Summary of A Comparative Study Of Convolutional and Recurrent Neural Networks For Storm Surge Prediction in Tampa Bay, by Mandana Farhang Ghahfarokhi et al.
A Comparative Study of Convolutional and Recurrent Neural Networks for Storm Surge Prediction in Tampa Bay
by Mandana Farhang Ghahfarokhi, Seyed Hossein Sonbolestan, Mahta Zamanizadeh
First submitted to arxiv on: 11 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Atmospheric and Oceanic Physics (physics.ao-ph)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper compares three deep learning architectures (CNN-LSTM, LSTM, and 3D-CNN) for surrogate storm surge modeling in the Tampa Bay area. It trains and tests these models using high-resolution atmospheric data and historical water level data to evaluate their performance. The results show that CNN-LSTM outperforms the others with a test loss of 0.010 and an R-squared score of 0.84. LSTM achieved lower training losses but poorer generalization, while 3D-CNN showed reasonable performance but instability under extreme conditions. A case study on Hurricane Ian highlights the robustness and accuracy of CNN-LSTM in extreme scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper compares three deep learning models to predict storm surges in Tampa Bay. It uses special data from the atmosphere and water levels to test these models. The results show that one model is better than the others at predicting surges. This model is good at both training and testing, which means it’s reliable. Another model did well during training but not as well during testing. A third model was okay but had problems with extreme weather conditions. The paper also uses a real hurricane example to show that this best-performing model works well even in severe situations. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Generalization » Lstm
