FarmCan: a physical, statistical, and machine learning   model to forecast crop water deficit for farms

Sadri, Sara; Famiglietti, James S.; Pan, Ming; Beck, Hylke E.; Berg, Aaron; Wood, Eric F.

doi:https://doi.org/10.5194/hess-26-5373-2022

Articles | Volume 26, issue 20

https://doi.org/10.5194/hess-26-5373-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Experiments in Hydrology and Hydraulics

https://doi.org/10.5194/hess-26-5373-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 26, issue 20

Research article

|

27 Oct 2022

Research article |

| 27 Oct 2022

FarmCan: a physical, statistical, and machine learning model to forecast crop water deficit for farms

Sara Sadri, James S. Famiglietti, Ming Pan, Hylke E. Beck, Aaron Berg, and Eric F. Wood

Data sets

MOD16A3GF MODIS/Terra Net Evapotranspiration Gap-Filled Yearly L4 Global 500 m SIN Grid V00 S. Running, Q. Mu, M. Zhao, and A. Moreno https://doi.org/10.5067/MODIS/MOD16A3GF.006

Short summary

A farm-scale hydroclimatic machine learning framework to advise farmers was developed. FarmCan uses remote sensing data and farmers' input to forecast crop water deficits. The 8 d composite variables are better than daily ones for forecasting water deficit. Evapotranspiration (ET) and potential ET are more effective than soil moisture at predicting crop water deficit. FarmCan uses a crop-specific schedule to use surface or root zone soil moisture.