Journal of Instrumentation Technology & Innovations Review Article
EcoSense AI: An Intelligent IoT-Based Environmental Monitoring and Forecasting System
Abstract
Environmental degradation caused by air, water, and soil pollution poses a severe global threat to human health and ecosystem stability. Existing IoT- based monitoring systems classify only current pollution levels but lack predictive capability, geospatial context, and tamper-proof data integrity. This paper presents EcoSense AI—a unified low-cost intelligent environmental monitoring system built on an ESP32 microcontroller with MQ135, DHT11, turbidity, and GPS sensors. The system integrates a Random Forest classifier for pollution-level classification, an Isolation Forest algorithm for anomaly detection, and a Long Short-Term Memory (LSTM) network for 6–24-hour AQI forecasting. A GPS module enables real-time neighbourhood-level pollution heatmapping via Leaflet.js. Bayesian drift correction compensates for sensor degradation, and an IOTA-based blockchain ledger provides tamper-evident data provenance for each reading. Experimental results demonstrate strong performance. The system achieves a classification accuracy of 93.8%, a 12-hour LSTM forecasting RMSE of 4.2 AQI units, and an anomaly detection F1-score of 91.4%. Comparative analysis confirms EcoSense AI is, to the best of our knowledge, among the few low-cost systems simultaneously providing all six capabilities: classification, forecasting, anomaly detection, geospatial heatmapping, blockchain integrity, and sensor drift correction. By integrating real-time sensing, intelligent analysis, predictive modelling, and safe data management, the suggested architecture enables ongoing environmental monitoring. While machine learning detects anomalous patterns and predicts possible pollution trends, the integrated sensing unit records environmental variables across locations. Blockchain technology increases confidence in recorded measurements, and geospatial visualisation facilitates location-specific analysis. The system is intended for scalable implementation in community-based environmental management, public health monitoring, industrial settings, educational institutions, and smart cities.
Keywords
References (13)
- Biswal SR, Choudhury TR, Panda B, Mishra S. An improved IoT based hybrid predictive load forecasting model for a greenhouse integrated with demand side management. IEEE Access. 2025 Jun 13;13:108446-65..
- Wan Z, Song Y, Cao Z. Environment dynamic monitoring and remote control of greenhouse with ESP8266 NodeMCU. In2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) 2019 Mar 15 (pp. 377-382). IEEE.
- Collado E, Calderón S, Cedeño B, De León O, Centella M, García A, Sáez Y. Open-source Internet of Things (IoT)-based air pollution monitoring system with protective case for tropical environments. HardwareX. 2024 Sep 1;19:e00560.
- Ajakwe IU, Ajakwe SO, Lee JM, Kim DS. Internet- of-Things-blockchain integration in environmental pollution monitoring data management: trends and techniques. International Journal of Environmental Science and Technology. 2025 Nov;22(15):16123- 42.
- Essamlali I, Nhaila H, El Khaili M. Advances in machine learning and IoT for water quality monitoring: A comprehensive review. Heliyon. 2024 Mar 30;10(6).
- Singh M, Ahmed S. IoT based smart water management systems: A systematic review. Mater Today Proc. 2021;46(11 Pt 11):5211-8. doi:10.1016/j.matpr.2020.08.588.
- Mitreska Jovanovska E, Batz V, Lameski P, Zdravevski E, Herzog MA, Trajkovik V. Methods for urban air pollution measurement and forecasting: challenges, opportunities, and solutions. Atmosphere. 2023;14(9):1441. doi:10.3390/atmos14091441
- Ahmed S, Pasha A, Kumer T, Akhtaruzzaman M, Hossain M. Advancements in Air Quality Monitoring Systems: A Comprehensive Review of Emerging Technologies for Enhancing Environmental Health. Indoor Air. 2026;2026(1):3080684.
- Garcia A, Saez Y, Harris I, Huang X, Collado E. Advancements in air quality monitoring: a systematic review of IoT-based air quality monitoring and AI technologies. Artificial Intelligence Review. 2025 Jun 11;58(9):275.
- Bouchriti Y, Ait Haddou M, Achbani A, Rida J, Sine H, Lkoul A, Kabbachi B. Air Quality in Morocco: What Interim Targets to adopt from the World Health Organization Air Quality Guidelines 2021? A Nationwide Analysis. InE3S Web of Conferences 2025 (Vol. 632, p. 01009). EDP Sciences.
- Sharma M, Bhattacharya A. National Air Quality Index. Control of Urban Pollution. 2014;82:16-58.
- Saxena AK, Pandey R, Singh NK. Latency analysis and reduction methods for edge computing. In2023 IEEE World Conference on Applied Intelligence and Computing (AIC) 2023 Jul 29 (pp. 480-484). IEEE.
- Saxena AK, Pandey R, Singh NK. Optimizing Edge Node Efficiency Through Data Reduction Using Dimension Reduction Techniques. In2024 IEEE 16th International Conference on Computational Intelligence and Communication Networks (CICN) 2024 Dec 22 (pp. 1237-1241). IEEE.