Sponsor:
National Science Foundation, award number CCF-1029166Project Team Members:
Northwestern University
- Alok Choudhary
- Wei-keng Liao
- Ankit Agrawal
- William Hendrix
- Zhengzhang Chen
- Mostofa Patwary
- Prabhat Kumar
North Carolina A&T State University
North Carolina State University
University of Minnesota
Understanding Climate Change: A Data Driven Approach
Introduction
Data-driven approaches that have been highly successful in other scientific disciplines hold significant potential for application in environmental sciences. This Expeditions project aims to address key challenges in the science of climate change by developing methods that leverage the abundance of climate and ecological data available from satellite and ground-based sensors, the observational record for atmospheric, oceanic, and terrestrial processes, and physics-based climate model simulations. To realize this ambitious goal, novel methodologies appropriate to climate change science are being developed. These innovative approaches will help provide new understanding of the complex nature of the Earth system and the mechanisms contributing to the adverse consequences of climate change, such as increased frequency and intensity of hurricanes, precipitation regime shifts, and the propensity for extreme weather events that result in environmental and socioeconomic disasters. Methodologies developed as part of this project will be used to advance scientific knowledge, to gain actionable insights, and to inform policymakers.
The education and mentoring opportunities from this Expeditions project go significantly above and
beyond what can be achieved with a single PI-driven or smaller-scale collaborative project.
The goals are as follows:
- Train students and postdoctoral researchers in the fields of data mining, climate data procurement and analysis, pattern recognition, image processing, and the design and implementation of algorithms including the use of distributed platforms.
- Create educational initiatives to engage students (including women and those from underrepresented minorities) to create interest and awareness of the work in this area. The Expeditions team is collaborating with the Interdisciplinary Scientific Environmental Technology (ISET) program, whose objective is to provide opportunities for underrepresented students to study climate or environmental sciences and the related technologies.
- Design and develop techniques for identifying the structure of climatological data on a decadal scale.
- Design and develop methodologies for Accurate Forecasting of Adverse Spatio-Temporal Events.
- Design and develop a set of data analysis kernels as part of an effort to provide a library of high performance implementations of standard data mining kernels.
- Present the developed techniques, methodologies and data analysis kernels in the form of technical papers or at related technical conferences.
Publications
- Zhengzhang Chen, Yusheng Xie, Yu Cheng, Kunpeng Zhang, Ankit Agrawal, Wei-keng Liao, Nagiza Samatova, Alok Choudhary, Forecast Oriented Classification of Spatio-Temporal Extreme Events, to appear in the proceedings of the 23rd International Joint Conference on Artificial Intelligence to be held in Beijing, China, on August 3-9, 2013.
- Zhengzhang Chen, John Jenkins, Jinfeng Rao, Alok Choudhary, Fredrick Semazzi, Anatoli V. Melechko, Vipin Kumar, Nagiza F. Samatova, Automatic Detection and Correction of Multi-class Classification Errors Using System Whole-part Relationships, to appear in the proceedings of the 13th SIAM International Conference on Data Mining (SDM 2013), Austin, Texas, USA, May 2-4, 2013.
- Zhengzhang Chen, William Hendrix, Hang Guan, Issac K. Tetteh, Alok Choudhary, Fredrick Semazzi, Nagiza F. Samatova, Discovery of extreme events-related communities in contrasting groups of physical system networks, Data Mining and Knowledge Discovery, September 2012.
- Zhengzhang Chen, Huseyin Sencan, William Hendrix, Tatdow Pansombut, Frederick Semazzi, Alok Choudhary, Vipin Kumar, Anatoli Melechko, Nagiza F. Samatova, Classification of Emerging Extreme Event Tracks in Multi-Variate Spatio-Temporal Physical Systems Using Dynamic Network Structures: Application to Hurricane Track Prediction, In the Proceedings of Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011), pages 1478–1484, Barcelona, Spain, July, 2011.
Datasets
- Data for Spatio-Temporal Extreme Events Prediction Tasks - Version 1.0
External Links
- Collaborative Climate Change work at University of Minnesota.