Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy
Using the global climate model outputs without any adjustment may bring errors in water resources and climate change investigations. This study tackles the critical issue of bias correction temperature in ERA5-Land reanalysis for 10 ground stations in northern Italy using nine machine learning (ML)...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2024-01-01
|
| Series: | Journal of Water and Climate Change |
| Subjects: | |
| Online Access: | http://jwcc.iwaponline.com/content/15/1/271 |
| _version_ | 1797202719950241792 |
|---|---|
| author | Majid Niazkar Reza Piraei Andrea Menapace Pranav Dhawan Daniele Dalla Torre Michele Larcher Maurizio Righetti |
| author_facet | Majid Niazkar Reza Piraei Andrea Menapace Pranav Dhawan Daniele Dalla Torre Michele Larcher Maurizio Righetti |
| author_sort | Majid Niazkar |
| collection | DOAJ |
| description | Using the global climate model outputs without any adjustment may bring errors in water resources and climate change investigations. This study tackles the critical issue of bias correction temperature in ERA5-Land reanalysis for 10 ground stations in northern Italy using nine machine learning (ML) techniques. Among standalone ML models, XGBoost regression emerged as the most effective standalone ML model, outperforming others across 6 out of 10 stations, while random forest regression, Gaussian process regression, and support vector regression obtained the second to fourth places. In contrast, AdaBoost regression (ABR) achieved the least favorable performance. Furthermore, nine ensemble ML models are proposed to correct bias of the reanalysis of temperature data. The results indicated that the K-nearest neighbors-based ensemble model excelled and secured the top rank in 7 out of 10 stations, while the multiple linear regression-based ensemble model achieved the highest precision in 4 out of 10 stations. Furthermore, other ML-based ensemble models displayed satisfactory results. On the other hand, the ABR-based ensemble model exhibited the lowest accuracy among ML-based ensemble models. The findings highlight the potential of ML-based ensemble models in effectively addressing bias correction in climate data.
HIGHLIGHTS
Proposing nine ensemble ML models for bias correction.;
Introducing nine standalone ML models for bias correction.;
Correcting temperature data of ERA5-Land for a case study in northern Italy.;
Comparison of different ML-based models for bias correction.;
Correcting data of climate data can enhance studying climate change impact assessment.; |
| first_indexed | 2024-03-08T03:17:21Z |
| format | Article |
| id | doaj.art-12f3bba05a06422296f267179b4d9ee6 |
| institution | Directory Open Access Journal |
| issn | 2040-2244 2408-9354 |
| language | English |
| last_indexed | 2024-04-24T08:07:55Z |
| publishDate | 2024-01-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Journal of Water and Climate Change |
| spelling | doaj.art-12f3bba05a06422296f267179b4d9ee62024-04-17T08:44:02ZengIWA PublishingJournal of Water and Climate Change2040-22442408-93542024-01-0115127128310.2166/wcc.2023.669669Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern ItalyMajid Niazkar0Reza Piraei1Andrea Menapace2Pranav Dhawan3Daniele Dalla Torre4Michele Larcher5Maurizio Righetti6 Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Department of Civil Engineering, Shiraz University, 7134851156 Shiraz, Iran Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, Italy Using the global climate model outputs without any adjustment may bring errors in water resources and climate change investigations. This study tackles the critical issue of bias correction temperature in ERA5-Land reanalysis for 10 ground stations in northern Italy using nine machine learning (ML) techniques. Among standalone ML models, XGBoost regression emerged as the most effective standalone ML model, outperforming others across 6 out of 10 stations, while random forest regression, Gaussian process regression, and support vector regression obtained the second to fourth places. In contrast, AdaBoost regression (ABR) achieved the least favorable performance. Furthermore, nine ensemble ML models are proposed to correct bias of the reanalysis of temperature data. The results indicated that the K-nearest neighbors-based ensemble model excelled and secured the top rank in 7 out of 10 stations, while the multiple linear regression-based ensemble model achieved the highest precision in 4 out of 10 stations. Furthermore, other ML-based ensemble models displayed satisfactory results. On the other hand, the ABR-based ensemble model exhibited the lowest accuracy among ML-based ensemble models. The findings highlight the potential of ML-based ensemble models in effectively addressing bias correction in climate data. HIGHLIGHTS Proposing nine ensemble ML models for bias correction.; Introducing nine standalone ML models for bias correction.; Correcting temperature data of ERA5-Land for a case study in northern Italy.; Comparison of different ML-based models for bias correction.; Correcting data of climate data can enhance studying climate change impact assessment.;http://jwcc.iwaponline.com/content/15/1/271bias correctionensemble modelera5-landmachine learningxgboost |
| spellingShingle | Majid Niazkar Reza Piraei Andrea Menapace Pranav Dhawan Daniele Dalla Torre Michele Larcher Maurizio Righetti Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy Journal of Water and Climate Change bias correction ensemble model era5-land machine learning xgboost |
| title | Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy |
| title_full | Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy |
| title_fullStr | Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy |
| title_full_unstemmed | Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy |
| title_short | Bias correction of ERA5-Land temperature data using standalone and ensemble machine learning models: a case of northern Italy |
| title_sort | bias correction of era5 land temperature data using standalone and ensemble machine learning models a case of northern italy |
| topic | bias correction ensemble model era5-land machine learning xgboost |
| url | http://jwcc.iwaponline.com/content/15/1/271 |
| work_keys_str_mv | AT majidniazkar biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT rezapiraei biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT andreamenapace biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT pranavdhawan biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT danieledallatorre biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT michelelarcher biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly AT mauriziorighetti biascorrectionofera5landtemperaturedatausingstandaloneandensemblemachinelearningmodelsacaseofnorthernitaly |