A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections
A new machine learning based bias correction method is presented and applied to sea level in a regional climate model. The bias corrections derived using this method depend on the state of the model it corrects. This contrasts with conventional bias correction methods that operate on distributions o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stockholm University Press
2023-02-01
|
| Series: | Tellus: Series A, Dynamic Meteorology and Oceanography |
| Subjects: | |
| Online Access: | https://account.a.tellusjournals.se/index.php/up/article/view/3216 |
| _version_ | 1797867999925895168 |
|---|---|
| author | Magnus Hieronymus Fredrik Hieronymus |
| author_facet | Magnus Hieronymus Fredrik Hieronymus |
| author_sort | Magnus Hieronymus |
| collection | DOAJ |
| description | A new machine learning based bias correction method is presented and applied to sea level in a regional climate model. The bias corrections derived using this method depend on the state of the model it corrects. This contrasts with conventional bias correction methods that operate on distributions of output variables. The dependence on model states allows for better performance on classical skill scores, but it also limits the applicability of the method to models that can perform hindcasts. A very large dataset of corrected hourly sea levels from many different emission scenarios is created. In total the dataset contains over 2600 model years and exists for seven different tide-gauge stations on the Swedish Baltic Sea coast. The prevalence of significant trends in yearly sea level maximum is found to be independent of emission scenario, suggesting that anthropogenic climate change is no significant driver of storm surge variability in the area. Lastly, the dataset is used to estimate return levels for very long return periods, and the block length used in the return level computation is found to affect the result at some stations. This suggests that the commonly used annual maximum approach is not always applicable for determining return levels for sea level. |
| first_indexed | 2024-04-09T23:49:08Z |
| format | Article |
| id | doaj.art-63fdfa19d87a47448a34485ee9f870f5 |
| institution | Directory Open Access Journal |
| issn | 1600-0870 |
| language | English |
| last_indexed | 2024-04-09T23:49:08Z |
| publishDate | 2023-02-01 |
| publisher | Stockholm University Press |
| record_format | Article |
| series | Tellus: Series A, Dynamic Meteorology and Oceanography |
| spelling | doaj.art-63fdfa19d87a47448a34485ee9f870f52023-03-17T13:06:36ZengStockholm University PressTellus: Series A, Dynamic Meteorology and Oceanography1600-08702023-02-01751129–144129–14410.16993/tellusa.32162665A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate ProjectionsMagnus Hieronymus0https://orcid.org/0000-0002-0786-7438Fredrik Hieronymus1https://orcid.org/0000-0003-0930-6068Swedish meteorological and hydrological institute, NorrköpingInstitute of Neuroscience and Physiology, University of GothenburgA new machine learning based bias correction method is presented and applied to sea level in a regional climate model. The bias corrections derived using this method depend on the state of the model it corrects. This contrasts with conventional bias correction methods that operate on distributions of output variables. The dependence on model states allows for better performance on classical skill scores, but it also limits the applicability of the method to models that can perform hindcasts. A very large dataset of corrected hourly sea levels from many different emission scenarios is created. In total the dataset contains over 2600 model years and exists for seven different tide-gauge stations on the Swedish Baltic Sea coast. The prevalence of significant trends in yearly sea level maximum is found to be independent of emission scenario, suggesting that anthropogenic climate change is no significant driver of storm surge variability in the area. Lastly, the dataset is used to estimate return levels for very long return periods, and the block length used in the return level computation is found to affect the result at some stations. This suggests that the commonly used annual maximum approach is not always applicable for determining return levels for sea level.https://account.a.tellusjournals.se/index.php/up/article/view/3216bias correctionsextreme sea levelsneural networkmachine learning |
| spellingShingle | Magnus Hieronymus Fredrik Hieronymus A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections Tellus: Series A, Dynamic Meteorology and Oceanography bias corrections extreme sea levels neural network machine learning |
| title | A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections |
| title_full | A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections |
| title_fullStr | A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections |
| title_full_unstemmed | A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections |
| title_short | A Novel Machine Learning Based Bias Correction Method and Its Application to Sea Level in an Ensemble of Downscaled Climate Projections |
| title_sort | novel machine learning based bias correction method and its application to sea level in an ensemble of downscaled climate projections |
| topic | bias corrections extreme sea levels neural network machine learning |
| url | https://account.a.tellusjournals.se/index.php/up/article/view/3216 |
| work_keys_str_mv | AT magnushieronymus anovelmachinelearningbasedbiascorrectionmethodanditsapplicationtosealevelinanensembleofdownscaledclimateprojections AT fredrikhieronymus anovelmachinelearningbasedbiascorrectionmethodanditsapplicationtosealevelinanensembleofdownscaledclimateprojections AT magnushieronymus novelmachinelearningbasedbiascorrectionmethodanditsapplicationtosealevelinanensembleofdownscaledclimateprojections AT fredrikhieronymus novelmachinelearningbasedbiascorrectionmethodanditsapplicationtosealevelinanensembleofdownscaledclimateprojections |