检索结果-内蒙古大学图书馆

Accelerating Community-Wide Evaluation of AI models for Global Weather Prediction by Facilitating Access to model Output

引用

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY 2025年第1期106卷 E68-E76页

作者： Radford, Jacob T. Ebert-Uphoff, Imme Stewart, Jebb Q. Musgrave, Kate D. Demaria, Robert Tourville, Natalie Hilburn, Kyle Colorado State Univ Cooperat Inst Res Atmosphere Ft Collins CO 80523 USA NOAA Global Syst Lab Boulder CO 80305 USA Colorado State Univ Elect & Comp Engn Ft Collins CO USA

Numerous artificial intelligence-based weather prediction (AIWP) models have emerged over the past 2 years, mostly in the private sector. There is an urgent need to evaluate these models from a meteorological perspective, but access to the output of these models is limited. We detail two new resources to facilitate access to AIWP model output data in the hope of accelerating the investigation of AIWP models by the meteorological community. First, a 3-yr (and growing) reforecast archive beginning in October 2020 containing twice daily 10-day forecasts for FourCastNet v2-small, Pangu-Weather, and GraphCast Operational is now available via an Amazon Simple Storage Service (S3) bucket through NOAA's Open Data Dissemination (NODD) program (https://***/***). This reforecast archive was initialized with both the NOAA's Global Forecast System (GFS) and ECMWF's Integrated Forecasting System (IFS) initial conditions in the hope that users can begin to perform the feature-based verification of impactful meteorological phenomena. Second, real-time output for these three models is visualized on our web page(https://***) along with output from the GFS and the IFS. This allows users to easily compare output between each AIWP model and traditional, physics-based models with the goal of familiarizing users with the characteristics of AIWP models and determine whether the output aligns with expectations, is physically consistent and reasonable, and/or is trustworthy. We view these two efforts as a first step toward evaluating whether these new AIWP tools have a place in forecast operations.

关键词： Numerical weather prediction/ forecasting model evaluation/ performance Artificial intelligence model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Can Ingredients-Based Forecasting Be Learned? Disentangling a Random Forest's Severe Weather Predictions

引用

WEATHER AND FORECASTING 2025年第2期40卷 237-258页

作者： Mazurek, Alexandra c. Hill, Aaron j. Schumacher, Russ s. Mcdaniel, Hanna j. Colorado State Univ Dept Atmospher Sci Ft Collins CO 80523 USA Florida State Univ Dept Earth Ocean & Atmospher Sci Tallahassee FL USA Univ Oklahoma Sch Meteorol Norman OK USA

Machine learning (ML)-based models have been rapidly integrated into forecast practices across the weather forecasting community in recent years. While ML tools introduce additional data to forecasting operations, there is a need for explainability to be available alongside the model output such that the guidance can be transparent and trustworthy for the forecaster. This work makes use of the algorithm tree interpreter (TI) to disaggregate the contributions of meteorological features used in the Colorado State University Machine Learning Probabilities (CSU-MLP) system, a random forest-based ML tool that produces real-time probabilistic forecasts for severe weather using inputs from the Global Ensemble Forecast System. TI feature contributions are analyzed in time and space for CSU-MLP day 2 and day 3 individual hazard (tornado, wind, and hail) forecasts and day 4 aggregate severe forecasts over a 2-yr period. For individual forecast periods, this work demonstrates that feature contributions derived from TI can be interpreted in an ingredients-based sense, effectively making the CSU-MLP physically interpretable. When investigated in an aggregate sense, TI illustrates that the CSU-MLP system's predictions use meteorological inputs in ways that are consistent with the spatiotemporal patterns seen in meteorological fi elds that pertain to severe storm climatology. A discussion on how these insights could benefi t forecast operations more broadly is also provided. SIGNIFICANCE STATEMENT: Machine learning tools are becoming more common in weather forecasting settings, and there is a need to provide information to meteorologists on how machine learning models make their predictions in real time. Severe weather forecasts made by an operational machine learning model are deconstructed into meteorological components in a way that offers physically insightful context to the model's predictions. The results show that the machine learning model uses the input meteorological fi

关键词： Severe storms Forecast verification/skill Operational forecasting Machine learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

ProbSevere Version 3: Improved Exploitation of Data Fusion and Machine Learning for Nowcasting Severe Weather

引用

WEATHER AND FORECASTING 2024年第12期39卷 1937-1958页

作者： Cintineo, John l. Pavolonis, Michael j. Sieglaff, Justin m. Univ Wisconsin Madison Cooperat Inst Meteorol Satellite Studies Madison WI 53705 USA NOAA NESDIS Ctr Satellite Applicat & Res Ctr Satellite Applicat & Res Madison WI USA

National Oceanic and Atmospheric Administration (NOAA)/Cooperative Institute for Meteorological Satellite Studies (CIMSS) ProbSevere, or the "probability of severe" models, provide next-hour probabilistic guidance on severe weather in the United States (large hail, strong wind gusts, and tornadoes) using machine learning and meteorological data from remotely sensed platforms and short-term numerical weather models. ProbSevere has been widely used by NOAA's National Weather Service (NWS) since 2016. ProbSevere version 3 employs multiplatform, multiscale storm object identification and tracking to collect storm features and then uses gradient boosting decision trees to make predictions of convective hazards from the extracted predictors. ProbSevere v3 was trained, validated, and tested on data from 2018 to 2023. Results demonstrate improved performance over ProbSevere v2 for the majority of the United States across all seasons, spanning a wide range of meteorological regimes. The greatest improvements are for the hail, wind, and any severe models, whereas the tornado model demonstrated modest improvement. ProbSevere v3 models were evaluated by NWS forecasters in simulated real-time experiments from 2021 to 2023. The majority of forecasters preferred ProbSevere v3 over v2 due to improved confidence in predictions and greater lead times for the issuance of severe weather warnings. An analysis of predictor importance revealed several radar, lightning, satellite, and numerical model fi elds that strongly contribute to the model predictions, which is consistent with past research and knowledge of severe thunderstorm forecasting. This reinforces the importance of environmental data fusion for nowcasting severe weather associated with midlatitude convection. SIGNIFICANCE STATEMENT: This study details the updates made to a U.S.-wide, real-time, probabilistic severe- weather guidance system aimed to improve forecaster confidence and the accuracy of the U.S. National Weather Se

关键词： Thunderstorms Remote sensing Nowcasting Probability forecasts/models/distribution Machine learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Ensemble Forecast and Predictability Analysis of the Kuroshio Intrusion into the South China Sea

引用

JOURNAL OF PHYSICAL OCEANOGRAPHY 2024年第7期54卷 1503-1517页

作者： Qian, Junkai Wang, Qiang Liang, Peng Peng, Suqi Wang, Huizan Wu, Yanling Hohai Univ Key Lab Marine Hazards Forecasting Minist Nat Resources Nanjing Peoples R China Hohai Univ Coll Oceanog Nanjing Peoples R China Guangdong Ocean Univ Coll Ocean & Meteorol Zhanjiang Peoples R China Natl Univ Def Technol Coll Meteorol & Oceanog Changsha Peoples R China

The Kuroshio intrusion (KI) into the South China Sea (SCS) significantly fi cantly affects the environment, ecology, and climate change of the SCS. However, due to the nonlinearity of KI, its numerical prediction often requires a large ensemble size to measure prediction uncertainty. The huge computational costs of large numbers of members and high-resolution numerical models pose significant fi cant challenges for KI prediction. We, therefore, construct a Kuroshio ensemble deep learning prediction system (KurNet) by taking different values of parameters to predict KI paths because the deep learning models have high prediction skills and low computational cost. The KurNet containing 64 ensemble members not only can output ensemble mean forecast results of the Kuroshio path but also can estimate probability density functions for the path types. The KurNet illustrates a high predictive ability for the KI with the mean classification fi cation accuracy of 71.9% and root-mean-square error of 0.913 on the testing set, which is superior to the single control prediction by-- 1.0%-2.9%, although the control prediction model is selected as one of the ensemble members with the best predictive ability on the validation set. Furthermore, the predictability analysis of 10 KI events indicates that when the lead time is 3 days, the most important areas are in the east of Luzon Island due to the upstream Kuroshio transport. As the lead time increases, the most important area is in the Luzon Strait due to the eddy activity. Observing system simulation experiments reveal that the KI forecast skill can be enhanced by-- 12%-18% when uncertainties of the input data in these important regions are removed.

关键词： Ocean circulation Sensitivity studies Uncertainty Ensembles Deep learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Exploring the Usefulness of Machine Learning Severe Weather Guidance in the Warn-on-Forecast System: Results from the 2022 NOAA Hazardous Weather Testbed Spring Forecasting Experiment

引用

WEATHER AND FORECASTING 2024年第7期39卷 1023-1044页

作者： Flora, Montgomery L. Gallo, Burkely Potvin, Corey K. Cark, Adam J. Wilson, Katie Univ Oklahoma Cooperat Inst Severe & High Impact Weather Res & O Norman OK 73019 USA NOAA OAR Natl Severe Storms Lab Norman OK 73072 USA Storm Predict Ctr Norman OK USA Univ Oklahoma Sch Meteorol Norman OK USA US Air Force 557th Weather Wing Offutt Afb NE USA Rand Corp Santa Monica CA USA

Artificial intelligence (AI) is gaining popularity for severe weather forecasting. Recently, the authors developed an AI system using machine learning (ML) to produce probabilistic guidance for severe weather hazards, including (WoFS) as input. Known as WoFS-ML-Severe, it performed well in retrospective cases, but its operational usefulness had yet to be determined. To examine the potential usefulness of the ML guidance, we conducted a control and treatment (experimental) group experiment during the 2022 NOAA Hazardous Weather Testbed Spring Forecasting Experiment (HWT-SFE). The control group had full access to WoFS, while the experimental group had access to WoFS and ML products. Explainability graphics were also integrated into the WoFS web viewer. Both groups issued 1-h convective outlooks for each hazard. After issuing their forecasts, we surveyed participants on their confidence, the number of products viewed, and the usefulness of the ML guidance. We found the ML-based outlooks outperformed non-ML-based outlooks for multiple verification metrics for all three hazards and were rated subjectively higher by the participants. However, the difference in confidence between the two groups was not significant, and the experimental group self-reported viewing more products than the control group. Participants had mixed sentiments toward explainability products as it improved their understanding of the input/output relationships, but viewing them added to their workload. Although the experiment demonstrated the usefulness of ML guidance for severe weather forecasting, there are avenues to improve upon the ML guidance, and more training and exposure are needed to exploit its benefits fully.

关键词： Social Science Severe storms Forecast veri fi cation/skill Short-range prediction Machine learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Interpretable Convolutional Neural Network for Analyzing Precipitation in the Pre-Rainy Season of South China

引用

JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY 2024年第3期63卷 387-399页

作者： Liu, Shengjun Yan, Wenjie Liu, Xinru Hu, Yamin Yanga, Dangfu Cent South Univ Sch Math & Stat Changsha Peoples R China Guangdong Climate Ctr Guangzhou Peoples R China

The research and application of convolutional neural networks (CNNs) on statistical downscaling have been hampered by the fact that deep learning is highly dependent on sample size and is considered to be a black-box model. Therefore, a CNN model with transfer learning (CNN-TL) is proposed to study the pre-rainy season precipitation of South China. First, an augmented monthly dataset is created by sliding a fixed-length window over the daily circulation field and precipitation data for the entire year. Next, a base CNN network is pretrained on the augmented dataset, and then the network parameters are tuned on the actual monthly dataset from South China. Then, guided backpropagation is conducted to obtain the distribution regions of the key features and explain the net. The coefficient of determination R2 and root-mean-square error (RMSE) show that the CNN-TL model has higher explanatory power and better fitting performance than the feature extraction-based random forest. In comparison with the base CNN, the transfer learning approach can improve the explanatory power of the model by 10.29% and reduce the average RMSE by 6.82%. In addition, the interpretation results of the model show that the critical regions are primarily South China and its surrounding areas, including the Indochina Peninsula, the Bay of Bengal, and the South China Sea. Furthermore, the ablation experiments and composite analysis illustrate that these regions are very important.

关键词： Downscaling Statistics Deep learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Deep Low-Shot Learning for Biological Image Classification and visualization From Limited Training Samples

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第5期34卷 2528-2538页

作者： Cai, Lei Wang, Zhengyang Kulathinal, Rob Kumar, Sudhir Ji, Shuiwang Washington State Univ Sch Elect Engn & Comp Sci Pullman WA 99164 USA Texas A&M Univ Dept Comp Sci & Engn College Stn TX 77843 USA Temple Univ Dept Biol Philadelphia PA 19122 USA

Predictive modeling is useful but very challenging in biological image analysis due to the high cost of obtaining and labeling training data. For example, in the study of gene interaction and regulation in Drosophila embryogenesis, the analysis is most biologically meaningful when in situ hybridization (ISH) gene expression pattern images from the same developmental stage are compared. However, labeling training data with precise stages is very time-consuming even for developmental biologists. Thus, a critical challenge is how to build accurate computational models for precise developmental stage classification from limited training samples. In addition, identification and visualization of developmental landmarks are required to enable biologists to interpret prediction results and calibrate models. To address these challenges, we propose a deep two-step low-shot learning framework to accurately classify ISH images using limited training images. Specifically, to enable accurate model training on limited training samples, we formulate the task as a deep low-shot learning problem and develop a novel two-step learning approach, including data-level learning and feature-level learning. We use a deep residual network as our base model and achieve improved performance in the precise stage prediction task of ISH images. Furthermore, the deep model can be interpreted by computing saliency maps, which consists of pixel-wise contributions of an image to its prediction result. In our task, saliency maps are used to assist the identification and visualization of developmental landmarks. Our experimental results show that the proposed model can not only make accurate predictions but also yield biologically meaningful interpretations. We anticipate our methods to be easily generalizable to other biological image classification tasks with small training datasets. Our open-source code is available at https://***/divelab/lsl-fly.

关键词： Training Task analysis Feature extraction Biological system modeling Deep learning Annotations Biological information theory Biological image classification deep two-step low-shot learning Drosophila in situ hybridization (ISH) images limited training samples model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Tutorial for Operational Meteorology. Part I: Traditional Machine Learning

引用

WEATHER AND FORECASTING 2022年第8期37卷 1509-1529页

作者： Chase, Randy J. Harrison, David R. Burke, Amanda Lackmann, Gary M. McGovern, Amy Univ Oklahoma Sch Comp Sci Norman OK 73019 USA Univ Oklahoma Sch Meteorol Norman OK 73019 USA Univ Oklahoma NSF AI Inst Res Trustworthy AI Weather Climate & Norman OK 73019 USA Univ Oklahoma Cooperat Inst Severe & High Impact Weather Res & Norman OK 73019 USA NOAA NWS Storm Predict Ctr Norman OK USA North Carolina State Univ Dept Marine Earth & Atmospher Sci Raleigh NC USA

Recently, the use of machine learning in meteorology has increased greatly. While many machine learning methods are not new, university classes on machine learning are largely unavailable to meteorology students and are not required to become a meteorologist. The lack of formal instruction has contributed to perception that machine learning methods are "black boxes" and thus end-users are hesitant to apply the machine learning methods in their everyday workflow. To reduce the opaqueness of machine learning methods and lower hesitancy toward machine learning in meteorology, this paper provides a survey of some of the most common machine learning methods. A familiar meteorological example is used to contextualize the machine learning methods while also discussing machine learning topics using plain language. The following machine learning methods are demonstrated: linear regression, logistic regression, decision trees, random forest, gradient boosted decision trees, naive Bayes, and support vector machines. Beyond discussing the different methods, the paper also contains discussions on the general machine learning process as well as best practices to enable readers to apply machine learning to their own datasets. Furthermore, all code (in the form of Jupyter notebooks and Google Colaboratory notebooks) used to make the examples in the paper is provided in an effort to catalyze the use of machine learning in meteorology.

关键词： Radars Radar observations Satellite observations Forecasting techniques Nowcasting Operational forecasting Artificial intelligence Classification Data science Decision trees Machine learning model interpretation and visualization Regression Support vector machines Other artificial intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Using Explainable Machine Learning Forecasts to Discover Subseasonal Drivers of High Summer Temperatures in Western and Central Europe

引用

MONTHLY WEATHER REVIEW 2022年第5期150卷 1115-1134页

作者： Van Straaten, Chiem Whan, Kirien Coumou, Dim Van den Hurk, Bart Schmeits, Maurice Royal Netherlands Meteorol Inst KNMI De Bilt Netherlands Vrije Univ Amsterdam Inst Environm Studies IVM Amsterdam Netherlands Potsdam Inst Climate Impact Res Potsdam Germany Deltares Delft Netherlands

Reliable subseasonal forecasts of high summer temperatures would be very valuable for society. Although state-of-the-art numerical weather prediction (NWP) models have become much better in representing the relevant sources of predictability like land and sea surface states, the subseasonal potential is not fully realized. Complexities arise because drivers depend on the state of other drivers and on interactions over multiple time scales. This study applies statistical modeling to ERA5 data, and explores how nine potential drivers, interacting on eight time scales, contribute to the subseasonal predictability of high summer temperatures in western and central Europe. Features and target temperatures are extracted with two variations of hierarchical clustering, and are fitted with a machine learning (ML) model based on random forests. Explainable AI methods show that the ML model agrees with physical understanding. Verification of the forecasts reveals that a large part of predictability comes from climate change, but that reliable and valuable subseasonal forecasts are possible in certain windows, like forecasting monthly warm anomalies with a lead time of 15 days. Contributions of each driver confirm that there is a transfer of predictability from the land and sea surface state to the atmosphere. The involved time scales depend on lead time and the forecast target. The explainable AI methods also reveal surprising driving features in sea surface temperature and 850 hPa temperature, and rank the contribution of snow cover above that of sea ice. Overall, this study demonstrates that complex statistical models, when made explainable, can complement research with NWP models, by diagnosing drivers that need further understanding and a correct numerical representation, for better future forecasts.

关键词： Statistical forecasting Subseasonal variability Machine learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

Comparing and Interpreting Differently Designed Random Forests for Next-Day Severe Weather Hazard Prediction

引用

WEATHER AND FORECASTING 2022年第6期37卷 871-899页

作者： Loken, Eric D. Clark, Adam J. McGovern, Amy Univ Oklahoma Cooperat Inst Mesoscale Meteorol Studies Norman OK 73019 USA Natl Severe Storms Lab NOAA OAR Norman OK 73072 USA Univ Oklahoma Sch Meteorol Norman OK 73019 USA

Recent research has shown that random forests (RFs) can create skillful probabilistic severe weather hazard forecasts from numerical weather prediction (NWP) ensemble data. However, it remains unclear how RFs use NWP data and how predictors should be generated from NWP ensembles. This paper compares two methods for creating RFs for next-day severe weather prediction using simulated forecast data from the convection-allowing High-Resolution Ensemble Forecast System, version 2.1 (HREFv2.1). The first method uses predictors from individual ensemble members (IM) at the point of prediction, while the second uses ensemble mean (EM) predictors at multiple spatial points. IM and EM RFs are trained with all predictors as well as predictor subsets, and the Python module tree interpreter (TI) is used to assess RF variable importance and the relationships learned by the RFs. Results show that EM RFs have better objective skill compared to similarly configured IM RFs for all hazards, presumably because EM predictors contain less noise. In both IM and EM RFs, storm variables are found to be most important, followed by index and environment variables. Interestingly, RFs created from storm and index variables tend to produce forecasts with greater or equal skill than those from the all-predictor RFs. TI analysis shows that the RFs emphasize different predictors for different hazards in a way that makes physical sense. Further, TI shows that RFs create calibrated hazard probabilities based on complex, multivariate relationships that go well beyond thresholding 2-5-km updraft helicity.

关键词： Ensembles Forecasting Artificial intelligence Decision trees Machine learning model interpretation and visualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：