基于坡度分级的旺业甸林场森林蓄积量反演

打开文本图片集

中图分类号：S758.51;TP751 文献标志码：A 文章编号：1000-2006（2025）06-0013-13

Abstract：【Objective】To improvetheaccuracyofforest stockvolume inversionandprovideareference forremote sensingestimationofforest stock volumeinareas withcomplex terrain，this studyaimstoconstructamulti-sourceremote sensingdataset and examine theimpactof terrain correction at different slope clasifications on theestimation results. 【Method】Using Sentinel-2and GF-6remote sensing images，combinedwith fieldmeasurement data from Wangyedian ForestFarminChifeng，Inner Mongolia，this studyconstructedmultipletraditionalnon-parametric modelsandensemble learning modelstoinvert theforeststock volumeofWangyedianForestFarm.Toreduce theinfluenceof terrain fluctuations on inversion results，，terraincorrections were performedon the images using the Teilet，VECA，and SCS + C methodsatdifferent slopeclassfications toimprovetheaccuracyofforest stockvolume inversion.【Result】Theestimation performance of ensemble learning algorithms was generally superior tothatof traditional non-parametric models，withthe random forest model demonstrating thebest performanceamong all models.Comparedwith the random forestmodel constructed using asingledata source，combining Sentinel-2andGF-6dataimprovedtheinversionresultsof forest stock volume inversion performance，reducing the root mean square error（RMSE）of the models using Boruta by 7.41% and 9.61% ，respectively.After terrain correction based on slopeclassfication，the RMSE of the model decreased by 18.48% ，and the spatial distribution of foreststock volume showeda high degree of consistencywith theactual situation in WangyedianForest Farm.【Conclusion】Using Sentinel-2 and GF-6asdata sources，the constructed ensemble learning algorithms can more efectively estimate forest stockvolume.Terrain correction basedon slopeclassificationsignificantly improves the estimation accuracy of forest stock volume.

Keywords：forest stock volume；remote sensing inversion；federated data source；topographic correction; slopeclassification

森林生态系统是生物圈中最大的碳库，对全球碳循环具有重要意义[1]。（剩余21215字）