Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment
Tide tables are the method of choice for water level predictions in most coastal regions. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet United States National Ocean Service (NOS) standards. Wind forcing has been recognized as the main variable not include...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad de Costa Rica
2012-03-01
|
| Series: | Revista de Matemática: Teoría y Aplicaciones |
| Online Access: | https://revistas.ucr.ac.cr/index.php/matematica/article/view/258 |
| _version_ | 1797763080759803904 |
|---|---|
| author | Zack Bowles Philippe E. Tissot Tissot Patrick Michaud Alexey Sadovski |
| author_facet | Zack Bowles Philippe E. Tissot Tissot Patrick Michaud Alexey Sadovski |
| author_sort | Zack Bowles |
| collection | DOAJ |
| description | Tide tables are the method of choice for water level predictions in most coastal regions. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet United States National Ocean Service (NOS) standards. Wind forcing has been recognized as the main variable not included. The performance of the tide tables is particularly poor in shallow embayments. Recent research has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric
pressure can greatly improve over the tide charts for locations including open coast and deep embayments. In this paper, the ANN modeling technique is applied to a shallow embayment, the station of Rockport, located near Corpus Christi, Texas. The ANN model performance is compared against the NOS tide charts and the persistence model for the years 1997 to 2001. The performance is assessed using NOS criteria including Central Frequency (CF of 15 cm), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). Over the study period, the performances of the three models (tide table, persistence, ANN) are respectively CF’s of 85%, 95.8% and 96.9%, MDPOs of 16, 14 and 5.9 hours, and MDNOs of 72.8 hours, 0.6 and 9.5 hours. |
| first_indexed | 2024-03-12T19:36:27Z |
| format | Article |
| id | doaj.art-6882e0136ce04167b4f9e513d3de16b3 |
| institution | Directory Open Access Journal |
| issn | 2215-3373 |
| language | English |
| last_indexed | 2024-03-12T19:36:27Z |
| publishDate | 2012-03-01 |
| publisher | Universidad de Costa Rica |
| record_format | Article |
| series | Revista de Matemática: Teoría y Aplicaciones |
| spelling | doaj.art-6882e0136ce04167b4f9e513d3de16b32023-08-02T04:07:17ZengUniversidad de Costa RicaRevista de Matemática: Teoría y Aplicaciones2215-33732012-03-01121-213915010.15517/rmta.v12i1-2.258243Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow EmbaymentZack Bowles0Philippe E. Tissot Tissot1Patrick Michaud2Alexey Sadovski3Texas A& M University-Corpus Christi, Division of Nearshore ResearchTexas A& M University-Corpus Christi, Division of Nearshore ResearchTexas A& M University-Corpus Christi, Division of Nearshore ResearchTexas A& M University, Department of Computing and Mathematical SciencesTide tables are the method of choice for water level predictions in most coastal regions. However, for many locations along the coast of the Gulf of Mexico, tide tables do not meet United States National Ocean Service (NOS) standards. Wind forcing has been recognized as the main variable not included. The performance of the tide tables is particularly poor in shallow embayments. Recent research has shown that Artificial Neural Network (ANN) models including input variables such as previous water levels, tidal forecasts, wind speed, wind direction, wind forecasts and barometric pressure can greatly improve over the tide charts for locations including open coast and deep embayments. In this paper, the ANN modeling technique is applied to a shallow embayment, the station of Rockport, located near Corpus Christi, Texas. The ANN model performance is compared against the NOS tide charts and the persistence model for the years 1997 to 2001. The performance is assessed using NOS criteria including Central Frequency (CF of 15 cm), Maximum Duration of Positive Outliers (MDPO), and Maximum Duration of Negative Outliers (MDNO). Over the study period, the performances of the three models (tide table, persistence, ANN) are respectively CF’s of 85%, 95.8% and 96.9%, MDPOs of 16, 14 and 5.9 hours, and MDNOs of 72.8 hours, 0.6 and 9.5 hours.https://revistas.ucr.ac.cr/index.php/matematica/article/view/258 |
| spellingShingle | Zack Bowles Philippe E. Tissot Tissot Patrick Michaud Alexey Sadovski Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment Revista de Matemática: Teoría y Aplicaciones |
| title | Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment |
| title_full | Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment |
| title_fullStr | Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment |
| title_full_unstemmed | Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment |
| title_short | Artificial Neural Network Predictions of Water Levels in a Gulf of Mexico Shallow Embayment |
| title_sort | artificial neural network predictions of water levels in a gulf of mexico shallow embayment |
| url | https://revistas.ucr.ac.cr/index.php/matematica/article/view/258 |
| work_keys_str_mv | AT zackbowles artificialneuralnetworkpredictionsofwaterlevelsinagulfofmexicoshallowembayment AT philippeetissottissot artificialneuralnetworkpredictionsofwaterlevelsinagulfofmexicoshallowembayment AT patrickmichaud artificialneuralnetworkpredictionsofwaterlevelsinagulfofmexicoshallowembayment AT alexeysadovski artificialneuralnetworkpredictionsofwaterlevelsinagulfofmexicoshallowembayment |