FEW: A Workshop to Identify Interdisciplinary Data Science Approaches and Challenges to Enhance Understanding of Interactions of Food Systems and Water Systems

University Of Minnesota-Twin Cities, Minneapolis MN

Investigators

Abstract

In coming decades, the world population is projected to grow significantly increasing the demand for food, water, energy, and other resources. Furthermore, these resource challenges may be amplified due to climate change, urbanization, and the interdependent and interconnected nature of food, energy, and other resources. Furthermore, these resource challenges may be amplified due to environmental changes, urbanization, and the interdependent and interconnected nature of food, energy and water (FEW) systems, which were traditionally analyzed and planned independently. Such piece-meal approaches (e.g., bio-fuels) to solving problems in one system (e.g., energy) have led to unanticipated problems (e.g., increase in food prices) in other systems. The goal of the nexus FEW security approach is to reduce such surprises by understanding, appreciating and visualizing the interconnections and interdependencies in the FEW system of systems at local, regional and global levels. However, the nexus approach for sustainable management of global resources faces significant challenges due to differences in data collection protocols, data representation standards, access to complete data and data analysis tools. In addition, the FEW system of systems provides major challenges and opportunities for novel data science research. Although data science analysis methods extensively applied to large and complicated systems, such as social networks, data science efforts in complex physical systems (e.g., system of FEW systems) have been far more meager. Given FEW systems' rich data-driven history, there is a tremendous opportunity to systematically integrate novel large-scale data analysis methods with the physical, experiential, process oriented, and even conceptual knowledge that the broad climate, water, and energy research communities have developed. In addition, data science methods need to account for dependence between models, variables, locations and seasons (of food, energy and water systems) to reduce the risk of yielding misleading results. There is a tremendous need to significantly advance data science and realize the promise of the nexus approach to meet societal challenges in the face of population growth, urbanization and climate change. The proposed workshop will gather thought leaders from both data science and the relevant areas of system of food, water, and energy systems. This workshop will use both FEW nexus pull and data science technology push discussions to identify data science challenges in understanding, appreciating and visualizing the FEW systems. The first two successive sessions will explore these opposing directions. The second day will identify FEW inspired data science grand challenges in a synthesis session. Specifically, the goal of this workshop will be to create a vision of how data driven methods could make a significant contribution to understanding interactions between FEW systems and what research is needed to realize that vision. This proposal provides a detailed schedule of milestone and tasks including this team's resume for leading visioning workshops. The proposed workshop will facilitate and enable interdisciplinary partnerships between data scientists and FEW nexus researchers from academia, industry and federal agencies to develop innovative, interdisciplinary research approaches enhancing the understanding, appreciation, and visualization of the interactions between FEW systems. It has potential to formulate next generation data science research agenda towards better understanding, appreciation and visualization of the interactions and interdependencies among FEW systems. Workshop report will be included in reading lists of graduate courses on data science in Ph.D. to integrate the results in education. The report will also be used in professional graduate data science degrees for workforce training. A key goal will be to diversify participation across career stages, under-represented groups, geographies, and disciplines (e.g., machine learning, data mining, geo-spatial analytics, and nexus of food, water and energy systems).