Isotopes in environmental and health studies. 2025 Jun 16:1-22. doi: 10.1080/10256016.2025.2508811 Q41.42025

Exploring stable isotope patterns in monthly precipitation across Southeast Asia using contemporary deep learning models and SHapley Additive exPlanations (SHAP) techniques

基于深度学习模型和SHAP技术探讨东南亚地区月降水稳定同位素特征翻译改进

Mojtaba Heydarizad¹, Nathsuda Pumijumnong², Masoud Minaei^{3 4}, Pouya Salari⁵, Rogert Sorí⁶, Hamid Ghalibaf Mohammadabadi⁷

作者单位 +展开

作者单位

¹ State Key Laboratory of Marine Geology, Tongji University, Shanghai, People's Republic of China.

² Faculty of Environment and Resource Studies, Mahidol University, Nakhon Pathom, Thailand.

³ Department of Geography, Ferdowsi University of Mashhad, Mashhad, Iran.

⁴ Geographic Information Science/System and Remote Sensing Laboratory (GISSRS: Lab), Ferdowsi University of Mashhad, Mashhad, Iran.

⁵ Department of Geology, Ferdowsi University of Mashhad, Mashhad, Iran.

⁶ Centro de Investigación Mariña, Universidade de Vigo, Environmental Physics Laboratory (EPhysLab), Ourense, Spain.

⁷ Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.

DOI: 10.1080/10256016.2025.2508811 PMID: 40522311

摘要中英对照阅读

Stable isotopes are crucial for understanding water cycles and climate dynamics, particularly in tropical regions. However, establishing and maintaining precipitation sampling stations in Southeast Asia is challenging due to high costs and logistical issues. Consequently, many areas in this region have limited or no sampling stations with adequate stable isotope data. To address this problem, developing models that simulate stable isotope contents using ma... ...点击完成人机验证后继续浏览

稳定同位素对于理解水循环和气候动力学至关重要，尤其是在热带地区。然而，在东南亚建立和维护降水采样站面临高昂的成本和物流问题的挑战。因此，该地区的许多区域缺乏足够的稳定同位素数据或根本没有采样站。为了解决这个问题，利用机器学习（ML）技术特别是深度学习来模拟降水中的稳定同位素含量是一种有前景的方法。在这项研究中，我们考察了六大尺度气候模式（遥相关指数）和局部气象参数对东南亚六个关键站点包括曼谷、吉隆坡、雅加达、哥打巴鲁、贾亚普拉和新加坡的降水中稳定同位素含量的影响。应用深度神经网络（DNN）模型进行模拟，并通过各种评价指标将其性能与偏最小二乘回归（PLSR）模型进行了比较。DNN在所有研究站点上始终表现出更优的准确性，突显了DNN准确模拟热带降水中的稳定同位素含量的有效性。SHapley Additive exPlanations（SHAP）技术得出的重要性排序完全符合从DNN重要性函数获得的结果。此外，SHAP总结图强调了关键特征如降水量和潜在蒸发对模型预测的贡献。依赖关系图进一步说明了这些特征与预测响应之间的关系，揭示了影响模型行为的非线性相互作用。这项研究为大型尺度气候驱动因素与局部天气模式之间复杂的交互作用提供了新的见解，并推动了基于同位素的气候变化研究中机器学习的应用。本研究使用的技术为在热带气候下将ML应用于同位素分析提供了一个框架，可以推广到全球类似区域。

关键词：降水；SHAP分析；东南亚；机器学习模型；模拟；验证。

翻译效果不满意？用Ai改进或寻求AI助手帮助，对摘要进行重点提炼

相关内容

期刊名：Isotopes in environmental and health studies

缩写：ISOT ENVIRON HEALT S

ISSN：1025-6016

e-ISSN：1477-2639

IF/分区：1.4/Q4

文章目录更多期刊信息

全文链接

官方链接

PMC全文

引文链接

复制

已复制！

格式：

Exploring stable isotope patterns in monthly precipitation across Southeast Asia using contemporary deep learning models and SHapley Additive exPlanations (SHAP) techniques

基于深度学习模型和SHAP技术探讨东南亚地区月降水稳定同位素特征翻译改进

Characteristics of tritium, stable isotopes and chemical components in monthly precipitation at Hiroshima, Japan

日本广岛月降水氚、稳定同位素和化学成分的特征分析

New SHapley Additive ExPlanations (SHAP) Approach to Evaluate the Raw Materials Interactions of Steel-Fiber-Reinforced Concrete

新的SHAP（SHapely Additive exPlanations）方法评估钢筋纤维混凝土原材料之间的相互作用

Interpretable prediction of cardiopulmonary complications after non-small cell lung cancer surgery based on machine learning and SHapley additive exPlanations

基于机器学习和SHapley additive exPlanations的心肺并发症的可解释预测(非小细胞肺癌手术后)

Detection of Monkeypox Cases Based on Symptoms Using XGBoost and Shapley Additive Explanations Methods

基于症状使用XGBoost和Shapley Additive Explanations方法检测猴痘病例

A model for predicting academic performance on standardised tests for lagging regions based on machine learning and Shapley additive explanations

基于机器学习和Shapley Additive解释模型预测落后地区标准化考试学业表现

Leukocyte deep learning classification assessment using Shapley additive explanations algorithm

基于Shapley Additive解释算法的白细胞深度学习分类评估方法研究

Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

基于 boosting集成学习模型的SHAPley Additive exPlanations在道路交通伤害严重程度预测与分析中的应用研究

An artificial neural network-pharmacokinetic model and its interpretation using Shapley additive explanations

基于神经网络的药代动力学模型及其利用合作对策解释方法分析

Exploring stable isotope patterns in monthly precipitation across Southeast Asia using contemporary deep learning models and SHapley Additive exPlanations (SHAP) techniques

基于深度学习模型和SHAP技术探讨东南亚地区月降水稳定同位素特征 翻译改进

Characteristics of tritium, stable isotopes and chemical components in monthly precipitation at Hiroshima, Japan

日本广岛月降水氚、稳定同位素和化学成分的特征分析

New SHapley Additive ExPlanations (SHAP) Approach to Evaluate the Raw Materials Interactions of Steel-Fiber-Reinforced Concrete

新的SHAP（SHapely Additive exPlanations）方法评估钢筋纤维混凝土原材料之间的相互作用

Interpretable prediction of cardiopulmonary complications after non-small cell lung cancer surgery based on machine learning and SHapley additive exPlanations

基于机器学习和SHapley additive exPlanations的心肺并发症的可解释预测(非小细胞肺癌手术后)

Detection of Monkeypox Cases Based on Symptoms Using XGBoost and Shapley Additive Explanations Methods

基于症状使用XGBoost和Shapley Additive Explanations方法检测猴痘病例

A model for predicting academic performance on standardised tests for lagging regions based on machine learning and Shapley additive explanations

基于机器学习和Shapley Additive解释模型预测落后地区标准化考试学业表现

Leukocyte deep learning classification assessment using Shapley additive explanations algorithm

基于Shapley Additive解释算法的白细胞深度学习分类评估方法研究

Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

基于 boosting集成学习模型的SHAPley Additive exPlanations在道路交通伤害严重程度预测与分析中的应用研究

An artificial neural network-pharmacokinetic model and its interpretation using Shapley additive explanations

基于神经网络的药代动力学模型及其利用合作对策解释方法分析

基于深度学习模型和SHAP技术探讨东南亚地区月降水稳定同位素特征翻译改进