AI Based Radiation Emission Risk, Environmental Impact, and Mitigation Planning System

Radiation estimation plays an important role in understanding radiation levels and supporting effective environmental monitoring and risk assessment. This project presents a Radiation Estimation System using Machine Learning and the Internet of Things (IoT), integrating Random Forest Regression with real-time sensor data collection and web-based monitoring. An ESP32 microcontroller collects environmental parameters and transmits the readings to the ThingSpeak cloud platform. A machine learning model processes relevant environmental parameters to estimate radiation levels, while a Flask-based web application provides prediction results, historical records, and visual analysis. SQLite is used to store predictio n history for further reference. By combining environmental data collection, machine learning-based estimation, and accessible web monitoring, the proposed system aims to support radiation assessment, environmental safety, and informed decision-making. The project contributes to Sustainable Development Goal 3 (SDG 3): Good Health and Well-being, by promoting data-driven radiation monitoring and supporting awareness of potential radiation risks to human health and the environment.