Abstract：Remote sensing monitoring of forest resources is one of the important application directions of remote sensing. Traditional measurement methods cost a lot of workforce and material resources. Scientific forest resource prediction can improve work efficiency and reduce measurement costs. Forest stock volume is an important index to evaluate the quality of forest ecosystems. The forest stock volume inversion model is a mathematical model used to estimate the forest stock volume, which has the functions of learning and prediction. The same ground features are quite different in different light or shadow areas. The band ratio can be used to reduce the error of the results in modeling light and shadow areas to a certain extent. The forest stock volume prediction model usually selects spectral information and texture features as the main modeling factors. It does not fully consider the impact of different models on the prediction accuracy when selecting multi-characteristic variables such as band ratio, vegetation index, and topographic factors. In order to compare the accuracy of different models, this article takes Milin County in Tibet Autonomous Region as the research area, and uses Landsat OLI images, DEM data and forest resource survey data as data sources to extract analyze spectral information, texture features and topographic factors. Three forest volume inversion models based on multi-features are established. The three models are multiple stepwise regression models, BP neural network models and random forest models. The effects of different methods on the inversion of forest stock are studied. The coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) are used to evaluate the fit and accuracy of the model. The results showed that the fit and accuracy of the random forest model are the best (R2=0.739, MAE=55.352 m3·ha-1, RMSE=63.195 m3·ha-1). The result is higher than the multiple stepwise regression model (R2=0.541, MAE=58.317 m3·ha-1, RMSE=71.562 m3·ha-1) and BP neural network model (R2=0.477, MAE=67.503 m3·ha-1, RMSE=73.226 m3·ha-1). The predicted value range of the model is 121.3~372.8 m3·ha-1 and it is relatively close to the actual value. The results showed that the inversion of forest stock volume based on multi-features is effective in practical applications, and different models have different effects on the inversion accuracy of forest stock volume. The random forest regression model has the highest accuracy in this inversion study of forest stock volume, and it can be better applied to remote sensing monitoring of forest resources. This study can provide a reference for selecting forest stock volume inversion methods and help continuously improve the forest resource remote sensing monitoring system.
Key words：Inversion of stock volume; Multiple Stepwise Regression; BP Neural Network; Random Forest; Landsat OLI
李子朝，毕守东，崔玉环，郝 泷. 耦合多种特征的森林蓄积量反演方法比较——以雅鲁藏布江流域森林为例[J]. 光谱学与光谱分析, 2022, 42(10): 3263-3268.
LI Zi-zhao, BI Shou-dong, CUI Yu-huan, HAO Shuang. Comparison of Forest Stock Volume Inversion Methods Coupled With Multiple Features——A Case Study of Forest in Yarlung Zangbo River Basin. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3263-3268.
[1] HAO Shuang, LIU Hua, CHEN Yong-fu, et al(郝 泷, 刘 华, 陈永富, 等). Mountain Research(山地学报), 2017, 35(2): 246.
[2] JIAN Yong-feng, HAN Ze-min, HUANG Guang-ti, et al(菅永峰, 韩泽民, 黄光体, 等). Acta Ecologica Sinica(生态学报), 2021, 41(6): 2161.
[3] ZENG Wei-sheng, SUN Xiang-nan, WANG Liu-ru, et al(曾伟生, 孙乡楠, 王六如, 等). Scientia Silvae Sinicae(林业科学), 2021, 57(2): 31.
[4] ZHU Si-ming, WANG Zhen-xi, PEI Yuan, et al(朱思名, 王振锡, 裴 媛, 等). Journal of Arid Land Resources and Environment(干旱区资源与环境), 2020, 34(10): 160.
[5] YANG Liu, FENG Zhong-ke, YUE De-peng, et al(杨 柳, 冯仲科, 岳德鹏, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(7): 2140.
[6] Obata S, Cieszewski C J, Lowe R C, et al. Remote Sensing, 2021, 13(2): 218.
[7] Mauya E W, Koskinen J, Tegel K, et al. Forests, 2019, 10(3): 279.
[8] ZHOU Jun-hong, WANG Zi-zhi, LIAO Sheng-xi, et al(周俊宏, 王子芝, 廖声熙, 等). Transactions of the Chinese Society for Agricultural Engineering(农业工程学报), 2021, 37(4): 216.
[9] JIANG Fu-gen, SUN Hua, ZHAO Feng, et al(蒋馥根, 孙 华, ZHAO Feng, 等). Journal of Forest and Environment(森林与环境学报), 2019, 39(5): 497.
[10] TANG Yu, SHI Tie-mao, BU Ying-jie, et al(汤 煜, 石铁矛, 卜英杰, 等). Chinese Journal of Ecology(生态学杂志), 2020, 39(4): 1387.
[11] CHENG Wen-sheng, FENG Zhong-ke, YU Jing-xin(程文生, 冯仲科, 于景鑫). Transactions of The Chinese Society for Agricultural Machinery(农业机械学报), 2017, 48(3): 245.
[12] LI Xu-qing, LI Long, ZHUANG Lian-ying, et al(李旭青, 李 龙, 庄连英, 等). Transactions of The Chinese Society for Agricultural Machinery(农业机械学报), 2019, 50(6): 226.
[13] LIU Yan-jun, XIA Kai, FENG Hai-lin, et al(刘彦君, 夏 凯, 冯海林, 等). Acta Scientiae Circumstantiae(环境科学学报), 2019, 39(4): 1241.
[14] MENG Shi-li, PANG Yong, ZHANG Zhong-jun, et al(蒙诗栎, 庞 勇, 张钟军, 等). Journal of Remote Sensing(遥感学报), 2017, 21(5): 812.
[15] ZHU Wan-kuan, XU Yu-xing, WANG Zhi-chao, et al(竹万宽, 许宇星, 王志超, 等). Scientia Silvae Sinicae(林业科学), 2020, 56(5): 1.
