Scholarlink

<p>Terrestrial carbon flux dynamics are strongly influenced by climate variability, particularly in tropical dry forests (TDFs), which are drought-adapted ecosystems characterized by pronounced seasonality. However, the impacts of extreme climate events on carbon flux in TDFs remain poorly understood. In this study, we investigate the sensitivity of carbon flux to climate extremes and essential climate variables (ECVs) by integrating 11 years of net ecosystem exchange (NEE) data with 17 extreme climate indices and 8 ECVs, using a Random Forest model interpreted through Shapley Additive exPlanations (SHAP). We find that carbon flux dynamics in the SRNP-EMSS are governed primarily by ECVs rather than short-term extreme events. Results indicate that soil temperature (27.1% importance; SHAP = 0.427), vapor pressure deficit (VPD) (19.5%; SHAP = 0.265), soil moisture (13.6%; SHAP = 0.235), and air temperature (17.8%; SHAP = 0.134) emerged as the dominant drivers of carbon flux variability. These variables exhibited nonlinear responses and clear ecological thresholds: soil temperature above 26.6 °C, VPD exceeding 11 kPa, and soil moisture below 25% triggered a shift from carbon sink to source. Seasonal patterns also revealed higher carbon sourcing during dry seasons (mean SHAP =  + 0.038) and greater sinking during wet seasons (mean SHAP = –0.046). While TDFs appear resilient to short-term extremes, our results highlight increasing vulnerability to sustained climatic shifts, underscoring the importance of monitoring key climate thresholds to preserve the carbon sink capacity of these ecosystems.</p> Graphical Abstract <p>Understanding how tropical dry forests respond to climate variability is essential for predicting their role in the global carbon cycle. This study examines how extreme climate events and fundamental climatic conditions regulate terrestrial carbon flux dynamics in a TDF ecosystem. The central research question inquires whether short-term climate extremes or sustained environmental conditions exert a stronger influence on ecosystem carbon exchange and resilience. Monthly NEE derived from EC observations was analyzed together with a comprehensive set of ECVs and extreme climate indices. An ML framework based on random forest regression was applied to quantify the sensitivity of carbon flux to individual climate drivers and to capture nonlinear responses. Model interpretation techniques were employed to identify the dominant drivers, assess their directional effects, and detect the critical thresholds that drive transitions between carbon sink and carbon source states. Results indicate that carbon dynamics in the TDFs are primarily controlled by sustained climatic conditions rather than by short-lived extreme events. Soil temperature, atmospheric demand, and moisture availability emerge as the most influential controls, with identifiable thresholds beyond which the ecosystem’s carbon sequestration capacity declines. These findings demonstrate a strong short-term resilience of the ecosystem to episodic climate extremes. Furthermore, gradual drying trends may progressively weaken the carbon sink function of TDFs. While short-term resilience provides a buffer against rapid disturbances, long-term shifts in baseline climate conditions pose a substantial risk to ecosystem stability. Overall, these findings illustrated the balance between resilience and vulnerability, emphasizing sustained climate change as a critical driver of future carbon flux dynamics.</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

Decoding Carbon Flux Variability in Response to Climate Extremes in a Tropical Dry Forest Using Machine Learning

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Mohammed Abdaki,
  • Arturo Sanchez-Azofeifa,
  • Hendrik F. Hamann

摘要

Terrestrial carbon flux dynamics are strongly influenced by climate variability, particularly in tropical dry forests (TDFs), which are drought-adapted ecosystems characterized by pronounced seasonality. However, the impacts of extreme climate events on carbon flux in TDFs remain poorly understood. In this study, we investigate the sensitivity of carbon flux to climate extremes and essential climate variables (ECVs) by integrating 11 years of net ecosystem exchange (NEE) data with 17 extreme climate indices and 8 ECVs, using a Random Forest model interpreted through Shapley Additive exPlanations (SHAP). We find that carbon flux dynamics in the SRNP-EMSS are governed primarily by ECVs rather than short-term extreme events. Results indicate that soil temperature (27.1% importance; SHAP = 0.427), vapor pressure deficit (VPD) (19.5%; SHAP = 0.265), soil moisture (13.6%; SHAP = 0.235), and air temperature (17.8%; SHAP = 0.134) emerged as the dominant drivers of carbon flux variability. These variables exhibited nonlinear responses and clear ecological thresholds: soil temperature above 26.6 °C, VPD exceeding 11 kPa, and soil moisture below 25% triggered a shift from carbon sink to source. Seasonal patterns also revealed higher carbon sourcing during dry seasons (mean SHAP =  + 0.038) and greater sinking during wet seasons (mean SHAP = –0.046). While TDFs appear resilient to short-term extremes, our results highlight increasing vulnerability to sustained climatic shifts, underscoring the importance of monitoring key climate thresholds to preserve the carbon sink capacity of these ecosystems.

Graphical Abstract

Understanding how tropical dry forests respond to climate variability is essential for predicting their role in the global carbon cycle. This study examines how extreme climate events and fundamental climatic conditions regulate terrestrial carbon flux dynamics in a TDF ecosystem. The central research question inquires whether short-term climate extremes or sustained environmental conditions exert a stronger influence on ecosystem carbon exchange and resilience. Monthly NEE derived from EC observations was analyzed together with a comprehensive set of ECVs and extreme climate indices. An ML framework based on random forest regression was applied to quantify the sensitivity of carbon flux to individual climate drivers and to capture nonlinear responses. Model interpretation techniques were employed to identify the dominant drivers, assess their directional effects, and detect the critical thresholds that drive transitions between carbon sink and carbon source states. Results indicate that carbon dynamics in the TDFs are primarily controlled by sustained climatic conditions rather than by short-lived extreme events. Soil temperature, atmospheric demand, and moisture availability emerge as the most influential controls, with identifiable thresholds beyond which the ecosystem’s carbon sequestration capacity declines. These findings demonstrate a strong short-term resilience of the ecosystem to episodic climate extremes. Furthermore, gradual drying trends may progressively weaken the carbon sink function of TDFs. While short-term resilience provides a buffer against rapid disturbances, long-term shifts in baseline climate conditions pose a substantial risk to ecosystem stability. Overall, these findings illustrated the balance between resilience and vulnerability, emphasizing sustained climate change as a critical driver of future carbon flux dynamics.