CBI AI2ES

 
 


CBI AI2ES

The Conrad Blucher Institute AI2ES program is a partnership with the NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES) and other local community stakeholders. As a partner of the institute, the Conrad Blucher Institute at Texas A&M University-Corpus Christi will lead research in Coastal AI and partner with Del Mar College to develop a new innovative Certificate in Artificial Intelligence. AI models will include developing coastal fog and inundation predictions to support commerce and emergency management as well as predictive models to help with the conservation of endangered sea turtles. TAMU-CC will work with institute partners to use explainable AI (XAI) to better understand coastal processes and with local agencies and institute partners to better understand the communication of AI predictions to end users.

AMS 2024

CBI AI2ES presented 23 presentations at the 2024 American Meteorological Society’s annual conference in Baltimore, MD. Click the button below to learn more about the information presented, and to view the available presentations.

Predictive Tools

 

News and Updates:

  • These presentations will be delivered by CBI AI2ES students and faculty at the 2023 American Meteorological Society Annual Meeting in Denver, Colorado from January 8-12th, 2023.

    • Marzban, C., Liu, J., & Tissot, P. (2023, January 8-12). Sampling Variability and Local Minima [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Nguyen, C. T., Nachamkin, J., Krell, E., Estrada, B. Jr., Walker, A., Peterson, D. A., Campbell, J., & Tissot, P. E. (2023, January 8-12). Machine Learning Approaches for Distinguishing Haboobs from Other Wind Events in Arizona [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Williams, J. K., Demuth, J. L., Griffin, S., McGovern, A., Musgrave, K. D., Stewart, J. Q., & Tissot P. E. (2023, January 8-12). R2O Successes and Challenges in the NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES) The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Krell, E., Kamangir, H., Collins, W., King, S. A., & Tissot, P. (2023, January 8-12). The Influence of Grouping Spatio-Temporal Features on Explainable Artificial Intelligence (XAI): A Case Study with FogNet, a 3D CNN for Coastal Fog Prediction [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Vicens-Miquel, M., Tissot, P. E., Medrano, A. PhD, & Kamangir, H. (2023, January 8-12). Deep learning architectures for water level predictions [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Pilartes-Congo, J., Vicens-Miquel, M., Starek, M. J., & Tissot, P. E. (2023, January 8-12). Application of Close-Range Stereophotogrammetry for Predicting Coastal Inundation [Conference presentation]. The 21st Symposium on the Coastal Environment of 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Colburn, K., Tissot, P. E., & Vicens-Miquel, M. (2023, January 8-12). Comparison of Human Delineated Ocean Beach Wet/Dry Shorelines with AI Predictions [Poster presentation]. The 21st Symposium on the Coastal Environment of the 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Duff, C., Woodall, J., Tissot, P. E., White, M., & Vicens-Miquel, M. (2023, January 8-12). Long Short-Term Memory Predictions of Water Temperature for Cold Stunning Events [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Marines, A., Ramirez, D., Vicens-Miquel, M., & Tissot, P. E. (2023, January 8-12). Comparison of Machine Learning Models for the Prediction of Water Level at a Tide Gauge [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Kamangir, H., Krell, E. A., Collins, W. G., Tissot, P. E., King, S. A., Gagne II, Ph.D, D. J., & Schreck, J. (2023, January 8-12). FogNet-V2: Deep Spatio-variable Transformer for Coastal Fog Forecasting [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Kastl, M., Mahlke, H., Pilartes-Congo, J., Vicens-Miquel, M., Salazar, J., Nguyen, S., & Tissot, P. E. (2023, January 8-12). Pier Mounted Stereo Cameras to Measure Time Series of Total Water Levels [Poster presentation]. The 21st Symposium on the Coastal Environment of the 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • White, M., Tissot, P. E., Duff, C., Woodall, J., King, S. A., Williams, J. K., & Colburn, B. (2023, January 8-12). AI Ensemble Predictions for Cold Stunning Events in the Shallow Laguna Madre [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Colburn, B., Tissot, P. E., Williams, J. K., King, S.A., Collins, W. G., Kamangir, H., Gaudet, Ph.D. L., Krell, E. A., Nguyen, S., & De Los Santos, P. (2023, January 8-12). A Variational Autoencoder for Coastal Fog Predictions: Architecture, Performance and R2X Potential [Conference presentation]. The 22nd Conference on Artificial Intelligence for Environmental Science, 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

    • Millien, J., Edwards, D., Colburn, K., Vicens-Miquel, M., Pilartes-Congo, J., Stephenson, S., & Tissot, P. E. (2023, January 8-12). Change Analysis of Time Series of Beach Digital Elevation Models and Shoreline Wet/Dry Lines [Conference presentation]. The 21st Symposium on the Coastal Environment of the 103nd Annual Meeting of the American Meteorological Society Annual Meeting, Denver, CO, United States.

  • CBI AI2ES unveils their new portal page for public use on the Coastal Dynamics Lab website! This page features multiple data tools including:

    • Live conditions at Nueces County’s Horace Caldwell Pier (Surf Cam)

    • Live water level measurements and predictions over two weeks

    • Water levels and significant wave height over two weeks

    Scroll up to the portal linked at the top of this page, or click here to automatically visit our new home for CBI AI2ES prediction/data tools. Thank you again to NSF and Nueces County Coastal Parks for their help and contribution to many of these live data graphs and the camera stream at Horace Caldwell Pier.


COASTAL INUNDATION PROJECT:

Coastal inundations can have a major impact on beach management and safety. The frequency of flooding is increasing exponentially with relative sea level rise. This creates a need for more accurate models that can predict potential coastal inundation and alert beachgoers and officials of related hazards. The team is working on the creation of an AI inundation model capable to predict where the water will reach on the beach. This will be an invaluable addition to models that predict water levels at tide gauges but without including the water runup on the beach. Models predicting inundations on an hourly basis will help counties and cities better manage their beaches.

    • Created a dataset of over 3,000 drone based coastal images from 12 locations in Florida and Texas with labeled shoreline wet/dry line including elevations and Deep Learning predictions.

    • Undergraduate students developed water level predictions visualizations for stakeholders and scientists.

    • A set of cameras including a stereo camera are being installed on a local pier to provide point cloud time series

    • A peer reviewed conference paper (Vicens-Miquel et al.) “’Deep Learning Automatic Detection of the Wet/Dry Shoreline at Fish Pass, Texas” was accepted for IGARSS 2022 proceedings about to be followed by journal paper submission.

    (reported by the National Science Foundation, 2022)

 

SEA TURTLE CONSERVATION:

The Laguna Madre is home to many fish and sea turtle species, including juvenile green sea turtles, who take advantage of this rich and unique ecosystem. When strong cold fronts reach the South Texas coast, water temperature can decrease rapidly in the shallow waters of the Laguna Madre and other Texas Bays. During the strongest cold snaps, fishes and sea turtles can become and lethargic or fatally cold-stunned. The Texas Marine Cold Water Response Collaborative (TCRC) alerts organizations such as the Gulf Intracoastal Canal Association (GICA) to interrupt navigation during the recommended period needed for conservation groups to rescue sea life from these cold weather events. These predictive alerts reporting the onset and duration of cold stunning events are based on AI models developed by CBI in the late 2000’s, presently maintained and improved upon by CBI AI2ES members. The CBI AI2ES team continues work with collaborators to study how these AI predictions are understood and used by stakeholders.

    • The AI operational prediction model (shallow neural net) was extended to 120 hours lead time facilitating the decision process ahead of cold stunnings.

    • The team provided predictions and guidance for the determination and adjustment of the start and stop of navigation interruptions during a February 2022 cold stunning event.

    • Continued preparation of the stakeholder engagement including tentative agreement from stakeholders such as the Texas Marine Cold-water Response Collaborative and Texas Parks and Wildlife to participate.

    (reported by the National Science Foundation, 2022)

 

COASTAL FOG PREDICTIONS (FOGNET):

Coastal fog is a safety concern for transportation, particularly in a coastal city with frequent ship and plane travel. CBI AI2ES team has developed a sophisticated deep learning model, known as FogNet, which combines satellite sea surface temperatures and numerical model outputs to predict the onset of fog with 9 to 24 hours advance warning. The fog models are presently in their research stages, but AI2ES collaborators including CBI, the National Center for Atmospheric Research (NCAR), and The Weather Company/IBM, are working together to create operational models that are high performing, cost-effective, and meet most of the expectations of future users.

    • Paper “Importance of 3D convolution and physics on a deep learning coastal fog model” applying XAI to FogNet (Kamangir et al.) accepted in Environmental Modeling and Software. 

    • FogNet results including XAI are used as part of a collaboration with risk communication. 

    • The collaboration with risk communication has led to shifting FogNet to probabilistic outputs.

    • As part of a collaboration with IBM a VAE alternative to FogNet is being explored (would be easier to implement operationally).

    (reported by the National Science Foundation, 2022)

 

Contact Us

Please fill out the form below with any questions, comments, or potential collaboration opportunities.