Precision Improvement of Multi-Source Data Fusion Model in Forest Resources Survey

At present, the traditional data source method faces issues of low efficiency and lacking precision in the survey of forest resources in the domestic context, thus a more efficient and effective solution is quite urgent. Therefore, this paper aims to explore the multi-source data fusion model in the forest resources survey to enhance accuracy and efficiency. Our goal is to collect several sources of data by remote sensing images, in situ measurements, and climate data, assuring the data is mutually consistent and applicable with respect to each other in image registration and feature extraction. A multi-source data fusion model-that combined random forests and SVM is used for analysis, and predictive ability of the model is improved through cross-validation and parameter tuning. The <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{\mathbf{2}}$</tex> value of the fusion model in prediction is significantly improved at <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{0. 9 8}$</tex>. The use of the multi-source data fusion model can greatly enhance the accuracy and efficiency of forest resource surveys and thus provide solid data support for forest management.