人工智能时代地下水数值模拟教学转型升级探索

施小清 ,  吴吉春 ,  吴剑锋

中国地质教育 ›› 2026, Vol. 35 ›› Issue (5) : 5 -12.

PDF (3042KB)
中国地质教育 ›› 2026, Vol. 35 ›› Issue (5) : 5 -12.

人工智能时代地下水数值模拟教学转型升级探索

作者信息 +

Exploration of the Transformation and Upgrading of Groundwater Numerical Simulation Teaching in the Era of Artificial Intelligence

Author information +
文章历史 +
PDF (3114K)

摘要

地下水数值模拟的教学长期以“高精度拟合观测数据”为主要训练目标,但在多源数据快速增长与人工智能(AI)快速发展的背景下,以“拟合导向”的传统教学逐渐暴露出重拟合精度、轻预测不确定性与决策风险,重单一观测数据、轻多源数据融合,重软件操作、轻智能建模训练等局限。本文面向科学智能(AI for Science)范式变革,提出地下水数值模拟教学从“再现系统”转向“决策支持”的转型升级思路,构建覆盖本科生-研究生衔接的分层教学框架:本科阶段在夯实控制方程、数值求解与概念模型等内容的基础上,强化概率统计、数据处理与基础编程;研究生阶段面向真实地下水决策问题,融入不确定性量化、多源数据融合、AI替代模型与多目标优化,突出模型可信度与决策可用性。通过两个教学案例展示如何将建模过程转化为面向管理目标的课程任务。

关键词

人工智能 / 地下水数值模拟 / 决策支持 / 不确定性量化 / 教学改革

Key words

artificial intelligence / groundwater numerical simulation / decision support / uncertainty quantification / teaching reform

引用本文

引用格式 ▾
施小清,吴吉春,吴剑锋. 人工智能时代地下水数值模拟教学转型升级探索[J]. 中国地质教育, 2026, 35(5): 5-12 DOI:

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

薛禹群,吴吉春. 地下水数值模拟在我国回顾与展望:为《水文地质工程地质》创刊 40 年而作[J].水文地质工程地质,1997,24(4):21-24.

[2]

薛禹群. 中国地下水数值模拟的现状与展望[J].高校地质学报,2010,16(1):1.

[3]

Langevin C D,Hughes J D,Banta E R,et al. Documentation for the MODFLOW 6 groundwater flow model[R]US:Geological Survey,2017.

[4]

蒋小伟,梁四海,万力,等. “地下水动力学”课程教学中类比法的运用[J].中国地质教育,2012,21(2):88-91.

[5]

肖长来,梁秀娟,高淑贞,等. 地下水科学与工程专业本科实践教学环节改革与实践[J].中国地质教育,2012,21(1):28-33.

[6]

薛禹群,谢春红. 地下水数值模拟[M].北京:科学出版社,2007.

[7]

Anderson M P,Woessner W W,Hunt R J. Applied groundwater modeling:simulation of flow and advective transport[M].San Diego:Academic press,2015.

[8]

Hill M C,Tiedeman C R. Effective groundwater model calibration:with analysis of data,sensitivities,predictions,and uncertainty[M].Hoboken:John Wiley & Sons,2007.

[9]

Box G E. Science and statistics[J].Journal of the American Statistical Association,1976,71(356):791-799.

[10]

Reichstein M,Camps—valls G,Stevens B,et al. Deep learning and process understanding for data—driven Earth system science[J].Nature,2019,566(7743):195-204.

[11]

Zheng C,Bennett G D. Applied contaminant transport modeling[M]. New York:Wiley—Interscience,2002.

[12]

Beven K,Binley A. The future of distributed models:model calibration and uncertainty prediction[J].Hydrological processes,1992,6(3):279-298.

[13]

Doherty J E,Hunt R J,Tonkin M J. Approaches to highly parameterized inversion:A guide to using PEST for model—parameter and predictive—uncertainty analysis[M].Department of the Interior,US Geological Survey Reston,Virginia,2011.

[14]

Doherty J. Calibration and uncertainty analysis for complex environmental models[M].Boulder:Watermark Numerical Computing,2015.

[15]

Doherty J,Moore C. Decision support modeling:Data assimilation,uncertainty quantification,and strategic abstraction[J].Groundwater,2020,58(3):327-37.

[16]

Evensen G. Data assimilation:the ensemble Kalman filter[M]. Germany:Springer,2009.

[17]

White J T,Hunt R J,Fienen M N,et al. Approaches to highly parameterized inversion:PEST++ Version 5,a software suite for parameter estimation,uncertainty analysis,management optimization and sensitivity analysis[R]US:Geological Survey,2020.

[18]

White J T,Fienen M N,Doherty J E. A python framework for environmental model uncertainty analysis[J].Environmental Modelling & Software,2016(85):217-228.

[19]

Moore C,Doherty J. The cost of uniqueness in groundwater model calibration[J].Advances in Water Resources,2006,29(4):605-623.

[20]

康金正,莫绍星,康学远,等. 机器学习在地下水科学中的前沿进展与挑战[J].地学前缘,2026,33(1):483-499.

[21]

Shadab M A,Luo D,Hiatt E,et al. Investigating steady unconfined groundwater flow using physics informed neural networks[J].Advances in Water Resources,2023(177):104445.

[22]

吴吉春,曾献奎,祝晓彬. 地下水数值模拟基础[M].北京:中国水利水电出版社,2017.

[23]

杜新强,姜振蛟,田海龙,等. 地下水数值模拟基础[M].北京:中国水利水电出版社,2023.

[24]

Mclaughlin D,Townley L R. A reassessment of the groundwater inverse problem[J].Water Resources Research,1996,32(5):1131-1161.

[25]

Asher M J,Croke B F,Jakeman A J,et al. A review of surrogate models and their application to groundwater modeling[J].Water Resources Research,2015,51(8):5957-5973.

[26]

Engelhardt I,De Aguinaga J,Mikat H,et al. Complexity vs. simplicity:groundwater model ranking using information criteria[J].Groundwater,2014,52(4):573-583.

[27]

廖福,王广才. 中外地下水科学与工程学科本科培养对比的启示[J].中国地质教育,2023,32(4):69-74.

[28]

Water Resource Systems [Z].(2006—09—01)[2026—02—24].https://learn.mit.edu/c/topic/machine-learning?resource=3892.

[29]

Modflow 6 and FloPy (Short Course)[Z].(2024—05—31)[2026—02—24].https://igwmc.princeton.edu/modflow/courses-and-morel.

[30]

Groundwater II[Z].(2025—09—01)[2026—02—24].https://iac.ethz.ch/edu/courses/master/electives/groundwater-2.htmll.

[31]

Australian National University. Remote Sensing of Water Resources (EMSC3025)[Z].(2025—09—01)[2026—02—24].https://programsandcourses.anu.edu.au/course.

[32]

Wiggins G P,Mctighe J. Understanding by design[M]. USA:Ascd,2005.

[33]

Hmelo—silver C E. Problem—based learning:What and how do students learn?[J].Educational psychology review,2004,16(3):235-266.

[34]

Kinzelbach W,Wang H,Li Y,et al. Groundwater overexploitation in the North China Plain:A path to sustainability[M]. Germany Berlin:Springer Nature,2022.

[35]

Du J,Shi X,Mo S,et al. Deep learning based optimization under uncertainty for surfactant—enhanced DNAPL remediation in highly heterogeneous aquifers[J].Journal of Hydrology,2022(608):127639.

AI Summary AI Mindmap
PDF (3042KB)

6

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉