军事知识服务平台
基于机器学习的气候变化下大型水库水温结构预测
Predicting thermal structure in large reservoirs under climate change using machine learn-ing
摘要 为克服纯数据驱动模型缺乏物理约束的局限性,实现传统水库水温模型在未来气候非平稳情景下的快速预测,本文提出一种融合物理机制与数据驱动的水库水温结构预测框架.基于三板溪水库2007-2016年实测资料,结合一维水动力—水温GLM模型、RF-BiLSTM机器学习模型、全球气候模型GCMs,反演三板溪水库历史水温结构,预测未来气候情景下2023-2100年水温结构演变情势.研究结果表明:(1)基于一维水动力—水温GLM模型和实测数据,生成物理约束下的训练数据集,克服了纯数据驱动模型在缺乏物理机制时的伪关联问题,RF-BiLSTM水温预测框架的模拟精度R2>0.9.(2)全球气候模型GCMs反演结果表明,三板溪水库未来气温呈现显著的上升趋势(P<0.01),SSP5-8.5情景下的气温升高幅度远大于SSP2-4.5情景,而降水呈显著增加趋势.(3)至2100年,在SSP2-4.5和SSP5-8.5情境下,三板溪水库平均水温预计分别上升0.39和0.87 ℃,且呈现明显的垂向差异性:表层升温更显著,预计分别上升0.94和2.04 ℃,年均底表温差(TSI)分别上升1.32和1.55 ℃,最大TSI都发生在8月.年均水体稳定度分别增加643.41 J/m2(增幅为7.85%)和1829.47 J/m2(增幅为22.31%),水温分层加剧可增加表层藻类水华和营养盐层化富集的风险,还可导致下游鱼类产卵时间提前.本文提出了物理机制和数据驱动深度融合新思路,可为水库水温管理提供技术支撑.
Abstract:
To address the limitations of data-driven models,which lack physical constraints,and to enable rapid prediction of res-ervoir thermal structure under future non-stationary climate scenarios,this study proposes a hybrid framework integrating physical mechanisms with data-driven modeling for predicting reservoir water temperature profiles.Using observed data from the Sanbanxi Reservoir(2007-2016),a one-dimensional hydrodynamic-water temperature model(GLM),a Random Forest-Bidirectional Long Short-Term Memory(RF-BiLSTM)machine learning model,and Global Climate Models(GCMs),we reconstructed the historical thermal structure of the reservoir and projected its evolution under future climate scenarios from 2023 to 2100.The results indicate the following:(1)A physically constrained training dataset generated by combining the GLM model with measured data effectively mitigates spurious correlations inherent in purely data-driven approaches.The RF-BiLSTM prediction framework achieved high sim-ulation accuracy,with R2>0.9.(2)Projections from GCMs show a significant increasing trend in future air temperature at the Sanbanxi Reservoir.The temperature increase under the SSP5-8.5 scenario is substantially greater than that under SSP2-4.5,while precipitation also exhibits a significant upward trend.(3)By 2100,the average water temperature in the reservoir is projec-ted to rise by 0.39 ℃ and 0.87 ℃ under the SSP2-4.5 and SSP5-8.5 scenarios,respectively,showing pronounced vertical differ-entiation.Surface warming is more significant,with projected increases of 0.94 ℃ and 2.04 ℃,respectively.The annual mean surface-bottom temperature difference is expected to increase by 1.32 ℃ and 1.55 ℃,with the maximum vertical difference occur-ring in August.Annual water column stability is projected to increase by 643.41 J/m2(an increase of 7.85%)and 1829.47 J/m2(an increase of 22.31%)respectively,indicating intensified thermal stratification.This could elevate the risks of surface algal blooms and nutrient stratification enrichment,while also advancing the spawning timing of downstream fish.This study presents a novel approach that deeply integrates physical mechanisms with data-driven techniques,providing technical support for reservoir water temperature management.
刊 名 湖泊科学 ISTICEIPKU
年,卷(期): 2026, 38(5)
机标分类号: TV622 P467 P333
在线出版日期: 2026年9月28日
基金项目: 2024YFC3214600:国家重点研发计划52522905:国家自然科学基金52379061:国家自然科学基金BK20230099:江苏省自然科学基金SKS-2025053:水利部重大科技项目,