Applications of Gaussian process regression for predicting blue water footprint: Case study in Ad Daqahliyah, Egypt

Timely and reliable water footprint prediction is imperative and prerequisite to mitigate climate risk and ensure water and food security and enhance the water-use efficiency. This study aims to model the Water Footprint (WF) by using the four kernels of Gaussian processes models (Polynomial, Normalized Poly, Radial Basis Function RBF, and Pearson Universal Function PUK) and select the best kernel with best climate scenario. This study investigates the predicting WF of maize based on meteorological variables including maximum temperature (Tmax), minimum temperature (Tmin), mean temperature (Tmean), solar radiation (SR), wind speed (WS), and vapor pressure deficit (VPD), Extraterrestrial radiation (Ra) relative humidity (RH) and crop coefficient (Kc) by applying ten scenarios of climate variables in the Egyptian Nile Delta, Ad Daqahliyah Governorate for predicting blue WF of maize during 2000-2019. The main findings are following as, firstly; based on developing four kernels, the performance of the PUK kernel in predicting blue WF is far better than the other three kernels followed by the Poly kernel. Secondly; for PUK kernel, model 7 (Tmax, Tmin, Tmean, WS, Sunshine Hours (SH), VPD and SR) has good performance which is close to models 8 (model 7 + Ra), model 9 (model 7 + Ra and RH) and model 10 (all inputs). Thirdly; in all four kernels, the error rate in small blue WF values is higher than the other values, moreover, the error value decreases at the medium blue WF values, while, it increases again at large WF values. Therefore, the developed models in this study can help and promote the decision makers to manage and secure the water resources management under the extreme climate events.

Automated summary

This study aims to model the Water Footprint (WF) using Gaussian processes models and select the best kernel with best climate scenario for predicting blue WF of maize in the Egyptian Nile Delta. The results show that the PUK kernel performs better than the other three kernels, with model 7 being the most accurate for predicting blue WF values. The error rate is higher in small WF values and increases again at large WF values for all four kernels.