Tackling Food Insecurity Using Remote Sensing and Machine Learning-Based Crop Yield Prediction

Precise estimation of crop yield is crucial for ensuring food security, managing the supply chain, optimally utilizing resources, promoting economic growth, enhancing climate resilience, controlling losses, and mitigating risks in the agricultural industry. Accurate yield prediction depends upon several interactive factors, including crop genotype, climate conditions, soil fertility, sowing & irrigation plan, and crop management practices. For this purpose, remote sensing data and machine learning (ML) algorithms are emerging as indispensable tools that can significantly increase farm productivity while using minimal resources and reducing environmental impact. In this context, the study presents a framework for wheat grain yield prediction using three regression techniques including Random Forest, Xtreme Gradient Boosting (XGB) regression, and Least Absolute Shrinkage & Selection Operator (LASSO) regression. Various aspects of the three models are investigated and results are compared to explore the optimal technique. Drone-based multispectral sensors are employed to acquire data from three wheat experimental fields with three different sowing dates (SD1, SD2, SD3), and the effect of the seeding plan on crop yield is examined. The prediction performance of models is assessed at different growth stages of the crop using several evaluation metrics. The results show that LASSO achieved the highest performance in April with the coefficient of determination (R2) of 0.93 and mean absolute error (MAE) of 21.72. The average annual predicted yield is 260.54 g/m2, 201.64 g/m2, and 47.29 g/m2 in the wheat field with SD1, SD2, and SD3 respectively. This study can help farmers and agronomists to make informed decisions about crop management activities such as planting & harvest plans, and resource handling.