Skip to main content

Master of Environmental Data Science
(2022)

Renewable Energy Siting Predictors Observed from National Data for Wind and Solar (RESPOND Wind and Solar)

Wind turbines in a field

Group Members: Paloma Cartwright, Joseph (Joe) DeCesaro, Daniel Kerstan, Desik Somasundaram

Faculty Advisors: Ranjit Deshmukh

Client: UCSB Environmental Science Department

Description

The deployment of renewable energy in a timely fashion to mitigate climate change is one of the greatest challenges facing the world today. There‚Äôs significant pressure for aggressive renewable energy development; however, without understanding the relationships between renewable energy development and local or regional siting criteria, clean energy policies could result in unintended consequences or end up being less effective. 

There is currently a considerable knowledge gap on the topic of renewable energy siting predictors and potential explanatory variables. The objective of this analysis is to identify the historic drivers of wind and solar power plant siting. Variables that will be evaluated include: environmental sensitivity, land leasing or acquisition value, distance to the nearest road, slope, population density, socioeconomic indicators like median household income, distance to the nearest substations or transmission line, capacity factor, natural hazard risks, and renewable energy targets. 

Machine learning approaches will be used to generate a predictive model for future siting. The goal is to help policymakers and other stakeholders better understand the drivers of renewable energy siting and leverage the results in future planning studies to spur rapid renewable energy development in a more equitable, sustainable, and deliberate manner.
 

Client contact: Grace Wu, Environmental Science 

arrow up icon