Scholarlink

<p>Assessing regional carbon balance is crucial for developing effective greenhouse gas management strategies under global climate change. This study presents a CatBoost gradient boosting machine learning model to evaluate spatiotemporal variability of net ecosystem exchange of CO<sub>2</sub> in terrestrial ecosystems. Applied to Japanese islands for 2024, the model effectively accounts for multiple factors influencing CO<sub>2</sub> exchange and provides spatial distribution of CO<sub>2</sub> fluxes at regional scale with monthly temporal resolution. The model demonstrated high prediction accuracy with an average coefficient of determination (R<sup>2</sup>) of 0.77 across all ecosystems. By integrating remote sensing data, ground-based measurements and environmental parameters through machine learning, this study provides a comprehensive framework for understanding regional CO<sub>2</sub> exchange patterns. Results can be applied to CO<sub>2</sub> fluxes assessments in other regions and contribute to developing climate mitigation measures. This modeling approach offers a valuable tool for monitoring ecosystem responses to changing climate conditions and informing regional carbon management policies.</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

Machine learning technique for net ecosystem exchange of carbon dioxide simulation and assessment: a regional analysis of Japanese islands

  • 期刊论文

  • 发表日期：

    2026年4月24日

查看全文
  • Artem Gorbarenko,
  • Elizaveta Gorbarenko,
  • Dmitry Mikhailov,
  • Alexander Vlasov,
  • Muhammad Saeed

摘要

Assessing regional carbon balance is crucial for developing effective greenhouse gas management strategies under global climate change. This study presents a CatBoost gradient boosting machine learning model to evaluate spatiotemporal variability of net ecosystem exchange of CO2 in terrestrial ecosystems. Applied to Japanese islands for 2024, the model effectively accounts for multiple factors influencing CO2 exchange and provides spatial distribution of CO2 fluxes at regional scale with monthly temporal resolution. The model demonstrated high prediction accuracy with an average coefficient of determination (R2) of 0.77 across all ecosystems. By integrating remote sensing data, ground-based measurements and environmental parameters through machine learning, this study provides a comprehensive framework for understanding regional CO2 exchange patterns. Results can be applied to CO2 fluxes assessments in other regions and contribute to developing climate mitigation measures. This modeling approach offers a valuable tool for monitoring ecosystem responses to changing climate conditions and informing regional carbon management policies.