可解释性
可扩展性
灵活性(工程)
中尺度气象学
传递函数
数学优化
估计理论
水文模型
计算机科学
机器学习
限制
地表径流
代表(政治)
一致性(知识库)
人工智能
气候模式
数据挖掘
作者
Moritz Feigl,Mathew Herrnegger,Karsten Schulz
出处
期刊:
[Springer Science+Business Media]
日期:2026-02-13
卷期号:4 (2): 158-168
被引量:7
标识
DOI:10.1038/s44221-026-00583-3
摘要
Abstract The estimation of parameters for distributed hydrological and land-surface models is inherently difficult, particularly in data-scarce regions. We present a novel approach that employs variational autoencoders (VAEs) that have been trained as text-generating models to automatically generate optimal, interpretable parameter transfer functions. This AI-driven methodology transforms equation discovery into continuous latent-space optimization, thereby improving the interpretability of the model and the efficiency of the process. When evaluating this method in a prediction-in-ungauged-basins setting with the mesoscale Hydrological Model (mHM) across 162 German basins, it showed significant improvements in runoff predictions compared to both traditional regionalization techniques and state-of-the-art regional Long Short-Term Memory (LSTM) networks. The generated transfer functions are robust, scalable, and physically interpretable, which is a substantial improvement in the field of large-scale process-based environmental modeling.
科研通智能强力驱动
Strongly Powered by AbleSci AI