Abstract
We performed a comparative analysis of the prediction accuracy of machine learning methods and ordinary Kriging (OK) hybrid methods for forest volume models based on multi-source remote sensing data combined with ground survey data. Taking Larix olgensis, Pinus koraiensis, and Pinus sylvestris plantations in Mengjiagang forest farms as the research object, based on the Chinese Academy of Forestry LiDAR, charge-coupled device, and hyperspectral (CAF-LiTCHy) integrated system, we extracted the visible vegetation index, texture features, terrain factors, and point cloud feature variables, respectively. Random forest (RF), support vector regression (SVR), and an artificial neural network (ANN) were used to estimate forest volume. In the small-scale space, the estimation of sample plot volume is influenced by the surrounding environment as well as the neighboring observed data. Based on the residuals of these three machine learning models, OK interpolation was applied to construct new hybrid forest volume estimation models called random forest Kriging (RFK), support vector machines for regression Kriging (SVRK), and artificial neural network Kriging (ANNK). The six estimation models of forest volume were tested using the leave-one-out (Loo) cross-validation method. The prediction accuracies of these six models are better, with values above 0.6, and the prediction accuracy values of the hybrid models are all improved to different extents. Among the six models, the RFK hybrid model had the best prediction effect, with an reaching 0.915. Therefore, the machine learning method based on multi-source remote sensing factors is useful for forest volume estimation; in particular, the hybrid model constructed by combining machine learning and the OK method greatly improved the accuracy of forest volume estimation, which, thus, provides a fast and effective method for the remote sensing inversion estimation of forest volume and facilitates the management of forest resources.
Highlights
As an important part of the global ecosystem, the forest landscape plays an important role in maintaining the global carbon emission balance and curbing global warming, in which context forest volume is one of the important indicators [1,2]
After repeated experiments, suitable parameters were found using random search and grid search methods [58], and the inverse study area forest volume random forest (RF), support vector regression (SVR), and artificial neural networks (ANN) estimation models were established by combining the leave-one-out (Loo) crossvalidation method with the coefficient of determination, the root mean square error, and the mean absolute error as model evaluation indexes
Forest volume refers to the total amount of tree volume in a certain forest area, which is one of the basic indicators reflecting the overall scale and level of forest resources in a country or region
Summary
As an important part of the global ecosystem, the forest landscape plays an important role in maintaining the global carbon emission balance and curbing global warming, in which context forest volume is one of the important indicators [1,2]. We obtained multi-source remote sensing data for the Mengjiagang forest farm using the CAF-LiTCHy airborne observation integration system, and extracted the visible light vegetation index, texture feature, terrain factor, and laser radar point cloud feature variables. Combining this with the measured data of ground plot volume, we constructed an RF model, an SVR model, and an ANN model, as well as RFK, SVRK, and ANNK hybrid models, based on the residual OK interpolation of the machine learning model. We used these to estimate the forest volume in the study area, providing an efficient method for forest resource management research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
