Research Center of Forestry Remote Sensing and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, China.
Key Laboratory of Forestry Remote Sensing Based Big Data and Ecological Security for Hunan Province, Changsha 410004, China.
Sensors (Basel). 2020 Dec 17;20(24):7248. doi: 10.3390/s20247248.
Forest growing stem volume (GSV) reflects the richness of forest resources as well as the quality of forest ecosystems. Remote sensing technology enables robust and efficient GSV estimation as it greatly reduces the survey time and cost while facilitating periodic monitoring. Given its red edge bands and a short revisit time period, Sentinel-2 images were selected for the GSV estimation in Wangyedian forest farm, Inner Mongolia, China. The variable combination was shown to significantly affect the accuracy of the estimation model. After extracting spectral variables, texture features, and topographic factors, a stepwise random forest (SRF) method was proposed to select variable combinations and establish random forest regressions (RFR) for GSV estimation. The linear stepwise regression (LSR), Boruta, Variable Selection Using Random Forests (VSURF), and random forest (RF) methods were then used as references for comparison with the proposed SRF for selection of predictors and GSV estimation. Combined with the observed GSV data and the Sentinel-2 images, the distributions of GSV were generated by the RFR models with the variable combinations determined by the LSR, RF, Boruta, VSURF, and SRF. The results show that the texture features of Sentinel-2's red edge bands can significantly improve the accuracy of GSV estimation. The SRF method can effectively select the optimal variable combination, and the SRF-based model results in the highest estimation accuracy with the decreases of relative root mean square error by 16.4%, 14.4%, 16.3%, and 10.6% compared with those from the LSR-, RF-, Boruta-, and VSURF-based models, respectively. The GSV distribution generated by the SRF-based model matched that of the field observations well. The results of this study are expected to provide a reference for GSV estimation of coniferous plantations.
森林生长量（GSV）反映了森林资源的丰富程度和森林生态系统的质量。遥感技术可以实现强大而高效的 GSV 估算，因为它大大减少了调查时间和成本，同时便于定期监测。考虑到其红色边缘波段和较短的重访时间周期，选择 Sentinel-2 图像用于估算中国内蒙古旺业甸林场的 GSV。变量组合被证明对估计模型的准确性有显著影响。在提取光谱变量、纹理特征和地形因子后，提出了一种逐步随机森林（SRF）方法来选择变量组合，并建立随机森林回归（RFR）模型进行 GSV 估算。然后，将线性逐步回归（LSR）、Boruta、随机森林变量选择（VSURF）和随机森林（RF）方法作为参考，与提出的 SRF 进行比较，以选择预测因子和 GSV 估算。结合观测的 GSV 数据和 Sentinel-2 图像，利用 LSR、RF、Boruta、VSURF 和 SRF 确定的变量组合，通过 RFR 模型生成 GSV 的分布。结果表明，Sentinel-2 红色边缘波段的纹理特征可以显著提高 GSV 估算的准确性。SRF 方法可以有效地选择最佳变量组合，基于 SRF 的模型的结果具有最高的估计精度，与基于 LSR、RF、Boruta 和 VSURF 的模型相比，相对均方根误差分别降低了 16.4%、14.4%、16.3%和 10.6%。基于 SRF 的模型生成的 GSV 分布与实地观测结果吻合较好。本研究结果有望为针叶林的 GSV 估算提供参考。
