Maize yield forecasting model for using satellite multispectral imagery at Kaharole in Dinajpur district

Abstract

The cultivation of maize, a high-yielding grain, has seen increased in Northern Bangladesh. Traditional crop yield prediction is costly and error-prone, often delaying its post-harvest activities. This study used remote sensing (RS) techniques for forecasting pre-harvest maize yield to improve the management system. The normalized difference vegetation index (NDVI) was widely used to predict crop yield. The study used Landsat 8(~ 30 m) and Sentinel 2A (~ 10 m) high resolution data for 2018-2019 and 2019-2020 to predict maize yield based on the year 2020-2021 at Kaharole upazila in Dinajpur district. The single cloud free image acquisition date based on maximum NDVI for both satellite images was used for each maize growing period to develop the yield prediction model. A regression model was performed between NDVI values and 20 farmers filed-level maize yields. The absolute mean error of prediction was about 10.15% for Landsat 8 and 8.82% for Sentinel 2A compared to the actual maize yield during 2020-2021. It can be concluded that NDVI data extracted from Sentinel 2A high resolution satellite images can be successfully used to predict the maize yield with appreciable accuracy. This research recommends the implementation of satellite multispectral imagery for accurate maize yield forecasting to enhance agricultural planning and resource management.

Bangladesh J. Agril. Res. 49(2): 105-123, June 2024