Underground drainage systems are hazardous environments where the accumulation of toxic and combustible gases such as methane, carbon monoxide, and liquefied petroleum gas (LPG) poses serious risks to human life and infrastructure. Traditional inspection methods are inefficient and unsafe. This paper proposes an AI-assisted IoT-based toxic gas prediction and water level monitoring system. The system integrates MQ2 and MQ3 gas sensors and an ultrasonic sensor with an ESP32 microcontroller for real-time data acquisition. A lightweight prediction model analyzes trends in gas concentration to provide early warnings before reaching critical thresholds. Alerts are generated via buzzer, GSM module, and GPS tracking. The proposed system improves safety, reduces response time, and supports smart city infrastructure.

The Real-Time Prediction of Toxic Gases in Underground Drainage presented in this project represents a comprehensive and reliable approach to ensuring safety in domestic and industrial environments through continuous gas monitoring and real-time alerting. Traditional gas detection methods often rely on standalone detectors or manual inspection, which may not provide timely alerts or remote notification during emergency situations. This system addresses those limitations by integrating intelligent sensing, automated decision-making, and both local and remote alert mechanisms, thereby enhancing overall safety and responsiveness. The system architecture is designed to be modular, scalable, and efficient, consisting of multiple functional blocks including gas sensing units (MQ2 and MQ3), the ESP32 microcontroller, threshold evaluation logic, alert generation modules, and optional communication and display interfaces. The gas sensors continuously monitor the surrounding air for the presence of combustible or harmful gases and convert gas concentration into electrical signals. These signals are processed by the ESP32, which compares real-time values against predefined safety thresholds to determine hazardous conditions. The use of programmable thresholds ensures flexibility and adaptability for different environments and gas sensitivity requirements.

1.Al-Ali, A. R., Zualkernan, I., & Aloul, F. (2017). A mobile GPRS-sensors array for air pollution monitoring. IEEE Sensors Journal, 10(10), 1666–1671. 2.Bhattacharya, S., Saha, S., & Mukherjee, A. (2019). Design and development of an IoT-based gas leakage detection system. International Journal of Engineering Research & Technology (IJERT), 8(6), 450–455. 3.Kumar, R., Rajasekaran, M. P., & Kumar, N. (2016). An IoT-based patient monitoring system using Raspberry Pi. International Conference on Computing Technologies and Intelligent Data Engineering (ICCTIDE), IEEE. 4.Sharma, P., Singh, A., & Kaur, M. (2018). LPG gas leakage detection and alert system using microcontroller. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 7(4), 1456– 1462. 5.Kaur, A., & Kaur, A. (2017). Gas leakage detection and control system using Arduino. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2(5), 456–460. 6.Mahalingam, A., Naayagi, R. T., & Mastorakis, N. (2012). Design and implementation of an economic gas leakage detector. Recent Researches in Applications of Electrical and Computer Engineering, 20–24. 7. Lee, I., & Lee, K. (2015). The Internet of Things (IoT): Applications, investments, and challenges for enterprises. Business Horizons, 58(4), 431– 440. 8.Banerjee, T., Roy, S., & Das, A. (2020). Smart gas leakage detection system with mobile alert using IoT. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 9(3), 2108–2112. 9.Espressif Systems. (2023). ESP32 Technical Reference Manual. Espressif Systems Co., Ltd. 10.Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers. 11.MQ-2 Gas Sensor Datasheet. (n.d.). Hanwei Electronics. Reference for LPG, propane, methane, and smoke detection characteristics. 12.MQ-3 Gas Sensor Datasheet. (n.d.). Hanwei Electronics. Reference for alcohol and volatile gas detection. 13.GSM Module SIM800 Datasheet. (n.d.). SIMCom Wireless Solutions. Reference for SMS-based alert communication. 14.GPS Module NEO-6M Datasheet. (n.d.). u-blox AG. Reference for location tracking and positioning accuracy. 15.Rafiullah, M., Khan, A., & Shah, S. A. (2021). IoT-based safety monitoring systems for smart homes. IEEE Access, 9, 145120–145134.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close