Estimating Groundnut Yield in Smallholder Agriculture Systems Using PlanetScope Data

Crop yield is related to household food security and community resilience, especially in smallholder agricultural systems. As such, it crucial accurately estimate within-season order provide critical information for farm management decision making. Therefore, the primary objective of this paper assess most appropriate method, indices, growth stage predicting groundnut systems northern Malawi. We have estimated two farms using observed vegetation indices (VIs), which were derived from multitemporal PlanetScope satellite data. Simple linear, multiple linear (MLR), random forest (RF) regressions applied prediction. The leave-one-out cross-validation method was used validate models. results showed that (i) modelling approaches, RF model five important variables (RF5) best approach yield, with a coefficient determination (R2) 0.96 root mean square error (RMSE) 0.29 kg/ha, followed by MLR (R2 = 0.84, RMSE 0.84 kg/ha); addition, (ii) predict during R5/beginning seed stage. RF5 four different farms. yields compared total reported revealed generally yields, margins ranging between 0.85% 11%. errors are within post-harvest loss indicate VIs, open-source remote sensing data, can be facilitate farming planning.