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{180259,
        author = {Dr. Somu. K and Ananthi.M and Riventh.R and Sabapathi.P and Surya.A and Thangabalu.G},
        title = {Gps-Based Environmental Monitoring Using Cnn-Lstm},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {1038-1044},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180259},
        abstract = {Environmental monitoring plays a critical role in the preservation of ecological balance and public health. Combining GPS technology with Wireless Sensor Networks (WSNs) has significantly promoted real-time tracking of the environment and data collection from various geographical locations. However, managing such complex data streams requires advanced computational techniques to ensure accuracy and efficiency. This paper introduced a hybrid Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) model enables an intelligent environmental monitoring system to classify environments by analyzing spatial correlations, resulting in robust and interpretable predictions. While, Z-score normalization ensures that all normalized sensor data—regardless of unit or scale—is brought to a uniform range. Then, focused on Support Vector Regression (SVR) method identifies the most influential features (e.g., pollutant concentration over temperature), improving computational efficiency. Finally, the CNN-LSTM method ensures the environmental monitoring system is accurate, real-time, and GPS-aware, ready to deploy on mobile platforms or embedded IoT nodes. The system also includes data visualization modules, allowing for easy representation of real-time and forecasted environmental metrics on geographic maps. Through delivering accurate location-based environmental knowledge, the system enables real-time decision support in disaster management, pollution mitigation, and city planning. The output of simulation is evidence that proposed system enhances predictive accuracy for the forecast of environmental conditions and provides effective area-wise monitoring. Embedding GPS with predictive analytics brings an impressive resolution to proactive, intelligent, and responsive environmental administration.},
        keywords = {Environmental Monitoring, GPS Technology, WSN, Predictive Modelling, CNN, SVR, LSTM.},
        month = {June},
        }