NOAA Center for Satellite Applications and Research banner
Intranet • Contact • Skip navigation
National Oceanographic & Atmospheric Administration website NOAA Center for Satellite Applications and Research website

For a printable version of the agenda, click here!

Remote access: Webex URL
Meeting number: 909 473 760; Password: starAI
Join by phone: +1(415)-527-5035 US Toll
Access code: 909 473 760

Please remember to mute your microphone!

23 April 2019
Time Presentations / Topics Speaker Affiliation
0700 - 0830 Registration 1, 2
0830 - 0940 Plenary Session
0830 - 0835 Workshop logistics Kevin Garrett NOAA/NESDIS
0835 - 0845 Welcoming remarks and introduction of keynote speakers Harry Cikanek Director NOAA/NESDIS/STAR
0845 - 0900 NOAA Priorities and Plans, Keynote Speaker Dr. Neil Jacobs NOAA Administrator
0900 - 0910 Perspectives on Exploiting AI / ML in NESDIS Dr. Steve Volz Assistant Administrator of NOAA/NESDIS
0910 - 0920 Thoughts on Exploiting AI / ML in the National Weather Service (NWS) Dr. Louis Uccellini Assistant Administrator of NOAA/NWS
0920 - 0940 NOAA Data Strategy and AI Potential Contribution, Keynote Speaker Dr. Ed Kearns NOAA Chief Data Officer
0940 - 1010 Leadership Panel Discussion
Facilitator: Harry Cikanek (Director, NOAA/NESDIS/STAR)
1010 - 1030 Coffee break
1030 - 1250 Session 1 (S1) - Overview Talks
Chairs: Amy McGovern (University of Oklahoma) and Kenneth Casey (NOAA/NCEI)
1030 - 1050 The AMS AI Committee: 25 Years and counting of supporting the community Phillip Tissot3 Corpus Christi, Texas A&M University
1050 - 1110 Overview of NOAA AI activities in Satellite Observations and NWP: Status and Perspectives Sid Boukabara NOAA/NESDIS
1110 - 1130 Use of AI in Forecasting and Decision Services at The Weather Company John K. Williams3 The Weather Company, IBM Business
1130 - 1150 Artificial Intelligence Applications at NCAR Sue Ellen Haupt3 NCAR
1150 - 1210 Opportunities for using AI methods in weather forecasting at ECMWF Alan Geer3 ECMWF
1210 - 1230 Alphabet AI and Weather Jason Hickey3 Google
1230 - 1250 AI for Science: Applications of NVIDIA GPUs for Numerical Weather Prediction David Hall3 NVIDIA
1250 - 1255 Group photo
1255 - 1350 Lunch break
1350 - 1450 1st Poster Session (1P)
1450 - 1610 Session 2 (S2) - Satellite Earth Observations and Applications - Part I
Chairs: David Hall (NVIDIA) and Sid Boukabara (NOAA/NESDIS)
1450 - 1510 Combining the power of experts and machine learning to explore NASA and NOAA data: a few examples Tianle Yuan3 UMBC JCET/NASA GSFC
1510 - 1530 Recent Application of Machine Learning Techniques to Environmental Science at PNNL Philip Rasch3 PNNL
1530 - 1550 Preparing AI-Enabled Weather and Environment Satellite Big Data Allen Huang SSEC/CIMSS
1550 - 1610 Development of Convolutional Neural Networks for Ice and Flood Detection from Synthetic Aperture Radar (SAR) Sean Helfrich NOAA/NESDIS
1610 - 1630 Coffee break
1630 - 1730 1st Panel Discussion Facilitator: Allen Huang (University of Wisconsin)
1630 - 1730

Topic: How can scientists and engineers embrace AI technology to enhance their work?

Panel Members:

  • Kayo Ide (Univ. Of Maryland)
  • Amy McGovern (Univ. Of Oklahoma)
  • Phillip Tissot (Texas A&M - Corpus Christi)
  • Sue Ellen Haupt (NCAR)
  • John Williams (The Weather Company, IBM Business)
  • David Hall (NVIDIA)
1830 - 2030 No-host Social Dinner (Location TBD)

4-22-2019 5:40 pm


Remote access: Webex URL
Meeting number: 903 651 377; Password: starAI
Join by phone: +1(415)-527-5035 US Toll
Access code: 903 651 377

Please remember to mute your microphone!

24 April 2019
Time Presentations / Topics Speaker Affiliation
0830 - 1010 Session 2 (S2) - Satellite Earth Observations and Applications - Part II
Chairs: Sue Ellen Hupt (NCAR) and Jason Hickey (Google)
0830 - 0850 Improving Processing and Extracting Value from Satellite Observations through Deep Learning Jebb Stewart NOAA/OAR
0850 - 0910 Democratizing machine learning through AI for Earth's API framework Patrick Flickinger Microsoft, AI for Earth
0910 - 0930 Using Deep Learning to Extract Regions of Interest from Satellite Data Christina Kumler NOAA/OAR
0930 - 0950 Quantitative Precipitation Estimate Results from a Convolutional Neural Network Machine Learning Model Micheal Simpson CIMSS/NSSL
0950 - 1010 A Deep Neural Network Perspective on Atmospheric Motion Vectors Fei He UCLA
1010 - 1030 Coffee break
1030 - 1210 Session 2 (S2) - Satellite Earth Observations and Applications - Part III
Chairs: Jebb Stewart (NOAA/OAR/ESRL, CIRA) and Nikuni Oza (NASA/Ames and NASA/ESTO)
1030 - 1050 EarthInsights: Parallel Clustering of Large Earth Science Datasets on the Summit Supercomputer Sarat Sreepathi Oak Ridge National Lab
1050 - 1110 Developing fine-scale snow cover fraction estimates using deep learning Soni Yatheendradas UMD/GSFC
1110 - 1130 Intermediate Frame Interpolation to Improve Temporal Coverage of GOES-16/17 Thomas Vandal NASA Ames
1130 - 1150 Deep learning for estimating land surface response with uncertainty: soil moisture and other opportunities Chaopeng Shen Pennsylvania State University
1150 - 1210 Deep learning estimation of tropical cyclone intensity from microwave satellite imagery Tony Wimmers UW-CIMSS
1210 - 1310 Lunch break
1310 - 1410 2nd Poster Session (2P)
1410 - 1550 Session 3 (S3) - Nowcasting and NWP data assimilation
Chairs: Kevin Garrett (NOAA/NESDIS/STAR) and Kayo Ide (University of Maryland)
1410 - 1430 Machine learning meets data assimilation Peter Jan van Leeuwen Colorado State University
1430 - 1450 Improvement to hurricane track and intensity forecast by exploiting satellite data and machine learning Narges Shahroudi RTi@NOAA/NESDIS
1450 - 1510 Machine Learning Based Applications for Environmental Hazard Detection: Data vs. Actionable Information, User Evaluations, and Future Possibilities Michael Pavolonis NOAA/NESDIS/STAR
1510 - 1530 Development of Merged Cloud Forecasts from Satellite and Numerical Model Data Jason Nachamkin Naval Research Laboratory
1530 - 1550 Data driven numerical methods partial differential equations Jason Hickey Google
1550 - 1610 Coffee break
1610 - 1730 Session 4 (S4) - Environmental and Numerical Modeling - Part I
Chairs: Vladimir Krasnopolsky (NOAA/NWS/NCEP) and John Williams (The Weather Company, an IBM Business)
1610 - 1630 Machine Learning for Climate Extremes: Training is Everything William Collins3 UC Berkley
1630 - 1650 Machine learning for moist physics parameterizations in weather and climate models Christopher Bretherton3 University of Washington
1650 - 1710 Machine Learning for Predicting the Evolution of Large Complex Spatiotemporally Chaotic Systems Edward Ott3 UMD
1710 - 1730 Training Neural Network Parameterizations with Near-Global Cloud-Resolving Models Noah D Brenowitz University of Washington

4-16-2019 5:53 pm


Remote access: Webex URL
Meeting number: 901 865 234; Password: starAI
Join by phone: +1(415)-527-5035 US Toll
Access code: 901 865 234

Please remember to mute your microphone!

25 April 2019
Time Presentations / Topics Speaker Affiliation
0830 - 1010 Session 4 (S4): Environmental and Numerical Modeling - Part II
Chairs: Pete Childs (Priogen Energy) and Phillip Tissot (Texas A&M-Corpus Christi, AMS AI Committee Member)
0830 - 0850 Neural network applications in numerical modeling Vladimir Krasnopolsky NOAA/NWS
0850 - 0910 Atmospheric chemistry modeling and air quality forecasting using machine learning Christoph Keller NASA/GMAO
0910 - 0930 Improving reference evapotranspiration forecasting with numerical weather predictions Hanoi Medina Auburn University
0930 - 0950 Analog Forecast Models for Space Weather Predictions Eric Kihn NOAA/NESDIS
0950 - 1010 A deep learning model to improve WRF forecasts: a case study of temperature, relative humidity, and wind speed Yunsoo Choi University of Houston
1010 - 1030 Coffee break
1030 - 1230 Session 5 (S5): Post-Forecast and Extreme Weather
Chairs: John Ten Hoeve (NOAA/NWS Office of Org. Excellence) and Vladimir Krasnopolsky (NOAA/NWS)
1030 - 1050 Using Machine Learning to Improve Prediction and Understanding of Convective Hazards Amy McGovern3 University of Oklahoma
1050 - 1110 Leveraging AI for Tropical Cyclone Prediction Stephanie Stevenson CIRA/NHC
1110 - 1130 Hybrid AI hurricane forecasting system: deep learning ensemble approach and Kalman filter Yunsoo Choi University of Houston
1130 - 1150 Nonlinear Wave Ensemble Averaging using Neural Networks Ricardo Martins Campos University of Lisbon
1150 - 1210 Nowcasting Lightning Events with a Cloud-based Deep Learning approach Valliappa Lakshmanan Google
1210 - 1230 Using Artificial Neural Networks to Improve CFS Week 3-4 Precipitation and 2 Meter Air Temperature Forecasts Yun Fan NOAA/NWS
1230 - 1330 Lunch break
1330 - 1350 Live Survey from the audience (on recommendations and suggestions)4
1350 - 1500 Session VI: Conclusion General Discussion
Facilitator: John Ten Hoeve (NOAA/NWS Office of Org Excellence)
1350 - 1400 Special Talk: Building bridges between domain scientists and machine learning experts: the essential role of weather/climate scientists in machine learning collaborations Imme Ebert-Uphoff Colorado State University
1400 - 1500 Topic: Where do we go from here?

Panel Members:

  • Imme Ebert-Uphoff (Colorado State University)
  • Vladimir Krasnopolsky (NOAA/NWS/NCEP)
  • Kenneth Casey (NOAA/NCEI)
  • Jebb Stewart (NOAA/OAR/ESRL, CIRA)
  • Nikuni Oza (NASA/Ames and NASA/ESTO)
  • Jason Hickey (Google)
  • Pete Childs (Priogen Energy)
1500 - 1700 Session VII: Parallel Sessions (Tutorials)
Facilitator: Kevin Garrett (NOAA/NESDIS)

4-25-2019 9:09 am

List of Posters and Presenters
Title First author / presenter Affiliation
Poster Session 1.P: Tuesday, April 23
Leveraging NWP for ML Coastal Predictions and Other Coastal ML Applications Phillippe Tissot Texas A&M University/Corpus Christi
Automatic Extraction of Internal Solitary Wave Signature in HIMAWARI-8 Images Based on Deep Convolutional Neural Networks Shuangshang Zhang University of Maryland Eastern Shore
Separation of Forecast Wind Wave Systems Using K-Means Clustering Andre van der Westhuysen IMSG at NOAA/NWS
Improvements in Remotely-Sensed Cloud Property Estimation using Simple Machine Learning Models Charles H. White University of Wisconsin/CIMSS
Machine learning approach to understanding vegetation distribution and dynamics using high resolution remote sensing Jitendra Kumar Oak Ridge National Laboratory
Nighttime sea-fog detection from geostationary satellite using machine learning DaeSeong Choi, Seyun Min, Jae Kim Pusan National University
AI and Meteorology/Remote Sensing Applications Research at PGCAP/INPE Rafael Santos Brazilian National Institute for Space Research
A Fully Connected Scheme for Detection of Convective Rain from Satellite Passive Microwave Measurements Veljko Petkovic CSU/UMD
The new machine learning toolbox within NOAA's Microwave Integrated Retrieval System Ryan Honeyager IMSG at NOAA/NESDIS
Development and application of a 33-year daily multi-layer cropland soil moisture dataset in China using machine learning Yaling Liu Columbia University
An improved ATMS-based Hurricane Warm Core Animation System (HWCAS) Using Convolutional Neural Network Method Ding Liang GST
Interpretable AI for Deep-Learning-Based Meteorological Applications Eric Wendoloski The Aerospace Corporation
Improving Validation Performance of VIIRS Radiometric Measurements with ICVS Machine Learning-based Clear-Sky Mask Algorithm Xingming Liang GST Inc.
AI for water infrastructure mapping in Africa Pamela Collins Conservation International
Dimensionality Reduction for Fast and Accurate Radiative Transfer Patrick Stegmann JCSDA
Airmass Properties from GOES ABI Using Machine Learning Kyle Hilburn CIRA/CSU
Exploring AI Capabilities with JPSS/STAR Integrated Calibration/Validation Syste Banghua Yan NOAA/NESDIS/STAR
CrIS Subpixel Cloud detection and ATMS Sensor Monitoring using Machine Learning Technology Likun Wang Riverside at NOAA/NESDIS
Retrieving aerosol optical depth over land from satellites by using a machine learning algorithm to build the relationships between surface reflectance at different wavelengths Tianning Su UMD
How much better can we do in identifying aerosols and distinct cloud types from radiometers by harnessing recent advances in deep learning methods? Willem Marais University of Wisconsin/CIMSS
How Data Mining Approaches Can or Will Improve Satellite Land Observational Data Product Accuracies? Xiwu Zhan NOAA/NESDIS
Machine Learning for Winter Precipitation Type Supervised by Citizen Science (mPING) Observations Plus a New Tornado Detection Algorithm for the WSR-88D Dual-Polarization Radar Kim Elmore SSEC/CIMSS
Reconstruction of missing data in GOCI AOD using a deep learning algorithm Yunsoo Choi University of Houston
Leveraging deep learning hyperparameter tuning frameworks for intelligent WRF ensembles Derek D. Jensen Lawrence Livermore National Laboratory
Enterprise Validation to Characterize AI Products Performance Anthony L Reale NOAA/NESDIS
GSICS Action Tracker: A Supervised Machine Learning Content extraction tool on Google Cloud Manik Bali UMD/ESSIC
Improving Atmospheric River Forecasts with Convolutional Neural Networks William Chapman Oceanography

List of Posters and Presenters
Title First author / presenter Affiliation
Poster Session 2.P: Wednesday, April 24
Spatio-Temporal Climate Causality Analytics Jianwu Wang UMBC
Stochastic PDE model identification from partial noisy data Fei Lu Johns Hopkins University
Creating Synthetic Weather Radar Images Using Convolutional Neural Networks Christopher Mattioli MIT Lincoln Laboratory
Satellite Imaging Techniques for the Analysis of High-Impact Historical Severe Thunderstorm Events Kenneth Pryor NOAA/NESDIS
The improvement of predictability for very short range precipitation using Micro-genetic algorithm Jiyeon Jang KMA
INPE Nowcasting system: Steps toward an automatic severe storm forecasting system in Brazil Alan James Peixoto Calheiros Brazilian National Institute for Space Research
Assessing the variability of VIIRS Day/Night Band observed nocturnal light sources for use in atmospheric retrievals via k-means clustering Jeremy Solbrig Colorado State Univerisity
Improving hydrological simulations via the integration of remotely sensed data assimilation in coupled land surface and hydrologic model framework Chandana Gangodagamage NASA
Modelling HPC workloads with (some) Machine Learning Antonino Bonanni ECMWF
Convective Storm Nowcasting: Capabilities of Remote Sensing in Central Europe Patrik Benacek Charles University in Prague
Atlantic Basin RI Prediction Enhancement through NWP Spatial Information Alexandria Grimes Mississippi State University
Learning to automatically detect avalanche deposits from SAR satellite imagery Sophie Giffard-Roisin, Saumya Sinha University of Colarado
Is your Model right today? Marina Frants, Dean Wakeham XST, Inc.
Engaging Freshmen Undergraduates in Atmospheric Data Science. Alexandra Jones University of Maryland
Advancing Predictive Understanding of Terrestrial Ecosystem through Machine Learning Dan Lu Oak Ridge National Laboratory
Visceralization of Future Climate Change S. Karthik Mukkavilli Montreal Institute for Learning Algorithms
Translating climate and remote sensing information into improved decision making in agriculture and water resources Di Tian Auburn University
Interpretation of Deep-learning Models for Short-term Forecasting of Tornadogenesis Ryan Lagerquist University of Oklahoma
A Study on the Bias Correction of the Surface Temperature Forecast using Recurrent Neural Networks KIM MANKI KMA
Post-processing 12-36 hour multi-model ensemble PQPFs using a random forest Eric Loken University of Oklahoma/CIMMS
Machine Learning Parameterizations from the Surface to the Clouds David Gagne University of Oklahoma
Linking GOES-R observations and Multi-Radar/Multi-Sensor precipitation using unsupervised learning approach Shruti A Upadhyaya CIMMS
TPUs, TensorFlow Research Cloud, and Mesh Tensorflow Peter Dolan Google/Deep Mind
An Evaluation of Deep Learning Approaches for Nationwide Land Cover Mapping Chris Robinson Lynker Tech at the NOAA Office for Coastal Management


1Please complete registration as early as possible to avoid expected delays on Tuesday morning.
2Survey questions regarding feedbacks on using AI in satellite data exploitation and NWP will be distributed during the registration. Participants are encouraged to review and participate in the live survey on Thursday afternoon.
3Invited Talk
4Results of this survey will help formulate NOAA's data and AI strategy in the future.

Level A conformance icon, W3C-WAI Web Content Accessibility Guidelines 1.0 and Valid HTML 4.01 IconDept. of Commerce  •  NOAA  •  NESDIS  •  Website Owner: STAR  •  Contact webmaster  •  Last revised: April 23, 2019
Heartbleed Notice  •  Privacy Policy  •  Disclaimers  •  Information Quality  •  Accessibility  •  Search  •  Customer Survey
icon: valid HTML 4.01 transitional. Level A conformance icon, W3C-WAI Web Content Accessibility Guidelines 1.0