Interpretation the Influence of Hydrometeorological Variables on Soil Temperature Prediction Using the Potential of Deep Learning Model

• DOI: 10.51526/kbes.2023.4.1.55-77
• Publication Date: 2023-05-02T00:33:13Z
• Authors: Salah Elsayed; Meenu Gupta; Gopal Chaudhary; Soham Taneja; Harshit Gaur; Mohamed Gad; Mohamed Hamdy Eid; Attila Kovács; Szűcs Péter; Aissam Gaagai; Urs Schmidhalter
• Keywords: Hydrometeorology; Predictive modelling; Dew point

The importance of soil temperature (ST) quantification can contribute to diverse ecological modelling processes as well for agricultural activities. Over the literature, it was evident that supports more than 95% living habitats and food production on earth, this demand will increase 500 years’ times in expected consumption 2060. This paper aims analyses contrastive approach predict ST a certain region with help different machine learning models, including Random Forest (RF), Support Vector, Neural Network (NN), Linear Regression (LR) Long Short-Term Memory (LSTM). study utilized hourly humidity, dew point, rainfall, solar radiation, barometer readings formulation models. Various performance criteria were employed evaluate prediction skills models results depicted promising ability belong LSTM despite acceptable accuracy achieved by other outcomes revealed model attained lowest root mean square error (RMSE = 3.3255) decreased average 6% regards NN 3.4796), SVM 3.5766), RF 3.8128), improved LR 15%. is compliance latest industry standards allows low-cost experimental performances low powered edge computing devices.