Researchers Earn Grant to Digitize Massive Encyclopedia of Invertebrates

University of Kansas researchers have been awarded a $1.5 million grant from the National Science Foundation to develop a searchable online database and library that links the 50-plus volumes of the "Treatise on Invertebrate Paleontology," an important resource on climate change, evolution and other biodiversity research. "Treatise" classifies all known extinct and living invertebrates (creatures without backbones), which make up 95 percent of the animal species. Finding new ways to electronically extract, analyze and store this authoritative compilation will lead to greater understanding of mass extinctions, evolutionary recoveries and current environmental threats. An interdisciplinary team of researchers from KU’s Department of Electrical Engineering and Computer Science and Paleontological Institute will create the Invertebrate Paleontology Knowledgebase to transform data management. "IPKbase will help researchers more easily connect the dots," said Xue-wen Chen, associate professor of electrical engineering and computer science and principal investigator of IPKbase. "The amount of information is overwhelming, and we are developing tools to help them mine data. By developing a fast and flexible online information repository, we will enable greater access to critical information." KU researchers will develop a three-step process for IPKbase to handle the highly complex and immense "Treatise" data. Computational tools will extract and integrate images, text and numerical data. For example, image-based searches would allow paleontologists to compare photographs of a newly discovered fossil with known images. New data analysis, modeling and visualization techniques will discover patterns and provide meaningful interpretation. Finally, IPKbase would index information for easy retrieval and sharing. James Miller, associate professor of EECS, and Luke Han, Bo Luo and Brian Potetz, all assistant professors of EECS, will be co-investigators on the project. Paul Selden, the Gulf-Hedberg Distinguished Professor of Invertebrate Paleontology, director of KU’s Paleontological Institute and editor of the "Treatise on Invertebrate Paleontology," will be a co-investigator as well. They will conduct the research at KU’s Information and Telecommunication Technology Center. "After half a century of scholars compiling and benefitting from this important repository of knowledge, today’s researchers will have greater access to its knowledge through its digital presence and the incredible data mining techniques which our computer scientist colleagues are developing," Selden said. "This project will allow students of paleontology, young and old, and researchers in related industries, move forward on a variety of problems of concern to mankind."