Soybean seed composition prediction from standing crops using PlanetScope satellite imagery and machine learning

Soybean is a pivotal agricultural commodity around the world, primarily because of its high seed protein and oil concentration. Therefore, farmers, breeders and end-users are highly interested in understanding and predicting the soybean seed composition traits from the individual field level or agroecosystem. Seed composition traits are the proportions of different chemical and physical makeup of soybean seeds. Frequent daily coverage of PlanetScope (PS) satellite provides a unique opportunity of estimating seed composition due to its ability to track crop growth and development with its unique combination of high spatial and temporal resolution. We aim to predict six different soybean seed composition traits (i.e., protein, oil, sucrose, fiber, ash, starch) using PS imagery of standing soybean crops and machine learning algorithms. We developed multi-stream deep neural network which is based on two types of recurrent neural networks, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) that utilize temporal phenology observed from PS. Four statistical machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVR) were used for comparison. Our results show that GRU worked well for protein (R2 0.36, NRMSE 3.62%) and oil (R2 0.53, NRMSE 4.78%), SVR showed the best results for sucrose (R2 0.74, NRMSE 8.34%), fiber (R2 0.21, NRMSE 4.20%), and starch (R2 0.15, NRMSE 16.84%), and PLSR provided the best result for ash (R2 0.60, NRMSE 1.70%). Among the features, vegetation indices at later reproductive stages were found as the most important variables compared to texture features. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation.