Scholarlink

<p>Decadal climate prediction offers critical scientific guidance for policymakers and supports socioeconomic sustainability. Nevertheless, state-of-the-art dynamical models remain limited in predicting the intricate multidecadal variability in Eurasian surface air temperature (SAT) at mid-to-high latitudes several years in advance. Here, we present a hybrid deep learning model–Gated Recurrent Unit augmented with batch normalization and attention mechanism (GRUBA) –that significantly enhances decadal prediction skill through advanced postprocessing of multi-model ensemble outputs. By incorporating K-means temporal clustering, GRUBA sequentially refines each SAT cluster according to its distinct decadal variability. During the test period of 2004–2021, the averaged anomaly correlation coefficient skill improves from –0.23 to 0.83, and the mean square skill score from –0.37 to 0.68 compared to the unweighted multi-model ensemble mean. This substantial improvement arises in part from the attention mechanism, which effectively reduces model spread. Furthermore, SHAP (Shapley Additive exPlanations) analysis reveals that GRUBA assigns higher weights to better-performing ensemble members.</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

Deep learning model for enhancing decadal prediction of Eurasian surface air temperature

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月16日

查看全文
  • Yuhao Chen,
  • Yanyan Huang,
  • Danwei Qian,
  • Dapeng Zhang,
  • Ni Huang,
  • Zhicong Yin,
  • Huijun Wang

摘要

Decadal climate prediction offers critical scientific guidance for policymakers and supports socioeconomic sustainability. Nevertheless, state-of-the-art dynamical models remain limited in predicting the intricate multidecadal variability in Eurasian surface air temperature (SAT) at mid-to-high latitudes several years in advance. Here, we present a hybrid deep learning model–Gated Recurrent Unit augmented with batch normalization and attention mechanism (GRUBA) –that significantly enhances decadal prediction skill through advanced postprocessing of multi-model ensemble outputs. By incorporating K-means temporal clustering, GRUBA sequentially refines each SAT cluster according to its distinct decadal variability. During the test period of 2004–2021, the averaged anomaly correlation coefficient skill improves from –0.23 to 0.83, and the mean square skill score from –0.37 to 0.68 compared to the unweighted multi-model ensemble mean. This substantial improvement arises in part from the attention mechanism, which effectively reduces model spread. Furthermore, SHAP (Shapley Additive exPlanations) analysis reveals that GRUBA assigns higher weights to better-performing ensemble members.