Anass Houdou , Kenza Khomsi , Luca Delle Monache , Weiming Hu , Saber Boutayeb , Lahcen Belyamani , Fayez Abdulla , Imad el Badisy , Wael K. Al-Delaimy , Mohamed Khalis
{"title":"利用U-net加强摩洛哥5天颗粒物(PM10)预报:一种深度学习方法","authors":"Anass Houdou , Kenza Khomsi , Luca Delle Monache , Weiming Hu , Saber Boutayeb , Lahcen Belyamani , Fayez Abdulla , Imad el Badisy , Wael K. Al-Delaimy , Mohamed Khalis","doi":"10.1016/j.atmosres.2025.108439","DOIUrl":null,"url":null,"abstract":"<div><div>Accurately predicting particulate matter is crucial for preventing health risks and protecting public health. This study improves the accuracy of particulate matter <span><math><mi>d</mi><mo>≤</mo><mn>10</mn><mspace></mspace><mi>μm</mi></math></span> (<span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> <!-->) forecasts over Morocco for the next five days using a U-Net-based deep learning model, marking the first work of its kind in the Middle East and North Africa (MENA) region. The U-Net model was used to post-process and improve <span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> forecasts from the Copernicus Atmosphere Monitoring Service (CAMS), with reanalysis data from CAMS serving as a reference to guide the model's learning. The U-Net architecture was modified to predict outputs at a resolution different from the inputs, eliminating the need for interpolation and preserving critical spatial details. The results demonstrated significant improvements over two baselines—CAMS forecasts and the Analog Ensemble model (AnEn)—by enhancing metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (<span><math><msup><mi>R</mi><mn>2</mn></msup></math></span>), Index of Agreement (IOA), and biases, particularly in regions prone to dust storms, during the period prior to the CAMS forecast upgrade in mid-2023. In the second half of 2023, U-Net continued to improve predictions; however, the effect of the upgrade cycle became evident in its errors. This highlights the importance of retraining U-Net with updated data as it becomes available to maintain its reliability in operational forecasting systems. U-Net also proved effective in capturing particulate pollution, providing reliable predictions for values up to 500 <span><math><mi>μg</mi><mo>/</mo><mi>m</mi><mn>3</mn></math></span>. These findings underscore U-Net's potential for operational forecasting, supporting accurate early warnings to mitigate the health and environmental impacts of <span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> <!--> pollution.</div></div>","PeriodicalId":8600,"journal":{"name":"Atmospheric Research","volume":"328 ","pages":"Article 108439"},"PeriodicalIF":4.4000,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing 5-day particulate matter (PM10) forecasts in Morocco using U-net: A deep learning approach\",\"authors\":\"Anass Houdou , Kenza Khomsi , Luca Delle Monache , Weiming Hu , Saber Boutayeb , Lahcen Belyamani , Fayez Abdulla , Imad el Badisy , Wael K. Al-Delaimy , Mohamed Khalis\",\"doi\":\"10.1016/j.atmosres.2025.108439\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Accurately predicting particulate matter is crucial for preventing health risks and protecting public health. This study improves the accuracy of particulate matter <span><math><mi>d</mi><mo>≤</mo><mn>10</mn><mspace></mspace><mi>μm</mi></math></span> (<span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> <!-->) forecasts over Morocco for the next five days using a U-Net-based deep learning model, marking the first work of its kind in the Middle East and North Africa (MENA) region. The U-Net model was used to post-process and improve <span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> forecasts from the Copernicus Atmosphere Monitoring Service (CAMS), with reanalysis data from CAMS serving as a reference to guide the model's learning. The U-Net architecture was modified to predict outputs at a resolution different from the inputs, eliminating the need for interpolation and preserving critical spatial details. The results demonstrated significant improvements over two baselines—CAMS forecasts and the Analog Ensemble model (AnEn)—by enhancing metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (<span><math><msup><mi>R</mi><mn>2</mn></msup></math></span>), Index of Agreement (IOA), and biases, particularly in regions prone to dust storms, during the period prior to the CAMS forecast upgrade in mid-2023. In the second half of 2023, U-Net continued to improve predictions; however, the effect of the upgrade cycle became evident in its errors. This highlights the importance of retraining U-Net with updated data as it becomes available to maintain its reliability in operational forecasting systems. U-Net also proved effective in capturing particulate pollution, providing reliable predictions for values up to 500 <span><math><mi>μg</mi><mo>/</mo><mi>m</mi><mn>3</mn></math></span>. These findings underscore U-Net's potential for operational forecasting, supporting accurate early warnings to mitigate the health and environmental impacts of <span><math><msub><mi>PM</mi><mn>10</mn></msub></math></span> <!--> pollution.</div></div>\",\"PeriodicalId\":8600,\"journal\":{\"name\":\"Atmospheric Research\",\"volume\":\"328 \",\"pages\":\"Article 108439\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2025-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Atmospheric Research\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0169809525005319\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atmospheric Research","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0169809525005319","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
Enhancing 5-day particulate matter (PM10) forecasts in Morocco using U-net: A deep learning approach
Accurately predicting particulate matter is crucial for preventing health risks and protecting public health. This study improves the accuracy of particulate matter ( ) forecasts over Morocco for the next five days using a U-Net-based deep learning model, marking the first work of its kind in the Middle East and North Africa (MENA) region. The U-Net model was used to post-process and improve forecasts from the Copernicus Atmosphere Monitoring Service (CAMS), with reanalysis data from CAMS serving as a reference to guide the model's learning. The U-Net architecture was modified to predict outputs at a resolution different from the inputs, eliminating the need for interpolation and preserving critical spatial details. The results demonstrated significant improvements over two baselines—CAMS forecasts and the Analog Ensemble model (AnEn)—by enhancing metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (), Index of Agreement (IOA), and biases, particularly in regions prone to dust storms, during the period prior to the CAMS forecast upgrade in mid-2023. In the second half of 2023, U-Net continued to improve predictions; however, the effect of the upgrade cycle became evident in its errors. This highlights the importance of retraining U-Net with updated data as it becomes available to maintain its reliability in operational forecasting systems. U-Net also proved effective in capturing particulate pollution, providing reliable predictions for values up to 500 . These findings underscore U-Net's potential for operational forecasting, supporting accurate early warnings to mitigate the health and environmental impacts of pollution.
期刊介绍:
The journal publishes scientific papers (research papers, review articles, letters and notes) dealing with the part of the atmosphere where meteorological events occur. Attention is given to all processes extending from the earth surface to the tropopause, but special emphasis continues to be devoted to the physics of clouds, mesoscale meteorology and air pollution, i.e. atmospheric aerosols; microphysical processes; cloud dynamics and thermodynamics; numerical simulation, climatology, climate change and weather modification.