Machine Learning Lead (CIRA) / Research Professor (ECE)
- Office Location:
CIRA building - Room 41
Please visit our CIRA ML website to learn about CIRA’s ML/AI activities.
I have three highly connected roles here at Colorado State University:
- Machine learning lead at the Cooperative Institute for Research in the Atmosphere (CIRA). I joined CIRA in July 2019 to support its use of machine learning (ML) techniques.
- CSU lead for the NSF AI Institute for Research on Trustworthy AI in Weather, Climate and Coastal Oceanography (AI2ES). AI2ES is a 5-year $20M AI institute funded by the NSF, led by Amy McGovern at OU. It just got funded in Fall 2020. CSU is one of the primary partners of the institute.
- Research Professor in Electrical and Computer Engineering (ECE). I joined ECE in 2011.
Since 2019 I spend most of my time working at CIRA. Key activities include:
- Working directly on CIRA projects,
- Providing support for CIRA research scientists working with ML,
- Teaching customized ML lessons, such as our bi-weekly ML core lessons and our CIRA Short Course on ML for Weather and Climate.
Below are some samples of the work I’m involved in:
- Thoughts on the proper use of AI for weather and climate:
- Highly cited paper: Why we need to focus on developing ethical, responsible, and trustworthy artificial intelligence approaches for environmental science. Environmental Data Science (2022)
- Thoughtfully Using Artificial Intelligence in Earth Science (2019)
- Intelligent Systems for Geosciences: An Essential Research Agenda (2018)
- Machine Learning for the Geosciences: Challenges and Opportunities (2018)
- Three Steps to Successful Collaboration with Data Scientists (2017)
- Explainable AI for geoscience applications:
- Carefully choose the baseline: Lessons learned from applying XAI attribution methods for regression tasks in geoscience (2023)
- Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience (2022)
- Neural network attribution methods for problems in geoscience: A novel synthetic benchmark dataset (2022)
- Indicator Patterns of Forced Change Learned by an Artificial Neural Network (2020)
- Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability (2020)
- Exploring AI / math methods for weather and climate:
- Creating and evaluating uncertainty estimates with neural networks for environmental-science applications (2023)
- A Primer on Topological Data Analysis to Support Image Analysis Tasks in Environmental Science (2023)
- Can We Integrate Spatial Verification Methods into Neural Network Loss Functions for Atmospheric Science? (2022)
- CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences (2021)
- Evaluation, Tuning and Interpretation of Neural Networks for Working with Images in Meteorological Applications (2020)
- Application-focused work:
- Low Cloud Detection in Multilayer Scenes Using Satellite Imagery with Machine Learning Methods (2022)
- Using Deep Learning to Emulate and Accelerate a Radiative Transfer Model (2021)
- Machine Learning for Clouds and Climate (2021, book chapter, to appear)
- Using deep learning to nowcast the spatial coverage of convection from Himawari-8 satellite data (2021)
- Applying machine learning methods to detect convection using Geostationary Operational Environmental Satellite-16 (GOES-16) advanced baseline imager (ABI) data (2021)
- Development and Interpretation of a Neural Network-Based Synthetic Radar Reflectivity Estimator Using GOES-R Satellite Observations (2020)
- Causal discovery for weather and climate:
- A Causality-Based View of the Interaction between Synoptic- and Planetary-Scale Atmospheric Disturbances (2020)
- Tropospheric and Stratospheric Causal Pathways Between the MJO and NAO (2019)
- Causal discovery in the geosciences—Using synthetic data to learn how to interpret results (2017)
- A new type of climate network based on probabilistic graphical models: Results of boreal winter versus summer (2012)
- Causal Discovery for Climate Research Using Graphical Models (2012)
- Education at the intersection of ML and weather/climate:
See longer list of publications below.
How to reach me:
- Send email to firstname.lastname@example.org
- My office is at CSU’s Foothills campus: CIRA building, Room 41.
Refereed Conference Papers
Non-Refereed Conference Publications and Presentations (only abstracts reviewed)
Editor of Proceedings
Recent and Upcoming Invited Talks
Technical Reports (additional preprints listed within categories above)