Evaluation of pedotransfer functions to estimate some of soil hydraulic characteristics in North Africa: A case study from Morocco

Soil hydraulic properties are an important factor to optimize and adapt water management for a given crop. Pedotransfer functions (PTFs) present solution predict soil variables such as properties, using fundamental properties. In this research, we compared two sources of information: iSDAsoil data field data, in four regions Morocco. We then used evaluate published developed new PTFs information estimate gravimetric moisture content at saturation ( w 0 ), capacity 330 ) permanent wilting point 15000 ). A total 331 samples were collected from regions: Doukkala, Gharb-Loukous, Moulouya Tadla. The was divided into calibration validation datasets. For development different PTFs, simple linear regression, multiple regression tree, Cubist algorithm, random forest approaches. by Dijkerman (Geoderma, 1988, 42, 29–49) presented the best performance, showing lower RMSE, Bias MAE other PTFs. Using develop models based on clay, silt organic matter input showed performance after (R 2 0.590, 0.785, 0.786 , respectively). Regarding techniques machine learning, with algorithms 0.930, 0.955, 0.954 represent low cost easy technique improve efficiency farmers.