G. Lazoglou, Theo Economou, Christina Anagnostopoulou, G. Zittis, Anna Tzyrkalli, Pantelis Georgiades, J. Lelieveld
{"title":"在欧洲气候预测中利用机器学习对细雨偏差进行多变量调整","authors":"G. Lazoglou, Theo Economou, Christina Anagnostopoulou, G. Zittis, Anna Tzyrkalli, Pantelis Georgiades, J. Lelieveld","doi":"10.5194/gmd-17-4689-2024","DOIUrl":null,"url":null,"abstract":"Abstract. Precipitation holds significant importance as a climate parameter in various applications, including studies on the impacts of climate change. However, its simulation or projection accuracy is low, primarily due to its high stochasticity. Specifically, climate models often overestimate the frequency of light rainy days while simultaneously underestimating the total amounts of extreme observed precipitation. This phenomenon, known as “drizzle bias”, specifically refers to the model's tendency to overestimate the occurrence of light precipitation events. Consequently, even though the overall precipitation totals are generally well represented, there is often a significant bias in the number of rainy days. The present study aims to minimize the drizzle bias in model output by developing and applying two statistical approaches. In the first approach, the number of rainy days is adjusted based on the assumption that the relationship between observed and simulated rainy days remains the same in time (thresholding). In the second, a machine learning method (random forest or RF) is used for the development of a statistical model that describes the relationship between several climate (modelled) variables and the observed number of wet days. The results demonstrate that employing a multivariate approach yields results that are comparable to the conventional thresholding approach when correcting sub-periods with similar climate characteristics. However, the importance of utilizing RF becomes evident when addressing periods exhibiting extreme events, marked by a significantly distinct frequency of rainy days. These disparities are particularly pronounced when considering higher temporal resolutions. Both methods are illustrated on data from three EURO-CORDEX climate models. The two approaches are trained during a calibration period, and they are applied for the selected evaluation period.\n","PeriodicalId":12799,"journal":{"name":"Geoscientific Model Development","volume":null,"pages":null},"PeriodicalIF":4.0000,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multivariate adjustment of drizzle bias using machine learning in European climate projections\",\"authors\":\"G. Lazoglou, Theo Economou, Christina Anagnostopoulou, G. Zittis, Anna Tzyrkalli, Pantelis Georgiades, J. Lelieveld\",\"doi\":\"10.5194/gmd-17-4689-2024\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract. Precipitation holds significant importance as a climate parameter in various applications, including studies on the impacts of climate change. However, its simulation or projection accuracy is low, primarily due to its high stochasticity. Specifically, climate models often overestimate the frequency of light rainy days while simultaneously underestimating the total amounts of extreme observed precipitation. This phenomenon, known as “drizzle bias”, specifically refers to the model's tendency to overestimate the occurrence of light precipitation events. Consequently, even though the overall precipitation totals are generally well represented, there is often a significant bias in the number of rainy days. The present study aims to minimize the drizzle bias in model output by developing and applying two statistical approaches. In the first approach, the number of rainy days is adjusted based on the assumption that the relationship between observed and simulated rainy days remains the same in time (thresholding). In the second, a machine learning method (random forest or RF) is used for the development of a statistical model that describes the relationship between several climate (modelled) variables and the observed number of wet days. The results demonstrate that employing a multivariate approach yields results that are comparable to the conventional thresholding approach when correcting sub-periods with similar climate characteristics. However, the importance of utilizing RF becomes evident when addressing periods exhibiting extreme events, marked by a significantly distinct frequency of rainy days. These disparities are particularly pronounced when considering higher temporal resolutions. Both methods are illustrated on data from three EURO-CORDEX climate models. The two approaches are trained during a calibration period, and they are applied for the selected evaluation period.\\n\",\"PeriodicalId\":12799,\"journal\":{\"name\":\"Geoscientific Model Development\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2024-06-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geoscientific Model Development\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.5194/gmd-17-4689-2024\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geoscientific Model Development","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.5194/gmd-17-4689-2024","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
Multivariate adjustment of drizzle bias using machine learning in European climate projections
Abstract. Precipitation holds significant importance as a climate parameter in various applications, including studies on the impacts of climate change. However, its simulation or projection accuracy is low, primarily due to its high stochasticity. Specifically, climate models often overestimate the frequency of light rainy days while simultaneously underestimating the total amounts of extreme observed precipitation. This phenomenon, known as “drizzle bias”, specifically refers to the model's tendency to overestimate the occurrence of light precipitation events. Consequently, even though the overall precipitation totals are generally well represented, there is often a significant bias in the number of rainy days. The present study aims to minimize the drizzle bias in model output by developing and applying two statistical approaches. In the first approach, the number of rainy days is adjusted based on the assumption that the relationship between observed and simulated rainy days remains the same in time (thresholding). In the second, a machine learning method (random forest or RF) is used for the development of a statistical model that describes the relationship between several climate (modelled) variables and the observed number of wet days. The results demonstrate that employing a multivariate approach yields results that are comparable to the conventional thresholding approach when correcting sub-periods with similar climate characteristics. However, the importance of utilizing RF becomes evident when addressing periods exhibiting extreme events, marked by a significantly distinct frequency of rainy days. These disparities are particularly pronounced when considering higher temporal resolutions. Both methods are illustrated on data from three EURO-CORDEX climate models. The two approaches are trained during a calibration period, and they are applied for the selected evaluation period.
期刊介绍:
Geoscientific Model Development (GMD) is an international scientific journal dedicated to the publication and public discussion of the description, development, and evaluation of numerical models of the Earth system and its components. The following manuscript types can be considered for peer-reviewed publication:
* geoscientific model descriptions, from statistical models to box models to GCMs;
* development and technical papers, describing developments such as new parameterizations or technical aspects of running models such as the reproducibility of results;
* new methods for assessment of models, including work on developing new metrics for assessing model performance and novel ways of comparing model results with observational data;
* papers describing new standard experiments for assessing model performance or novel ways of comparing model results with observational data;
* model experiment descriptions, including experimental details and project protocols;
* full evaluations of previously published models.