A Rule-Based Transparent Machine Learning Approach for Precision Crop Protection: Modeling Orchard Microclimatic Orientations and Cherry Fruit Fly Pupal Habitats.

Although traditional machine learning models demonstrate high accuracy in agricultural prediction scenarios, their "black box" nature prevents them from transparently presenting decision-making mechanisms and limits their reliability in integrated pest management (IPM) processes. In this study, the Cherry Fruit Fly (Rhagoletis cerasi) was investigated. A rule-based, explainable artificial intelligence (XAI) framework is proposed for characterizing bio-edaphic profiles associated with observed Cherry Fruit Fly Pupal Count (CfPC) density levels and classifying microclimatic aspects (Aspects) using measurable edaphic and biological parameters. The developed hierarchical rule inference engine parses the decision trees of the LightGBM classifier, which achieved the highest performance when benchmarked against 10 baseline machine learning algorithms (11 models in total), and extracts human-interpretable results that can be directly interpreted by experts. In Experiment 1, the analysis characterized the combinations of observed CfPC and edaphic conditions associated with Low, Medium, and High pupal-density profiles, whereas Experiment 2 evaluated the classification of canopy aspect from the measured bio-edaphic variables. According to the derived rules, continuous biological counts (CfPC) serve as the primary biological reference, while edaphic parameters such as soil temperature, pH, lime content, and water saturation percentage characterize additional soil conditions associated with the observed pupal-density profiles. These synthesized rules provide an interpretable representation of the bio-edaphic patterns observed within the studied orchards and may support the development of future precision crop-protection strategies following independent validation.