Smarter Planet solutions increasingly need to bring together multiple models from a broad range of areas to guide investment, planning, and policy decisions around highly complex issues such as population health, public safety, and disaster preparedness. These include simulation models developed both inside and outside of IBM.
The Splash project provides a prototype platform for combining existing heterogeneous simulation models and datasets to create composite simulation models of complex systems, thereby facilitating cross-disciplinary modeling, simulation, and optimization.
Splash loosely couples models via data exchange, exploiting and extending data-integration, workflow management, and simulation technologies. Splash enables interoperability and reuse of models and data across multiple disciplines by semi-automatically exploiting model schemas and data mappings to create new combinations of models and data. The resulting composite models can be used to conduct deep predictive analytics, enabling "what-if" analyses to assess intended and unintended consequences. This approach provides a powerful way for scientists, engineers, and decision makers to collaborate across disciplines, and to effectively and efficiently understand the tradeoffs inherent in complex problems and their proposed solutions.
More precisely, Splash is a platform that facilitates systematic and reliable creation of composite models from simpler component models. The main idea is that multiple component model and data sources can be linked together through directed data flow to create a coherent and useful composite model. Both data sources and models are heterogeneous and independently created, using different data formats, programming languages, operating systems, simulation paradigms, and so on, and embodying different assumptions. To make disparate models and data go together in Splash, all models and data are described with metadata using Splash Actor Description Language (SADL). SADL descriptions of models and data are fundamental to the interoperability of models and data, just as schemas are fundamental to the interoperability of data, and enables model and data discovery, semi-automatic generation of data transformations between models, orchestration of a simulation run, and the design and execution of simulation experiments. Splash can exploit technologies such as Hadoop to achieve scalability in its data transformations, and the experiment-management component allows systematic and efficient exploration of the behavior of composite models, as well as sensitivity analysis and stochastic optimization.
Contact: Paul Maglio
Peter J. Haas, Yannis Sismanis: On aligning massive time-series data in Splash. In BigData 2012.
Peter J. Haas, Nicole C. Barberis, Piyaphol Phoungphol, Ignacio G. Terrizzano, Wang-Chiew Tan, Patricia G. Selinger, Paul P. Maglio: Splash: Simulation optimization in complex systems of systems. In Proceedings of 50th Annual Allerton Conference. on Communication, Control and Computing, 2012.
Cheryl A. Kieliszewski, Paul P. Maglio, Melissa Cefkin: On modeling value constellations to understand complex service system interactions. In European Management Journal, Special Issue.
Wang-Chiew Tan, Peter J. Haas, Ronald L. Mak, Cheryl A. Kieliszewski, Patricia G. Selinger, Paul P. Maglio, Susanne Glissman, Melissa Cefkin, Yinan Li: Splash: A Platform for Analysis and Simulation of Health. In Proceedings of ACM International Health Informatics Symposium (IHI), 2012.
Paul P. Maglio: Modeling complex service systems. In Service Science, 3(4), pp. i-ii, 2011.
Joseph P. Bigus, Murray Campbell, Boaz Carmeli, Melissa Cefkin, Henry Chang, Ching-Hua Chen-Ritzo, William F. Cody, Shahram Ebadollahi, Alexandre V. Evfimievski, Ariel Farkash, Susanne Glissmann, David Gotz, Tyrone Grandison, Daniel Gruhl, Peter J. Haas, Mark J. H. Hsiao, Pei-Yun Sabrina Hsueh, Jianying Hu, Joseph M. Jasinski, James H. Kaufman, Cheryl A. Kieliszewski, Martin S. Kohn, Sarah E. Knoop, Paul P. Maglio, Ronald L. Mak, Haim Nelken, Chalapathy Neti, Hani Neuvirth, Yue Pan, Yardena Peres, Sreeram Ramakrishnan, Michal Rosen-Zvi, Sondra R. Renly, Pat Selinger, Amnon Shabo, Robert Sorrentino, Jimeng Sun, Tanveer Fathima Syeda-Mahmood, Wang Chiew Tan, Ying Y. Y. Tao, Reza Yaesoubi, Xinxin Zhu: Information technology for healthcare transformation. In IBM Journal of Research and Development, 55(5), pp. 6, 2011,
Peter J. Haas, Paul P. Maglio, Patricia G. Selinger, Wang-Chiew Tan: Data is Dead... without What-If Models. In Proceedings of Very Large Data Bases Endowment, PVLDB 2011.
Melissa Cefkin, Susanne M. Glissman, Peter J. Haas, Paul P. Maglio, Patricia Selinger, Wang-Chiew Tan: SPLASH: A Progress Report on Combining Simulations for Better Health Policy. INFORMS Healthcare 2011.
Melissa Cefkin, Cheryl A. Kieliszewski, Paul P. Maglio: When are calories like furniture? Modeling service systems to improve health. Service Research and Innovation Institute Global Conference (SRII), 2011.
Paul P. Maglio, Patty L. Mabry: Agent-Based Models and Systems Science Approaches to Public Health. American Journal of Preventive Medicine, 40(3), pp. 392-394.
Melissa Cefkin, Susanne M. Glissman, Peter J. Haas, Leila Jalali, Paul P. Maglio, Patricia Selinger, Wang-Chiew Tan: "SPLASH: A Progress Report on Building a Platform for a 360 Degree View of Health". Proceedings of the 5th INFORMS Workshop on Data Mining and Health Informatics, DM-HI 2010.
Paul P. Maglio, Melissa Cefkin, Peter J. Haas, Patricia Selinger: "Social Factors in Creating an Integrated Capability for Health System Modeling and Simulation". Advances in Social Computing: Third International Conference on Conference on Social Computing, Behavioral Modeling, and Prediction, SBP10, 2010.