Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment
Coastal dissolved oxygen (DO) concentrations have a profound impact on nearshore ecosystems and, in recent years, there has been an increased prevalance of low DO hypoxic events that negatively impact nearshore organisms. Even with advanced numerical models, accurate prediction of coastal DO variabi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/8/12/1007 |
| _version_ | 1797545217599995904 |
|---|---|
| author | Manuel Valera Ryan K. Walter Barbara A. Bailey Jose E. Castillo |
| author_facet | Manuel Valera Ryan K. Walter Barbara A. Bailey Jose E. Castillo |
| author_sort | Manuel Valera |
| collection | DOAJ |
| description | Coastal dissolved oxygen (DO) concentrations have a profound impact on nearshore ecosystems and, in recent years, there has been an increased prevalance of low DO hypoxic events that negatively impact nearshore organisms. Even with advanced numerical models, accurate prediction of coastal DO variability is challenging and computationally expensive. Here, we apply machine learning techniques in order to reconstruct and predict nearshore DO concentrations in a small coastal embayment while using a comprehensive set of nearshore and offshore measurements and easily measured input (training) parameters. We show that both random forest regression (RFR) and support vector regression (SVR) models accurately reproduce both the offshore DO and nearshore DO with extremely high accuracy. In general, RFR consistently peformed slightly better than SVR, the latter of which was more difficult to tune and took longer to train. Although each of the nearshore datasets were able to accurately predict DO values using training data from the same site, the model only had moderate success when using training data from one site to predict DO at another site, which was likely due to the the complexities in the underlying dynamics across the sites. We also show that high accuracy can be achieved with relatively little training data, highlighting a potential application for correcting time series with missing DO data due to quality control or sensor issues. This work establishes the ability of machine learning models to accurately reproduce DO concentrations in both offshore and nearshore coastal waters, with important implications for the ability to detect and indirectly measure coastal hypoxic events in near real-time. Future work should explore the ability of machine learning models in order to accurately forecast hypoxic events. |
| first_indexed | 2024-03-10T14:12:21Z |
| format | Article |
| id | doaj.art-131948083b4b451387c60ec23e72a146 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T14:12:21Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-131948083b4b451387c60ec23e72a1462023-11-21T00:01:12ZengMDPI AGJournal of Marine Science and Engineering2077-13122020-12-01812100710.3390/jmse8121007Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal EmbaymentManuel Valera0Ryan K. Walter1Barbara A. Bailey2Jose E. Castillo3Computational Science Research Center, San Diego State University, San Diego, CA 92182, USAPhysics Department, California Polytechnic State University, San Luis Obispo, CA 93407, USAComputational Science Research Center, San Diego State University, San Diego, CA 92182, USAComputational Science Research Center, San Diego State University, San Diego, CA 92182, USACoastal dissolved oxygen (DO) concentrations have a profound impact on nearshore ecosystems and, in recent years, there has been an increased prevalance of low DO hypoxic events that negatively impact nearshore organisms. Even with advanced numerical models, accurate prediction of coastal DO variability is challenging and computationally expensive. Here, we apply machine learning techniques in order to reconstruct and predict nearshore DO concentrations in a small coastal embayment while using a comprehensive set of nearshore and offshore measurements and easily measured input (training) parameters. We show that both random forest regression (RFR) and support vector regression (SVR) models accurately reproduce both the offshore DO and nearshore DO with extremely high accuracy. In general, RFR consistently peformed slightly better than SVR, the latter of which was more difficult to tune and took longer to train. Although each of the nearshore datasets were able to accurately predict DO values using training data from the same site, the model only had moderate success when using training data from one site to predict DO at another site, which was likely due to the the complexities in the underlying dynamics across the sites. We also show that high accuracy can be achieved with relatively little training data, highlighting a potential application for correcting time series with missing DO data due to quality control or sensor issues. This work establishes the ability of machine learning models to accurately reproduce DO concentrations in both offshore and nearshore coastal waters, with important implications for the ability to detect and indirectly measure coastal hypoxic events in near real-time. Future work should explore the ability of machine learning models in order to accurately forecast hypoxic events.https://www.mdpi.com/2077-1312/8/12/1007dissolved oxygenrandom forestsupport vector machinemachine learning regressionhypoxia |
| spellingShingle | Manuel Valera Ryan K. Walter Barbara A. Bailey Jose E. Castillo Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment Journal of Marine Science and Engineering dissolved oxygen random forest support vector machine machine learning regression hypoxia |
| title | Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment |
| title_full | Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment |
| title_fullStr | Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment |
| title_full_unstemmed | Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment |
| title_short | Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment |
| title_sort | machine learning based predictions of dissolved oxygen in a small coastal embayment |
| topic | dissolved oxygen random forest support vector machine machine learning regression hypoxia |
| url | https://www.mdpi.com/2077-1312/8/12/1007 |
| work_keys_str_mv | AT manuelvalera machinelearningbasedpredictionsofdissolvedoxygeninasmallcoastalembayment AT ryankwalter machinelearningbasedpredictionsofdissolvedoxygeninasmallcoastalembayment AT barbaraabailey machinelearningbasedpredictionsofdissolvedoxygeninasmallcoastalembayment AT joseecastillo machinelearningbasedpredictionsofdissolvedoxygeninasmallcoastalembayment |