4.7 Article

A Transformer-Based Framework for Parameter Learning of a Land Surface Hydrological Process Model

期刊

REMOTE SENSING
卷 15, 期 14, 页码 -

出版社

MDPI
DOI: 10.3390/rs15143536

关键词

parameters calibration; transformer; SMAP observation; soil moisture prediction; deep learning; MODIS evapotranspiration data

向作者/读者索取更多资源

This paper proposes a hydrological parameter calibration training framework consisting of a transformer-based parameter learning model (ParaFormer) and a surrogate model based on LSTM. ParaFormer uses self-attention mechanisms to learn a global mapping from observed data to the parameters to be calibrated, capturing spatial correlations. The surrogate model takes the calibrated parameters as inputs and simulates the observable variables, overcoming the challenges of combining complex hydrological models with a deep learning platform.
The effective representation of land surface hydrological models strongly relies on spatially varying parameters that require calibration. Well-calibrated physical models can effectively propagate observed information to unobserved variables, but traditional calibration methods often result in nonunique solutions. In this paper, we propose a hydrological parameter calibration training framework consisting of a transformer-based parameter learning model (ParaFormer) and a surrogate model based on LSTM. On the one hand, ParaFormer utilizes self-attention mechanisms to learn a global mapping from observed data to the parameters to be calibrated, which captures spatial correlations. On the other hand, the surrogate model takes the calibrated parameters as inputs and simulates the observable variables, such as soil moisture, overcoming the challenges of directly combining complex hydrological models with a deep learning (DL) platform in a hybrid training scheme. Using the variable infiltration capacity model as the reference, we test the performance of ParaFormer on datasets of different resolutions. The results demonstrate that, in predicting soil moisture and transferring calibrated parameters in the task of evapotranspiration prediction, ParaFormer learns more effective and robust parameter mapping patterns compared to traditional and state-of-the-art DL-based parameter calibration methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据