A Data Science Approach to Understanding Residential Water Contamination in Flint

Chojnacki, Alex; Dai, Chengyu; Farahi, Arya; Shi, Guo Hai; Webb, Jared; Zhang, Daniel T.; Abernethy, Jacob; Schwartz, Eric M.

doi:10.1145/3097983.3098078

Cited by 16 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) In municipal services, predictive analytics tools have been used to direct resources for maintenance, repair, or inspection by prioritizing or bipartite ranking by risk of failure or contamination [11,37]. Proposals to use new data sources such as 311 data, which incur the self-selection bias of citizen complaints, may introduce inequities in resource allocation [29].…”

Section: Introductionmentioning

confidence: 99%

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric

Kallus¹,

Zhou²

2019

Preprint

View full text Add to dashboard Cite

Where machine-learned predictive risk scores inform high-stakes decisions, such as bail and sentencing in criminal justice, fairness has been a serious concern. Recent work has characterized the disparate impact that such risk scores can have when used for a binary classification task. This may not account, however, for the more diverse downstream uses of risk scores and their non-binary nature. To better account for this, in this paper, we investigate the fairness of predictive risk scores from the point of view of a bipartite ranking task, where one seeks to rank positive examples higher than negative ones. We introduce the xAUC disparity as a metric to assess the disparate impact of risk scores and define it as the difference in the probabilities of ranking a random positive example from one protected group above a negative one from another group and vice versa. We provide a decomposition of bipartite ranking loss into components that involve the discrepancy and components that involve pure predictive ability within each group. We use xAUC analysis to audit predictive risk scores for recidivism prediction, income prediction, and cardiac arrest prediction, where it describes disparities that are not evident from simply comparing within-group predictive performance.

show abstract

Section: Introductionmentioning

confidence: 99%

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric

Kallus¹,

Zhou²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The environment information such as building conditions can be used to evaluate fire risk in urban areas [105], [97], [94]. Also, in the case of water system monitoring, the test results of water samples are used [101], [95], [107]. On the other hand, the happenings of other kinds of anomalous events are sometimes affected by environmental factors as well.…”

Section: Environment Datamentioning

confidence: 99%

Urban Anomaly Analytics: Description, Detection, and Prediction

Zhang

et al. 2022

IEEE Trans. Big Data

View full text Add to dashboard Cite

Urban anomalies may result in loss of life or property if not handled properly. Automatically alerting anomalies in their early stage or even predicting anomalies before happening are of great value for populations. Recently, data-driven urban anomaly analysis frameworks have been forming, which utilize urban big data and machine learning algorithms to detect and predict urban anomalies automatically. In this survey, we make a comprehensive review of the state-of-the-art research on urban anomaly analytics. We first give an overview of four main types of urban anomalies, traffic anomaly, unexpected crowds, environment anomaly, and individual anomaly. Next, we summarize various types of urban datasets obtained from diverse devices, i.e., trajectory, trip records, CDRs, urban sensors, event records, environment data, social media and surveillance cameras. Subsequently, a comprehensive survey of issues on detecting and predicting techniques for urban anomalies is presented. Finally, research challenges and open problems as discussed.

show abstract

“…A large portion of this money went toward replacing the city's lead and galvanized steel service lines, a process begun in early 2016 and nearly complete at the end of 2019. Although this pace has put Flint in a position to eliminate its lead‐based infrastructure faster than any other American city in history, the process has not been without delays and controversy, particularly over the use of a computer algorithm to predict the locations of lead service lines (Abernethy, Chojacki, Farahi, Schwartz, & Webb, ; Chojnacki et al, ). Other funds have been directed to nutritional programs aimed at mitigating the effects of lead on the body, as well as a variety of health care, educational, and social services (Ruckart et al, ).…”

Section: Response To the Flint Water Crisismentioning

confidence: 99%

The Flint water crisis

Pauli

2020

WIREs Water

View full text Add to dashboard Cite

The Flint water crisis is one of the most significant environmental contamination events in recent American history. In April 2014, the city of Flint, Michigan, while under the control of an emergency manager appointed by the governor, switched its drinking water supply from Lake Huron water treated and distributed by the Detroit Water and Sewerage Department to the Flint River. Failure to treat the water properly at the Flint Water Treatment Plant led to a variety of problems with water quality and public health. Low chlorine in parts of the water system fostered bacterial growth and contributed to an historic outbreak of Legionnaires' disease in 2014-2015. High levels of trihalomethanes brought the city into violation of the Safe Drinking Water Act in late 2014. Finally, systemic lead contamination-revealed through a collaborative sampling effort by local activists and engineers in the summer of 2015resulted from corrosive water eating into lead pipes and other lead-bearing components of Flint's water infrastructure. In October 2015, after considerable public pressure, the city switched back to Lake Huron water. Efforts by federal, state, and local officials to respond to the crisis have focused on restoring water quality, repairing and replacing dangerous and damaged pipes, and addressing public health needs. At the popular level, residents and activists have continued to fight for accountability, reparations, and restoration. A variety of causal explanations for the crisis have been put forward, some focusing on water treatment, regulation, and infrastructure, others on the political context created by state takeover of the city, and others on historical factors like structural racism, deindustrialization, and depopulation.

show abstract

A Data Science Approach to Understanding Residential Water Contamination in Flint

Cited by 16 publications

References 9 publications

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric

Urban Anomaly Analytics: Description, Detection, and Prediction

The Flint water crisis

Contact Info

Product

Resources

About