EvapoDeep: A Dual Deep Learning Framework Utilizing GNSS Data for Evapotranspiration Modeling and Predictive Analysis
Modeling and predicting reference Evapotranspiration (ET<sub>0</sub>) is crucial for effective water resource management and the protection of natural ecosystems. While the Penman–Monteith (PM) equation is widely recognized for its high accuracy in estimating ET<sub>0<...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11072228/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Modeling and predicting reference Evapotranspiration (ET<sub>0</sub>) is crucial for effective water resource management and the protection of natural ecosystems. While the Penman–Monteith (PM) equation is widely recognized for its high accuracy in estimating ET<sub>0</sub>, it requires extensive meteorological data, which is often unavailable at many synoptic stations. In contrast, the Thornthwaite (TH) model is simpler and more widely used but suffers from limited accuracy. Previous studies have demonstrated that calibrating the TH model with additional variables can improve its accuracy; however, these efforts have been largely preliminary. This study addresses the accuracy gap by developing EvapoDeep, an advanced model for ET<sub>0</sub> modeling and prediction that leverages deep learning techniques. Initially, the difference in ET<sub>0</sub> (DET<sub>0</sub>) between the TH and PM models is calculated. This DET<sub>0</sub> is then modeled using an advanced Convolutional Neural Network-based deep learning method. The modeling component of EvapoDeep uses Global Navigation Satellite Systems (GNSS)-based Precipitable Water Vapor data from California, utilizing one year of GNSS measurements. In the final phase, the prediction component of EvapoDeep employs the generated ET<sub>0</sub> time series to predict ET<sub>0</sub> for the subsequent day using Long Short-Term Memory (LSTM) networks, demonstrating the model’s ability to handle temporal dependencies through its LSTM component. The EvapoDeep model significantly improved accuracy, achieving a root mean square error (RMSE) of 0.32 mm, compared to the TH model’s RMSE of 1.09 mm, representing a 70% improvement. In addition, the next-day ET<sub>0</sub> predictions yielded an RMSE of 0.29 mm, underscoring their high predictive performance. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |