GDD Workshop 2018

August 20-21

Room 313, Pyle Center, UW-Madison, Madison, WI USA


GeoDeepDive brings over 7M scholarly publications and computing capacity within reach. This free workshop focuses on integrating publications into academic and industry discovery steps and workflows. Workshop supported by NSF C4P.


Anyone interested in learning about or applying algorithmic approaches to knowledge and data discovery and aggregation from published documents. Whether a student, librarian, domain scientist, technologist or industry consultant, all are welcome regardless of field or technical skill level.


Monday, August 20th

Time Event Presenter Description
9:00-9:30 Welcome / Breakfast Shanan Peters & Miron Livny Logistics and motivation for the workshop
9:30-10:45Participant talks I Ron Stewart (UW-Madison), Kinderminer
Joanna Walsh (British Geol.Survey), Place-name extraction
Samuel Hansen (ACMEScience), math topic modeling
10:45-11:00coffee break
11:00-12:15Participant talks II David Von Bargen (MinDat), rock & mineral entity recognition
Simon Goring (UW-Madison), Data Repository workflows
Brandon Serna (USGS), Knowledge Extraction Algorithms
12:15-1:15 lunch
1:15-2:00Participant talks III Julia Wilcots (MIT), DB augmentation
Bjørn Kopperud (Oslo), bio KBC
2:00-2:15 coffee break
2:15-4:00GDD project development and current status Miron Livny (WID, CompSci), Center for High Throughput Computing
Aimee Glassel (Libraries), licensing publisher content
Ian Ross (CompSci), document acquisition/processing pipeline
John Czaplewski (Geosci), vocabularly labeling and API
Shanan Peters (Geosci), next steps
4:00-? Hands-on and idea development activities Small groups Tackling/framing problems of interest to participants, with data and code or ideas and paper

Tuesday, August 21st

Time Event Leader Description
9:00-9:30 Welcome / Coffee Shanan Peters Finishing up GDD infrastructure and current capability
9:30-12:00 Participant Talks IV
GDD future steps
John Czaplewski (UW-Madison), tables & figures
Drew Muscente (Harvard), paleo data mining
Simon Goring, geodiveR demo
Leah Morgan, Geochron activity
Donato Giovannelli, physiology of prokaryotes
Mathew Clapham, trace fossil location/extraction
12:00-1:00 Lunch on your own Enjoy food carts and local establishments
1:00-? Hands-on and idea development activities Small groups Tackling problems of interest to participants, with data and code or ideas and paper

Participant List

Noah Anderson
Kristin Bergmann (MIT)
Marjorie Cantine (MIT)
Grace Chen (UW-Madison)
Matthew Clapham (UC Santa Cruz)
Cameron Cook (UW-Madison)
Mark Craven (UW-Madison)
Carol Doyle (Northwestern)
Karen Dunn (UW-Madison)
Marie Dvorzak (UW-Madison)
Allison Enright
Donato Giovannelli (NRC Italy)
Simon Goring (UW-Madison)
Samuel Hansen (UW-Madison)
Mary Hitchcock (UW-Madison)
KT Horning (UW-Madison)
Florence Hsia (UW-Madison)
Fang Huang (RPI)
Erika Ito (U Mass)
C. Brenhin Keller (UC Berkeley)
Sid Kiblawi (UW-Madison)
Lee Konrad (UW-Madison)
Bjørn Tore Kopperud (Uni. Oslo)
Benjamin Kumpf (U. Victoria)
Weijia Li (UW-Madison)
Scott Lidgard (Field Museum)
Chao Liu (Carnegie)
Akshay Mehra (Princeton)
Clare Michaud (UW-Madison)
Leah Morgan (U.S. Geol. Survey)
Shaunna Morrison (Carnegie)
Ashley Murphy (Rutgers)
Drew Muscente (Harvard)
Thomas Ngo (UW-Madison)
Feifei Pan (RPI)
Daven Quinn (UW-Madison)
Robin Rider (UW-Madison)
Allen Schaen (UW-Madison)
Brandon Serna (U.S. Geol. Survey)
Brad Singer (UW-Madison)
Gretchen Stahlman (Univ. of Arizona)
Becky Standard (UW-Madison)
Ron Stewart (UW-Madison)
David Von Bargen (
Jo Walsh (British Geological Survey)
Jack Williams (UW-Madison)
Shiyan Wei (UW-Madison)
Tao Wen (Penn State)
Julia Wilcots (MIT)
Andrew Zaffos (Univ. of Arizona)

GeoDeepDive Team @UW-Madison

Shanan Peters (Geoscience)
Miron Livny (Computer Sciences, WID)
Aimee Glassel (Libraries)
Ian Ross (Computer Sciences)
John Czaplewski (Geoscience)

Overaching workshop goals:

Additional workshop information

UW-Madison and the GDD team are committed to providing a safe, productive, and welcoming environment. All formal participants, observers and any others in attendance are expected to treat all other participants as well as staff and other community members with respect and consideration. We value a diversity of views, opinions, and backgrounds and expect that communication will involve constructive critiquing of ideas rather than individuals. UW-Madison and units on campus have many statements on expected conduct that pertain to this workshop. Of particular relevance to this meeting is the UW-Libraries code of conduct, which we expect all participants to follow.


If you have questions, or if you would like to volunteer a presentation, please email Shanan Peters @ peters --at- geology -dot-- wisc --dot-- edu


Funding provided by the Cyber for Paleo (C4P) NSF EarthCube research coordination network (NSF 1340301). GeoDeepDive project supported by NSF ICER 1343760.