Urban water systems are not self-contained units, economically or ecologically. They rely on larger biophysical supports from natural capital. The behavior of such systems as a whole and the interactions between subcomponents can be observed. The optimization at system level to achieve overall system efficiency will not only avoid burden shifting and inform more efficient subsystem design, but also provide sustainability and resiliency for the systems. Complex, dynamic human-environment coupled water systems require a paradigm shift from the traditional "siloed" (drinking water, wastewater, stormwater etc.) management approach and a move towards more holistic approaches to address the multiple issues facing municipal water systems. The concepts of fit-for-purpose, resource recovery and decentralization to maximize resource use (energy, nutrients, materials, and water) have been considered to provide more sustainable solutions to satisfy various water services. Here we present a design of an urban water system for cities of the future to emphasize how different water system services can be organized in an organic entirety, and how such paradigm shift designs are substantially more efficient than existing centralized water systems. A unique thermodynamically-based accounting tool and life cycle assessment are used to showcase the quantification of the energy distribution of the systems, and the associated environmental impacts and cost. It provides in-depth analyses of the economic trade-offs, environmental impacts and system performances. The detailed holistic evaluation helps decision-makers design more robust, effective and sustainable urban water systems.
Bio: Dr. Ma is from US EPA Office of Research and Development. Her primary research efforts focus on applying new sustainability metrics to environmental management for sustainability. Currently, she is involved in developing system-based tools to holistically assess water systems and help transform our water systems towards a more sustainable future. Dr. Ma is one of U.S. EPA's leading experts on water infrastructure carbon footprint, greenhouse gas emission reduction, infrastructure resilience, water-energy-nutrient nexus, water reuse, resource recovery, life cycle thinking, climate change adaptation and mitigation, integrated assessment metrics and system solutions. Dr. Ma served as a part of the US Government expert review panel for Working Group II of the Intergovernmental Panel on Climate Change (IPCC)'s recent Sixth Assessment Report. She was also a part of the US delegation to the IPCC P-55 session, supporting the Department of State in negotiation with other nations' delegates in the approval of the IPCC Summaries for Policymakers (SPM).
Disclaimer: This abstract is distributed solely for the purpose of pre-dissemination peer review under applicable information quality guidelines. It has not been formally disseminated by the U.S. Environmental Protection Agency. It does not represent and should not be construed to represent any agency determination or policy.
Predictive modeling with class-imbalanced data has proven to be a challenging task. This problem is well studied, but the era of big data is producing extreme levels of imbalance that are increasingly difficult to model. In addition to the modeling challenges that are associated with these highly imbalanced data sets, we have found that performance evaluation also requires careful considerations. In this talk, we demonstrate how the popular area under the receiver operating characteristic curve can provide misleading results and recommend that any evaluation of imbalanced big data also includes the area under the precision-recall curve.
Bio: Dr. Taghi M. Khoshgoftaar is Motorola Endowed Chair professor of the Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University and the Director of NSF Big Data Training and Research Laboratory. His research interests are in big data analytics, data mining and machine learning, health informatics and bioinformatics, social network mining, security analytics, fraud detection, and software engineering. He has published more than 850 refereed journal and conference papers in these areas. He was the conference chair of the IEEE International Conference on Machine Learning and Applications (ICMLA 2019 and ICMLA 2016). He is the Co-Editor-in Chief of the journal of Big Data. He has served on organizing and technical program committees of various international conferences, symposia, and workshops. Also, he has served as North American Editor of the Software Quality Journal and was on the editorial boards of the journals Multimedia Tools and Applications, Knowledge and Information Systems, and Empirical Software Engineering and is on the editorial boards of the journals Software Quality, Software Engineering and Knowledge Engineering, and Social Network Analysis and Mining. For the selected publications, please see Dr. Khoshgoftaar's Google Scholar link below: https://scholar.google.com/citations?user=-PgNSCAAAAAJ&hl=en