Estimation of aboveground biomass from PolSAR and PolInSAR using regression-based modelling techniques

Abstract

In the field of forestry studies, microwave remote sensing has broad applications due to the penetration into the semi-transparent media. This feature is used for the estimation of biophysical parameters and monitoring of deforestation. Therefore, the estimation of biophysical parameters is essential for assessing carbon stock management. Hence, the aboveground biomass (AGB) using synthetic aperture radar (SAR) data is recognized as typical approaches in forest application. However, the integrated use of polarimetric (PolSAR) and interferometric (PolInSAR) data might be more efficient tools for AGB mapping. Accordingly, in this study with the integrated data, the efficiency of machine learning techniques including random forest regression (RFR) and multiple linear regression (MLR) model were assessed and compared for the prediction of AGB. The analyses were performed using an image pair of fully polarimetric Radarsat-2 C-band data set and the related field data of Malhan Forest Range, Dehradun Forest Division, which were collected using the systematic sampling technique. Particularly, the training and testing of the models were done using the field sample plots. The experimental results showed that the RFR algorithm provided a better prediction result of AGB than the MLR model. The correlation coefficient (R 2 ) and root-mean-square error (RMSE) for the RFR algorithm was estimated to be around 0.65 and 24.33 Mg/ha, respectively, while for the MLR model, R2 and RMSE are estimated as 0.54 and 33.05 Mg/ha, respectively. Therefore, it was concluded that the prediction of AGB through the machine learning technique using PolSAR and PolInSAR data has a significant advantage for accurate estimation of the AGB.

Pearl Millet Crop Biophysical Parameter Retrieval From Space Borne Polarimetric SAR Data Using Machine Learning

“…The results reveal that RFR provides more reliable estimations for both biomass and height. This aligns with findings in previous studies that have also demonstrated RFR's superior performance in estimating various parameters such as forest biomass (Mangla et al., 2016; Mukhopadhyay et al., 2022), corn height (Xie et al., 2021), and vegetation parameters (P. Kumar et al., 2018). RMSE values for both wet biomass and height fall within acceptable limits with the errors in retrieval around 14% and 12% respectively.…”

“…In the studies by Mukhopadhyay et al. (2022) and Xie et al. (2021) for forest above‐ground biomass and corn height estimation, RFR outperformed MLR and SVR, respectively.…”

“…In the study by P. Kumar et al (2018), for estimating wheat parameters from Sentinel-1A data RFR outperformed other algorithms (SVR, ANN, and LR). In the studies by Mukhopadhyay et al (2022) and Xie et al (2021) for forest above-ground biomass and corn height estimation, RFR outperformed MLR and SVR, respectively.…”

“…Also, in the study carried out by Bouchat et al (2022), generation of the LUT for the entire range was difficult for high biomass crop. Several machine learning techniques like Random Forest (RFR), Multiple Linear Regression (MLR), Support Vector Regression (SVR), and Artificial Neural Network (ANN) are now being explored for estimating plant geophysical parameters as they are comparatively stable (Hosseini et al, 2021;Mangla et al, 2016;Mukhopadhyay et al, 2022;Xie et al, 2021). Algorithm behind Random Forest and Linear Regression are two different approaches of regression.…”

Forest Biomass Assessment Using Multisource Earth Observation Data: Techniques, Data Sets and Applications

“…High-resolution optical satellite data like IRS LISS-IV (Heyojoo & Nandy, 2014;Manna et al, 2014) and very high-resolution data like Worldview-2 and Cartosat (Pandey et al, 2020;Pargal et al, 2017) have been employed for AGB estimation in forests as well as tree outside forests at both forest stand and tree levels. Microwave data, including synthetic aperture radar (SAR), interferometric SAR (InSAR), and polarimetric InSAR (PolInSAR) data, have also been utilized for AGB estimation across various scales (Ghosh & Behera, 2021;Mukhopadhyay et al, 2022).…”