Designing a Data Schema for AI-Driven Greenhouse and Vertical Farming LED Solutions

Designing a comprehensive data schema and framework for AI-driven LED lighting optimization in greenhouses and vertical farming, with the goal of standardizing agronomic, operational, and environmental inputs into an AI-ready structure. This framework will enable accurate simulations of energy use, crop growth, yield performance, and ROI outcomes, creating a foundation for grower-friendly decision-making tools. By mapping input variables to measurable outputs, the project will guide growers in selecting the most effective lighting solutions that balance productivity, sustainability, and cost-efficiency across diverse controlled-environment agriculture settings.

Data Framework for LED Optimization in Greenhouses and Vertical Farming

Lumesmart Inc. seeks to enhance its LED lighting solutions by leveraging AI to simulate performance across diverse greenhouse and vertical farming environments. The goal of this project is to design a comprehensive data collection and analysis framework that will serve as the foundational training input for an AI tool. This AI tool will be capable of simulating how different LED lighting solutions perform under various agronomic and operational conditions, ultimately generating ROI-focused recommendations for growers. Students will be tasked with identifying key data points necessary for accurate and actionable AI simulations. These data points may include environmental factors, crop types, growth stages, and energy consumption metrics. By applying classroom knowledge in data analysis and AI, students will contribute to creating a robust framework that supports Lumesmart Inc.'s mission to optimize LED lighting solutions for sustainable agriculture. Key Responsibilities Identify and document key data inputs (e.g., crop type, growth stage, planting density, fixture height, light spectrum, electricity rates). Recommend additional agronomic and environmental variables to improve AI-driven simulations. Develop a grower-facing input form to standardize data collection. Propose a mapping framework linking each input to outputs (fixture selection, energy use, yield, ROI). Design a reporting structure for how results can be automated into grower-friendly ROI reports once AI is integrated.

Designing a Data Schema for AI-Driven Greenhouse and Vertical Farming LED Solutions

The project will produce a structured AI-ready data schema with defined variables, a standardized data collection form for growers, and a mapping framework that links inputs to LED performance metrics. Students will also deliver a comprehensive final report outlining methodology, recommendations, and practical next steps for integrating AI-driven simulations that connect lighting strategies to crop yield, energy efficiency, and ROI in greenhouses and vertical farming. 

AI-Powered Lighting Advisor for Greenhouses and Vertical Farming

About the Project: LumeSmart Inc. is a woman-owned Canadian cleantech company founded in 2013. We specialize in LED lighting solutions for agricultural, commercial, and residential use. Our goal is to support sustainable local food production by helping growers — from greenhouses to vertical farms — access the right lighting systems for their crops. This project invites students to build a basic AI-powered tool that simulates how a grower might input simple information (e.g., crop type, square footage, growing environment), and receive a lighting recommendation output based on internal data we provide. This prototype will support LumeSmart’s sales and consulting process and will help us better engage customers interested in sustainable farming. Confidential Use Statement: This tool is intended for internal business use only at LumeSmart. It will be used to support customer recommendations, and the information it provides will be free only to clients who purchase our LED products . Students will work under a non-disclosure agreement (NDA) to protect proprietary data, and will be encouraged to focus on the technical logic and tool-building , not on business operations or product decisions. Objectives (Refocused and Clear): Build a prototype system or chatbot that accepts grower inputs (e.g., crop type, growing method, area size). Map these inputs to a structured logic or database (provided by LumeSmart) to generate simple lighting suggestions. Output results such as: “Recommended: LumeSmart X100, Qty: 12, Spectrum: Full Red/Blue” in a basic web form or chatbot. Ensure the tool structure can be scaled in the future with more crops or product types.