森林工程2025，Vol.41Issue(5)：904-911,8.DOI:10.7525/j.issn.1006-8023.2025.05.004
基于机器学习的森林碳储量时空分布模拟
Spatiotemporal Simulation of Forest Carbon Storage Based on Machine Learning
摘要
Abstract
Forest carbon storage is a critical component of global carbon cycle research and plays a significant role in ad-dressing climate change.This study focused on the northern slope of the Zhangguangcai Mountains in Heilongjiang Prov-ince.By combining ground observation data with Landsat TM(thematic mapper)/OLI(operational land imager)data,multiple machine learning models were applied,along with the bootstrap aggregating ensemble learning algorithm,to simulate forest carbon storage.The results showed that from 1990 to 2022,the forest carbon storage in the study area ex-hibited a significant increasing trend,with an annual average carbon storage of(80.77±0.27)Mg C/hm2.The spatial distribution demonstrated notable heterogeneity,with high carbon storage areas concentrated in flat and semi-mountain-ous regions.Additionally,the mean growing-season temperature was found to have a highly significant positive correla-tion with forest carbon storage(P<0.01),indicating that temperature was the primary climatic factor influencing carbon storage changes.This study provides a novel approach for forest carbon storage accurate simulation carbon sink manage-ment.关键词
遥感/深度学习/Bagging集成学习/气候因子Key words
Remote sensing/deep learning/Bagging ensemble learning/climatic factors分类
农业科技引用本文复制引用
崔立东,贺丹,刘玉龙,丛喜东,刘丹..基于机器学习的森林碳储量时空分布模拟[J].森林工程,2025,41(5):904-911,8.基金项目
黑龙江省自然科学基金联合引导项目(LH2024C114). （LH2024C114）
