Development and Validation of Innovative Machine Learning Models for Predicting Date Palm Mite Infestation on Fruits

The date palm mite (DPM), Oligonychus afrasiaticus (McGregor), is a key pest of unripe fruits. detection this depends largely on the visual observations webs it produces green One most important problems DPM control lack an accurate decision-making approach for monitoring and predicting infestation Therefore, study aimed to develop, evaluate, validate prediction models fruits based meteorological variables (temperature, relative humidity, wind speed, solar radiation) physicochemical properties (weight, firmness, moisture content, total soluble solids, sugar, tannin content) using two machine learning (ML) algorithms, i.e., linear regression (LR) decision forest (DFR). data in area were acquired IoT-based weather station. popular cultivars, Khalas Barhee, analyzed at different fruit development stages. performance LR DFR implemented Microsoft Azure ML. evaluation developed indicated that was more than model input variables, (R2 = 0.842), 0.895), combination both 0.921). Accordingly, deployed as fully functional web service into cloud platform Excel add-ins. validation showed able predict count 0.918). by Ml studio enhanced fast easy-to-use approach. These findings demonstrated Studio integrated can be powerful tool management.