Purdue Institute for Physical Artificial Intelligence

Workshop on Establishing Purdue's 1st Biodiversity Database

Amid global biodiversity loss and the artificial intelligence (AI) revolution, there is an unprecedented demand for FAIR biodiversity data from artificial intelligence and all other research communities. Purdue has many biodiversity datasets – some of which are the world’s largest or the most unique – but little has been done to catalog these resources and make them available to Purdue research communities and beyond.

To address this, we are going to host a 4-hour workshop (both in-person and online), with the following preliminary agenda:

  • Session A (2 hours): A presentation (10-15 min each) by individuals/groups on their biodiversity data capacity and/or needs;
  • Session B (2 hours): A group discussion on how we can integrate existing data from various sources into a coherent biodiversity/herbaria database. How this database will be used, maintained, and updated with FAIR access.

We welcome all researchers (faculty and staff) to join this workshop (lunch provided), who have digitized flora and fauna records, including (but not limited to): plant survey, forest inventory, herbaria records, plant images, vertebrate and invertebrate records, bioacoustics data, microbial records, as well as associated habitat conditions such as bioclimatic and soil information.

Participants of this workshop will receive the following benefits:

  1. To help define the features of Purdue’s 1st biodiversity database to make it accessible and usable by more people;
  2. To be an accelerator for all upcoming AI developments and biodiversity conservation applications;
  3. To receive acknowledgments of your intellectual property, and to promote your IPs in international applications;
  4. To be a coauthor for a data descriptor paper invited by Scientific Data (Springer Nature, IF 11.2), and all future research publications in which your data will be used.

To help us better accommodate your schedule and other needs, please answer the following brief survey questions. Your answers will remain confidential and will be purged after the workshop. 

Coordinators: Jingjing Liang (College of Agriculture), Ximena Bernal (College of Science), Edward Delp (College of Engineering), Ningning Nicole Kong (Libraries and School of Information Studies), Xiaohui Carol Song (Rosen Center for Advanced Computing)

Panelists: Stephen L Cameron, Daniel Park, Bryan Pijanowski, Rabern Simmons, Aaron D. Smith, Christopher Charles Wirth

Co-hosts: Purdue Institute for a Sustainable Future (ISF), Purdue Institute for Physical AI (IPAI)