Copyright © 2026 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{205416,
        author = {Mohammed Fahaduddin and Sabhah Fatima and Danish Quadri and Ishrat Tamreen and Mohammed Abdul},
        title = {AI-Driven Multimodal Fusion Sensor for Real-Time In-Situ Detection of Microplastics in Soil},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {6738-6746},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205416},
        abstract = {Microplastic contamination in agricultural soil has emerged as a significant environmental challenge affecting soil health, crop productivity, and ecosystem sustainability. Conventional detection techniques such as Fourier Transform Infrared Spectroscopy (FTIR) and Raman spectroscopy are laboratory-intensive, expensive, and unsuitable for real-time field deployment. This study proposes an AI-driven multimodal fusion sensing framework for real-time in-situ detection of microplastics in soil. The proposed system integrates optical reflectance sensing, electrical conductivity and impedance sensing, dielectric moisture sensing, and environmental sensing within a unified sensor probe architecture. Multi-source sensor data are processed through preprocessing, feature extraction, normalization, and AI-based fusion models including Random Forest, XGBoost, and neural network ensembles. An optional drone-assisted mapping layer enables large-scale contamination visualization using RGB and multispectral imaging. A synthetic dataset consisting of 900 samples was used to evaluate the proposed framework. Experimental analysis demonstrated high prediction accuracy for contamination classification and concentration estimation. The proposed system provides a low-cost, scalable, and field-deployable alternative to laboratory spectroscopy approaches for environmental monitoring and precision agriculture applications.},
        keywords = {Microplastics, Sensor Fusion, Soil Monitoring, Machine Learning, Multimodal Sensing, Precision Agriculture, Environmental Sensing.},
        month = {June},
        }