Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay
Abstract A high‐resolution wave model is crucial for accurate modeling of sediment and organic material transports, but its computational costs hinder direct coupling to an ecosystem model. We developed a machine learning model using long short‐term memory to simulate large‐scale, high‐resolution wa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2024-03-01
|
| Series: | Earth and Space Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023EA003303 |
| _version_ | 1827290273918484480 |
|---|---|
| author | Jian Shen Zhengui Wang Jiabi Du Yinglong J. Zhang Qubin Qin |
| author_facet | Jian Shen Zhengui Wang Jiabi Du Yinglong J. Zhang Qubin Qin |
| author_sort | Jian Shen |
| collection | DOAJ |
| description | Abstract A high‐resolution wave model is crucial for accurate modeling of sediment and organic material transports, but its computational costs hinder direct coupling to an ecosystem model. We developed a machine learning model using long short‐term memory to simulate large‐scale, high‐resolution waves. Trained with numerical wave model (NWM) outputs and wind data from nine locations, our model successfully replicates NWM results for daily mean significant wave height and period in Chesapeake Bay with identical spatial resolution. Compared to the NWM, the data‐driven model has root‐mean‐square errors below 6 cm for daily mean significant wave height and 1 s for the wave period in the bay. It demonstrates excellent model skills and can accurately forecast daily mean significant wave height and period at NOAA wave stations comparable to NWMs. Using minimal wind data and having a short runtime, our data‐driven model shows promise as an alternative for wave forecasting and coupling with sediment and ecological models. |
| first_indexed | 2024-04-24T12:13:44Z |
| format | Article |
| id | doaj.art-8b6f21a1e40e4349a9cdb09f12e2f412 |
| institution | Directory Open Access Journal |
| issn | 2333-5084 |
| language | English |
| last_indexed | 2024-04-24T12:13:44Z |
| publishDate | 2024-03-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Earth and Space Science |
| spelling | doaj.art-8b6f21a1e40e4349a9cdb09f12e2f4122024-04-08T08:47:01ZengAmerican Geophysical Union (AGU)Earth and Space Science2333-50842024-03-01113n/an/a10.1029/2023EA003303Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake BayJian Shen0Zhengui Wang1Jiabi Du2Yinglong J. Zhang3Qubin Qin4Viginia Institute of Marine Science, William & Mary Gloucester Point VA USAViginia Institute of Marine Science, William & Mary Gloucester Point VA USADepartment of Marine and Coastal Environmental Science Texas A&M University at Galveston Texas TX USAViginia Institute of Marine Science, William & Mary Gloucester Point VA USADepartment of Coastal Studies East Carolina University Wanchese NC USAAbstract A high‐resolution wave model is crucial for accurate modeling of sediment and organic material transports, but its computational costs hinder direct coupling to an ecosystem model. We developed a machine learning model using long short‐term memory to simulate large‐scale, high‐resolution waves. Trained with numerical wave model (NWM) outputs and wind data from nine locations, our model successfully replicates NWM results for daily mean significant wave height and period in Chesapeake Bay with identical spatial resolution. Compared to the NWM, the data‐driven model has root‐mean‐square errors below 6 cm for daily mean significant wave height and 1 s for the wave period in the bay. It demonstrates excellent model skills and can accurately forecast daily mean significant wave height and period at NOAA wave stations comparable to NWMs. Using minimal wind data and having a short runtime, our data‐driven model shows promise as an alternative for wave forecasting and coupling with sediment and ecological models.https://doi.org/10.1029/2023EA003303wavemachine learningdata‐driven modelSCHISMChesapeake Bay |
| spellingShingle | Jian Shen Zhengui Wang Jiabi Du Yinglong J. Zhang Qubin Qin Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay Earth and Space Science wave machine learning data‐driven model SCHISM Chesapeake Bay |
| title | Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay |
| title_full | Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay |
| title_fullStr | Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay |
| title_full_unstemmed | Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay |
| title_short | Machine Learning‐Based Wave Model With High Spatial Resolution in Chesapeake Bay |
| title_sort | machine learning based wave model with high spatial resolution in chesapeake bay |
| topic | wave machine learning data‐driven model SCHISM Chesapeake Bay |
| url | https://doi.org/10.1029/2023EA003303 |
| work_keys_str_mv | AT jianshen machinelearningbasedwavemodelwithhighspatialresolutioninchesapeakebay AT zhenguiwang machinelearningbasedwavemodelwithhighspatialresolutioninchesapeakebay AT jiabidu machinelearningbasedwavemodelwithhighspatialresolutioninchesapeakebay AT yinglongjzhang machinelearningbasedwavemodelwithhighspatialresolutioninchesapeakebay AT qubinqin machinelearningbasedwavemodelwithhighspatialresolutioninchesapeakebay |