HDLEP model estimates field evapotranspiration and primary gross domestic product

Entitled “Hybrid deep learning model with water-carbon coupling constraints for simultaneous estimation of field evapotranspiration and gross primary production” for possible publication in Water Resources Research.

Data:

The Eddy covariance observational flux,  meteorological, soil and crop data of the sunflower and maize field. The first study site, Site 1, is situated in the sunflower field at the Heji station (40°43′ N, 107°16′ E, 1,038 m), covering the experimental period from 2019 to 2022. The second study site, Site 2, is situated in the maize field at the Fenzidi station (41°09′ N, 107°39′ E 1,032 m), covering the experimental period from 2017 to 2020. For each site, we collected the following variables at half-hourly temporal resolution. 

Code:

All the codes were executed in Python. The provided mixed deep learning model code can be run on Jupyter Notebook.