I am a Research Scientist at Colorado State University researching machine learning applications for extreme rainfall and severe weather. I have a general interest in all things predictability and forecasting, and in particular ensemble sensitivity analysis, targeted observing, convective-scale data assimilation, machine learning, and ensemble forecasting of high-impact weather.
Postprocessing numerical weather prediction (NWP) model output to improve point-based and localized forecasts has been a topic of research for over 50 years (e.g., MOS). Statistical models are used to deduce relationships between pre-defined predictors and the phenomena of interest. Machine learning (ML) has emerged within atmospheric science as a new method to postprocess large NWP datasets to explicitly predict events that are unresolvable by NWP model output (e.g., extreme precipitation, tornadoes). One benefit of ML models is they are capable at learning the underlying spatio-temporal biases in NWP model output, thereby "correcting" biases in ML-based forecasts. I am interested in applying ML and deep learning (DL) techniques with global convection-parameterizing and convection-allowing models to create probablistic hazard outlooks (e.g., Hill et al. 2020a, Hill and Schumacher 2021, Schumacher et al. 2021, Hill et al. 2022) that are beneficial to operational forecast centers (e.g., Storm Prediction Center, Weather Prediction Center). This work is being supported by two grants from the National Oceanic and Atmospheric Administration Joint Technology Transfer Initiative program.
Predictability of convective processes is easily discerned through the application of Ensemble Sensitivity Analysis (ESA), which relates changes in model initial conditions to changes in a forecast metric through univariate regressions. ESA is capable of diagnosing dynamic regions and features that are critical to successful forecasts of convection initiation and intensity (e.g., Hill et al. 2016). I continue to employ ESA to examine dynamic sensitivies of convection forecasts with convection-allowing models (e.g., Hill et al. 2016, Hill et al. 2021) and am interested in exploring how sensitivities vary across convection regimes and climates.
Observations of small-scale atmospheric prcesses become critical for convection-allowing model forecasts when convective processes are explicitly simulated. However, the selection of additional observations to improve forecasts is often subjective, even though objective methods exist to select observations in dynamically relevant regions. Ensemble sensitivity analysis (ESA) provides a framework to determine additional observing locations that dynamically relate earlier state variables (e.g., 2-m temperature) and a particular forecast metric (e.g., reflectivity) to reduce forecast uncertainty after the new observation is assimilated. I have examined ESA-based targeting at convection-allowing resolutions in idealized simulations (e.g., Hill et al. 2020b) and continue to explore its utility for real-data cases and storm-scale applications, for instance, targeting in-storm observations with Unmanned Aerial Systems and assimilating them into CM1 model simulations.
Data assimilation procedures, which combine first-guess four-dimensional snap shots of the atmosphere with observations, have evolved significantly over the last two decades to improve forecasts at all scales of motion. I am particularly interested in the ensemble Kalman filter (EnKF), which has a broad application at convective scales, and methodological parameters that control inflation, localization, and ensemble spread, which help to create reliable ensemble forecasts. Specifically, as a component of the VORTEX-SE project, I am investigating the influence of near-surface thermodynamic observations on deep convection in the southeast U.S. through retrospective data assimilation experiments with the High Resolution Rapid Refresh Ensemble (e.g., Hill et al. 2021).
I have been involved in a number of field programs that aimed to better understand the dynamics of severe storms, either through targeted deployments of observational assets in and near supercell thunderstorms (e.g., Targeted Observations by Radars and UAS of Supercells, TORUS) or deployments of mobile and portable near-surface platforms to observe heterogenieties preceeding convection in the southeast U.S. (e.g., VORTEX-SE). These experiences have propelled an interest in engineering platforms designed to observe severe storms (e.g., small, lightweight platforms) as well as the observations obtained that may elucidate new dynamic information to help advance warnings of severe-storm hazards. These interests are being supported by a National Oceanic and Atmospheric Administration grant through the VORTEX-SE Program.
Cold-pool dynamics, supercell dynamics, tornadogenesis, tornado sturcture, radar remote sensing, microsphyics, electrification, single-cell thunderstorms, multi-cell thunderstorms
Parcel theory, fluid dynamics, atmospheric waves, dryline dynamics, frontogenesis, stability, shallow and deep convective processes, mesoscale convective systems, sounding analyses, low-level jets
Discretization and finite differencing, governing dynamic equations, parameterization schemes, deterministic and ensemble forecasting, verification, data assimilation, chaos theory, predictability, WRF model, initial condition problems
Least squares problem, maximum likelihood estimation, statistical filtering, objective analysis, coordinate transformations, random forests, neural networks, convolutional neural networks, advanced machine learning/deep learning methods
Energy cycle, atmospheric forces, vertical structure of the atmosphere, atmospheric composition, stability, thermodynamics and clouds, air masses, cyclones, climate cycles, thunderstorms, tornadoes, forecasting
Linux, bash scripting, Fortran, Python, version control (git, GitHub), object-based programming, Lorenz model
Dissertation: Demonstration of ensemble sensitivity-based targeted observing for convective-scale applications: Perfect-model experiments
Thesis: Mesoscale data assimilation and ensemble sensitivity analysis towards improved predictability of dryline convection
Research Advisor: Dr. Robert Houze Jr.
Advisor: Dr. Russ Schumacher
Advisors: Drs. Christopher Weiss and Brian Ancell
ATMO 1300: Introduction to Atmospheric Science
Cheeseman, Michael, B. Ford, Z. Rosen, E. Wendt, A. DesRosiers, A. J. Hill, C. L’Orange, C. Quinn, M. Long, S. H. Jathar, J. Volckens, and J. R. Pierce, 2023: Investigating sub-city gradients of air quality: lessons learned with low-cost PM2.5 and AOD monitors and machine learning. Atmospheric Chemistry and Physics, in review.
Hill, A. J., R. S. Schumacher, and I. Jirak, 2023: A new paradigm for medium-range severe weather forecasts: probabilistic random forest-based predictions.. Weather and Forecasting, in press.
Hill, A. J. and R. S. Schumacher, 2021: Forecasting excessive rainfall with random forests and a deterministic convection-allowing model. Weather and Forecasting, 36, 1693-1711, doi:10.1175/WAF-D-21-0026.1.
Schumacher, R. S., A. J. Hill, M. Klein, J. Nelson, M. Erickson, S. M. Trojniak, and G. R. Herman, 2021: From random forests to flood forecasts: A research to operations success story. Bulletin of the American Meteorological Society, 102, E1742-E1755, doi:10.1175/BAMS-D-20-0186.1.
Hill, A. J., C. C. Weiss, and D. C. Dowell, 2021: Influence of a portable near-surface observing network on experimental ensemble forecasts of deep convection hazards during VORTEX-SE, Weather and Forecasting, 36, 1141-1167, doi:10.1175/WAF-D-20-0237.1.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2020b: Factors influencing ensemble sensitivity-based targeted observing prediction at convection-allowing resolutions. Monthly Weather Review, 148, 4497-4517, doi:10.1175/MWR-D-20-0015.1.
Hill, A. J., G. R. Herman, and R. S. Schumacher, 2020a: Forecasting severe weather with random forests. Monthly Weather Review, 148, 2135--2161, doi:10.1175/MWR-D-19-0344.1.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2016: Ensemble sensitivity analysis for mesoscale forecasts of dryline convection initiation. Monthly Weather Review, 144, 4161-4182. doi:10.1175/MWR-D-15-0338.1
Rasmussen, K. L., A. J. Hill, V. E. Toma, M. D. Zuluaga, P. J. Webster, and R. A. Houze, Jr., 2014: Multiscale analysis of three consecutive years of anomalous flooding in Pakistan Quart. J. Roy. Meteor. Soc., 141, 1259-1276. doi:10.1002/qj.2433.
*Hill, A. J., R. S. Schumacher, 2023: Exploring Definitions of Excessive Rainfall when Generating Machine Learning-based Probabilistic Excessive Rainfall Forecasts from a Global Reforecast Dataset. 37th Conference on Hydrology, Denver, CO, 13B.5.
*Hill, A. J., R. S. Schumacher, and I. Jirak, 2023: Understanding and Interpreting Medium-Range Predictions of Severe Weather with Random Forests. 22nd Conference on Artificial Intelligence for Environmental Science, Denver, CO, 5A.3.
*Hill, A. J., V. A. Gensini, and R. S. Schumacher, 2023: Medium-Range Machine Learning Forecasts for Severe Convective Storms. 22nd Conference on Artificial Intelligence for Environmental Science, Denver, CO, 11A.3.
*Hill, A. J., R. S. Schumacher, I. Jirak, 2022: Medium-Range Severe Weather Predictions with Random Forests. 30th Conference on Severe Local Storms, Santa Fe, NM, 4.1B.
(invited) Hill, A. J., 2022: Generating Probabilistic Machine-Learned Forecasts for Severe Weather and Excessive Rainfall Prediction. National Weather Service Central Region Headquarters, virtual.
Hill, A. J., 2022: Probabilistic Predictions of Severe Weather with Machine Learning. Columbia, SS Weather Forecast Office Severe Weather Workshop, virtual.
Hill, A. J. and R. S. Schumacher, 2022: Medium-range Predictions of Severe Weather with Machine Learning. 31st Conference on Weather Analysis and Forecasting/27th Conference on Numerical Weather Prediction, J7.2.
Hill, A. J. and R. S. Schumacher, 2021: Medium-range forecasts of hazardous weather with machinelearning. 3rd NOAA Workshop on Leverage AI in Environmental Sciences, virtual.
Hill, A. J., R. S. Schumacher, and J. Escobedo, 2021: Extending predictions of hazardous weather into the medium-range with machine learning. 2nd Knowledge-guided Machine Learning Workshop, virtual, poster.
Hill, A. J. and R. S. Schumacher, 2021: Advancing probabilistic prediction of high-impact weather using ensemble reforecasts and machine learning. National Weather Service AI Team, virtual.
Hill, A. J., E. James, R. S. Schumacher, M. Klein, J. Nelson, and M. J. Erickson, 2021: CSU CAM-based First Guess Excessive Rainfall Outlook Products. Hydrometeorological Testbed Flash Flood and Intense Rainfall Experiment, virtual.
(invited) Hill, A. J., 2021: Learning from machines: High-impact weather forecasting with Artificial Intelligence. University of Florida Department of Geography, virtual.
(invited) Hill, A. J., 2021: Learning from machines: improving high-impact weather forecasts with Artificial Intelligence. Northern Illinois University Department of Geographic and Atmospheric Sciences, virtual.
Hill, A. J. and R. S. Schumacher, 2021: Medium-range severe weather forecasts with random forests, 20th Conference on Artificial Intelligence for Environmental Science.
Hill, A. J. and R. S. Schumacher, 2021: Short-term excessive rainfall forecasts using random forests and a deterministic convection-allowing model, 20th Conference on Artificial Intelligence for Environmental Science.
(invited) Hill, A. J., 2020: Machine learning and AI for high-impact weather. NWS Southern Region Science Circle, virtual.
(invited) Hill, A. J. and R. S. Schumacher, 2020: Forecasting our future: machine learning and AI for high-impact weather. National Weather Association Annual Meeting, virtual.
(invited) Hill, A. J., 2020: Statistical tools for high impact weather. Naval Postgradaute School, Monterey, CA.
Hill, A. J. and R. S. Schumacher, 2020: Heavy precipitation and flash flood forecasts using random forests and convection-allowing models. 30th Conference on Weather Analysis and Forecasting/26th Conference on Numerical Weather Prediction, Boston, MA, J71.2.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2018: Towards improving forecasts of severe convection along the dryline through targeted observing with ensemble sensitivity analysis. 29th Conference on Severe Local Storms, Stowe, VT, paper 14.2.
Hill, A. J., C. C. Weiss, and D. C. Dowell, 2018: Exploring the utility of assimilating observations from a mesoscale network of StickNet platforms during VORTEX-SE with the High Resolution Rapid Refresh Ensemble. 29th Conference on Severe Local Storms, Stowe, VT, paper 74.
(invited) Hill, A. J., 2018: The utility of ensemble-sensitivity analysis for targeted observing, ensemble subsetting, and investigating environmental controls on storm characteristics. Cooperative Institute for Research in the Atmosphere, Fort Collins, CO.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2018: Ensemble-sensitivity analysis based observation targeting experiments for mesoscale convection forecasts and factors influencing observation-impact prediction. 22nd Conference on Integrated Observing and Assimilation Systems for the Atmosphere, Oceans, and Land Surface, Austin, TX, paper 613.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2017: Ensemble sensitivity-based observation targeting experiments for Southern Plains dryline convection. 21st Conference on Integrated Observing and Assimilation Systems for the Atmosphere, Oceans, and Land Surface, Seattle, WA, paper 15.5.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2016: Ensemble sensitivity-based observation targeting OSSEs for Southern Plains dryline convection. 20th Conference on Integrated Observing and Assimilation Systems for the Atmosphere, Oceans, and Land Surface, New Orleans, LA, paper J7.7.
Hill, A. J., B. Burghardt, and B. C. Ancell, 2015: Advanced ensemble techniques for improved predictability of storm-scale features. 1st Ensemble Design Workshop for Storm-Scale Ensembles, Boulder, CO.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2014: Mesoscale ensemble sensitivity of dryline convective initiation. Preprints, 27th Conference on Severe Local Storms, Madison, WI, paper 8B.4.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2014: Applicaiton of mesoscale ensemble-based sensitivity analysis to observation targeting. 26th Conference on Weather Analysis and Forecasting / 22nd Conference on Numerical Weather Prediction, Atlanta, GA, paper 610.
Hill, A. J., C. C. Weiss, and B. C. Ancell, 2013: Utilizing Ensemble Sensitivity for Data Denial Experiments of the 4 April 2012 Dallas, Texas Dryline-Initiated Convective Outbreak Using West Texas Mesonet Observations and WRF-DART Data Assimilation. Preprints, 15th Conference on Mesoscale Processes, Portland, OR, paper 11.