Submitted by Christy Getz on
Indoor cannabis cultivation consumes significant amounts of electricity for lighting, climate control, and dehumidification. Estimating total energy usage dedicated to both licensed and unlicensed indoor cultivation cultivation and its associated emissions will be a great step for improvements within the industry. This project seeks to understand and quantify the energy use associated with indoor cannabis production across California, with a focus on identifying trends in unlicensed cultivation. By examining energy consumption patterns of commercial indoor cannabis cultivators, we aim to estimate the scope of unlicensed indoor cannabis production and its impact on the state’s energy resources. The project will leverage data from utilities using the CPUC Energy Data Request Program allowing us to analyze energy usage patterns of indoor cannabis cultivation facilities.
A machine learning model will be trained on the energy signature of cultivation facilities to support the estimation of the energy consumption across california. The findings will inform California policymakers on the overall energy usage of indoor cannabis cultivation and then effective energy management strategies for the cannabis industry, contributing to a broader understanding of sustainable energy practices.
This role involves gathering data on energy patterns linked to indoor cannabis cultivation, and supporting the development of a machine-learning model to estimate indoor cultivation in California. Students will primarily focus on preprocessing data from utility companies, creating relevant features such as time-based variables and helping to implement and train various machine learning algorithms. Additionally, the student could also participate in model evaluation, creating visualizations to represent the findings, and conducting literature reviews.
The ideal candidate for the project will be a student interested in the energy, machine learning, geospatial modeling, and environmental management. Necessary skills include attention to detail, strong communication and documentation skills. Familiarity with programmingin Python or R is a plus. However, this project welcomes undergraduates with little or no experience in these fields, offering them the chance to develop their skills as research scientists, and serve as an integral part of a research team.