Fine-Resolution Residential Smart Water Meter Data
Synthetic end-use water data. These time series data are synthetic data that reproduce observations of actual residential water end uses (as .csv files), based on the labeled end-use water data for a test home in central Illinois. The actual data were collected with 1-second temporal resolution over a 4-week study period, with representative synthetic data created from a Conditional Tabular Generative Adversarial Network (CTGAN). Three synthetic data scenarios are available: 3,800 observations of imbalanced data classes; 12,000 observations of balanced data classes; and 12,000 observations of imbalanced data classes.
Associated publication:
- Z. Heydari and A.S. Stillwell. (2024). “Comparative Analysis of Supervised Classification Algorithms for Residential Water End Uses.” Water Resources Research, 60(6), e2023WR036690.
Labeled end-use water data. These time series data are labeled, ground-truthed residential water end use data (as .csv files) for a test home in central Illinois. The original data were collected with 1-second temporal resolution and were then resampled to investigate the effects of temporal aggregation. Labeled water use data are available here.
Associated publication:
- Z. Heydari, A. Cominola, and A.S. Stillwell. (2022). “Is smart water meter temporal resolution a limiting factor to residential water end-use classification? A quantitative experimental analysis.” Environmental Research: Infrastructure and Sustainability, 2(4), 045004.
Appliance/fixture time series data. These time series data are residential appliance/fixture level water use observations (as .csv files) for a test home in central Illinois, with data collection via a smart water meter with 1-second temporal resolution. These observations formed the training data for disaggregation and classification of residential water use events. Appliance/fixture water use time series are available here.
Associated publications:
- G.M. Bethke, A.R. Cohen, and A.S. Stillwell. (2021). “Disaggregating residential sector high-resolution smart water meter data into appliance end-uses with unsupervised machine learning.” Environmental Science: Water Research & Technology. 7(3), 487-503.
- G.M. Bethke. (2020). Disaggregation and Classification of Residential Water Events from High-Resolution Smart Water Meter Data Using Unsupervised Machine Learning Methods. M.S. thesis in Civil Engineering, University of Illinois at Urbana-Champaign.
Using Socioeconomic Data to Predict Multi-Family Residential Electricity Consumption
These data are representative of multi-family residential electricity consumption in the greater Chicago area, provided as average electricity consumption in multi-family housing by month. Electricity demand profiles were compared with socioeconomic data from the U.S. Census to create a multiple linear regression model of multi-family residential electricity consumption. Data to create the regression model are available here.
Associated publications:
- J.E. Pesantez, G.E. Wackerman, and A.S. Stillwell. (2023). “Analysis of single- and multi-family residential electricity consumption in a large urban environment: Evidence from Chicago, IL.” Sustainable Cities and Society, 88(1), 104250.
- G.E. Wackerman. (2020). Using Socioeconomic Data to Predict Multi-Family Residential Electricity Consumption. Senior thesis in Electrical Engineering, University of Illinois Urbana-Champaign.
Opportunities for Non-Potable Water Reuse Based on Potential Supplies and Demands in the United States
This resource contains the organized underlying data and analysis code for assessing opportunities for non-potable water reuse in the United States. Data were collected from publicly accessible sources as noted and are organized on a HUC-12 basis to estimate areas where potential supplies of reclaimed water might meet existing non-potable demands from power generation, irrigated agriculture, and industry and manufacturing. The organized data are available to download via HydroShare.
Associated publications:
- A.G. Hastie, V.V. Otrubina, and A.S. Stillwell. (2023). “Identifying Opportunities for Nonpotable Water Reuse Based on Potential Supplies and Demands in the United States.” ACS ES&T Water.
- A.G. Hastie, V.V. Otrubina, and A.S. Stillwell. (2022). “Lack of Clarity Around Policies, Data Management, and Infrastructure May Hinder the Efficient Use of Reclaimed Water Resources in the United States.” ACS ES&T Water, 2(12), 2289-2296.
- A.G. Hastie. (2022). Opportunities for Non-Potable Water Reuse in the United States based on a Supply-Demand Assessment and Review of State Policies. M.S. thesis in Civil Engineering, University of Illinois Urbana-Champaign.
The Urban Energy-Water Nexus: Utility-Level Water Flows and Embedded Energy
This database represents the culmination of a two-year effort to obtain data from cities across the United States via open records requests in order to determine the state of the U.S. urban energy-water nexus. Data were requested at the daily or monthly scale when available for 127 cities across the United States, represented by 253 distinct water and sewer districts. Data were requested from cities larger than 100,000 people and from each state. In the case of states that did not have cities that met these criteria, the largest cities in those states were selected. The resulting database represents a drinking water service population of 81.4 million and a wastewater service population of 86.2 million people. Average daily demands for the United States were calculated to be 560 liters per capita for drinking water and 500 liters per capita of wastewater. The embedded energy within each of these resources is 340 kWh/1000 m³ and 430 kWh/1000 m³, respectively. Data download available via HydroShare.
Associated publications:
- C.M. Chini and A.S. Stillwell. (2017). “Where Are All the Data? The Case for a Comprehensive Water and Wastewater Utility Database.” Journal of Water Resources Planning and Management, 143(3), 01816005.
- C.M. Chini and A.S. Stillwell. (2018). “The State of U.S. Urban Water: Data and the Energy-Water Nexus.” Water Resources Research, 54(3), 1796-1811.