AIoT-Driven Pest Monitoring Approach for Real-Time Tuta absoluta Detection in a Controlled Greenhouse Environment

South American tomato leaf miner Tuta absoluta (Meyrick) (Lepidoptera: Gelechiidae) is responsible for significant biological invasions of tomato crops, perturbing global food production. To develop smart pest monitoring systems to control T. absoluta populations in tomato crops in greenhouse settings, this study highlights the use of AI-based pest detection and population prediction models to detect pest instances and forecast populations in advance. A real-time image dataset was collected in greenhouse conditions to train various object detection models such as YOLOv10, YOLOv11, and YOLOv26 for the early detection of T. absoluta. A dataset of 317 trap images was deployed to evaluate the detection capabilities of pest detection models. The YOLOv26s model outperformed its counterpart approaches in terms of pest detection accuracy by delivering 92.4% (mAP50), and YOLOv26n delivered an inference speed of 0.064 s on test data. For early prediction of the male moth population, abiotic parameter data were collected through IoT sensors alongside pest biological data to generate early forecasts. Feature engineering and feature selection approaches were used for data preparation to model male moth population dynamics. Machine learning approaches and a hybrid linear-tree stacking framework were implemented to model pest dynamics in relation to different meteorological parameters. The hybrid stacking model resulted in an NRMSE value of 0.31 when predicting the one-week-ahead population of male T. absoluta.