Application of neural networks and support vector machine for significant wave height prediction
For the purposes of planning and operation of maritime activities, information about wave height dynamics is of great importance. In the paper, real-time prediction of significant wave heights for the following 0.5–5.5 h is provided, using information from 3 or more time points. In the first stage,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2017-07-01
|
| Series: | Oceanologia |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0078323417300271 |
| _version_ | 1811342556187852800 |
|---|---|
| author | Jadran Berbić Eva Ocvirk Dalibor Carević Goran Lončar |
| author_facet | Jadran Berbić Eva Ocvirk Dalibor Carević Goran Lončar |
| author_sort | Jadran Berbić |
| collection | DOAJ |
| description | For the purposes of planning and operation of maritime activities, information about wave height dynamics is of great importance. In the paper, real-time prediction of significant wave heights for the following 0.5–5.5 h is provided, using information from 3 or more time points. In the first stage, predictions are made by varying the quantity of significant wave heights from previous time points and various ways of using data are discussed. Afterwards, in the best model, according to the criteria of practicality and accuracy, the influence of wind is taken into account. Predictions are made using two machine learning methods – artificial neural networks (ANN) and support vector machine (SVM). The models were built using the built-in functions of software Weka, developed by Waikato University, New Zealand. |
| first_indexed | 2024-04-13T19:12:52Z |
| format | Article |
| id | doaj.art-c186909a60ad4b8ca02efd41d79d2309 |
| institution | Directory Open Access Journal |
| issn | 0078-3234 |
| language | English |
| last_indexed | 2024-04-13T19:12:52Z |
| publishDate | 2017-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Oceanologia |
| spelling | doaj.art-c186909a60ad4b8ca02efd41d79d23092022-12-22T02:33:47ZengElsevierOceanologia0078-32342017-07-0159333134910.1016/j.oceano.2017.03.007Application of neural networks and support vector machine for significant wave height predictionJadran Berbić0Eva Ocvirk1Dalibor Carević2Goran Lončar3Croatian Hydrological and Meteorological Service, Zagreb, CroatiaThe Faculty of Civil Engineering, University of Zagreb, Zagreb, CroatiaThe Faculty of Civil Engineering, University of Zagreb, Zagreb, CroatiaThe Faculty of Civil Engineering, University of Zagreb, Zagreb, CroatiaFor the purposes of planning and operation of maritime activities, information about wave height dynamics is of great importance. In the paper, real-time prediction of significant wave heights for the following 0.5–5.5 h is provided, using information from 3 or more time points. In the first stage, predictions are made by varying the quantity of significant wave heights from previous time points and various ways of using data are discussed. Afterwards, in the best model, according to the criteria of practicality and accuracy, the influence of wind is taken into account. Predictions are made using two machine learning methods – artificial neural networks (ANN) and support vector machine (SVM). The models were built using the built-in functions of software Weka, developed by Waikato University, New Zealand.http://www.sciencedirect.com/science/article/pii/S0078323417300271Significant wave heightWave predictionMachine learningANNSVM |
| spellingShingle | Jadran Berbić Eva Ocvirk Dalibor Carević Goran Lončar Application of neural networks and support vector machine for significant wave height prediction Oceanologia Significant wave height Wave prediction Machine learning ANN SVM |
| title | Application of neural networks and support vector machine for significant wave height prediction |
| title_full | Application of neural networks and support vector machine for significant wave height prediction |
| title_fullStr | Application of neural networks and support vector machine for significant wave height prediction |
| title_full_unstemmed | Application of neural networks and support vector machine for significant wave height prediction |
| title_short | Application of neural networks and support vector machine for significant wave height prediction |
| title_sort | application of neural networks and support vector machine for significant wave height prediction |
| topic | Significant wave height Wave prediction Machine learning ANN SVM |
| url | http://www.sciencedirect.com/science/article/pii/S0078323417300271 |
| work_keys_str_mv | AT jadranberbic applicationofneuralnetworksandsupportvectormachineforsignificantwaveheightprediction AT evaocvirk applicationofneuralnetworksandsupportvectormachineforsignificantwaveheightprediction AT daliborcarevic applicationofneuralnetworksandsupportvectormachineforsignificantwaveheightprediction AT goranloncar applicationofneuralnetworksandsupportvectormachineforsignificantwaveheightprediction |