Rice biophysical parameter retrieval with optical satellite imagery: a comparative assessment of parametric and non-parametric models

This article presents a comparison of parametric and non-parametric models in rice biomass and leaf area index (LAI) retrieval using optical satellite imagery. Four parametric models including the linear, quadratic, logarithmic and exponential models, and four non-parametric models that include RF, SVM, kNN, and GBDT were applied, respectively, on the optical satellite dataset. GBDT produced the most accurate biomass estimates (RMSE of 191.8 g/m(2)) before heading and the quadratic model produced the most accurate biomass estimates (RMSE of 364.7 g/m(2)) after heading. RF registered the most accurate LAI estimates (RMSE of 0.79 m(2)/m(2)) before heading, whereas the quadratic model recorded the most accurate LAI estimates (RMSE of 1.04 m(2)/m(2)) after heading. Non-parametric models outperformed their parametric counterparts at before heading, whereas the reverse is the case after heading. These findings provide a guide to the optimal choice of empirical models for rice biomass and LAI retrieval with optical imagery.

Automated summary

This study compares the performance of parametric and non-parametric models in estimating rice biomass and LAI using optical satellite imagery. The findings suggest that non-parametric models outperform parametric models before heading, while the opposite is true after heading. These results provide guidance for selecting appropriate models for estimating rice biomass and LAI.