用六大负责任AI原则提升地下水预测准确率与可信度
A Responsible Artificial Intelligence Framework for Groundwater Modeling
- 基于六项责任原则构建地下水预测框架
- Transformer模型在精度与鲁棒性上优于LSTM
- 适合关注可持续水资源管理的研究者
人工智能的快速发展引发了关于如何部署符合人类价值观和伦理标准的责任型AI系统的广泛讨论。相较于医疗、能源或金融领域，AI在地下水领域的应用相对有限，相关责任型AI研究更为稀缺。以黑河中游流域为研究区，本文提出透明性、技术稳健性、隐私治理、公平性、可问责性和可持续性六项责任型AI原则。利用多源水文气象数据构建LSTM与Transformer时间序列模型，并通过事后可解释性分析、蒙特卡洛模拟和情景分析进行验证。结果表明，Transformer在准确性、鲁棒性和可解释性方面均优于LSTM，证明了责任型AI原则在地下水预测中的可操作性与实际价值，有助于支持气候变化与人类活动背景下的可持续水资源管理。
原文摘要 · Abstract (English)
The rapid development and widespread application of artificial intelligence (AI) have sparked intense discussions on how to deploy responsible AI systems in a manner aligned with human values and ethical standards. Compared to fields like healthcare, energy, or finance, the application of AI in groundwater is relatively limited, and research on responsible AI is even more scarce. Taking the middle reaches of the Heihe River Basin as the study area, this paper proposes six Responsible AI principles: transparency, technical robustness, privacy governance, fairness, accountability, and sustainability. LSTM and Transformer time-series models are developed using multi-source hydrometeorological data, and validated via post-hoc interpretability, Monte Carlo simulation, and scenario analysis. The results show that Transformer outperforms LSTM in accuracy, robustness, and interpretability, demonstrating the operability and practical value of Responsible AI principles in groundwater prediction to support sustainable water management under climate change and human activities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。