AUTHOR=Zhang Xiaoli , Li Lu , Liu Yanfeng , Wu Yong , Tang Jing , Xu Weiheng , Wang Leiguang , Ou Guanglong 

TITLE=Improving the accuracy of forest aboveground biomass using Landsat 8 OLI images by quantile regression neural network for Pinus densata forests in southwestern China

JOURNAL=Frontiers in Forests and Global Change

VOLUME=Volume 6 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/forests-and-global-change/articles/10.3389/ffgc.2023.1162291

DOI=10.3389/ffgc.2023.1162291

ISSN=2624-893X

ABSTRACT=It is a challenge to reduce the uncertainties from under-estimation and over-estimation of forest aboveground biomass (AGB) which is common in optical remote sensing imagery. In this study, four models, namely, the linear stepwise regression (LSR): artificial neural network (ANN): quantile regression (QR): and quantile regression neural network (QRNN): were used to estimate Pinus densata forest AGB data through collecting 146 sample plots combined with Landsat 8-Operational Land Imager (OLI) images in Shangri-La City, Yunnan Province, southwestern China. The results showed that compared with LSR, the R2 and mean square error (RMSE) of ANN, QR, and QRNN have improved significantly. In particular, QRNN was able to significantly improve the situation of over-estimation and under-estimation when we estimated forest biomass, which had the highest R2 (0.924) and lowest RMSE (15.636 Mg/ha) for the whole biomass segment. Meanwhile, through model validation, we can find that QRNN had the highest R2 (0.761) and lowest RMSE (6.155 Mg/ha) on the biomass segment of <40 Mg/ha. Furthermore, it had the highest R2 (0.989) and lowest RMSE (3.041 Mg/ha) on the biomass segment of >160 Mg/ha, which offered great potential for improving the estimation accuracy of Pinus densata forest AGB. In conclusion, QRNN, combining the advantages of QR and ANN, provides great potential for improving the estimation accuracy and reducing the uncertainties from the over-estimation and under-estimation in forest AGB estimation using optical remote sensing data.