General Lab Information

Line Pouchard

Res Staff 5 Computational, C3D, Computational Science Initiative

Line Pouchard

Brookhaven National Laboratory

Computational Science Initiative
Bldg. 725, Room 2-120
P.O. Box 5000
Upton, NY 11973-5000

(631) 344-4626
pouchard@bnl.gov

Preferred Gender Pronouns (PGPs): she

Dr. Line Pouchard is a Staff Scientist who has led multiple inter-disciplinary teams to create new approaches for data management, curation, and discovery for over 20 years.  Her current research focuses on provenance in workflows at scale, computational reproducibility, and enabling explainable and interpretable AI, applied to domains of interest to the DOE, including Extreme Scale Computing and Scientific User Facilities.    She previously held research positions at Purdue University, Oak Ridge National Laboratory, and a Joint Appointment at the University of Tennessee, Knoxville.

Expertise | Research | Education | Appointments | Publications


Expertise

  • Reproducibility for computational and data-intensive science
  • Research Data Management for HPC and AI/ML driven discovery
  • Provenance and FAIR principles for HPC and ML

Research Activities

  • Provenance for performance analysis and workflow execution at extreme scales
  • Data curation and discovery, including at DOE Scientific User Facilities
  • Computational reproducibility
  • Text mining from the scientific literature
  • Explainable and interpretable AI

Education

  • M.S., Information Science, University of Tennessee, Knoxville
  • Ph.D., Comparative Literature, The Graduate Center, City University of New York

Professional Appointments

  • 2023-present, Research Staff 5, Computational Science, C3D
  • 2022-2023, Chair, Diversity, Equity & Inclusion Council, Computational Science Initiative,  BNL
  • 2017-2022, Senior Researcher, Center for Data-Driven Discovery, Computational Science Initiative, Brookhaven National Laboratory
  • 2014-2016, Assistant Professor and Computational Science Information Specialist, Research Data Group, Purdue University Libraries
  • 2013-2014, Joint Faculty Appointment, School of Information Sciences, University of Tennessee, Knoxville
  • 2001-2014, Staff Scientist/Research Associate, Computer Science and Mathematics Division, Oak Ridge National Laboratory
  • 1999-2001, Post-doctoral Appointment, Oak Ridge Associated Universities

Selected Publications

  • Pouchard L, Islam T, Nicolae B (2022) Challenges for Implementing FAIR Digital Objects with High Performance Workflows. Research Ideas and Outcomes 8:. https://doi.org/10.3897/rio.8.e94835
  • Hickmon N, Varadharajan C, Hoffman F, et al (2022) Artificial Intelligence for Earth System Predictability (AI4ESP) Workshop Report. https://doi.org/10.2172/1888810. Chapter on Explainability.
  • Park G, Rayz J, Pouchard L (2022) Figure Descriptive Text Extraction using Ontological Representation
  • Plale BA, Malik T, Pouchard LC (2021) Reproducibility Practice in High-Performance Computing: Community Survey Results. Computing in Science & Engineering 23:55–60. https://doi.org/10.1109/mcse.2021.3096678
  • Park G, Pouchard L (2021) Advances in scientific literature mining for interpreting materials characterization. Machine Learning: Science and Technology 2:045007. doi: 10.1088/2632-2153/abf751
  • Pouchard L, Soto C, Branstetter M, Prakash G (2021) FAIR data infrastructure and tools for AI-assisted streamflow prediction. https://doi.org/10.2172/1769710
  • Foster I, Ainsworth M, Bessac J, et al (2021) Online data analysis and reduction: An important Co-design motif for extreme-scale computers. The International Journal of High Performance Computing Applications 35:617–635. https://doi.org/10.1177/10943420211023549
  • Serbin S, Giangrande S, Kuang C, et al (2021) AI to Automate ModEx for Optimal Predictive Improvement and Scientific Discovery. https://doi.org/10.2172/1769662
  • Pouchard L, Y Lin, and H Van Dam (2020). Replicating Machine Learning Experiments in Materials Sciences. In: Advances in Parallel Computing, Parallel Computing: Technology Trends, vol. 36., eds. I Foster, GR Joubert, L Kucera, WE Nagel, and F Peters, pp. 743-755.
  • Acharya A, Agarwal R, Baker MB, et al (2020) Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19. Journal of Chemical Information and Modeling 60:5832–5852. https://doi.org/10.1021/acs.jcim.0c01010
  • Kelly C, Ha S, Huck K, Van Dam H, Pouchard L, Matyasfalvi G, Tang L, D'Imperio N, Xu W, Yoo S, Van Dam KK (2020) Chimbuko: A Workflow-Level Scalable Performance Trace Analysis Tool. ISAV'20 In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization. doi: 10.1145/3426462.3426465
  • Pouchard L, Juhas P, Park G, Van Dam H, Campbell SI, Stavitski E, Billinge S, Wright CJ (2020) Provenance Infrastructure for Multi-modal X-ray Experiments and Reproducible Analysis. Handbook on Big Data and Machine Learning in the Physical Sciences 307–331. doi: 10.1142/9789811204579_0015
  • Peterka T, Bard D, Bennett JC, Bethel EW, Oldfield RA, Pouchard L, Sweeney C, Wolf M (2020) Priority research directions for in situ data management: Enabling scientific discovery from diverse data sources. The International Journal of High Performance Computing Applications 34:409–427. doi: 10.1177/1094342020913628
  • Pouchard L, Kleese van Dam K, Campbell SI (2019) Experimental Data Curation at Large Instrument Facilities with Open Source Software. International Journal of Digital Curation 14:114–125. doi: 10.2218/ijdc.v14i1.637
  • Pouchard L, Baldwin S, Elsethagen T, Jha S, Raju B, Stephan E, Tang L, Van Dam KK (2019) Computational reproducibility of scientific workflows at extreme scales. The International Journal of High Performance Computing Applications 33:763–776. doi: 10.1177/1094342019839124
  • Park G, Pouchard L (2019) Scientific Literature Mining for Experiment Information in Materials Design. 2019 New York Scientific Data Summit (NYSDS). https://doi.org/10.1109/nysds.2019.8909726
  • Pouchard L, Huck K, Matyasfalvi G, et al (2018) Prescriptive provenance for streaming analysis of workflows at scale. 2018 New York Scientific Data Summit (NYSDS). https://doi.org/10.1109/nysds.2018.8538951
  • Foster I, Ainsworth M, Allen B, Bessac J, Cappello F, Choi JY, Constantinescu E, Davis PE, Di S, Di W, Guo H, Klasky S, Van Dam KK, Kurc T, Liu Q, Malik A, Mehta K, Mueller K, Munson T, Ostouchov G, Parashar M, Peterka T, Pouchard L, Tao D, Tugluk O, Wild S, Wolf M, Wozniak JM, Xu W, Yoo S (2017) Computing Just What You Need: Online Data Analysis and Reduction at Extreme Scales. Euro-Par 2017: Parallel Processing 3–19. doi: 10.1007/978-3-319-64203-1_1
  • Zhang B, Pouchard LC, Smith PM, Gasc A, Pijanowski BC (2016) Data storage and sharing for the long tail of science. 2016 New York Scientific Data Summit (NYSDS). doi: 10.1109/nysds.2016.7747811
  • Gopavarapu P, Pouchard LC, Pujol S (2016) Increasing Datasets Discoverability in an Engineering Data Platform using Keyword Extraction. Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries. doi: 10.1145/2910896.2925443
  • Pouchard L (2016) Revisiting the Data Lifecycle with Big Data Curation. International Journal of Digital Curation 10:176–192. doi: 10.2218/ijdc.v10i2.342
  • Tuarob S, Pouchard LC, Mitra P, Giles CL (2015) A generalized topic modeling approach for automatic document annotation. International Journal on Digital Libraries 16:111–128. doi: 10.1007/s00799-015-0146-2
  • Hernández JM, Pouchard L, McDonald J, Prowell S (2013) Developing a power measurement framework for cyber defense. Proceedings of the Eighth Annual Cyber Security and Information Intelligence Research Workshop on - CSIIRW '13. doi: 10.1145/2459976.2460008
Line Pouchard

Brookhaven National Laboratory

Computational Science Initiative
Bldg. 725, Room 2-120
P.O. Box 5000
Upton, NY 11973-5000

(631) 344-4626
pouchard@bnl.gov

Line's Links