COastal MOrphodynamics and Machine LeArning: Building an Inclusive International Network of Scientists

This global initiative aims to establish an international network of scientists passionate about coastal processes and the application of machine learning techniques. The objective is to foster knowledge exchange, collaboration, and innovation in understanding and predicting coastal processes using cutting-edge data-driven approaches. By organizing online seminars, researchers from around the world can share their expertise, present their findings, and engage in interdisciplinary discussions. This network seeks to be inclusive, welcoming scientists from diverse backgrounds and expertise levels, ensuring a broad range of perspectives. Through this collaborative platform, participants can forge connections, build partnerships, and collectively contribute to addressing the challenges of coastal morphodynamics. By exploring the power of machine learning and promoting open collaboration, this network strives to enhance predictive capability, advance knowledge and promote novel modelling strategies.  

COMO MoLA was initiated by Kristen Splinter (University of New South Wales), Harshinie Karunarathna (Swansea University), Daniel Buscombe (USGS), Evan Goldstein (UNC Greensboro), Nadia Senechal (University of Bordeaux), Sean Vitousek (USGS) and Giovanni Coco (University of Auckland).

Since this is a global network, the zoominars will happen at the speaker’s preferred time with the recording posted on this page asap. 

Join in using the form at the bottom of this page   

• Naeini, S.S. and Snaiki, R., 2024. A novel hybrid machine learning model for rapid assessment of wave and storm surge responses over an extended coastal region. Coastal Engineering, 190, p.104503.
• Naeini, S.S. and Snaiki, R., 2024. A physics-informed machine learning model for time-dependent wave runup prediction. Ocean Engineering, 295, p.116986.
• Naeini, S.S., Snaiki, R. and Wu, T., 2024. Advancing Spatio-temporal Storm Surge Prediction with Hierarchical Deep Neural Networks. arXiv preprint arXiv:2410.12823.

• Thilakarathne S, Suzuki T, Mäll M.  Machine learning-driven approach to quantify the beach susceptibility to  storm-induced erosion. Coastal Engineering Journal. 2024 Apr  2;66(2):216-33.
• Thilakarathne, S., Suzuki, T., Mäll,  M. and Banno, M., 2024. Identifying key morphometrics to post-storm  beach recovery through explainable AI. Scientific Reports, 14(1), p.14261.
• Thilakarathne, S., Suzuki, T. and  Mäll, M., 2023. Applying artificial neural networks for predicting beach  vulnerability to storm-induced erosion. Journal of JSCE, 11(2), pp.23-18101.

•  Kumar, Pavitra, and Nicoletta Leonardi. "Exploring mega‐nourishment interventions using Long Short‐Term Memory (LSTM) models and the sand engine surface MATLAB framework." Geophysical Research Letters 51, no. 4 (2024): e2023GL106042.
• Kumar, P. and Leonardi, N., 2023. Coastal forecast through coupling of Artificial Intelligence and hydro-morphodynamical modelling. Coastal Engineering Journal, 65(3), pp.450-469.
• Kumar, P. and Leonardi, N., 2023. A novel framework for the evaluation of coastal protection schemes through integration of numerical modelling and artificial intelligence into the Sand Engine App. Scientific Reports, 13(1), p.8610.

• Kang, B., Feagin, R.A., Huff, T. and  Durán Vinent, O., 2024. Stochastic properties of coastal flooding  events–Part 1: convolutional-neural-network-based semantic segmentation  for water detection. Earth Surface Dynamics, 12(1), pp.1-10.

• Kang, B., Feagin, R.A., Huff, T. and  Durán Vinent, O., 2024. Stochastic properties of coastal flooding  events–Part 2: Probabilistic analysis. Earth Surface Dynamics, 12(1), pp.105-115.

• Kang, B. and Duran Vinent, O., 2023.  The Application of CNN-Based Image Segmentation for Tracking Coastal  Erosion and Post-Storm Recovery. Remote Sensing, 15(14), p.3485.

• Thompson, M., Zelich, I., Watterson,  E. and Baldock, T.E., 2021. Wave peel tracking: A new approach for  assessing surf amenity and analysis of breaking waves. Remote Sensing, 13(17), p.3372.
• Thompson, M.E., Atkinson, A.,  Watterson, E., Naderi, N., Loehr, H. and Baldock, T.E., 2023. A camera  based method for assessing surf amenity of submerged nearshore  structures in a wave basin by quantifying wave breaking. Ocean Engineering, 286, p.115606.
• Codes can be found at https://github.com/mikeyt120/

• Karunarathna, H. and Reeve, D.E. (2013) A hybrid approach to model shoreline change at multiple timescales, Continental Shelf Research. 66, pp.29-35. doi.org/10.1016/j.csr.2013.06.019.
• Horrillo-Caraballo and Reeve, 2010, An investigation of the performance of a data-driven model on sand and shingle beaches, Coastal Engineering, DOI:10.1111/j.1753-318X.2008.00013.x 
• Ions et al., Gaussian Process Regression Approach for Predicting Wave Attenuation Through Rigid Vegetation, Applied Ocean Research (in press) https://nhess.copernicus.org/articles/19/2295/2019/

• Warrick, J.A., Stevens, A.W., Miller, I.M., Harrison, S.R., Ritchie, A.C. and Gelfenbaum, G., 2019. World’s largest dam removal reverses coastal erosion. Scientific Reports, 9(1), p.13968.
• Buscombe, D. and Goldstein, E.B., 2022. A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9(9), p.e2022EA002332.
• Buscombe, D., Warrick, J.A., Ritchie, A., East, A., McHenry, M., McCoy, R., Foxgrover, A. (2024, in review). Remote sensing large-wood storage downstream of reservoirs during and after dam removal: Elwha River, Washington, USA. Earth and Space Science.

• Gomez-de la Peña, E., Coco, G., Whittaker, C. and Montano, J., 2023. On the use of Convolutional Deep Learning to predict shoreline change. Earth Surface Dynamics, 11, 1145–1160, https://doi.org/10.5194/esurf-11-1145-2023  
• Goldstein, E. B., Coco, G., & Plant, N. G. (2019). A review of machine learning applications to coastal sediment transport and morphodynamics. Earth-Science Reviews, doi.org/10.1016/j.earscirev.2019.04.022

Please click on the link below to receive and email about upcoming COMO MoLA zoominars. 

You can also use the form to let us know if you want to give a talk!

 https://forms.office.com/Pages/ResponsePage.aspx?id=pM_2PxXn20i44Qhnufn7o0iD4P5C4N5PvHxDzB0QgAdUREFWOTQzS0VMUUkwMTJJVzE1RkgyWFhEUy4u