Fugen Jiang, Muli Deng, Jie Tang, Liyong Fu, Hua Sun
{"title":"结合星载LiDAR和Sentinel-2图像估算中国北方森林地上生物量","authors":"Fugen Jiang, Muli Deng, Jie Tang, Liyong Fu, Hua Sun","doi":"10.1186/s13021-022-00212-y","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Fast and accurate forest aboveground biomass (AGB) estimation and mapping is the basic work of forest management and ecosystem dynamic investigation, which is of great significance to evaluate forest quality, resource assessment, and carbon cycle and management. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), as one of the latest launched spaceborne light detection and ranging (LiDAR) sensors, can penetrate the forest canopy and has the potential to obtain accurate forest vertical structure parameters on a large scale. However, the along-track segments of canopy height provided by ICESat-2 cannot be used to obtain comprehensive AGB spatial distribution. To make up for the deficiency of spaceborne LiDAR, the Sentinel-2 images provided by google earth engine (GEE) were used as the medium to integrate with ICESat-2 for continuous AGB mapping in our study. Ensemble learning can summarize the advantages of estimation models and achieve better estimation results. A stacking algorithm consisting of four non-parametric base models which are the backpropagation (BP) neural network, k-nearest neighbor (kNN), support vector machine (SVM), and random forest (RF) was proposed for AGB modeling and estimating in Saihanba forest farm, northern China.</p><h3>Results</h3><p>The results show that stacking achieved the best AGB estimation accuracy among the models, with an R<sup>2</sup> of 0.71 and a root mean square error (RMSE) of 45.67 Mg/ha. The stacking resulted in the lowest estimation error with the decreases of RMSE by 22.6%, 27.7%, 23.4%, and 19.0% compared with those from the BP, kNN, SVM, and RF, respectively.</p><h3>Conclusion</h3><p>Compared with using Sentinel-2 alone, the estimation errors of all models have been significantly reduced after adding the LiDAR variables of ICESat-2 in AGB estimation. The research demonstrated that ICESat-2 has the potential to improve the accuracy of AGB estimation and provides a reference for dynamic forest resources management and monitoring.</p></div>","PeriodicalId":505,"journal":{"name":"Carbon Balance and Management","volume":"17 1","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9438156/pdf/","citationCount":"11","resultStr":"{\"title\":\"Integrating spaceborne LiDAR and Sentinel-2 images to estimate forest aboveground biomass in Northern China\",\"authors\":\"Fugen Jiang, Muli Deng, Jie Tang, Liyong Fu, Hua Sun\",\"doi\":\"10.1186/s13021-022-00212-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><p>Fast and accurate forest aboveground biomass (AGB) estimation and mapping is the basic work of forest management and ecosystem dynamic investigation, which is of great significance to evaluate forest quality, resource assessment, and carbon cycle and management. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), as one of the latest launched spaceborne light detection and ranging (LiDAR) sensors, can penetrate the forest canopy and has the potential to obtain accurate forest vertical structure parameters on a large scale. However, the along-track segments of canopy height provided by ICESat-2 cannot be used to obtain comprehensive AGB spatial distribution. To make up for the deficiency of spaceborne LiDAR, the Sentinel-2 images provided by google earth engine (GEE) were used as the medium to integrate with ICESat-2 for continuous AGB mapping in our study. Ensemble learning can summarize the advantages of estimation models and achieve better estimation results. A stacking algorithm consisting of four non-parametric base models which are the backpropagation (BP) neural network, k-nearest neighbor (kNN), support vector machine (SVM), and random forest (RF) was proposed for AGB modeling and estimating in Saihanba forest farm, northern China.</p><h3>Results</h3><p>The results show that stacking achieved the best AGB estimation accuracy among the models, with an R<sup>2</sup> of 0.71 and a root mean square error (RMSE) of 45.67 Mg/ha. The stacking resulted in the lowest estimation error with the decreases of RMSE by 22.6%, 27.7%, 23.4%, and 19.0% compared with those from the BP, kNN, SVM, and RF, respectively.</p><h3>Conclusion</h3><p>Compared with using Sentinel-2 alone, the estimation errors of all models have been significantly reduced after adding the LiDAR variables of ICESat-2 in AGB estimation. The research demonstrated that ICESat-2 has the potential to improve the accuracy of AGB estimation and provides a reference for dynamic forest resources management and monitoring.</p></div>\",\"PeriodicalId\":505,\"journal\":{\"name\":\"Carbon Balance and Management\",\"volume\":\"17 1\",\"pages\":\"\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2022-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9438156/pdf/\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Carbon Balance and Management\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://link.springer.com/article/10.1186/s13021-022-00212-y\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Carbon Balance and Management","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1186/s13021-022-00212-y","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Integrating spaceborne LiDAR and Sentinel-2 images to estimate forest aboveground biomass in Northern China
Background
Fast and accurate forest aboveground biomass (AGB) estimation and mapping is the basic work of forest management and ecosystem dynamic investigation, which is of great significance to evaluate forest quality, resource assessment, and carbon cycle and management. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), as one of the latest launched spaceborne light detection and ranging (LiDAR) sensors, can penetrate the forest canopy and has the potential to obtain accurate forest vertical structure parameters on a large scale. However, the along-track segments of canopy height provided by ICESat-2 cannot be used to obtain comprehensive AGB spatial distribution. To make up for the deficiency of spaceborne LiDAR, the Sentinel-2 images provided by google earth engine (GEE) were used as the medium to integrate with ICESat-2 for continuous AGB mapping in our study. Ensemble learning can summarize the advantages of estimation models and achieve better estimation results. A stacking algorithm consisting of four non-parametric base models which are the backpropagation (BP) neural network, k-nearest neighbor (kNN), support vector machine (SVM), and random forest (RF) was proposed for AGB modeling and estimating in Saihanba forest farm, northern China.
Results
The results show that stacking achieved the best AGB estimation accuracy among the models, with an R2 of 0.71 and a root mean square error (RMSE) of 45.67 Mg/ha. The stacking resulted in the lowest estimation error with the decreases of RMSE by 22.6%, 27.7%, 23.4%, and 19.0% compared with those from the BP, kNN, SVM, and RF, respectively.
Conclusion
Compared with using Sentinel-2 alone, the estimation errors of all models have been significantly reduced after adding the LiDAR variables of ICESat-2 in AGB estimation. The research demonstrated that ICESat-2 has the potential to improve the accuracy of AGB estimation and provides a reference for dynamic forest resources management and monitoring.
期刊介绍：
Carbon Balance and Management is an open access, peer-reviewed online journal that encompasses all aspects of research aimed at developing a comprehensive policy relevant to the understanding of the global carbon cycle.
The global carbon cycle involves important couplings between climate, atmospheric CO2 and the terrestrial and oceanic biospheres. The current transformation of the carbon cycle due to changes in climate and atmospheric composition is widely recognized as potentially dangerous for the biosphere and for the well-being of humankind, and therefore monitoring, understanding and predicting the evolution of the carbon cycle in the context of the whole biosphere (both terrestrial and marine) is a challenge to the scientific community.
This demands interdisciplinary research and new approaches for studying geographical and temporal distributions of carbon pools and fluxes, control and feedback mechanisms of the carbon-climate system, points of intervention and windows of opportunity for managing the carbon-climate-human system.
Carbon Balance and Management is a medium for researchers in the field to convey the results of their research across disciplinary boundaries. Through this dissemination of research, the journal aims to support the work of the Intergovernmental Panel for Climate Change (IPCC) and to provide governmental and non-governmental organizations with instantaneous access to continually emerging knowledge, including paradigm shifts and consensual views.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
