Key points are not available for this paper at this time.
Bangladesh is predominately an agriculture based country where an extensive part of its population is primarily employed in its agriculture sector. However, uncertain crop yields and inefficient farming infrastructure causes adverse effect in food security. Habiganj is selected as the study area because of its vulnerability to floods and drought due to its unique terrain. This paper presents a combination of agricultural mapping and monitoring of Habiganj with crop growth and yield prediction. Multi-spectral band images of Habiganj from Landsat-8 are processed and remote sensing indices, correlating to crop growth and yield are extracted. With options of K-means and Mask R-CNN methods, the change over the years is evaluated for crop growth estimation in both Python and Matlab. Then using two type machine learning algorithms crop yield of Habiganj is predicted from its existing parameters and for better accuracy future values of its datasets are predicted by using two type of time series analysis model. Such analytical reports and prediction allows monitoring crop growth dynamic and identifying early signs of reduction in crop productivity. Furthermore, comparative studies are concluded between two platforms, algorithms and time series analysis to determine the most suited environment and model for this research purpose.
Shahrin et al. (Thu,) studied this question.