Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187278,
        author = {Priyanka Pramod Mahalle and Jayshree Nilesh Balinge and Juhi Kisan Chavan},
        title = {Hybrid Deep Learning Framework for Integrated Crop Yield Prediction and Multi-Stage Pest Detection Using Adaptive IoT Sensor Networks in Precision Agriculture},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5546-5551},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187278},
        abstract = {This paper presents a novel Adaptive Ensemble Neural Network (AENN) that integrates Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and attention mechanisms for simultaneous crop yield prediction and pest detection in precision agriculture. Unlike existing approaches that address these challenges separately, our framework processes multimodal data from IoT sensors including soil monitors, weather stations, and visual systems. Field validation across 150 hectares over two agricultural seasons demonstrated 97.8% accuracy in crop yield prediction (R²=0.967) and 96.4% precision in pest detection across four major crops. The system achieved 31% yield improvement, 23% pesticide reduction, and 51% increase in net profit compared to conventional farming methods. The proposed adaptive sampling strategy reduced data transmission by 45% while maintaining prediction accuracy.},
        keywords = {Precision agriculture, Internet of Things, deep learning, crop yield prediction, pest detection, sensor networks, attention mechanisms},
        month = {November},
        }