结合哨兵-1 和哨兵-2 图像预测青藏高原东北部卓戈高原的土壤有机碳储量

IF 4.6 2区 环境科学与生态学 Q1 ECOLOGY
Junjie Lei, Changli Zeng, Lv Zhang, Xiaogang Wang, Chanhua Ma, Tao Zhou, Benjamin Laffitte, Ke Luo, Zhihan Yang, Xiaolu Tang
{"title":"结合哨兵-1 和哨兵-2 图像预测青藏高原东北部卓戈高原的土壤有机碳储量","authors":"Junjie Lei, Changli Zeng, Lv Zhang, Xiaogang Wang, Chanhua Ma, Tao Zhou, Benjamin Laffitte, Ke Luo, Zhihan Yang, Xiaolu Tang","doi":"10.1186/s13717-024-00515-7","DOIUrl":null,"url":null,"abstract":"Soil organic carbon (SOC) is a critical component of the global carbon cycle, and an accurate estimate of regional SOC stock (SOCS) would significantly improve our understanding of SOC sequestration and cycles. Zoige Plateau, locating in the northeastern Qinghai-Tibet Plateau, has the largest alpine marsh wetland worldwide and exhibits a high sensitivity to climate fluctuations. Despite an increasing use of optical remote sensing in predicting regional SOCS, optical remote sensing has obvious limitations in the Zoige Plateau due to highly cloudy weather, and knowledge of on the spatial patterns of SOCS is limited. Therefore, in the current study, the spatial distributions of SOCS within 100 cm were predicted using an XGBoost model—a machine learning approach, by integrating Sentinel-1, Sentinel-2 and field observations in the Zoige Plateau. The results showed that SOC content exhibited vertical distribution patterns within 100 cm, with the highest SOC content in topsoil. The tenfold cross-validation approach showed that XGBoost model satisfactorily predicted the spatial patterns of SOCS with a model efficiency of 0.59 and a root mean standard error of 95.2 Mg ha−1. Predicted SOCS showed a distinct spatial heterogeneity in the Zoige Plateau, with an average of 355.7 ± 123.1 Mg ha−1 within 100 cm and totaled 0.27 × 109 Mg carbon. High SOC content in topsoil highlights the high risks of significant carbon loss from topsoil due to human activities in the Zoige Plateau. Combining Sentinel-1 and Sentinel-2 satisfactorily predicted SOCS using the XGBoost model, which demonstrates the importance of selecting modeling approaches and satellite images to improve efficiency in predicting SOCS distribution at a fine spatial resolution of 10 m. Furthermore, the study emphasizes the potential of radar (Sentinel-1) in developing SOCS mapping, with the newly developed fine-resolution mapping having important applications in land management, ecological restoration, and protection efforts in the Zoige Plateau.","PeriodicalId":11419,"journal":{"name":"Ecological Processes","volume":"147 1","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of soil organic carbon stock combining Sentinel-1 and Sentinel-2 images in the Zoige Plateau, the northeastern Qinghai-Tibet Plateau\",\"authors\":\"Junjie Lei, Changli Zeng, Lv Zhang, Xiaogang Wang, Chanhua Ma, Tao Zhou, Benjamin Laffitte, Ke Luo, Zhihan Yang, Xiaolu Tang\",\"doi\":\"10.1186/s13717-024-00515-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Soil organic carbon (SOC) is a critical component of the global carbon cycle, and an accurate estimate of regional SOC stock (SOCS) would significantly improve our understanding of SOC sequestration and cycles. Zoige Plateau, locating in the northeastern Qinghai-Tibet Plateau, has the largest alpine marsh wetland worldwide and exhibits a high sensitivity to climate fluctuations. Despite an increasing use of optical remote sensing in predicting regional SOCS, optical remote sensing has obvious limitations in the Zoige Plateau due to highly cloudy weather, and knowledge of on the spatial patterns of SOCS is limited. Therefore, in the current study, the spatial distributions of SOCS within 100 cm were predicted using an XGBoost model—a machine learning approach, by integrating Sentinel-1, Sentinel-2 and field observations in the Zoige Plateau. The results showed that SOC content exhibited vertical distribution patterns within 100 cm, with the highest SOC content in topsoil. The tenfold cross-validation approach showed that XGBoost model satisfactorily predicted the spatial patterns of SOCS with a model efficiency of 0.59 and a root mean standard error of 95.2 Mg ha−1. Predicted SOCS showed a distinct spatial heterogeneity in the Zoige Plateau, with an average of 355.7 ± 123.1 Mg ha−1 within 100 cm and totaled 0.27 × 109 Mg carbon. High SOC content in topsoil highlights the high risks of significant carbon loss from topsoil due to human activities in the Zoige Plateau. Combining Sentinel-1 and Sentinel-2 satisfactorily predicted SOCS using the XGBoost model, which demonstrates the importance of selecting modeling approaches and satellite images to improve efficiency in predicting SOCS distribution at a fine spatial resolution of 10 m. Furthermore, the study emphasizes the potential of radar (Sentinel-1) in developing SOCS mapping, with the newly developed fine-resolution mapping having important applications in land management, ecological restoration, and protection efforts in the Zoige Plateau.\",\"PeriodicalId\":11419,\"journal\":{\"name\":\"Ecological Processes\",\"volume\":\"147 1\",\"pages\":\"\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ecological Processes\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.1186/s13717-024-00515-7\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ecological Processes","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1186/s13717-024-00515-7","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

土壤有机碳(SOC)是全球碳循环的重要组成部分,对区域土壤有机碳储量(SOCS)的准确估算将极大地提高我们对土壤有机碳固存和循环的认识。位于青藏高原东北部的卓戈高原拥有世界上最大的高寒沼泽湿地,对气候波动具有高度敏感性。尽管光学遥感技术在预测区域SOCS方面的应用日益广泛,但由于卓资高原多云天气,光学遥感技术在卓资高原具有明显的局限性,对SOCS空间模式的了解也十分有限。因此,本研究采用 XGBoost 模型--一种机器学习方法,综合哨兵-1、哨兵-2 和野外观测数据,对卓资高原 100 厘米范围内的 SOCS 空间分布进行了预测。结果表明,SOC 含量在 100 厘米范围内呈现垂直分布模式,表土中的 SOC 含量最高。十倍交叉验证方法表明,XGBoost 模型对 SOCS 空间分布模式的预测效果令人满意,模型效率为 0.59,根平均标准误差为 95.2 Mg ha-1。预测的 SOCS 在卓戈高原显示出明显的空间异质性,100 厘米内平均为 355.7 ± 123.1 Mg ha-1,总碳量为 0.27 × 109 Mg。表土中的高 SOC 含量凸显了卓戈高原人类活动导致表土碳大量流失的高风险。结合哨兵-1 和哨兵-2,利用 XGBoost 模型对 SOCS 进行了令人满意的预测,这表明了选择建模方法和卫星图像以提高在 10 米精细空间分辨率下预测 SOCS 分布效率的重要性。此外,该研究强调了雷达(哨兵-1)在绘制 SOCS 地图方面的潜力,新绘制的精细分辨率地图在佐格高原的土地管理、生态恢复和保护工作中具有重要应用价值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Prediction of soil organic carbon stock combining Sentinel-1 and Sentinel-2 images in the Zoige Plateau, the northeastern Qinghai-Tibet Plateau
Soil organic carbon (SOC) is a critical component of the global carbon cycle, and an accurate estimate of regional SOC stock (SOCS) would significantly improve our understanding of SOC sequestration and cycles. Zoige Plateau, locating in the northeastern Qinghai-Tibet Plateau, has the largest alpine marsh wetland worldwide and exhibits a high sensitivity to climate fluctuations. Despite an increasing use of optical remote sensing in predicting regional SOCS, optical remote sensing has obvious limitations in the Zoige Plateau due to highly cloudy weather, and knowledge of on the spatial patterns of SOCS is limited. Therefore, in the current study, the spatial distributions of SOCS within 100 cm were predicted using an XGBoost model—a machine learning approach, by integrating Sentinel-1, Sentinel-2 and field observations in the Zoige Plateau. The results showed that SOC content exhibited vertical distribution patterns within 100 cm, with the highest SOC content in topsoil. The tenfold cross-validation approach showed that XGBoost model satisfactorily predicted the spatial patterns of SOCS with a model efficiency of 0.59 and a root mean standard error of 95.2 Mg ha−1. Predicted SOCS showed a distinct spatial heterogeneity in the Zoige Plateau, with an average of 355.7 ± 123.1 Mg ha−1 within 100 cm and totaled 0.27 × 109 Mg carbon. High SOC content in topsoil highlights the high risks of significant carbon loss from topsoil due to human activities in the Zoige Plateau. Combining Sentinel-1 and Sentinel-2 satisfactorily predicted SOCS using the XGBoost model, which demonstrates the importance of selecting modeling approaches and satellite images to improve efficiency in predicting SOCS distribution at a fine spatial resolution of 10 m. Furthermore, the study emphasizes the potential of radar (Sentinel-1) in developing SOCS mapping, with the newly developed fine-resolution mapping having important applications in land management, ecological restoration, and protection efforts in the Zoige Plateau.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Ecological Processes
Ecological Processes Environmental Science-Ecological Modeling
CiteScore
8.50
自引率
4.20%
发文量
64
审稿时长
13 weeks
期刊介绍: Ecological Processes is an international, peer-reviewed, open access journal devoted to quality publications in ecological studies with a focus on the underlying processes responsible for the dynamics and functions of ecological systems at multiple spatial and temporal scales. The journal welcomes manuscripts on techniques, approaches, concepts, models, reviews, syntheses, short communications and applied research for advancing our knowledge and capability toward sustainability of ecosystems and the environment. Integrations of ecological and socio-economic processes are strongly encouraged.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信