Medium Range Daily Reference Evapotranspiration Forecasting by Using ANN and Public Weather Forecasts

Abstract

Medium range daily reference evapotranspiration (ET o ) forecasts are very helpful for farmers or irrigation system operators for improving their irrigation scheduling. We tested four artificial neural networks (ANNs) for ET o forecasting using forecasted temperatures data retrieved from public weather forecasts. Daily meteorological data were collected to train and validate the ANNs against the Penman-Monteith (PM) model. And then, the temperature forecasts for 7-day ahead were entered into the validated ANNs to produce ET o forecast outputs. The forecasting performances of models were evaluated through comparisons between the ET o forecasted by ANNs and ET o calculated by PM from the observed meteorological data. The correlation coefficients between observed and forecasted temperatures for all stations were all greater than 0.91, and the accuracy of the minimum temperature forecast (error within ± 2°C) ranged from 68.34 to 91.61 %, whereas for the maximum temperature it ranged from 51.78 to 57.44 %. The accuracy of the ET o forecast (error within ± 1.5 mm day −1 ) ranged from 75.53 to 78.14 %, the average values of the mean absolute error ranged from 0.99 to 1.09 mm day −1 , the average values of the root mean square error ranged from 0.87 to 1.36 mm day −1 , and the average values of the correlation coefficient ranged from 0.70 to 0.75. Water Resour ManageThe results suggested that ANNs can be considered as a promising ET o forecasting tool. The forecasting performance can be improved by promoting temperature forecast accuracy.

Evaluation and Bias Correction in WRF Model Forecasting of Precipitation and Potential Evapotranspiration

“…Statistical models are generally not appropriate for medium-range precipitation forecasting, considering the complex manner in which both local and synoptic-driven precipitation depend on temporal variation of many variables. In addition a main disadvantage of statistical models for weather prediction is that they cannot be implemented in locations lacking previous long-term observations to provide a reliable statistical basis (Kumar et al 2011), resulting in ET 0 predictions that are not accurate enough for precise irrigation (e.g., Luo et al 2015).…”

Estimation and Comparative Analysis of Daily Reference Evapotranspiration Based on Different Input Combinations and Different Models

“…Artificial Neural Network (ANN) has strong non-linear mapping ability and adaptive characteristics (Luo et al 2015). Back Propagation (BP) neural network is a mature and most used non-linear function approximation method, the BP neural network is the basic principle of forwarding transfer of information and error.…”

Parameterization and Application of Stanghellini Model for Estimating Greenhouse Cucumber Transpiration

“…About 40% of cucumbers grown in China are produced in greenhouses. It is necessary to provide cucumber crops with exact water requirements to improve the efficiency of irrigation water management [1,2]. Crop transpiration (T r ) plays an important role in efficient irrigation water management [3,4], and several models make it possible to predict T r [5].…”

“…Previous studies on the validation of the SM with greenhouse pepper [10], acer rubrum tree [11], and tomato [12,13] showed overestimations of the estimated values, but few studies pointed out the reasons these overestimations. The overestimations of the SM may be due to (1) parameterization difficulties of the canopy resistance (r c ) and aerodynamic resistance (r a ) in the model, or (2) that proper observation positions of the input micrometeorological data of the model are not determined due to the meteorological environment in greenhouses being heterogeneous, which is different from in open fields [14,15].…”