Scholarlink

<p>Wetlands are vital for global carbon storage, yet face significant pressures. This study quantifies wetland landscape pattern changes and their impact on carbon storage in the transboundary Irtysh River Basin (IRB) from 2000 to 2020, identifies key landscape drivers, and projects future carbon storage under distinct scenarios for 2030. We utilized multi-temporal land cover data (GWL_FCS30), landscape metrics (Fragstats), the InVEST model for carbon storage estimation, interpretable machine learning (NGBoost coupled with SHAP analysis) to link landscape patterns to carbon dynamics, sensitivity analysis, and the PLUS model for scenario-based future projections (Natural Scenario - S1, Wetland Protection - S2, Wetland Degradation - S3). From 2000 to 2020, total wetland area increased by 10,417&#xa0;km², primarily driven by marsh and swamp expansion, resulting in a net carbon storage increase from 2.827 × 10⁸ tC to 2.885 × 10⁸ tC (net gain: 5.8 × 10⁶ tC). Sensitivity analysis revealed high responsiveness (Sensitivity Index = 10.812) of carbon storage to wetland area change. The NGBoost model accurately predicted carbon storage based on landscape metrics (MSE = 0.682, RMSE = 0.8259, MAE = 0.7811). SHAP analysis identified the aggregation index (AI), largest patch index (LPI), and number of patches (NP) as the most critical landscape predictors influencing carbon storage. Future projections for 2030 estimate total carbon storage at 3.229 × 10⁸ tC under S1 (stabilization), increasing to 3.421 × 10⁸ tC under S2 (protection), but declining sharply to 1.871 × 10⁸ tC under S3 (degradation). Landscape structure, particularly aggregation and the extent of large patches, significantly influences wetland carbon storage in the IRB. Proactive wetland protection policies are crucial for enhancing and maintaining carbon sequestration capacity in this sensitive transboundary basin, contributing to regional climate change mitigation efforts.</p> Graphical abstract <p>This graphical abstract summarizes a study on wetland dynamics and carbon storage in the Irtysh River Basin (IRB) from 2000 to 2020, with 2030 projections, focusing on wetland conservation and carbon sink roles. Using GWL_FCS30 land use data, Fragstats 4.2, InVEST, NGBoost with SHAP, and the PLUS model, the study analyzes landscape patterns, estimates carbon storage, identifies key drivers (e.g., aggregation index, largest patch index), and simulates future scenarios. Results show marsh and swamp expansion, increased fragmentation, and carbon storage rising to 2.885 × 10⁸ tC by 2020. Projections for 2030 estimate 3.229 × 10⁸ tC (Natural Scenario), 3.421 × 10⁸ tC (Wetland Protection), and 1.871 × 10⁸ tC (Wetland Degradation). This visual highlights the importance of wetland conservation for enhancing carbon sequestration and informs sustainable land-use strategies in transboundary 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

Explainable Machine Learning Insights into Wetland Dynamics and Carbon Storage in the Irtysh River Basin

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月21日

查看全文
  • Kaiyue Luo,
  • Alim Samat,
  • Tim Van de Voorde,
  • Weiguo Jiang,
  • Jilili Abuduwaili

摘要

Wetlands are vital for global carbon storage, yet face significant pressures. This study quantifies wetland landscape pattern changes and their impact on carbon storage in the transboundary Irtysh River Basin (IRB) from 2000 to 2020, identifies key landscape drivers, and projects future carbon storage under distinct scenarios for 2030. We utilized multi-temporal land cover data (GWL_FCS30), landscape metrics (Fragstats), the InVEST model for carbon storage estimation, interpretable machine learning (NGBoost coupled with SHAP analysis) to link landscape patterns to carbon dynamics, sensitivity analysis, and the PLUS model for scenario-based future projections (Natural Scenario - S1, Wetland Protection - S2, Wetland Degradation - S3). From 2000 to 2020, total wetland area increased by 10,417 km², primarily driven by marsh and swamp expansion, resulting in a net carbon storage increase from 2.827 × 10⁸ tC to 2.885 × 10⁸ tC (net gain: 5.8 × 10⁶ tC). Sensitivity analysis revealed high responsiveness (Sensitivity Index = 10.812) of carbon storage to wetland area change. The NGBoost model accurately predicted carbon storage based on landscape metrics (MSE = 0.682, RMSE = 0.8259, MAE = 0.7811). SHAP analysis identified the aggregation index (AI), largest patch index (LPI), and number of patches (NP) as the most critical landscape predictors influencing carbon storage. Future projections for 2030 estimate total carbon storage at 3.229 × 10⁸ tC under S1 (stabilization), increasing to 3.421 × 10⁸ tC under S2 (protection), but declining sharply to 1.871 × 10⁸ tC under S3 (degradation). Landscape structure, particularly aggregation and the extent of large patches, significantly influences wetland carbon storage in the IRB. Proactive wetland protection policies are crucial for enhancing and maintaining carbon sequestration capacity in this sensitive transboundary basin, contributing to regional climate change mitigation efforts.

Graphical abstract

This graphical abstract summarizes a study on wetland dynamics and carbon storage in the Irtysh River Basin (IRB) from 2000 to 2020, with 2030 projections, focusing on wetland conservation and carbon sink roles. Using GWL_FCS30 land use data, Fragstats 4.2, InVEST, NGBoost with SHAP, and the PLUS model, the study analyzes landscape patterns, estimates carbon storage, identifies key drivers (e.g., aggregation index, largest patch index), and simulates future scenarios. Results show marsh and swamp expansion, increased fragmentation, and carbon storage rising to 2.885 × 10⁸ tC by 2020. Projections for 2030 estimate 3.229 × 10⁸ tC (Natural Scenario), 3.421 × 10⁸ tC (Wetland Protection), and 1.871 × 10⁸ tC (Wetland Degradation). This visual highlights the importance of wetland conservation for enhancing carbon sequestration and informs sustainable land-use strategies in transboundary basins