Data Intelligence For Improved Water Resource Management

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.