Data Intelligence For Improved Water Resource Management
Abstract
Technological enhancements have decreased the cost of data collection, increased our
ability to share data, and expanded our insights concluded from data. These modern
abilities, commonly described as big data, are rapidly affecting decision making methodologies
across the world. With the increased amount of data present in the 21st century,
we are not limited by quantity of information, but rather by our ability to deduce
sensible intelligence from the massive amounts and different types of information
present. To harness the power of data we must first understand what data we have,
how we collect it, and how we can standardize and integrate it. Then we can apply
analytical tools to transform the data to information, to knowledge and, finally,
to informed decision making.
This research project is an investigation into how the water sector is actively working
to integrate big data capabilities into managerial processes in the United States.
The content of this report is two-fold. First, the current state of water resources
data technologies, trends, initiatives, and opportunities are analyzed and recommendations
for advancement are provided. Second, the development of a proof of concept water
data application is presented to demonstrate how the water sector can use data to
improve managerial decision making.
Water resource management has historically been a data-driven discipline with consistent
measurements of water quantity and quality, as those measurements are of concern for
environmental and anthropogenic needs. However, mainly due to funding constraints,
the water sector has been slow compared to other industries to adopt big data capabilities.
Today, water managers’ eagerness to adjust systematics is made apparent through their
development of initiatives and products to harness the value of big data to improve
resource management. The primary example of this is the Open Water Data Initiative,
a top-down collaborative approach to create an “open water web” by transforming data
management from a one-to-one producer-to-user scheme to a many-to-many scheme. Throughout
federal agencies, this initiative is spreading best management practices, including
web service machine-to-machine communication and standardized schemas such as Water
ML 2.0. In both the private and public sector, products have been developed to serve
the data needs of a growing water market.
The availability of water data is inherently connected to regulations that determine
who collects data, how data is collected, and where data is housed. The Safe Drinking
Water Act and the Clean Water Act are the two primary laws that determine the water
quality data landscape of the nation. The stipulations of these acts present an opportunity
to aggregate publically available water quality data, and use it to gain a higher
resolution focus of the state of water quality in the nation.
Identification and segmentation of the various opportunities presented by big data
enables more effective implementation of the practices. My research presents a series
of recommendations to address these opportunities. Firstly, user needs should be
better defined so projects can be designed to fulfill specific goals and have a higher
probability of producing a sizable impact. To further harness the possibilities presented
by big data, all available data should be aggregated. Sensor technology, citizen
science data, and automated metering infrastructures are three examples of recently
developed data types that could be used to increase the amount of water quality data
available. Standardized schemas should be used to enable integrations of available
data sources. Finally, analytical tools should be employed to use the available information
and translate it into actionable intelligence in decision making processes.
As a model for how available, yet fragmented, data may be organized, aggregated, analyzed,
and visualized to add value to a specific purpose, the Water Quality Risk Assessment
Tool was developed and is presented in the report. The tool was built for the Duke
Nicholas Institute of Environmental Policy Solutions. It is a proof of concept map-based
web application that summarizes where, when, and to what extent water quality is out
of compliance or trending out of compliance for investors and credit rating agencies.
In its current form, the tool uses dissolved oxygen, pH, temperature, turbidity, and
specific conductance data from the Water Quality Portal and presents a summary dashboard
for the state of Colorado. This tool is designed to be used as a stepping stone for
an institution to scale the project to a larger service area with measureable value
for its users. It is accessible at https://mark-ziman.shinyapps.io/WQRAT_MZ/.
The contents of this report assess the strengths, weaknesses, and opportunities for
big data capabilities to improve water resource management. This comprehensive review
provides fundamental insights for water managers and water investors to understand
the water data framework and capitalize on the modern opportunities for advancement
presented by big data.
Type
Master's projectPermalink
https://hdl.handle.net/10161/11926Citation
Ziman, Mark (2016). Data Intelligence For Improved Water Resource Management. Master's project, Duke University. Retrieved from https://hdl.handle.net/10161/11926.Collections
More Info
Show full item record
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Rights for Collection: Nicholas School of the Environment
Works are deposited here by their authors, and represent their research and opinions, not that of Duke University. Some materials and descriptions may include offensive content. More info