OnionAider: A Model Driven Decision Support System for Weather and Pest-Occurrence Prediction in Onion Cultivation

Abstract

The cultivation of onions is crucial for meeting global demand, as they are widely consumed and used as a seasoning in various dishes worldwide. However, the production of onions is significantly affected by climatic factors and pest infestations. To address these challenges, this study presents OnionAider, a Model Driven Decision Support System that utilizes weather and pest-occurrence prediction models for onion cultivation. The system integrates descriptive, exploratory, historical, and AGILE methodologies to develop a comprehensive mobile application. The effectiveness of OnionAider was evaluated through data retrieval, questionnaires, and interviews with farmers, experts, and relevant stakeholders. The results indicate a strong relationship between climatic data and pest infestation in onions, with temperature and humidity being the primary predictors. The developed mobile application incorporates an algorithm derived from the Proponent-Rete method and offers valuable features for onion farmers. The system complies with ISO 25010 software compliance criteria. This article discusses the methodology, results, and implications of OnionAider in enhancing onion cultivation practices.