Coconut farming sustains livelihoods by providing food, cash, and cultural significance. This study introduces a new approach using the YOLOv8 algorithm to monitor coconut tree health, focusing on pest detection. The method utilizes YOLOv8’s ability to detect and identify infestation indicators on coconut trees using an extensive dataset. Transfer learning optimizes the model’s performance for assessing coconut tree health. Results demonstrate YOLOv8’s effectiveness in pinpointing infested coconut trees, showing promise for timely intervention in precision farming. It advances agricultural tech by enabling prompt pest responses and eco-friendly farming methods, underscoring AI’s vital role in crop management and food supply enhancement. The investigation’s findings highlight the effectiveness of YOLOv8, which outperforms traditional object recognition algorithms in terms of accuracy and speed. This validates YOLOv8 as a state-of-the-art technique for object recognition and detection in real-world scenarios.