Media

Wildfires and Prescribed Burns

KCRA 3 Sacramento: "Cal Fire, researchers see the proven benefits of controlled burning"

Prescribed Burns as a Tool to Mitigate Future Wildfire Smoke Exposure

Press: Press Release, Harvard Gazette, KCRA Sacramento, CBS Newspath, Missoulian

Compressed Sensing for Atmospheric Monitoring

ACCESS XVII Talk

Machine Learning for Atmospheric Chemistry Modeling

NASA GISS Seminar Series

Press: Editor’s Highlight from JAMES

Selected Conference Presentations

2023

12. M. Kelp, C. A. Keller, K. Wargan, B.M. Karpowicz, and D. J. Jacob. Tropospheric ozone dataassimilation in the NASA GEOS Composition Forecast Modeling System GEOS-CF v2.0 including direct assimilation of thermal infra-red radiances. AMS Annual Meeting, Denver, CO, January 12, 2023 (Talk slides)

2022

11. M. Kelp, T. Liu, and L.J. Mickley. Sensitivity of population-weighted smoke exposure towildfires in the western United States: implications for prescribed burning at the state level and in rural environmental justice communities. AGU Fall Meeting, Chicago, IL, December 14, 2022 (Talk slides)

10. M. Kelp, T. C. Fargiano, S. Lin, T. Liu, J. N. Kutz, and L.J. Mickley. Data-driven placement of PM2.5 air quality sensors in the United States: an approach to target urban environmental injustice. AGU Fall Meeting, Chicago, IL, December 12, 2022 (Talk slides)

9. M. Kelp, D.J. Jacob, and H. Lin. An Online-Learned Neural Network Chemical Solver for Stable and Long-Term Global Simulations of Atmospheric Chemistry in S2S Applications. AMS Annual Meeting, January 26, 2022 (Talk slides)

2021

8. M. Kelp, D.J. Jacob, and H. Lin. A recursive neural network chemical solver for fast long-term global simulations of atmospheric composition. AMS Annual Meeting, Virtual, January 13, 2021 (Talk slides)

2020

7. M. Kelp, J. N. Kutz, J.D. Marshall, and C. Tessum. Toward stable, general machine-learned models of the atmospheric chemical system. AGU Virtual Fall Meeting, December 7, 2020 (Talk)

6. M. Kelp and D.J. Jacob. A recursive neural network chemical solver for fast long-term global simulations of atmospheric composition. Atmospheric Chemical Mechanisms Conference, Virtual, November 18, 2020 (Lightning Talk)

2019

5. M. Kelp, J. N. Kutz, J.D. Marshall, and C. Tessum. Deep Learning Emulation and Compression of an Atmospheric Chemical System using a Chained Training Regime. AGU Fall Meeting, San Francisco, CA, December 13, 2019 (Poster)

2018

4. M. Kelp, C.W. Tessum, and J.D. Marshall. Orders-of-Magnitude Speedup in Atmospheric Chemistry Modeling through Neural Network-Based Emulation. AGU Fall Meeting, Washington D.C, December 12, 2018 (Poster)

3. M. Kelp, A.P. Grieshop, C.O. Reynolds, J. Baumgartner, G. Jain, K. Sethuramanand, and J.D. Marshall. Investigating Health-Relevant Air Pollution Concentration Linkages Across Multiple Seasons During Indoor Cookstove Campaign in Rural India. ISES-ISEE Joint Annual Meeting, Ottawa, CA, August 25, 2018 (Poster)

2016

2. M. Kelp, H.O.T. Pye, E.V. Fischer, J. Brewer, and J. Fry. Global Modeling of Secondary Organic Aerosol Production from Reaction of NO3 Radical with Speciated Monoterpenes. AAAR Annual Conference, Portland, OR, October 18, 2016 (Poster)

2015

1. M. Kelp, J. Brewer, C. Keller, and E.V. Fischer. Evaluating the Potential Importance of Monoterpene Degradation for Global Acetone Production. AGU Fall Meeting, San Francisco, CA, December 16, 2015 (Poster)