Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery

• Systematically evaluated the effects of GLCM parameters on rubber AGB estimation. • The combination of spectral and textural information improved predictive accuracy. • Support vector regression performed the best in AGB estimation with small samples. • Providing new insight on biophysical parameters estimation with a low-cost UAV system. Aboveground biomass (AGB), as a crucial indicator of forest growth and quality, plays an important role in monitoring the global carbon cycle and forest health. Rapid, accurate, and non-destructive assessment of AGB in rubber plantations is beneficial not only for predicting rubber yield but also for understanding the carbon storage potential in tropical areas. Previous studies have employed spectral information and texture features derived from unmanned aerial vehicle data to estimate the AGB of mangroves. However, few studies systematically assessed the effects of grey level co-occurrence matrix parameters for extracting texture features on AGB estimation in rubber plantations. Whether the combination of spectral information and texture features with suitable grey level co-occurrence matrix parameters selection derived from a low-cost unmanned aerial vehicle system can improve the AGB estimation accuracy remains unclear. To this end, this study evaluated the performance of spectral information and texture features derived from UAV-based high-resolution RGB imagery with different textural parameter settings. Three types of machine learning algorithms (support vector regression; random forest; extreme gradient boosting regressor) and stepwise multiple linear regression were used to compare and analyze their performance for AGB estimation of rubber plantations. The results indicated that appropriate textural parameter selection significantly improved the AGB estimation accuracy when using texture features alone. Among four regression techniques, stepwise multiple linear regression exhibited poor performance, while support vector regression performed the best. The best estimation accuracy ( R 2 = 0.752, RMSE = 28.72 t/ha) was obtained by support vector regression when using the combination of spectral information and texture features with the textural parameters of the orientation of 135°, displacement of 2 pixels, and moving window size parameter of 7 × 7 pixels. The findings suggested that the AGB estimation accuracy can be further improved by the integration of spectral information and texture features when considering appropriate textural parameters.