Scholarlink

<p>The average global temperature has risen and is expected to continue increasing due to the emission of greenhouse gases. South Asia (SA) has seen a notable rise in both hot days and nights over the past few decades, leading to numerous fatalities. This research investigates historical and future extreme high temperature (EHT) occurrences in SA, identifying their causal connections among geophysical drivers (GD) using causal discovery (CD). An Ensemble Machine Learning (EML) model was created to merge bias-corrected CMIP6 GCMs, enhancing the precision of future EHT event projections. The findings show that the EML algorithm performed exceptionally well (CC = 0.98) compared to conventional ensemble models, accurately capturing EHT events in SA. The intensity of hot days and nights (TXx and TNx) increased during the first (1991–2000) and second (2001–2010) decades examined, with warmer climate conditions (0.01–0.6&#xa0;°C). Future projections suggest that the intensity of hot days and nights will rise by up to 10&#xa0;°C by the end of the twenty-first century, with the frequency of hot days and nights (TX90p and TN90p) increasing by approximately ~ 50% in SA countries. Causal discovery (CD) findings imply that soil moisture, specific humidity, solar flux, aerosol optical depth, and cloud cover significantly influence EHT events in SA countries. This research offers valuable insights for crafting mitigation strategies and reducing future health risks in SA.</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

Unraveling extreme high-temperature events in South Asia: insights from ensemble learning models and geophysical drivers

  • 期刊论文

  • 发表日期：

    2025年7月30日

查看全文
  • Suravi Ghosh,
  • Priyanko Das,
  • Zhenke Zhang,
  • Jianzhong Lu,
  • Brian Odhiambo Ayugi,
  • Zhi Gao

摘要

The average global temperature has risen and is expected to continue increasing due to the emission of greenhouse gases. South Asia (SA) has seen a notable rise in both hot days and nights over the past few decades, leading to numerous fatalities. This research investigates historical and future extreme high temperature (EHT) occurrences in SA, identifying their causal connections among geophysical drivers (GD) using causal discovery (CD). An Ensemble Machine Learning (EML) model was created to merge bias-corrected CMIP6 GCMs, enhancing the precision of future EHT event projections. The findings show that the EML algorithm performed exceptionally well (CC = 0.98) compared to conventional ensemble models, accurately capturing EHT events in SA. The intensity of hot days and nights (TXx and TNx) increased during the first (1991–2000) and second (2001–2010) decades examined, with warmer climate conditions (0.01–0.6 °C). Future projections suggest that the intensity of hot days and nights will rise by up to 10 °C by the end of the twenty-first century, with the frequency of hot days and nights (TX90p and TN90p) increasing by approximately ~ 50% in SA countries. Causal discovery (CD) findings imply that soil moisture, specific humidity, solar flux, aerosol optical depth, and cloud cover significantly influence EHT events in SA countries. This research offers valuable insights for crafting mitigation strategies and reducing future health risks in SA.