Evaluating Sentinel-1A datasets for rice leaf area index estimation based on machine learning regression models

Three Sentinel-1A datasets in vertical transmitted and horizontal received (VH) and vertical transmitted and vertical received (VV) polarisations, and the linear combination of VH and VV (VHVV) are evaluated for rice green leaf area index (LAI) estimation using four machine learning regression models [Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), Random Forest (RF) and Gradient Boosting Decision Tree (GBDT)]. Results showed that for the entire growing season, VV outperformed VH, recording an R(2)of 0.68 and an RMSE of 0.98 m(2)/m(2)with the k-NN model. However, VHVV produced the most accurate estimates with GBDT (R(2)of 0.82 and RMSE of 0.68 m(2)/m(2)), followed by that of VHVV with RF (R(2)of 0.78 and RMSE of 0.90 m(2)/m(2)). Our findings have further confirmed that combining VH and VV data can achieve improved rice growth modelling, and that tree-based algorithms can better handle data dimensionality.

Automated summary

This study evaluates the application of Sentinel-1A satellite data for rice green leaf area index estimation and compares the performance of different polarizations and machine learning regression models. The results show that using VV data leads to relatively more accurate results, while the combination of VHVV is even more accurate than VV alone. Additionally, tree-based algorithms can better handle the dimensionality of the data.