Scholarlink

<p>Karst carbon sinks play a key role in narrowing the global carbon-balance gap. Reconstructing DIC (dissolved inorganic carbon)/DOC (dissolved organic carbon) concentrations with machine learning and couple them with the hydrochemistry-runoff method to more precisely quantify basin-scale karst carbon-sink flux. This study focuses on the Lijiang River Basin in Guangxi Zhuang Autonomous Region, China. Based on two years of field measurements (September 2015 to September 2017), we compared six machine-learning algorithms and selected random forest to build DIC and DOC concentration models (<i>R</i><sup>2</sup> reached 0.93 and 0.68, respectively). We then predicted monthly DIC/DOC in 2017 and, with the hydrochemistry-runoff method, estimated a carbonate carbon sink flux of 2.42 × 10<sup>5</sup> tCO<sub>2</sub>/(km<sup>2</sup>·yr) and an intensity of 43.41 tCO<sub>2</sub>/(km<sup>2</sup>·yr). The concentration prediction results are consistent with previous studies, supporting the reliability of both the model and the accounting. This study provides methodological innovation and a scientific basis for karst carbon-sink estimation, and offers a reference for application in sparsely monitored karst basins.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Watershed-scale Karst Carbon Sink Assessment: Based on DIC and DOC Concentration Model Construction

  • 期刊论文

  • 发表日期：

    2026年3月16日

查看全文
  • Xiaoya Lu,
  • Haodong Zheng,
  • Yan Zhen,
  • Qiong Xiao,
  • Ping’an Sun,
  • Ying Miao

摘要

Karst carbon sinks play a key role in narrowing the global carbon-balance gap. Reconstructing DIC (dissolved inorganic carbon)/DOC (dissolved organic carbon) concentrations with machine learning and couple them with the hydrochemistry-runoff method to more precisely quantify basin-scale karst carbon-sink flux. This study focuses on the Lijiang River Basin in Guangxi Zhuang Autonomous Region, China. Based on two years of field measurements (September 2015 to September 2017), we compared six machine-learning algorithms and selected random forest to build DIC and DOC concentration models (R2 reached 0.93 and 0.68, respectively). We then predicted monthly DIC/DOC in 2017 and, with the hydrochemistry-runoff method, estimated a carbonate carbon sink flux of 2.42 × 105 tCO2/(km2·yr) and an intensity of 43.41 tCO2/(km2·yr). The concentration prediction results are consistent with previous studies, supporting the reliability of both the model and the accounting. This study provides methodological innovation and a scientific basis for karst carbon-sink estimation, and offers a reference for application in sparsely monitored karst basins.