Evapotranspiration

Drone-based remote sensing offers the ability to rapidly generate ET maps within a season that can be used to make in-season decisions.

Random Forest (RF) and recurrent neural network models such as LSTM predict field-scale ET more accurately than process-based models. Vapor pressure and crop coefficients are key predictors for irrigated crops. ET forecasting for non-irrigated crop requires enhanced vegetation index. Short-term (3-day) forecasts have lower uncertainty, higher accuracy using RF.

A new framework based on a machine learning data-driven network to estimate and forecast evapotranspiration in agricultural areas was proposed.

For a wet year, pines ET is higher than potatoes. In dry years when pine ET is more moisture limited, pine evapotranspiration could be lower, according to previous studies.

An algorithm is developed that can accurately predict and forecast farm-scale regional daily out to 3 days. Daily ET forecast (3 days) model based on random forest (RF) has R2 and RMSE of 0.72 mm and 0.76mm respectively while recurrent neural network (RNN) ensemble forecast model was able to forecast 3 days ET with R2 and RMSE of 0.71 mm and 0.78 mm respectively.