SolarFlux AI Optimize Solar Potential with Machine Learning

Overview

This project, SolarFlux AI, was developed to make solar energy adoption easier, providing accurate and simple predictions of daily solar energy output for any city that provides weather data. The purpose of the experiment was to test whether an artificial intelligence model could reliably predict solar flux (Global Horizontal Irradiance GHI) and help users estimate how many solar panels they need based on their energy usage. The hypothesis was that a machine learning model, specifically K-Nearest Neighbors (KNN), could accurately forecast solar energy output using historical weather and solar data, and that this information could be used to support better solar planning decisions. To test this, several regression models were evaluated, including KNN, Random Forest, and Multi-Layer Perceptron. KNN was selected because it provided strong accuracy while remaining simple and computationally efficient. The model was trained and tested using solar and environmental data, and its performance was measured using RMSE and R² values. The final model was deployed in a web application that predicts GHI and estimates the number of solar panels needed based on user input SolarFlux AI Web App https://solarfluxai.streamlit.app/#enter-features There were no physical safety risks because the project was entirely computer-based. All work was conducted using publicly available datasets and online tools, making the experiment safe and ethical. Web App: https://solarfluxai.streamlit.app/#enter-features Blog:https://soham-gupta.webflow.io/blog/solarflux-ai-research-project Video: https://www.youtube.com/watch?v=rz7zgf7N1Eo Deck:https://docs.google.com/presentation/d/1VjFbKSFCZnwUSp1gvh9FrmILvjCB6rPVxghekbEM_9E/edit?usp=sharing

Competition history

• CSEF 2026 Environmental Engineering (Track 2) (Senior Division) · Entry S-12-15

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Environmental Engineering projects
• CSEF Environmental Engineering projects
• Every CSEF 2026 project