI values revealed variations in vegetation health, ranging from 0.044 to 0.148 in May and peaking at 0.110 to 0.450 in August. Supervised image classification identified an average rice cultivation area of 0.227 hectares. The actual rice yield was measured at 1512.624 kg/ha, while the model predicted a higher output of 4218.21 kg/ha. The prediction model exhibited an average root mean square error (RMSE) of 0.419, corresponding to an accuracy of 82%. This study highlights the potential of remote sensing technologies in tracking rice crop performance and mapping cultivated areas. These tools provide critical insights for data-driven decisions, enhancing rice sector development planning. By integrating remote sensing technologies, this research underscores their value in minimizing human involvement in estimating rice area and productivity indices. The study's findings have significant implications for rice production and food security in Nigeria and globally. The use of remote sensing technologies can help optimize rice production, reduce losses, and improve food availability and affordability. By leveraging these technologies, stakeholders can make informed decisions to enhance rice sector development, ultimately contributing to global food security.