首页期刊导航|大气科学进展（英文版）
期刊信息/Journal information
大气科学进展（英文版）
大气科学进展（英文版）

吴国雄、王会军、Da-Lin Zhang

双月刊

0256-1530

aas@mail.iap.ac.cn

010-82995054

100029

北京德胜门外中科院大气所

大气科学进展（英文版）/Journal Advances in Atmospheric SciencesCSCDCSTPCD北大核心SCI
查看更多>>本刊现为国家自然科学基金委员会重点资助期刊，是大气科学领域的学术性刊物，坚持“百花齐放，百家争鸣”的方针，努力反映大气科学领域的最新研究成果，及时刊登有创造性的学术论文及评述性文章，报道大气科学领域内的新动向、新问题。国内外大气科学领域著名科学家均向我刊投稿，编委由国内外大气科学领域知名科学家共40多人组成。
正式出版
收录年代

    Predictability Study of Weather and Climate Events Related to Artificial Intelligence Models

    Mu MUBo QINGuokun DAI
    1-8页
    查看更多>>摘要：Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather and climate phenomena.In the past few decades,dynamical numerical models have been the primary tools for predictability studies,achieving significant progress.Nowadays,with the advances in artificial intelligence(AI)techniques and accumulations of vast meteorological data,modeling weather and climate events using modern data-driven approaches is becoming trendy,where FourCastNet,Pangu-Weather,and GraphCast are successful pioneers.In this perspective article,we suggest AI models should not be limited to forecasting but be expanded to predictability studies,leveraging AI's advantages of high efficiency and self-contained optimization modules.To this end,we first remark that AI models should possess high simulation capability with fine spatiotemporal resolution for two kinds of predictability studies.AI models with high simulation capabilities comparable to numerical models can be considered to provide solutions to partial differential equations in a data-driven way.Then,we highlight several specific predictability issues with well-determined nonlinear optimization formulizations,which can be well-studied using AI models,holding significant scientific value.In addition,we advocate for the incorporation of AI models into the synergistic cycle of the cognition-observation-model paradigm.Comprehensive predictability studies have the potential to transform"big data"to"big and better data"and shift the focus from"AI for forecasts"to"AI for science",ultimately advancing the development of the atmospheric and oceanic sciences.
      原文链接:
    • 万方数据
    • 维普

    TianXing:A Linear Complexity Transformer Model with Explicit Attention Decay for Global Weather Forecasting

    Shijin YUANGuansong WANGBin MUFeifan ZHOU...
    9-25页
    查看更多>>摘要：In this paper,we introduce TianXing,a transformer-based data-driven model designed with physical augmentation for skillful and efficient global weather forecasting.Previous data-driven transformer models such as Pangu-Weather,FengWu,and FuXi have emerged as promising alternatives for numerical weather prediction in weather forecasting.However,these models have been characterized by their substantial computational resource consumption during training and limited incorporation of explicit physical guidance in their modeling frameworks.In contrast,TianXing applies a linear complexity mechanism that ensures proportional scalability with input data size while significantly diminishing GPU resource demands,with only a marginal compromise in accuracy.Furthermore,TianXing proposes an explicit attention decay mechanism in the linear attention derived from physical insights to enhance its forecasting skill.The mechanism can re-weight attention based on Earth's spherical distances and learned sparse multivariate coupling relationships,promptingTianXing to prioritize dynamically relevant neighboring features.Finally,to enhance its performance in medium-range forecasting,TianXing employs a stacked autoregressive forecast algorithm.Validation of the model's architecture is conducted using ERA5 reanalysis data at a 5.625° latitude-longitude resolution,while a high-resolution dataset at 0.25° is utilized for training the actual forecasting model.Notably,the TianXing exhibits excellent performance,particularly in the Z500(geopotential height)and T850(temperature)fields,surpassing previous data-driven models and operational full-resolution models such as NCEP GFS and ECMWF IFS,as evidenced by latitude-weighted RMSE and ACC metrics.Moreover,the TianXing has demonstrated remarkable capabilities in predicting extreme weather events,such as typhoons.
      原文链接:
    • 万方数据
    • 维普

    Improving the Seasonal Forecast of Summer Precipitation in Southeastern China Using a CycleGAN-based Deep Learning Bias Correction Method

    Song YANGFenghua LINGJing-Jia LUOLei BAI...
    26-35页
    查看更多>>摘要：Accurate seasonal precipitation forecasts,especially for extreme events,are crucial to preventing meteorological hazards and their potential impacts on national development,social activity,and security.However,the intensity of summer precipitation is often largely underestimated in many current dynamic models.This study uses a deep learning method called Cycle-Consistent Generative Adversarial Networks(CycleGAN)to improve the seasonal forecasts for June-July-August precipitation in southeastern China by the Nanjing University of Information Science and Technology Climate Forecast System(NUIST-CFS 1.0).The results suggest that the CycleGAN-based model significantly improves the accuracy in predicting the spatiotemporal distribution of summer precipitation compared to the traditional quantile mapping(QM)method.Using the unpaired bias-correction model,we can also obtain advanced forecasts of the frequency,intensity,and duration of extreme precipitation events over the dynamic model predictions.This study expands the potential applications of deep learning models toward improving seasonal precipitation forecasts.
      原文链接:
    • 万方数据
    • 维普

    A Machine Learning-Based Observational Constraint Correction Method for Seasonal Precipitation Prediction

    Bofei ZHANGHaipeng YUZeyong HUPing YUE...
    36-52页
    查看更多>>摘要：Seasonal precipitation has always been a key focus of climate prediction.As a dynamic-statistical combined method,the existing observational constraint correction establishes a regression relationship between the numerical model outputs and historical observations,which can partly predict seasonal precipitation.However,solving a nonlinear problem through linear regression is significantly biased.This study implements a nonlinear optimization of an existing observational constrained correction model using a Light Gradient Boosting Machine(LightGBM)machine learning algorithm based on output from the Beijing National Climate Center Climate System Model(BCC-CSM)and station observations to improve the prediction of summer precipitation in China.The model was trained using a rolling approach,and LightGBM outperformed Linear Regression(LR),Extreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost).Using parameter tuning to optimize the machine learning model and predict future summer precipitation using eight different predictors in BCC-CSM,the mean Anomaly Correlation Coefficient(ACC)score in the 2019-22 summer precipitation predictions was 0.17,and the mean Prediction Score(PS)reached 74.The PS score was improved by 7.87％and 6.63％compared with the BCC-CSM and the linear observational constraint approach,respectively.The observational constraint correction prediction strategy with LightGBM significantly and stably improved the prediction of summer precipitation in China compared to the previous linear observational constraint solution,providing a reference for flood control and drought relief during the flood season(summer)in China.
      原文链接:
    • 万方数据
    • 维普

    Unsupervised Meteorological Downscaling Based on Dual Learning and Subgrid-scale Auxiliary Information

    Jing HUJialing MUXiaomeng HUANGXi WU...
    53-66页
    查看更多>>摘要：Climate downscaling is used to transform large-scale meteorological data into small-scale data with enhanced detail,which finds wide applications in climate modeling,numerical weather forecasting,and renewable energy.Although deep-learning-based downscaling methods effectively capture the complex nonlinear mapping between meteorological data of varying scales,the supervised deep-learning-based downscaling methods suffer from insufficient high-resolution data in practice,and unsupervised methods struggle with accurately inferring small-scale specifics from limited large-scale inputs due to small-scale uncertainty.This article presents DualDS,a dual-learning framework utilizing a Generative Adversarial Network-based neural network and subgrid-scale auxiliary information for climate downscaling.Such a learning method is unified in a two-stream framework through up-and downsamplers,where the downsampler is used to simulate the information loss process during the upscaling,and the upsampler is used to reconstruct lost details and correct errors incurred during the upscaling.This dual learning strategy can eliminate the dependence on high-resolution ground truth data in the training process and refine the downscaling results by constraining the mapping process.Experimental findings demonstrate that DualDS is comparable to several state-of-the-art deep learning downscaling approaches,both qualitatively and quantitatively.Specifically,for a single surface-temperature data downscaling task,our method is comparable with other unsupervised algorithms with the same dataset,and we can achieve a 0.469 dB higher peak signal-to-noise ratio,0.017 higher structural similarity,0.08 lower RMSE,and the best correlation coefficient.In summary,this paper presents a novel approach to addressing small-scale uncertainty issues in unsupervised downscaling processes.
      原文链接:
    • 万方数据
    • 维普

    A Generative Adversarial Network with an Attention Spatiotemporal Mechanism for Tropical Cyclone Forecasts

    Xiaohui LIXinhai HANJingsong YANGJiuke WANG...
    67-78页
    查看更多>>摘要：Tropical cyclones(TCs)are complex and powerful weather systems,and accurately forecasting their path,structure,and intensity remains a critical focus and challenge in meteorological research.In this paper,we propose an Attention Spatio-Temporal predictive Generative Adversarial Network(AST-GAN)model for predicting the temporal and spatial distribution of TCs.The model forecasts the spatial distribution of TC wind speeds for the next 15 hours at 3-hour intervals,emphasizing the cyclone's center,high wind-speed areas,and its asymmetric structure.To effectively capture spatiotemporal feature transfer at different time steps,we employ a channel attention mechanism for feature selection,enhancing model performance and reducing parameter redundancy.We utilized High-Resolution Weather Research and Forecasting(HWRF)data to train our model,allowing it to assimilate a wide range of TC motion patterns.The model is versatile and can be applied to various complex scenarios,such as multiple TCs moving simultaneously or TCs approaching landfall.Our proposed model demonstrates superior forecasting performance,achieving a root-mean-square error(RMSE)of 0.71 m s-1 for overall wind speed and 2.74 m s-1 for maximum wind speed when benchmarked against ground truth data from HWRF.Furthermore,the model underwent optimization and independent testing using ERA5 reanalysis data,showcasing its stability and scalability.After fine-tuning on the ERA5 dataset,the model achieved an RMSE of 1.33 m s-1 for wind speed and 1.75 m s-1 for maximum wind speed.The AST-GAN model outperforms other state-of-the-art models in RMSE on both the HWRF and ERA5 datasets,maintaining its superior performance and demonstrating its effectiveness for spatiotemporal prediction of TCs.
      原文链接:
    • 万方数据
    • 维普

    Vision Transformer for Extracting Tropical Cyclone Intensity from Satellite Images

    Ye TIANWen ZHOUPaxson K.Y.CHEUNGZhenchen LIU...
    79-93页
    查看更多>>摘要：Tropical cyclone(TC)intensity estimation is a fundamental aspect of TC monitoring and forecasting.Deep learning models have recently been employed to estimate TC intensity from satellite images and yield precise results.This work proposes the ViT-TC model based on the Vision Transformer(ViT)architecture.Satellite images of TCs,including infrared(IR),water vapor(WV),and passive microwave(PMW),are used as inputs for intensity estimation.Experiments indicate that combining IR,WV,and PMW as inputs yields more accurate estimations than other channel combinations.The ensemble mean technique is applied to enhance the model's estimations,reducing the root-mean-square error to 9.32 kt(knots,1 kt ≈ 0.51 ms-1)and the mean absolute error to 6.49 kt,which outperforms traditional methods and is comparable to existing deep learning models.The model assigns high attention weights to areas with high PMW,indicating that PMW magnitude is essential information for the model's estimation.The model also allocates significance to the cloud-cover region,suggesting that the model utilizes the whole TC cloud structure and TC eye to determine TC intensity.
      原文链接:
    • 万方数据
    • 维普

    Joint Retrieval of PM2i5 Concentration and Aerosol Optical Depth over China Using Multi-Task Learning on FY-4A AGRI

    Bo LIDisong FULing YANGXuehua FAN...
    94-110页
    查看更多>>摘要：Aerosol optical depth(AOD)and fine particulate matter with a diameter of less than or equal to 2.5 μm(PM2.5)play crucial roles in air quality,human health,and climate change.However,the complex correlation of AOD-PM2.5 and the limitations of existing algorithms pose a significant challenge in realizing the accurate joint retrieval of these two parameters at the same location.On this point,a multi-task learning(MTL)model,which enables the joint retrieval of PM2.5 concentration and AOD,is proposed and applied on the top-of-the-atmosphere reflectance data gathered by the Fengyun-4A Advanced Geosynchronous Radiation Imager(FY-4A AGRI),and compared to that of two single-task learning models—namely,Random Forest(RF)and Deep Neural Network(DNN).Specifically,MTL achieves a coefficient of determination(R2)of 0.88 and a root-mean-square error(RMSE)of 0.10 in AOD retrieval.In comparison to RF,the R2 increases by 0.04,the RMSE decreases by 0.02,and the percentage of retrieval results falling within the expected error range(Within-EE)rises by 5.55％.The R2 and RMSE of PM2.5 retrieval by MTL are 0.84 and 13.76 μg m-3,respectively.Compared with RF,the R2 increases by 0.06,the RMSE decreases by 4.55 μg m-3,and the Within-EE increases by 7.28％.Additionally,compared to DNN,MTL shows an increase of 0.01 in R2 and a decrease of 0.02 in RMSE in AOD retrieval,with a corresponding increase of 2.89％in Within-EE.For PM2.5 retrieval,MTL exhibits an increase of 0.05 in R2,a decrease of 1.76 μg m-3 in RMSE,and an increase of 6.83％in Within-EE.The evaluation suggests that MTL is able to provide simultaneously improved AOD and PM2.5 retrievals,demonstrating a significant advantage in efficiently capturing the spatial distribution of PM2.5 concentration and AOD.
      原文链接:
    • 万方数据

    Short-Term Rolling Prediction of Tropical Cyclone Intensity Based on Multi-Task Learning with Fusion of Deviation-Angle Variance and Satellite Imagery

    Wei TIANPing SONGYuanyuan CHENYonghong ZHANG...
    111-128页
    查看更多>>摘要：Tropical cyclones(TCs)are one of the most serious types of natural disasters,and accurate TC activity predictions are key to disaster prevention and mitigation.Recently,TC track predictions have made significant progress,but the ability to predict their intensity is obviously lagging behind.At present,research on TC intensity prediction takes atmospheric reanalysis data as the research object and mines the relationship between TC-related environmental factors and intensity through deep learning.However,reanalysis data are non-real-time in nature,which does not meet the requirements for operational forecasting applications.Therefore,a TC intensity prediction model named TC-Rolling is proposed,which can simultaneously extract the degree of symmetry for strong TC convective cloud and convection intensity,and fuse the deviation-angle variance with satellite images to construct the correlation between TC convection structure and intensity.For TCs'complex dynamic processes,a convolutional neural network(CNN)is used to learn their temporal and spatial features.For real-time intensity estimation,multi-task learning acts as an implicit time-series enhancement.The model is designed with a rolling strategy that aims to moderate the long-term dependent decay problem and improve accuracy for short-term intensity predictions.Since multiple tasks are correlated,the loss function of 12 h and 24 h are corrected.After testing on a sample of TCs in the Northwest Pacific,with a 4.48 kt root-mean-square error(RMSE)of 6 h intensity prediction,5.78 kt for 12 h,and 13.94 kt for 24 h,TC records from official agencies are used to assess the validity of TC-Rolling.
      原文链接:
    • 万方数据
    • 维普

    Regional Storm Surge Forecast Method Based on a Neural Network and the Coupled ADCIRC-SWAN Model

    Yuan SUNPo HUShuiqing LIDongxue MO...
    129-145页
    查看更多>>摘要：Timely and accurate forecasting of storm surges can effectively prevent typhoon storm surges from causing large economic losses and casualties in coastal areas.At present,numerical model forecasting consumes too many resources and takes too long to compute,while neural network forecasting lacks regional data to train regional forecasting models.In this study,we used the DUAL wind model to build typhoon wind fields,and constructed a typhoon database of 75 processes in the northern South China Sea using the coupled Advanced Circulation-Simulating Waves Nearshore(ADCIRC-SWAN)model.Then,a neural network with a Res-U-Net structure was trained using the typhoon database to forecast the typhoon processes in the validation dataset,and an excellent storm surge forecasting effect was achieved in the Pearl River Estuary region.The storm surge forecasting effect of stronger typhoons was improved by adding a branch structure and transfer learning.
      原文链接:
    • 万方数据
    • 维普