Predictive AI Models for Early Pest Infestation Alerts Using Climate and Soil Data

Abstract

This research aims to develop predictive models that use artificial intelligence (AI) to forecast early pest infestations in agriculture by integrating climate and soil data. Pests significantly threaten global food security, causing up to 40% of crop losses annually, highlighting the need for proactive pest management strategies. The study uses a hybrid approach, combining Gradient Boosting Decision Trees (GBDT) and Long Short-Term Memory (LSTM) networks, to analyze how variables such as temperature, humidity, rainfall, soil pH, soil moisture, and nutrient levels influence pest behavior. The models were trained and tested on diverse datasets, and evaluation metrics like accuracy, precision, recall, F1-score, and ROC-AUC were used to determine their effectiveness. The Random Forest model showed the highest accuracy at 89%, making it the most reliable for early pest detection. The findings demonstrate the potential of AI in enhancing agricultural productivity by enabling early warnings, reducing pesticide use, and supporting more sustainable farming practices. This study contributes to the development of scalable, data-driven solutions that integrate environmental variables, enabling better pest management and supporting global food security efforts.