Benjamin Toms

  • Program Year: 2
  • Academic Institution: Colorado State University
  • Field of Study: Atmospheric Science
  • Academic Advisor: Elizabeth Barnes
  • Practicum(s):
    Lawrence Berkeley National Laboratory (2018)
    Oak Ridge National Laboratory (2019)
  • Degree(s):
    B.S. Civil Engineering, and B.S. Meteorology, University of Oklahoma, 2016

Summary of Research

How can we accelerate scientific discovery using machine learning and artificial intelligence? Machine learning has commonly been treated as a black box, but my collaborators and I are trying to break down this stigma. I use machine learning, mostly neural networks, to learn more about how we can predict climate and weather patterns relevant to decision making.

My current research focuses on decadal predictability. Can we use information about the ocean to predict climate over the continents years to a decade in the future? It seems like we can, but we also haven't identified all of the climate regimes that are most favorable for predictability on these time scales. Machine learning can help accelerate this process by efficiently identifying such climate regimes, which enables atmospheric scientists such as myself to focus on the physical mechanisms that produce these regimes.

Publications

Toms, B. A., K. Kashinath, Prabhat, and Da Yang: Using Deep Learning for Scientific Inference from Geospatial Data. Submitted to Geophysical Research Letters

Toms, B. A., S. C. van den Heever, E. M. Riley Dellaripa, S. M. Saleeby, and E. D. Maloney: The Relationship Between the Boreal Summertime Madden-Julian Oscillation and Tropical Deep Convective Morphology. Submitted to Journal of the Atmospheric Sciences

Toms. B. A., E. A. Barnes, E. D. Maloney, and S. C. van den Heever: The Global Signature of the Madden-Julian Oscillation and its Modulation by the Quasi-Biennial Oscillation. Submitted to Journal of Geophysical Research - Atmospheres

Riley Dellaripa, E. M., E. D. Maloney, B. A. Toms, S. M. Saleeby, and S. C. van den Heever: Topographic effects on the Luzon diurnal cycle during the BSISO. Submitted to Journal of the Atmospheric Sciences

Toms, B. A., J. M. Tomaszewski, D. D. Turner, and S. E. Koch, 2017: Analysis of a lower-tropospheric gravity wave train using direct and indirect measurement systems. Mon. Wea. Rev., 145, 2791-2812, https://doi.org/10.1175/MWR-D-16-0216.1

Toms, B. A., J. B. Basara, and Y. Hong, 2017: Usage of existing meteorological data networks for parameterized road ice formation modeling. J. Appl. Meteor. Climatol., 56, 1959-1976, https://doi.org/10.1175/JAMC-D-16-0199.1

Awards

National Awards:

(2017) DOE Computational Science Graduate Fellowship
(2016) American Meteorological Society Graduate Fellowship - Lockheed Martin Sponsorship
(2015) Barry M. Goldwater Scholar
(2015) Astronaut Scholarship Foundation Scholar
(2015) American Meteorological Society Named Scholar - Orville Family Endowment
(2014) National Institute of Standards and Technology (NIST) Summer Undergraduate Fellow


University Honors:

(2017) Mark and Kandi McCasland Award for Outstanding Undergraduate Research Paper
(2016) Letzeiser Honorable Mention - OU's 13 Most Outstanding Men
(2016) Outstanding Senior in Civil Engineering - OU CEES

Presentation Awards:

(2019) Outstanding Oral Presentation; 18th Conference on Artificial Intelligence and Computational Intelligence and its Application to the Environmental Sciences
(2019) Outstanding Oral Presentation; 32nd Conference on Climate Variability and Change
(2018) Outstanding Student Presentation; 33rd Conference on Hurricanes and Tropical Meteorology
(2017) 1st Place Oral Presentation; 33rd Conference on Environmental Information Processing Technologies
(2016) Outstanding Poster Presentation Honorable Mention; 3rd Conference on Atmospheric Biogeosciences
(2015) Best Student Presentation Award; 2015 AMS Meeting: 10th Symposium on Societal Applications
(2014) Best Undergraduate Oral Presentation; NWA 39th Annual Meeting