Cover: Demographic and Geographic Characteristics of Green Stormwater Infrastructure Investments in Five U.S. Cities

Demographic and Geographic Characteristics of Green Stormwater Infrastructure Investments in Five U.S. Cities

A Machine Learning–Based Analysis

Published Dec 4, 2023

by Michelle E. Miro, Susan A. Resetar, Kelly Hyde, Joshua Steier, Michael T. Wilson, Zara Fatima Abdurahaman, Vanessa Wolf

Download eBook for Free

FormatFile SizeNotes
PDF file 0.9 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.

Research Questions

  1. Which demographic and land-use characteristics are the most-strongly associated with green stormwater infrastructure investments across a set of five case study U.S. cities?
  2. How can machine learning be used to better understand and support green stormwater infrastructure?

Green stormwater infrastructure has been increasingly used across the United States over the past few decades. In some locations, cities have invested heavily in this type of infrastructure to reduce urban flooding and manage water quality. Green stormwater infrastructure also offers a variety of co-benefits to the surrounding community compared with traditional gray infrastructure. These co-benefits include reduced urban heat island effect, improved water quality, and enhanced aesthetics. This report presents the results of an exploratory machine learning–based analysis of green stormwater infrastructure asset data across five cities in the United States. Within each city, authors evaluated the location of installed green stormwater infrastructure based on the demographic and land use characteristics of the surrounding area. The goal of this analysis was to understand the local context surrounding green stormwater infrastructure investments. This evaluation can help cities understand the current potential for co-benefits of these investments and how future planning could enhance the co-benefits of green stormwater infrastructure.

Key Findings

  • Although no cities examined were consistently and deliberately planning based on a co-benefits framework, areas that were more strongly associated with green stormwater infrastructure had higher percentages of Hispanic or Latino residents, lower percentages of White residents, and higher percentages of residents who self-reported coronary health challenges.
  • City stormwater planning has predominately been consent decree–driven and publicly funded with a focus on reducing stormwater volumes. It is now, however, shifting toward an effort that is driven by compliance with municipal codes and that includes more private citizens. Ensuring these more-distributed approaches carefully consider co-benefits can enhance the impact of stormwater management moving forward.
  • Evaluating multiple machine learning approaches was advantageous in producing a better fit model for a given application and enhancing analytical flexibility. Modelers should also take care to understand the limitations, resolution, and relationships in their data and start simply before adding analytical complexity.
  • There is a growing appetite for advanced analytics in municipal planning, but machine learning analysts must have expertise in the meaning and application of the datasets they work with, must be able to logically explain the results of their analyses, and should follow best practices for communicating about artificial intelligence (of which machine learning is a subset) to ensure the utility of the analysis and tools they produce.

Research conducted by

Funding for this research was provided by gifts from RAND supporters and income from operations and conducted in the Community Health and Environmental Policy Program within RAND Social and Economic Well-Being.

This report is part of the RAND research report series. RAND reports present research findings and objective analysis that address the challenges facing the public and private sectors. All RAND reports undergo rigorous peer review to ensure high standards for research quality and objectivity.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.