New Article An innovative approach for calibrating hydrological surrogate deep learning models

Our new paper, titled “An innovative Approach for Calibrating Hydrological Surrogate Deep Learning Models" has been successfully published in the Journal of Remote Sensing -MDPI.

In this study, we introduce a novel framework designed to improve the calibration of surrogate deep learning hydrological models, tested with both soil moisture and actual evapotranspiration. By integrating multiple unsupervised models for data fusion and transformation, the proposed approach significantly enhances model accuracy, robustness, and reduces the complexity of deep learning model by enabling more efficient training.

You can access the full article here: https://www.mdpi.com/2072-4292/17/11/1916

Congratulations to our PhD student Amir Aieb