American Meteorological Society

2024

CBI AI2ES at the AMS 2024 Conference

CBI AI2ES presented 23 presentations at the 2024 American Meteorological Society’s annual conference in Baltimore, MD. Below you can find some of these presentations which have been made available, as well as a bibliography for all 2024 presentations.

  • Alonzo, J., Flores, Flores, E., Tissot, P.E., Anand, A., Ehrke, C., and Shelly, R.J. (2024, January 28 - February 1). Machine Learning Water Level Predictions for an Intermediate Location Using Connected Bodies of Water [Poster presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    DeSimone, A., Beasley, A., Anand, A., Colburn, B., Dasu, S., Tissot, P.E., and White, M. (2024, January 28 - February 1). Utilizing Neural Networks to Predict Water Temperatures in a Thermal Refuge [Poster presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Colburn, B., Tissot, P., Williams, J.K., King, S.A., Collins, W.G., Krell, E., Gaudet, H., and White, M. (2024, January 28 - February 1). A Variational Autoencoder for Coastal Visibility Predictions: Architecture, Performance and R2X Potential [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Abrams, L. R., Spore, J., Dusek, G., Tissot, P.E., Krell, E., and Moustahfid, H. (2024, January 28 - February 1). AI for Quality Control of Water Level Observations [Oral presentation]. The 22nd Symposium on the Coastal Environment of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Estrada, B., Walker, A., Nachamkin, J., Peterson, D. A., Nguyen, C. T., Campbell, J. R., and Tissot, P. E. (2024, January 28 - February 1). Are NASA Land Information System (LIS) Data Useful for Predicting Dust Storms? [Oral presentation]. The 16th Symposium on Aerosol Cloud Climate Interactions of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Hajiesmaeeli, M., Medrano, A., Tissot, P. E. (2024, January 28 - February 1). Digital Elevation Model Generation using Highly Oblique Stereo Imagery via Structure from Motion in a Coastal Area [Poster presentation]. The 22nd Symposium on the Coastal Environment of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Vicens-Miquel, M., Radin, C., Nieves, V., Tissot, P., and Medrano, A., (2024, January 28 - February 1). Empowering Coastal Resilience: A Multi-Layer Perceptron Approach for Subseasonal-to-Seasonal Sea Level Predictions in the Gulf of Mexico [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Miguel Marrero-Colominas, H., Shotande, M., Fagg, A. H., White, M., Tissot, P., and McGovern, A. (2024, January 28 - February 1). Estimating Uncertainty of Water Temperature Predictions for Cold-Stunning Events in the Laguna Madre [Poster presentation]. The 23rd Conference on

    Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Ehrke, C., Tissot, P. E., Vicens-Miquel, M., Estrada Jr., B., Mukai, K., and Glazer, B. (2024, January 28 - February 1). Estimation of Wave Height from Standard Deviation of Water Level Measured by a Low-Cost Water Level Sensor [Poster presentation]. The 22nd Symposium on the Coastal Environment of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Woodall, J., White, M., Marrero, H., Vicens-Miquel, M., and Tissot, P. E. (2024, January 28 - February 1). Exploring Cross-Validation Techniques for ML Predictions of Rare Cold-Stunning Events [Poster presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Kamangir, H., Krell, E., Collins, W. G., Tissot, P., King, S. A., and Gagne II, D. J. J. (2024, January 28 - February 1). FogNet-V2: Multi-view Tensorized Transformer for Coastal Fog Forecasting [Oral presentation]. The Second Symposium on the Future of Weather, Forecasting, and Practice of the 104th Annual Meeting of the American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Stephenson, S, Luscher, A., and Tissot, P. E. (2024, January 28 - February 1). Integrating Web Cameras into NOAA's Coastal Inundation Dashboard [Poster presentation]. The 22nd Symposium on the Coastal Environment of the 104th Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Gagne II, D. J., Williams, J. K., Stewart, J. Q., Demuth, J., Tissot, P. E., Kurbanovas, A., Nguyen, S., Justin, A. D., Radford, J. T., Wirz, C. D., Becker, C., Gantos, G., Martin, T., Petzke W., Grimit, E. P., Hoffman, K. T., Hill, A., Schumacher, A. B., Musgrave, K., and McGovern, A. (2024, January 28 - February 1). Lessons Learned from Building Real-Time Machine Learning Testbeds for AI2ES [Oral presentation]. The 14th Conference on Transition of Research to Operations of the 104th Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Collins, W. G., Krell, E., Tissot, P. E., and King, S. A. (2024, January 28 - February 1). Meteorological Interpretation of XAI Output Applied to a 3D Convolutional Neural Network Fog Prediction Model [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the 104th Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Wirz, C. D., Demuth, J. L., White, M., Radford, J. T., Tissot, P. E., Cains, M. G., Kamangir, H., Krell, E. A. Bostrom, A., King, S. A., Collins, W. G., and Williams, J. K. (2024, January 28 - February 1). NWS Forecaster Perceptions of New AI Guidance for Coastal Fog Prediction [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Vicens-Miquel, M., Tissot, P., and Medrano, A. (2024, January 28th - February 1). Performance and Comparison of Seq2Seq and Transformer Model Architectures for the Prediction of Water Levels from Hours to Days [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Kastl, M. A., Tissot, F., Nguyen, S., King, S. A., and Tissot, P. E. (2024, January 28th - February 1). Semi-Automating Research-to-Operation of AI Models with Python [Oral presentation]. The 14th Conference on Transition of Research to Operation of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Colburn, K. F. A., Vicens-Miquel, M., and Tissot, P. E. (2024, January 28 - February 1). The Use of Oblique Imagery and Ground Elevation Surveys to Generate a Time Series of Wet/Dry Shoreline Elevations [Poster presentation]. The 22nd Symposium on the Coastal Environment of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Collins, W. G., Colburn, B., Tissot, P. E., King, A., Krell, E., and Williams, J. K. (2024, January 28 - February 1). The Utility of Domain Knowledge When Developing Deep Learning Models to Predict Coastal Fog [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Nguyen, C. T., Krell, E. A., Nachamkin, J. Peterson, D. A., Hyer, E. J., Tissot, P. E., King, S. A., Estrada Jr, B., and Tory, K. J. (2024, January 28 - February 1). Toward Prediction of Pyrocumulonimbus with Machine Learning [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    White, M., Vicens-Miquel, M., Marrero, H., Tissot, P. E., Woodall, J., Duff, C., and Colburn, B. (2024, January 28 - February 1). Uncertainty Quantifications of the Onset and Offset of Cold-Stunning Events Using AI Ensemble Methods [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Krell, E. A., Kamangir, H., Collins, W. G., King, S. A., and Tissot, P. (2024, January 28 - February 1). Using Grouped Features to Improve Explainable AI Results for Atmospheric AI Models that use Gridded Spatial Data and Complex Machine Learning Techniques [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

    Tissot, P. E. (2024, January 28 - February 1). An Update on Coastal Artificial Intelligence and the AI2ES NSF AI Institute [Oral presentation]. The 23rd Conference on Artificial Intelligence for Environmental Science of the Annual American Meteorological Society Annual Meeting, Baltimore, MD, United States.

Presentations

Generation of Coastal Area DEM’s Using Oblique Stereo Imagery from Non-Metric Cameras with SfM Techniques

Mona Hajiesmaeeli

  • Generating a precise Digital Elevation Model (DEM) is crucial for coastal inundation predictions, as it provides essential elevation data necessary for accurate modeling of potential flooding. Coastal inundation predictions are important to anticipate and mitigate the impacts of rising sea levels, tropical storms, and other extreme weather events. This study focuses on an approach of generating DEMs using highly oblique stereo images coupled with non-metric cameras. These images are part of a time series captured at the beach located next to Horace Caldwell pier in Port Aransas, Texas. To do so, a pair of non-metric cameras, Amcrest Ultra4K, were mounted on the corners of an elevated building located at the entrance of the pier and overlooking the beach, and often overlapping with water runup on the beach. The cameras are about 8m above sand and the distance between them is ~20m, with a viewing angle of ~60 degrees from nadir. Generating highly accurate DEMs from oblique imagery is challenging since most software and equations are intended for vertical imagery. Structure from Motion (SFM) provides users with an accessible and efficient approach for generating three-dimensional models from images. However, challenges and limitations persist when utilizing stereo highly oblique images, particularly those captured with non-metric cameras. Overcoming these challenges would provide advantages such as simplified data acquisition, cost effectiveness, and flexibility in capturing diverse angles compared to conventional photogrammetry. The proposed approach enables efficient and accurate elevation assessment in a dynamic coastal environment through applying a series of calibration and image processing techniques including wavelet transformation, rectification, georeferencing the highly oblique images, and using SFM approach for creating the three-dimensional point cloud. In this study, to enhance feature matching, we employed a wavelet transformation to identify high-frequency features in vertical, horizontal, and diagonal directions. Subsequently, we incorporated these resultant images into the original image, effectively augmenting the sharpness of the initial image. In order to achieve a more precise DEM from highly oblique images, it is imperative to generate an orthoimage that undergoes a process of warping the source image. This transformation ensures consistent distance and area proportions in relation to real-world measurements. To accomplish this, the present study employed rectification within the MATLAB environment, while the georeferencing was executed using projective transformation within ArcGIS Pro software. To evaluate its vertical accuracy, the created DEM was compared with 14 RTK-GPS check point observations collected biweekly on the beach. The check points locations were measured using terrestrial surveying based on a 5´5 meter grid, and were compared with the DEM generated by structure from motion (SFM). The obtained vertical Root Mean Square Error (RMSE) using this process was approximately 0.21m.

Utilizing Neural Networks to Predict Water Temperatures in a Thermal Refuge

Andrew DeSimone, Anointiyae Beasley