Pub Date : 2023-06-14DOI: 10.1175/aies-d-22-0086.1
M. Molina, T. O’Brien, G. Anderson, M. Ashfaq, K. Bennett, W. Collins, K. Dagon, J. Restrepo, P. Ullrich
Climate variability and weather phenomena can cause extremes and pose significant risk to society and ecosystems, making continued advances in our physical understanding of such events of utmost importance for regional and global security. Advances in machine learning (ML) have been leveraged for applications in climate variability and weather, empowering scientists to approach questions using big data in new ways. Growing interest across the scientific community in these areas has motivated coordination between the physical and computer science disciplines to further advance the state of the science and tackle pressing challenges. During a recently held workshop that had participants across academia, private industry, and research laboratories, it became clear that a comprehensive review of recent and emerging ML applications for climate variability and weather phenomena that can cause extremes was needed. This article aims to fulfill this need by discussing recent advances, challenges, and research priorities in the following topics: sources of predictability for modes of climate variability, feature detection, extreme weather and climate prediction and precursors, observation-model integration, downscaling and bias correction. This article provides a review for domain scientists seeking to incorporate ML into their research. It also provides a review for those with some ML experience seeking to broaden their knowledge of ML applications for climate variability and weather.
{"title":"A Review of Recent and Emerging Machine Learning Applications for Climate Variability and Weather Phenomena","authors":"M. Molina, T. O’Brien, G. Anderson, M. Ashfaq, K. Bennett, W. Collins, K. Dagon, J. Restrepo, P. Ullrich","doi":"10.1175/aies-d-22-0086.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0086.1","url":null,"abstract":"\u0000Climate variability and weather phenomena can cause extremes and pose significant risk to society and ecosystems, making continued advances in our physical understanding of such events of utmost importance for regional and global security. Advances in machine learning (ML) have been leveraged for applications in climate variability and weather, empowering scientists to approach questions using big data in new ways. Growing interest across the scientific community in these areas has motivated coordination between the physical and computer science disciplines to further advance the state of the science and tackle pressing challenges. During a recently held workshop that had participants across academia, private industry, and research laboratories, it became clear that a comprehensive review of recent and emerging ML applications for climate variability and weather phenomena that can cause extremes was needed. This article aims to fulfill this need by discussing recent advances, challenges, and research priorities in the following topics: sources of predictability for modes of climate variability, feature detection, extreme weather and climate prediction and precursors, observation-model integration, downscaling and bias correction. This article provides a review for domain scientists seeking to incorporate ML into their research. It also provides a review for those with some ML experience seeking to broaden their knowledge of ML applications for climate variability and weather.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80442696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-08DOI: 10.1175/aies-d-22-0093.1
K. Hilburn
Convolutional neural networks (CNNs) are opening new possibilities in the realm of satellite remote sensing. CNNs are especially useful for capturing the information in spatial patterns that is evident to the human eye but has eluded classical pixelwise retrieval algorithms. However, the black box nature of CNN predictions makes them difficult to interpret, hindering their trustworthiness. This paper explores a new way to simplify CNNs that allows them to be implemented in a fully transparent and interpretable framework. This clarity is accomplished by moving the inner workings of the CNN out into a feature engineering step and replacing the CNN with a regression model. The specific example of GREMLIN (GOES Radar Estimation via Machine Learning to Inform NWP) is used to demonstrate that such simplifications are possible and show the benefits of the interpretable approach. GREMLIN translates images of GOES radiances and lightning into images of radar reflectivity, and previous research used Explainable AI (XAI) approaches to explain some aspects of how GREMLIN makes predictions. However, the Interpretable GREMLIN model shows that XAI missed several strategies, and XAI does not provide guarantees on how the model will respond when confronted with new scenarios. In contrast, the interpretable model establishes well defined relationships between inputs and outputs, offering a clear mapping of the spatial context utilized by the CNN to make accurate predictions; and providing guarantees on how the model will respond to new inputs. The significance of this work is that it provides a new approach for developing trustworthy AI models.
{"title":"Understanding Spatial Context in Convolutional Neural Networks using Explainable Methods: Application to Interpretable GREMLIN","authors":"K. Hilburn","doi":"10.1175/aies-d-22-0093.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0093.1","url":null,"abstract":"\u0000Convolutional neural networks (CNNs) are opening new possibilities in the realm of satellite remote sensing. CNNs are especially useful for capturing the information in spatial patterns that is evident to the human eye but has eluded classical pixelwise retrieval algorithms. However, the black box nature of CNN predictions makes them difficult to interpret, hindering their trustworthiness. This paper explores a new way to simplify CNNs that allows them to be implemented in a fully transparent and interpretable framework. This clarity is accomplished by moving the inner workings of the CNN out into a feature engineering step and replacing the CNN with a regression model. The specific example of GREMLIN (GOES Radar Estimation via Machine Learning to Inform NWP) is used to demonstrate that such simplifications are possible and show the benefits of the interpretable approach. GREMLIN translates images of GOES radiances and lightning into images of radar reflectivity, and previous research used Explainable AI (XAI) approaches to explain some aspects of how GREMLIN makes predictions. However, the Interpretable GREMLIN model shows that XAI missed several strategies, and XAI does not provide guarantees on how the model will respond when confronted with new scenarios. In contrast, the interpretable model establishes well defined relationships between inputs and outputs, offering a clear mapping of the spatial context utilized by the CNN to make accurate predictions; and providing guarantees on how the model will respond to new inputs. The significance of this work is that it provides a new approach for developing trustworthy AI models.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76025150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-06DOI: 10.1175/aies-d-23-0007.1
T. Sekiyama, S. Hayashi, Ryo Kaneko, K. Fukui
Surrogate modeling is one of the most promising applications of deep learning techniques in meteorology. The purpose of this study was to downscale surface wind fields in a gridded format at a much lower computational load. We employed a super-resolution convolutional neural network (SRCNN) as a surrogate model and created a 20-member ensemble by training the same SRCNN model with different random seeds. The downscaling accuracy of the ensemble mean remained stable throughout a year and was consistently better than that of the input wind fields. It was confirmed that (1) the ensemble spread was efficiently created, and (2) the ensemble mean was superior to individual ensemble members and (3) robust to the presence of outlier members. Training, validation, and test data for 10 years were computed via our nested mesoscale weather forecast models not derived from public analysis datasets or real observations. The predictands were 1-km gridded surface zonal and meridional winds, of which the domain was defined as a 180 km × 180 km area around Tokyo, Japan. The predictors included 5-km gridded surface zonal and meridional winds, temperature, humidity, vertical gradient of the potential temperature, elevation, and land/water ratio as well as 1-km gridded elevation and land/water ratio. Although a perfect surrogate of the weather forecast model could not be achieved, the SRCNN downscaling accuracy could likely enable us to apply this approach in high-resolution advection simulations considering its overwhelmingly high prediction speed.
代理建模是深度学习技术在气象学中最有前途的应用之一。本研究的目的是在更低的计算负荷下以网格形式缩小地面风场的规模。我们采用超分辨率卷积神经网络(SRCNN)作为代理模型，并通过使用不同的随机种子训练相同的SRCNN模型来创建一个20成员的集合。集合平均的降尺度精度在一年内保持稳定，并始终优于输入风场的降尺度精度。结果表明:(1)集合传播是有效的;(2)集合均值优于单个集合成员;(3)对异常值成员的存在具有鲁棒性。10年的训练、验证和测试数据是通过我们嵌套的中尺度天气预报模型计算的，而不是来自公共分析数据集或实际观测。预测结果为1 km网格化的地面纬向风和经向风，预测范围为日本东京附近180 km × 180 km的区域。预测因子包括5 km格点地面纬向风和经向风、温度、湿度、位温垂直梯度、高程和水陆比，以及1 km格点高程和水陆比。虽然无法获得一个完美的天气预报模型，但考虑到SRCNN的高预测速度，它的降尺度精度可能使我们能够将该方法应用于高分辨率平流模拟。
{"title":"Surrogate Downscaling of Mesoscale Wind Fields Using Ensemble Super-Resolution Convolutional Neural Networks","authors":"T. Sekiyama, S. Hayashi, Ryo Kaneko, K. Fukui","doi":"10.1175/aies-d-23-0007.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0007.1","url":null,"abstract":"\u0000Surrogate modeling is one of the most promising applications of deep learning techniques in meteorology. The purpose of this study was to downscale surface wind fields in a gridded format at a much lower computational load. We employed a super-resolution convolutional neural network (SRCNN) as a surrogate model and created a 20-member ensemble by training the same SRCNN model with different random seeds. The downscaling accuracy of the ensemble mean remained stable throughout a year and was consistently better than that of the input wind fields. It was confirmed that (1) the ensemble spread was efficiently created, and (2) the ensemble mean was superior to individual ensemble members and (3) robust to the presence of outlier members. Training, validation, and test data for 10 years were computed via our nested mesoscale weather forecast models not derived from public analysis datasets or real observations. The predictands were 1-km gridded surface zonal and meridional winds, of which the domain was defined as a 180 km × 180 km area around Tokyo, Japan. The predictors included 5-km gridded surface zonal and meridional winds, temperature, humidity, vertical gradient of the potential temperature, elevation, and land/water ratio as well as 1-km gridded elevation and land/water ratio. Although a perfect surrogate of the weather forecast model could not be achieved, the SRCNN downscaling accuracy could likely enable us to apply this approach in high-resolution advection simulations considering its overwhelmingly high prediction speed.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81713658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-05DOI: 10.1175/aies-d-22-0072.1
C. Nguyen, J. Nachamkin, D. Sidoti, Jacob Gull, A. Bienkowski, R. Bankert, M. Surratt
Given the diversity of cloud forcing mechanisms, it is difficult to classify and characterize all cloud types through the depth of a specific troposphere. Importantly, different cloud families often coexist even at the same atmospheric level. The Naval Research Laboratory (NRL) is developing machine learning-based cloud forecast models to fuse numerical weather prediction model and satellite data. These models were built for the dual purpose of understanding numericalweather prediction model error trends aswell as improving the accuracy and sensitivity of the forecasts. The framework implements a Unet-Convolutional Neural Network (UNet-CNN) with features extracted from clouds observed by the Geostationary Operational Environmental Satellite (GOES-16) as well as clouds predicted by the Coupled Ocean/Atmosphere Mesoscale Prediction System (COAMPS). The fundamental idea behind this novel framework is the application of UNet-CNN for separate variable sets extracted from GOES-16 and COAMPS to characterize and predict broad families of clouds that share similar physical characteristics. A quantitative assessment and evaluation based on an independent dataset for upper tropospheric (high) clouds suggests that UNet-CNN models capture the complexity and error trends of combined data from GOES-16 and COAMPS, and also improve forecast accuracy and sensitivity for different lead time forecasts (3-12 hours). This paper includes an overview of the machine learning frameworks as well as an illustrative example of their application, a comparative assessment of results for upper tropospheric clouds.
{"title":"Machine learning-based cloud forecast corrections for fusions of numerical weather prediction model and satellite data","authors":"C. Nguyen, J. Nachamkin, D. Sidoti, Jacob Gull, A. Bienkowski, R. Bankert, M. Surratt","doi":"10.1175/aies-d-22-0072.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0072.1","url":null,"abstract":"\u0000Given the diversity of cloud forcing mechanisms, it is difficult to classify and characterize all cloud types through the depth of a specific troposphere. Importantly, different cloud families often coexist even at the same atmospheric level. The Naval Research Laboratory (NRL) is developing machine learning-based cloud forecast models to fuse numerical weather prediction model and satellite data. These models were built for the dual purpose of understanding numericalweather prediction model error trends aswell as improving the accuracy and sensitivity of the forecasts. The framework implements a Unet-Convolutional Neural Network (UNet-CNN) with features extracted from clouds observed by the Geostationary Operational Environmental Satellite (GOES-16) as well as clouds predicted by the Coupled Ocean/Atmosphere Mesoscale Prediction System (COAMPS). The fundamental idea behind this novel framework is the application of UNet-CNN for separate variable sets extracted from GOES-16 and COAMPS to characterize and predict broad families of clouds that share similar physical characteristics. A quantitative assessment and evaluation based on an independent dataset for upper tropospheric (high) clouds suggests that UNet-CNN models capture the complexity and error trends of combined data from GOES-16 and COAMPS, and also improve forecast accuracy and sensitivity for different lead time forecasts (3-12 hours). This paper includes an overview of the machine learning frameworks as well as an illustrative example of their application, a comparative assessment of results for upper tropospheric clouds.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86831579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-05DOI: 10.1175/aies-d-22-0062.1
R. Jackson, B. Raut, Dario Dematties, S. Collis, Nicola, Ferrier, P. Beckman, Raman Sankaran, Yongho Kim, Seongha Park, Sean Shahkarami, R. Newsom
There is a need for long term observations of cloud and precipitation fall speeds for validating and improving rainfall forecasts from climate models. To this end, the U.S. Department of Energy’s Atmospheric Radiation Measurement (ARM) User Facility Southern Great Plains (SGP) site at Lamont, OK hosts five ARM Doppler lidars that can measure cloud and aerosol properties. In particular, the ARM Doppler lidars record Doppler spectra that contain information about the fall speeds of cloud and precipitation particles. However, due to bandwidth and storage constraints, the Doppler spectra are not routinely stored. This calls for the automation of cloud and rain detection in ARM Doppler lidar data so that the spectral data in clouds can be selectively saved and further analyzed. During the ARMing the Edge field experiment, a Waggle node capable of performing machine learning applications in situ was deployed at ARM’s SGP site for this purpose. In this paper, we develop and test four algorithms for the Waggle node to automatically classify ARM Doppler lidar data. We demonstrate that supervised learning using a ResNet50-based classifier will classify 97.6% of the clear air and 94.7% of cloudy images correctly, outperforming traditional peak detection methods. We also show that a convolutional autoencoder paired with k- means clustering identifies ten clusters in the ARM Doppler lidar data. Three clusters correspond to mostly clear conditions with scattered high clouds, and seven others correspond to cloudy conditions with varying cloud base heights.
{"title":"ARMing the Edge: Designing Edge Computing-capable Machine Learning Algorithms to Target ARM Doppler Lidar Processing","authors":"R. Jackson, B. Raut, Dario Dematties, S. Collis, Nicola, Ferrier, P. Beckman, Raman Sankaran, Yongho Kim, Seongha Park, Sean Shahkarami, R. Newsom","doi":"10.1175/aies-d-22-0062.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0062.1","url":null,"abstract":"\u0000There is a need for long term observations of cloud and precipitation fall speeds for validating and improving rainfall forecasts from climate models. To this end, the U.S. Department of Energy’s Atmospheric Radiation Measurement (ARM) User Facility Southern Great Plains (SGP) site at Lamont, OK hosts five ARM Doppler lidars that can measure cloud and aerosol properties. In particular, the ARM Doppler lidars record Doppler spectra that contain information about the fall speeds of cloud and precipitation particles. However, due to bandwidth and storage constraints, the Doppler spectra are not routinely stored. This calls for the automation of cloud and rain detection in ARM Doppler lidar data so that the spectral data in clouds can be selectively saved and further analyzed. During the ARMing the Edge field experiment, a Waggle node capable of performing machine learning applications in situ was deployed at ARM’s SGP site for this purpose. In this paper, we develop and test four algorithms for the Waggle node to automatically classify ARM Doppler lidar data. We demonstrate that supervised learning using a ResNet50-based classifier will classify 97.6% of the clear air and 94.7% of cloudy images correctly, outperforming traditional peak detection methods. We also show that a convolutional autoencoder paired with k- means clustering identifies ten clusters in the ARM Doppler lidar data. Three clusters correspond to mostly clear conditions with scattered high clouds, and seven others correspond to cloudy conditions with varying cloud base heights.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"126 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84956980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-31DOI: 10.1175/aies-d-22-0052.1
Andrew D. Justin, Colin Willingham, A. McGovern, J. Allen
We present and evaluate a deep learning first-guess front identification system that identifies cold, warm, stationary, and occluded fronts. Frontal boundaries play a key role in the daily weather around the world. Human-drawn fronts provided by the National Weather Service’s Weather Prediction Center, Ocean Prediction Center, Tropical Analysis & Forecast Branch, and Honolulu Forecast Office are treated as ground truth labels for training the deep learning models. The models are trained using ERA5 reanalysis data with variables known to be important to distinguishing frontal boundaries, including temperature, equivalent potential temperature, and wind velocity and direction at multiple heights. Using a 250 km neighborhood over the Continental United States domain, our best models achieve critical success index scores of 0.60 for cold fronts, 0.43 for warm fronts, 0.48 for stationary fronts, 0.45 for occluded fronts, and 0.71 using a binary classification system (front / no front), while scores over the full Unified Surface Analysis domain were lower. For cold and warm fronts and binary classification, these scores significantly outperform prior baseline methods that utilize 250 km neighborhoods. These first-guess deep learning algorithms can be used by forecasters to more effectively locate frontal boundaries and expedite the frontal analysis process.
{"title":"Toward Operational Real-time Identification of Frontal Boundaries Using Machine Learning","authors":"Andrew D. Justin, Colin Willingham, A. McGovern, J. Allen","doi":"10.1175/aies-d-22-0052.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0052.1","url":null,"abstract":"\u0000We present and evaluate a deep learning first-guess front identification system that identifies cold, warm, stationary, and occluded fronts. Frontal boundaries play a key role in the daily weather around the world. Human-drawn fronts provided by the National Weather Service’s Weather Prediction Center, Ocean Prediction Center, Tropical Analysis & Forecast Branch, and Honolulu Forecast Office are treated as ground truth labels for training the deep learning models. The models are trained using ERA5 reanalysis data with variables known to be important to distinguishing frontal boundaries, including temperature, equivalent potential temperature, and wind velocity and direction at multiple heights. Using a 250 km neighborhood over the Continental United States domain, our best models achieve critical success index scores of 0.60 for cold fronts, 0.43 for warm fronts, 0.48 for stationary fronts, 0.45 for occluded fronts, and 0.71 using a binary classification system (front / no front), while scores over the full Unified Surface Analysis domain were lower. For cold and warm fronts and binary classification, these scores significantly outperform prior baseline methods that utilize 250 km neighborhoods. These first-guess deep learning algorithms can be used by forecasters to more effectively locate frontal boundaries and expedite the frontal analysis process.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78525509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-26DOI: 10.1175/aies-d-22-0077.1
A. McGovern, R. Chase, Montgomery Flora, D. Gagne, Ryan Lagerquist, C. Potvin, Nathan Snook, Eric D. Loken
We present an overviewof recentwork on using artificial intelligence/machine learning techniques for forecasting convective weather and its associated hazards, including tornadoes, hail, wind, and lightning. These high-impact phenomena globally cause both massive property damage and loss of life yet they are quite challenging to forecast. Given the recent explosion in developing machine learning techniques across the weather spectrum and the fact that the skillful prediction of convective weather has immediate societal benefits, we present a thorough review of the current state of the art in artificial intelligence and machine learning techniques for convective hazards. Our review includes both traditional approaches, including support vector machines and decision trees as well as deep learning approaches. We highlight the challenges in developing machine learning approaches to forecast these phenomena across a variety of spatial and temporal scales. We end with a discussion of promising areas of future work for ML for convective weather, including a discussion of the need to create trustworthy AI forecasts that can be used for forecasters in real-time and the need for active cross-sector collaboration on testbeds to validate machine learning methods in operational situations.
{"title":"A Review of Machine Learning for Convective Weather","authors":"A. McGovern, R. Chase, Montgomery Flora, D. Gagne, Ryan Lagerquist, C. Potvin, Nathan Snook, Eric D. Loken","doi":"10.1175/aies-d-22-0077.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0077.1","url":null,"abstract":"\u0000We present an overviewof recentwork on using artificial intelligence/machine learning techniques for forecasting convective weather and its associated hazards, including tornadoes, hail, wind, and lightning. These high-impact phenomena globally cause both massive property damage and loss of life yet they are quite challenging to forecast. Given the recent explosion in developing machine learning techniques across the weather spectrum and the fact that the skillful prediction of convective weather has immediate societal benefits, we present a thorough review of the current state of the art in artificial intelligence and machine learning techniques for convective hazards. Our review includes both traditional approaches, including support vector machines and decision trees as well as deep learning approaches. We highlight the challenges in developing machine learning approaches to forecast these phenomena across a variety of spatial and temporal scales. We end with a discussion of promising areas of future work for ML for convective weather, including a discussion of the need to create trustworthy AI forecasts that can be used for forecasters in real-time and the need for active cross-sector collaboration on testbeds to validate machine learning methods in operational situations.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83016909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1175/aies-d-22-0057.1
Cameron C. Lee, S. Sheridan, G. Dusek, D. Pirhalla
With climate change causing rising sea-levels around the globe, multiple recent efforts in the United States have focused on the prediction of various meteorological factors that can lead to periods of anomalously high-tides despite seemingly benign atmospheric conditions. As part of these efforts, this research explores monthly-scale relationships between sea-level variability and atmospheric circulation patterns, and demonstrates two options for sub-seasonal to seasonal (S2S) predictions of anomalous sea-levels using these patterns as inputs to artificial neural network (ANN) models. Results on the monthly scale are similar to previous research on the daily scale, with above-average sea-levels and an increased risk of high-water events on days with anomalously low atmospheric pressure patterns and wind patterns leading to on-shore or downwelling-producing wind stress. Some wind patterns show risks of high-water events to be over 6-times higher than baseline risk, and exhibit an average water level anomaly of +94mm above normal. In terms of forecasting, nonlinear autoregressive ANN models with exogenous input (NARX models) and pattern-based lagged ANN (PLANN) models show skill over post-processed numerical forecast model output, and simple climatology. Damped-persistence forecasts and PLANN models show nearly the same skill in terms of predicting anomalous sea-levels out to 9 months of lead time, with a slight edge to PLANN models, especially with regard to error statistics. This perspective on forecasting – using predefined circulation patterns along with ANN models – should aid in the real-time prediction of coastal flooding events, among other applications.
{"title":"Atmospheric pattern-based predictions of S2S sea-level anomalies for two selected US locations","authors":"Cameron C. Lee, S. Sheridan, G. Dusek, D. Pirhalla","doi":"10.1175/aies-d-22-0057.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0057.1","url":null,"abstract":"\u0000With climate change causing rising sea-levels around the globe, multiple recent efforts in the United States have focused on the prediction of various meteorological factors that can lead to periods of anomalously high-tides despite seemingly benign atmospheric conditions. As part of these efforts, this research explores monthly-scale relationships between sea-level variability and atmospheric circulation patterns, and demonstrates two options for sub-seasonal to seasonal (S2S) predictions of anomalous sea-levels using these patterns as inputs to artificial neural network (ANN) models. Results on the monthly scale are similar to previous research on the daily scale, with above-average sea-levels and an increased risk of high-water events on days with anomalously low atmospheric pressure patterns and wind patterns leading to on-shore or downwelling-producing wind stress. Some wind patterns show risks of high-water events to be over 6-times higher than baseline risk, and exhibit an average water level anomaly of +94mm above normal. In terms of forecasting, nonlinear autoregressive ANN models with exogenous input (NARX models) and pattern-based lagged ANN (PLANN) models show skill over post-processed numerical forecast model output, and simple climatology. Damped-persistence forecasts and PLANN models show nearly the same skill in terms of predicting anomalous sea-levels out to 9 months of lead time, with a slight edge to PLANN models, especially with regard to error statistics. This perspective on forecasting – using predefined circulation patterns along with ANN models – should aid in the real-time prediction of coastal flooding events, among other applications.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74031535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-19DOI: 10.1175/aies-d-22-0047.1
Chiem van Straaten, K. Whan, D. Coumou, B. van den Hurk, M. Schmeits
Sub-seasonal forecasts are challenging for numerical weather prediction (NWP) and machine learning models alike. Forecasting two-meter temperature (t2m) with a lead-time of two or more weeks requires a forward model to integrate multiple complex interactions, like oceanic and land surface conditions leading to predictableweather patterns. NWPmodels represent these interactions imperfectly, meaning that in certain conditions, errors accumulate and model predictability deviates from real predictability, often for poorly understood reasons. To advance that understanding, this paper corrects conditional errors in NWP forecasts with an artificial neural network (ANN). The ANN post-processes ECMWF extended-range summer temperature forecasts by learning to correct the ECMWF-predicted probability that monthly t2m in western and central Europe exceeds the climatological median. Predictors are objectively selected from ECMWF forecasts themselves, and from states at initialization, i.e. the ERA5 reanalysis. The latter allows the ANN to account for sources of predictability that are biased in the NWP model itself. We attribute ANN-corrections with two explainable AI tools. This reveals that certain erroneous forecasts relate to tropical west Pacific sea surface temperatures at initialization. We conjecture that the atmospheric teleconnection following this source of predictability is imperfectly represented by the ECMWF model. Correcting the associated conditional errors with the ANN improves forecast skill.
{"title":"Correcting sub-seasonal forecast errors with an explainable ANN to understand misrepresented sources of predictability of European summer temperatures","authors":"Chiem van Straaten, K. Whan, D. Coumou, B. van den Hurk, M. Schmeits","doi":"10.1175/aies-d-22-0047.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0047.1","url":null,"abstract":"\u0000Sub-seasonal forecasts are challenging for numerical weather prediction (NWP) and machine learning models alike. Forecasting two-meter temperature (t2m) with a lead-time of two or more weeks requires a forward model to integrate multiple complex interactions, like oceanic and land surface conditions leading to predictableweather patterns. NWPmodels represent these interactions imperfectly, meaning that in certain conditions, errors accumulate and model predictability deviates from real predictability, often for poorly understood reasons. To advance that understanding, this paper corrects conditional errors in NWP forecasts with an artificial neural network (ANN). The ANN post-processes ECMWF extended-range summer temperature forecasts by learning to correct the ECMWF-predicted probability that monthly t2m in western and central Europe exceeds the climatological median. Predictors are objectively selected from ECMWF forecasts themselves, and from states at initialization, i.e. the ERA5 reanalysis. The latter allows the ANN to account for sources of predictability that are biased in the NWP model itself. We attribute ANN-corrections with two explainable AI tools. This reveals that certain erroneous forecasts relate to tropical west Pacific sea surface temperatures at initialization. We conjecture that the atmospheric teleconnection following this source of predictability is imperfectly represented by the ECMWF model. Correcting the associated conditional errors with the ANN improves forecast skill.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79007207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-14DOI: 10.1175/aies-d-22-0085.1
L. H. Leufen, F. Kleinert, M. Schultz
With the impact of tropospheric ozone pollution on humankind, there is a compelling need for robust air quality forecasts. Here, we introduce a novel deep learning (DL) forecasting system called O3ResNet that produces a four-day forecast for ground-level ozone. O3ResNet is based on a convolutional neural network with residual blocks. The model has been trained on 22 years of ozone and nitrogen oxides in-situ measurements and ERA5 reanalysis data from 2000 to 2021 at 328 stations in Central Europe located in rural and suburban environment. Our model outperforms the state-of-the-art Copernicus Atmosphere Monitoring Service regional forecast model ensemble for ground-level ozone with respect to the mean square error and mean absolute error of the daily maximum 8-hour running average ozone, thus marking a major milestone for DL-based ozone prediction. O3ResNet has a very small bias without requiring additional post-processing, and it generalizes well so that new stations can be added with no need to re-train the neural network. As the model works on hourly data, it can be easily adapted to output other air quality metrics. We conclude that O3ResNet is sufficiently advanced and robust to become a test application for operational air quality forecasting with DL.
{"title":"O3ResNet: A deep learning based forecast system to predict local ground-level daily maximum 8-hour average ozone in rural and suburban environment","authors":"L. H. Leufen, F. Kleinert, M. Schultz","doi":"10.1175/aies-d-22-0085.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0085.1","url":null,"abstract":"\u0000With the impact of tropospheric ozone pollution on humankind, there is a compelling need for robust air quality forecasts. Here, we introduce a novel deep learning (DL) forecasting system called O3ResNet that produces a four-day forecast for ground-level ozone. O3ResNet is based on a convolutional neural network with residual blocks. The model has been trained on 22 years of ozone and nitrogen oxides in-situ measurements and ERA5 reanalysis data from 2000 to 2021 at 328 stations in Central Europe located in rural and suburban environment. Our model outperforms the state-of-the-art Copernicus Atmosphere Monitoring Service regional forecast model ensemble for ground-level ozone with respect to the mean square error and mean absolute error of the daily maximum 8-hour running average ozone, thus marking a major milestone for DL-based ozone prediction. O3ResNet has a very small bias without requiring additional post-processing, and it generalizes well so that new stations can be added with no need to re-train the neural network. As the model works on hourly data, it can be easily adapted to output other air quality metrics. We conclude that O3ResNet is sufficiently advanced and robust to become a test application for operational air quality forecasting with DL.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84119445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：