大模型驱动的水利数据流通体系与建设路径研究
Large Language Model-Enabled Circulation of Water Conservancy Data: Architecture and Development Path
随着人工智能技术的快速发展,大模型已成为推动各行业数字化转型的重要驱动力。在水利领域,数据的高效流通对于提升水资源管理能力、优化水利工程运行、增强防灾减灾能力具有重要意义。大模型赋能水利数据流通仍面临安全脆弱、协同机制不健全、时效性不足、模型可解释性欠缺等问题。本文基于大模型技术,从水利数据共享程度低、监测能力薄弱、数据质量低、分析能力有限、数据价值挖掘不足、运维成本高的业务痛点出发,基于开放性、可拓展性、安全防护能力、标准统一原则,构建涵盖多源采集、混合存储、智能治理、敏捷服务、场景应用及内生安全的六层技术架构。系统剖析政策法规、标准规范、技术平台、人才梯队与试点示范五大维度的耦合机制与协同需求,构建面向大模型驱动的水利数据市场化、安全化、智能化流通的建设路径,为推进水利数据市场化配置和高效流通提供了理论支撑和实践指导。基于大模型的水利数据流通技术体系能够显著提升数据的可用性、可解释性与流通效率,驱动水利行业实现高质量数字化转型,为智慧水利体系的构建提供坚实的理论与技术基础。
The rapid advancement of artificial intelligence, particularly large language models (LLMs), has become a central catalyst for the digital transformation across multiple sectors. In the water conservancy field, the efficient circulation of data elements is critical for advancing water resource management, optimizing infrastructure operations, and enhancing disaster resilience. However, current LLM-enabled data circulation faces multiple challenges, including security vulnerabilities, weak cross-domain coordination, latency in data processing, and limited interpretability. Leveraging LLM technologies, this study starts by identifying critical challenges in the water conservancy domain, which include inadequate data sharing, subpar monitoring capabilities, poor data quality, constrained analytical abilities, underutilized data values, and elevated operational and maintenance expenses. Guided by the principles of open access, elastic scalability, full-chain security assurance, and standards-based interoperability, this study proposes a six-layer, data-centric architecture, encompassing multi-source data acquisition, hybrid storage, intelligent data governance, agile service orchestration, scenario-driven applications, and endogenous security. Furthermore, it analyzes the coupling mechanisms and collaborative requirements across five systemic dimensions: regulatory frameworks, data and model standards, platform technologies, talent ecosystems, and pilot-scale experimentation. Building on these insights, a development pathway is proposed for constructing an LLM-enabled ecosystem for the market-oriented, secure, and intelligent circulation of water conservancy data, providing theoretical support and practical guidance for facilitating the market-oriented allocation and efficient circulation of water conservancy data. The proposed architecture can significantly enhance data usability, interpretability, and circulation efficiency, thereby propelling the water conservancy sector toward high-quality digital transformation, and providing a solid theoretical and technical foundation for the establishment of a smart water conservancy system.
| [1] |
陈晓红,肖粲然,曹文治, 我国统一数据要素大市场框架体系与建设路径研究[J]. 中国工程科学,2025,27(1):40‒50. |
| [2] |
Chen X H,Xiao C R,Cao W Z,et al. Framework and pathway for the construction of a unified data-element market in China[J]. Strategic Study of CAE,2025,27(1):40-50. |
| [3] |
王浩,李晓晴. 国家水网主骨架和大动脉不断完善[N]. 人民日报,2024-10-09(14). |
| [4] |
Wang H,Li X Q. Continuous improvement of the main framework and major arteries of the national water network[N]. People’s Daily,2024-10-09(14). |
| [5] |
中共中央 国务院印发《国家水网建设规划纲要》[J]. 大坝与安全,2023(3):21. |
| [6] |
Central Committee of the Communist Party of China,State Council issuance of the outline for the construction planning of the national water network[J]. Dam & Safety,2023(3):21. |
| [7] |
数字中国建设整体布局规划[EB/OL]. (2023-02-27)[2026-01-21]. https://www.gov.cn/zhengce/2023-02/27/content_5743484.html. |
| [8] |
Overall layout plan for building a digital China[EB/OL]. (2023-02-27)[2026-01-21]. https://www.gov.cn/zhengce/2023-02/27/content_5743484.html. |
| [9] |
李永安. 大型水电项目融资与资本运作——三峡工程10年来的融资策略及实践[J]. 中国工程科学,2003,5(10):1-7. |
| [10] |
Li Y A. Financing & capital operations of large hydropower projects:A summary review of financing strategies & practices in Three Gorges Project[J]. Strategic Study of CAE,2003,5(10):1-7. |
| [11] |
中共中央 国务院关于构建数据基础制度更好发挥数据要素作用的意见[J]. 自然资源通讯,2022(24):14-18. |
| [12] |
Central Committee of the Communist Party of China,State Council. Opinions on establishing a basic data system to better tap the role of data as a production factor[J]. National Land & Resources Information,2022(24):14-18. |
| [13] |
关于大力推进智慧水利建设的指导意见[EB/OL].(2022-12-30)[2026-01-21]. http://www.mwr.gov.cn/zw/tzgg/tzgs/202201/t20220106_1564240.html. |
| [14] |
Guiding opinions on vigorously promoting the construction of smart water conservancy[EB/OL]. (2022-12-30)[2026-01-21]. http://www.mwr.gov.cn/zw/tzgg/tzgs/202201/t20220106_1564240.html. |
| [15] |
Wang L,Ma C,Feng X Y,et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science,2024,18(6):186345. |
| [16] |
Xi Z H,Chen W X,Guo X,et al. The rise and potential of large language model based agents:A survey[J]. Science China Information Sciences,2025,68(2):121101. |
| [17] |
Loukatos D,Kondoyanni M,Alexopoulos G,et al. On-device intelligence for malfunction detection of water pump equipment in agricultural premises:Feasibility and experimentation[J]. Sensors,2023,23(2):839. |
| [18] |
Luviano Soto I,Sánchez Y C,Raya A. Water quality polluted by total suspended solids classified within an artificial neural network approach[J]. Water Quality Research Journal,2025,60(1):214-228. |
| [19] |
白东东,丁扬威,田嘉皓, 国内数字孪生水利研究进展分析[J]. 人民长江,2025,56(S1):313-321. |
| [20] |
Bai D D,Ding Y W,Tian J H,et al. Analysis on research progress of digital twin water conservancy in China[J]. Yangtze River,2025,56(S1):313-321. |
| [21] |
Fereshtehpour M,Esmaeilzadeh M,Alipour R S,et al. Impacts of DEM type and resolution on deep learning-based flood inundation mapping[J]. Earth Science Informatics,2024,17(2):1125-1145. |
| [22] |
柴华,侯爱中,成建国, 人工智能水文预报模型技术研究进展[J]. 水文,2026,46(1):1-11. |
| [23] |
Chai H,Hou A Z,Cheng J G,et al. Research progress on artificial intelligence-based hydrological forecasting models[J]. Journal of China Hydrology,2026,46(1):1-11. |
| [24] |
邹晓涛,金思凡,黄天称, 水利数据要素构建与乘数效应激活路径[J]. 中国水利,2025 (5):15-28. |
| [25] |
Zou X T,Jin S F,Huang T C,et al. Construction of water data elements and activation pathways for multiplier effects[J]. China Water Resources,2025(5):15-28. |
| [26] |
李政,胡成盛,周振. 积极推进数据要素市场化配置改革[J]. 宏观经济管理,2025(3):70-77. |
| [27] |
Li Z,Hu C S,Zhou Z. Actively reform the market-oriented allocation of data elements[J]. Macroeconomic Management,2025(3):70-77. |
| [28] |
赵放,宋健,王洁霜. 数据要素市场化对营商环境的优化效应——基于政府和市场的双重视角[J]. 浙江工商大学学报,2025(3):104-115. |
| [29] |
Zhao F,Song J,Wang J S. Optimization effect of data factor marketization on business environment:Based on the dual perspective of government and market[J]. Journal of Zhejiang Gongshang University,2025(3):104-115. |
| [30] |
金和平,杨磊,涂晶, 基于混合数据库的长江流域数据要素流通平台构建[J]. 人民长江,2025,56(3):222-229. |
| [31] |
Jin H P,Yang L,Tu J,et al. Construction of data circulation platform for Changjiang River Basin based on hybrid database technology[J]. Yangtze River,2025,56(3):222-229. |
| [32] |
华美芳,张勇. 政府主导型数据交易平台的发展模式、困境与对策——基于经典扎根理论的研究[J]. 信息资源管理学报,2025,15(2):73-90. |
| [33] |
Hua M F,Zhang Y. The development pattern,dilemmas,and countermeasures of government-led data trading platforms:An analysis based on classical grounded theory[J]. Journal of Information Resources Management,2025,15(2):73-90. |
| [34] |
Muñoz-Carpena R,Carmona-Cabrero A,Yu Z W,et al. Convergence of mechanistic modeling and artificial intelligence in hydrologic science and engineering[J]. PLoS Water,2023,2(8):1-24. |
| [35] |
Feng D P,Liu J T,Lawson K,et al. Differentiable,learnable,regionalized process-based models with multiphysical outputs can approach state-of-the-art hydrologic prediction accuracy[J]. Water Resources Research,2022,58(10):e2022WR032404. |
| [36] |
Willard J D,Varadharajan C,Jia X W,et al. Time series predictions in unmonitored sites:A survey of machine learning techniques in water resources[J]. Environmental Data Science,2025,4:e7. |
| [37] |
李强,赵铜铁钢. 基于大语言模型的洪涝灾害统计调查[J]. 水利水电技术(中英文),2025,56(9):60-75. |
| [38] |
Li Q,Zhao T T G. Statistical survey on flood disasters based on large language model[J]. Water Resources and Hydropower Engineering,2025,56(9):60-75. |
| [39] |
Fu R,Jiao Y,Chen D,et al. Research on the application of large language models in shore power management decision[C]//2024 4th International Conference on Intelligent Power and Systems (ICIPS),2024:1348-1352. |
| [40] |
Lippolis A S,Lodi G,Nuzzolese A G. The water health open knowledge graph[J]. Scientific Data,2025,12:274. |
| [41] |
刘海彪,赵帅,陈伟昌, 水利感知网中数据传输规约研究[J]. 人民长江,2025,56(S1):364-367. |
| [42] |
Liu H B,Zhao S,Chen W C,et al. Research on data transmission protocol in water resources perception network[J]. Yangtze River,2025,56(S1):364-367. |
| [43] |
Gupta N S,Valarmathi B,Hiwanj I. A comparison of deep learning and machine learning methods for water quality prediction[C]//2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT),2025:1361-1368. |
| [44] |
吴华赟,胡国华,王利丽. 基于大模型的数据安全技术探索与研究[J]. 中国信息安全,2025(9):33-37. |
| [45] |
Wu H Y,Hu G H,Wang L L.Exploration and research on data security technology based on big model[J]. China Information Security,2025(9):33‒37. |
| [46] |
Wang X H,Li Y,Qiao Q,et al. Enhancing surface water quality parameter prediction using deep learning and feature augmentation methods[J]. Water,2025,17(24):3523. |
| [47] |
蒋云钟,冶运涛,赵红莉, 水利大数据研究现状与展望[J]. 水力发电学报,2020,39(10):1-32. |
| [48] |
Jiang Y Z,Ye Y T,Zhao H L,et al. Research status and prospects on water conservancy big data[J]. Journal of Hydroelectric Engineering,2020,39(10):1-32. |
| [49] |
董雅雯,李恒,刘佳, 大模型技术的发展与应用:现状、机遇与挑战[J]. 人工智能,2025 (1):110-118. |
| [50] |
Dong Y W,Li H,Liu J,et al. Development and application of large-model technology:Status quo,opportunities and challenges[J]. AI-View,2025(1):110-118. |
| [51] |
Aderemi I A,Kehinde T O,Daniel Okwor U,et al. Explainable AI for water quality monitoring:A systematic review of transparency,interpretability,and trust[J]. IEEE Sensors Reviews,2025,2:419-443. |
| [52] |
Shi J H,Ni L X,Liu J M,et al. Water quality prediction at large-Scale:Systematic assessment of decomposition-deep learning models[J]. Journal of Cleaner Production,2025,519:145995. |
| [53] |
Ding Y K,Zhu Y L,Feng J,et al. Interpretable spatio-temporal attention LSTM model for flood forecasting[J]. Neurocomputing,2020,403:348-359. |
| [54] |
Li X,Sun Q L,Zhang Y F,et al. Enhancing hydrological extremes prediction accuracy:Integrating diverse loss functions in Transformer models[J]. Environmental Modelling & Software,2024,177:106042. |
| [55] |
Sit M,Demiray B Z,Xiang Z R,et al. A comprehensive review of deep learning applications in hydrology and water resources[J]. Water Science and Technology,2020,82(12):2635-2670. |
| [56] |
雷畅,罗斌,黄艳.面向业务场景的水利数据模型构建方法[J/OL].人民长江,2025-12-01. http://www.rmcjzz.cjw.cn/cn/article/pdf/preview/57b1e289-70ad-4a73-a90e-9a271be8d849.pdf. |
| [57] |
Lei C,Luo B,Huang Y. Method for constructing water-resources data model oriented to business scenarios[J/OL]. Yangtze River:2025-12-01. http://www.rmcjzz.cjw.cn/cn/article/pdf/preview/57b1e289-70ad-4a73-a90e-9a271be8d849.pdf. |
| [58] |
Brown T,Mann B,Ryder N,et al. Advances in neural information processing systems[C]//Advances in Neural Information Processing Systems,2020:1877-1901. |
| [59] |
Hess P,Drüke M,Petri S,et al. Physically constrained generative adversarial networks for improving precipitation fields from Earth system models[J]. Nature Machine Intelligence,2022,4(10):828-839. |
| [60] |
Kim J,Kwon Y,Jo Y,et al. KG-GPT:A general framework for reasoning on knowledge graphs using large language models[C]//Findings of the Association for Computational Linguistics:EMNLP 2023,2023:9410-9421. |
| [61] |
Dong S J,Wang L B,Du B,et al. ChangeCLIP:Remote sensing change detection with multimodal vision-language representation learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2024,208:53-69. |
| [62] |
Micek S,Katzenmeyer B,Nichols A,et al. HydroGPT - on demand training for hydraulic modeling workflows[EB/OL]. 2025[2025-09-10].https://awschool.com.au/training/hydrogpt/. |
| [63] |
Mukherjee J. Discrimination of river sandbanks for sand mining in high-mineral regions using multispectral images[J]. Discover Geoscience,2025,3(1):100. |
| [64] |
Lin R H,Chen S,He Z Y,et al. Electricity behavior modeling and anomaly detection services based on a deep variational autoencoder network[J]. Energies,2024,17(16):3904. |
| [65] |
Guan X X,Shan B Y,Nguyen V D,et al. Beyond observed extremes:Can hybrid deep learning models improve flood prediction?[J]. EGUsphere Preprints,2025:EGUsphere‒2025‒1509. |
| [66] |
Büchel J,Vasilopoulos A,Simon W A,et al. Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing[J]. Nature Computational Science,2025,5(1):13-26. |
| [67] |
Hess P. When AI’s large language models shrink[J]. IEEE Spectrum,2023,60(11):28-33. |
| [68] |
Yao Y,Yu T Y,Zhang A,et al. Efficient GPT-4V level multimodal large language model for deployment on edge devices[J]. Nature Communications,2025,16:5509. |
| [69] |
Wu Y P,Yin X W,Zhou G Y,et al. Rising rainfall intensity induces spatially divergent hydrological changes within a large river basin[J]. Nature Communications,2024,15:823. |
| [70] |
Lu S B,Li W Q,Yao G B,et al. The changes prediction on terrestrial water storage in typical regions of China based on neural networks and satellite gravity data[J]. Scientific Reports,2024,14:16855. |
| [71] |
Zhang Z Y,Shan Y L,Zhao D D,et al. City level water withdrawal and scarcity accounts of China[J]. Scientific Data,2024,11:449. |
中国工程院咨询项目“健全现代化基础设施建设体制机制研究”(2024-JJZD-03)
国家自然科学基金资助项目(52408364)
湖南省自然科学基金资助项目(2024JJ6188)
Funding project: Chinese Academy of Engineering project "Research on Improving the Institutional Mechanisms for Modernizing Infrastructure Development"(2024-JJZD-03)
National Natural Science Foundation of China Project(52408364)
Hunan Provincial Natural Science Foundation(2024JJ6188)
/
| 〈 |
|
〉 |