Pub Date : 2023-04-01DOI: 10.1175/aies-d-22-0078.1
Shu‐Chih Yang, Fenghua Ling, Yue Li, Jing‐Jia Luo
The two-step U-Net model (TU-Net) contains a western North Pacific subtropical high (WNPSH) prediction model and a precipitation prediction model fed by the WNPSH predictions, oceanic heat content, and surface temperature. The data-driven forecast model provides improved 4-month lead predictions of the WNPSH and precipitation in the middle and lower reaches of the Yangtze River (MLYR), which has important implications for water resources management and precipitation-related disaster prevention in China. When compared with five state-of-the-art dynamical climate models including the Climate Forecast System of Nanjing University of Information Science and Technology (NUIST-CFS1.0) and four models participating in the North American Multi-Model Ensemble (NMME) project, the TU-Net produces comparable skills in forecasting 4-month lead geopotential height and winds at the 500- and 850-hPa levels. For the 4-month lead prediction of precipitation over the MLYR region, the TU-Net has the best correlation scores and mean latitude-weighted RMSE in each summer month and in boreal summer [June–August (JJA)], and pattern correlation coefficient scores are slightly lower than the dynamical models only in June and JJA. In addition, the results show that the constructed TU-Net is also superior to most of the dynamical models in predicting 2-m air temperature in the MLYR region at a 4-month lead. Thus, the deep learning-based TU-Net model can provide a rapid and inexpensive way to improve the seasonal prediction of summer precipitation and 2-m air temperature over the MLYR region. The purpose of this study is to examine the seasonal predictive skill of the western North Pacific subtropical high anomalies and summer rainfall anomalies over the middle and lower reaches of the Yangtze River region by means of deep learning methods. Our deep learning model provides a rapid and inexpensive way to improve the seasonal prediction of summer precipitation as well as 2-m air temperature. The work has important implications for water resources management and precipitation-related disaster prevention in China and can be extended in the future to predict other climate variables as well.
{"title":"Improving Seasonal Prediction of Summer Precipitation in the Middle–Lower Reaches of the Yangtze River Using a TU-Net Deep Learning Approach","authors":"Shu‐Chih Yang, Fenghua Ling, Yue Li, Jing‐Jia Luo","doi":"10.1175/aies-d-22-0078.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0078.1","url":null,"abstract":"\u0000The two-step U-Net model (TU-Net) contains a western North Pacific subtropical high (WNPSH) prediction model and a precipitation prediction model fed by the WNPSH predictions, oceanic heat content, and surface temperature. The data-driven forecast model provides improved 4-month lead predictions of the WNPSH and precipitation in the middle and lower reaches of the Yangtze River (MLYR), which has important implications for water resources management and precipitation-related disaster prevention in China. When compared with five state-of-the-art dynamical climate models including the Climate Forecast System of Nanjing University of Information Science and Technology (NUIST-CFS1.0) and four models participating in the North American Multi-Model Ensemble (NMME) project, the TU-Net produces comparable skills in forecasting 4-month lead geopotential height and winds at the 500- and 850-hPa levels. For the 4-month lead prediction of precipitation over the MLYR region, the TU-Net has the best correlation scores and mean latitude-weighted RMSE in each summer month and in boreal summer [June–August (JJA)], and pattern correlation coefficient scores are slightly lower than the dynamical models only in June and JJA. In addition, the results show that the constructed TU-Net is also superior to most of the dynamical models in predicting 2-m air temperature in the MLYR region at a 4-month lead. Thus, the deep learning-based TU-Net model can provide a rapid and inexpensive way to improve the seasonal prediction of summer precipitation and 2-m air temperature over the MLYR region.\u0000\u0000\u0000The purpose of this study is to examine the seasonal predictive skill of the western North Pacific subtropical high anomalies and summer rainfall anomalies over the middle and lower reaches of the Yangtze River region by means of deep learning methods. Our deep learning model provides a rapid and inexpensive way to improve the seasonal prediction of summer precipitation as well as 2-m air temperature. The work has important implications for water resources management and precipitation-related disaster prevention in China and can be extended in the future to predict other climate variables as well.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85182335","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 : 2023-03-27DOI: 10.1175/aies-d-22-0060.1
Rikhi Bose, A. Pintar, E. Simiu
The objective of this paper is to employ machine learning (ML) and deep learning (DL) techniques to obtain, from input data (storm features) available in or derived from the HURDAT2 database, models capable of simulating important hurricane properties (e.g., landfall location and wind speed) consistent with historical records. In pursuit of this objective, a trajectory model providing the storm center in terms of longitude and latitude, and intensity models providing the central pressure and maximum 1–min wind speed at 10m elevationwere created. The trajectory and intensity models are coupled and must be advanced together, six hours at a time, as the features that serve as inputs to the models at any given step depend on predictions at the previous time steps. Once a synthetic storm database is generated, properties of interest, such as the frequencies of large wind speeds may be extracted from any part of the simulation domain. The coupling of the trajectory and intensity models obviates the need for an intensity decay model inland of the coastline. Prediction results are compared to historical data, and the efficacy of the storm simulation models is evaluated at four sites: New Orleans, Miami, Cape Hatteras, and Boston.
{"title":"Simulation of Atlantic Hurricane Tracks and Features: A Coupled Machine Learning Approach","authors":"Rikhi Bose, A. Pintar, E. Simiu","doi":"10.1175/aies-d-22-0060.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0060.1","url":null,"abstract":"\u0000The objective of this paper is to employ machine learning (ML) and deep learning (DL) techniques to obtain, from input data (storm features) available in or derived from the HURDAT2 database, models capable of simulating important hurricane properties (e.g., landfall location and wind speed) consistent with historical records. In pursuit of this objective, a trajectory model providing the storm center in terms of longitude and latitude, and intensity models providing the central pressure and maximum 1–min wind speed at 10m elevationwere created. The trajectory and intensity models are coupled and must be advanced together, six hours at a time, as the features that serve as inputs to the models at any given step depend on predictions at the previous time steps. Once a synthetic storm database is generated, properties of interest, such as the frequencies of large wind speeds may be extracted from any part of the simulation domain. The coupling of the trajectory and intensity models obviates the need for an intensity decay model inland of the coastline. Prediction results are compared to historical data, and the efficacy of the storm simulation models is evaluated at four sites: New Orleans, Miami, Cape Hatteras, and Boston.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90547657","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 : 2023-03-10DOI: 10.1175/aies-d-22-0054.1
A. Ramos‐Valle, Joshua J. Alland, A. Bukvic
Many urban coastal communities are experiencing more profound flood impacts due to accelerated sea level rise that sometimes exceed their capacity to protect the built environment. In such cases, relocation may serve as a more effective hazard mitigation and adaptation strategy. However, it is unclear how urban residents living in flood-prone locations perceive the possibility of relocation and under what circumstances they would consider moving. Understanding the factors affecting an individual’s willingness to relocate due to coastal flooding is vital for developing accessible and equitable relocation policies. The main objective of this study is to identify the key considerations that would prompt urban coastal residents to consider permanent relocation due to coastal flooding. We leverage survey data collected from urban areas along the U.S. East Coast, assessing attitudes towards relocation, and design an artificial neural network (ANN) and a random forest (RF) model to find patterns in the survey data and indicate which considerations impact the decision to consider relocation. We trained the models to predict whether respondents would relocate due to socioeconomic factors, past exposure and experiences with flooding, and their flood-related concerns. Analyses performed on the models highlight the importance of flood-related concerns that accurately predict relocation behavior. Some common factors among the model analyses are concerns with increasing crime, the possibility of experiencing one more flood per year in the future, and more frequent business closures due to flooding.
{"title":"Using machine learning to understand relocation drivers of urban coastal populations in response to flooding","authors":"A. Ramos‐Valle, Joshua J. Alland, A. Bukvic","doi":"10.1175/aies-d-22-0054.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0054.1","url":null,"abstract":"\u0000Many urban coastal communities are experiencing more profound flood impacts due to accelerated sea level rise that sometimes exceed their capacity to protect the built environment. In such cases, relocation may serve as a more effective hazard mitigation and adaptation strategy. However, it is unclear how urban residents living in flood-prone locations perceive the possibility of relocation and under what circumstances they would consider moving. Understanding the factors affecting an individual’s willingness to relocate due to coastal flooding is vital for developing accessible and equitable relocation policies. The main objective of this study is to identify the key considerations that would prompt urban coastal residents to consider permanent relocation due to coastal flooding. We leverage survey data collected from urban areas along the U.S. East Coast, assessing attitudes towards relocation, and design an artificial neural network (ANN) and a random forest (RF) model to find patterns in the survey data and indicate which considerations impact the decision to consider relocation. We trained the models to predict whether respondents would relocate due to socioeconomic factors, past exposure and experiences with flooding, and their flood-related concerns. Analyses performed on the models highlight the importance of flood-related concerns that accurately predict relocation behavior. Some common factors among the model analyses are concerns with increasing crime, the possibility of experiencing one more flood per year in the future, and more frequent business closures due to flooding.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84310956","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 : 2023-03-03DOI: 10.1175/aies-d-22-0065.1
Elizabeth Carter, C. Hultquist, T. Wen
Globally available environmental observations (EOs), specifically from satellites and coupled earth systems models, represent some of the largest datasets of the digital age. As the volume of global EOs continues to grow, so does the potential of this data to help earth scientists discover trends and patterns in earth systems at large spatial scales. To leverage global EOs for scientific insight, earth scientists need targeted and accessible exposure to skills in reproducible scientific computing and spatiotemporal data science, and to be empowered to apply their domain understanding to interpret data-driven models for knowledge discovery. The GRRIEn (Generalizable, Reproducible, Robust, and Interpreted Environmental) analysis framework was developed to prepare earth scientists with an introductory statistics background and limited/no understanding of programming and computational methods to use global EOs to successfully generalize insights from local/regional field measurements across unsampled times and locations. GRRIEn analysis is generalizable, meaning results from a sample are translated to landscape scales by combining direct environmental measurements with global EOs using supervised machine learning; robust, meaning that model shows good performance on data with scale-dependent feature and observation dependence; reproducible, based on a standard repository structure so that other scientists can quickly and easily replicate the analysis with a few computational tools; and interpreted, meaning that earth scientists apply domain expertise to ensure that model parameters reflect a physically plausible diagnosis of the environmental system. This tutorial presents standard steps for achieving GRRIEn analysis by combining conventions of rigor in traditional experimental design with the open-science movement.
全球可获得的环境观测(EOs)，特别是来自卫星和耦合地球系统模型的观测，代表了数字时代一些最大的数据集。随着全球生态系统的数量持续增长，这些数据在帮助地球科学家在大空间尺度上发现地球系统的趋势和模式方面的潜力也在不断增加。为了利用全球EOs获得科学洞察力，地球科学家需要有针对性和可访问的可重复科学计算和时空数据科学技能，并被授权应用他们的领域理解来解释数据驱动的模型，以进行知识发现。GRRIEn (generizable, reproducibility, Robust, and interpret environment)分析框架的开发是为了让具有入门统计学背景和对编程和计算方法有限或没有理解的地球科学家准备好使用全球EOs来成功地概括来自未采样时间和地点的局部/区域现场测量的见解。GRRIEn分析是可推广的，这意味着通过使用监督机器学习将直接环境测量与全球EOs相结合，将样本结果转化为景观尺度;鲁棒性，即模型对具有尺度依赖特征和观测依赖的数据表现出良好的性能;可重复性，基于标准存储库结构，以便其他科学家可以使用一些计算工具快速轻松地复制分析;这意味着地球科学家运用该领域的专业知识来确保模型参数反映了对环境系统的物理上合理的诊断。本教程通过将传统实验设计中的严格惯例与开放科学运动相结合，介绍了实现GRRIEn分析的标准步骤。
{"title":"GRRIEn analysis: a data science cheat sheet for earth scientists learning from global earth observations","authors":"Elizabeth Carter, C. Hultquist, T. Wen","doi":"10.1175/aies-d-22-0065.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0065.1","url":null,"abstract":"\u0000Globally available environmental observations (EOs), specifically from satellites and coupled earth systems models, represent some of the largest datasets of the digital age. As the volume of global EOs continues to grow, so does the potential of this data to help earth scientists discover trends and patterns in earth systems at large spatial scales. To leverage global EOs for scientific insight, earth scientists need targeted and accessible exposure to skills in reproducible scientific computing and spatiotemporal data science, and to be empowered to apply their domain understanding to interpret data-driven models for knowledge discovery. The GRRIEn (Generalizable, Reproducible, Robust, and Interpreted Environmental) analysis framework was developed to prepare earth scientists with an introductory statistics background and limited/no understanding of programming and computational methods to use global EOs to successfully generalize insights from local/regional field measurements across unsampled times and locations. GRRIEn analysis is generalizable, meaning results from a sample are translated to landscape scales by combining direct environmental measurements with global EOs using supervised machine learning; robust, meaning that model shows good performance on data with scale-dependent feature and observation dependence; reproducible, based on a standard repository structure so that other scientists can quickly and easily replicate the analysis with a few computational tools; and interpreted, meaning that earth scientists apply domain expertise to ensure that model parameters reflect a physically plausible diagnosis of the environmental system. This tutorial presents standard steps for achieving GRRIEn analysis by combining conventions of rigor in traditional experimental design with the open-science movement.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78053268","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 : 2023-03-02DOI: 10.1175/aies-d-22-0063.1
Dario Dematties, B. Raut, Seongha Park, Robert C. Jackson, Sean Shahkarami, Yongho Kim, R. Sankaran, P. Beckman, S. Collis, N. Ferrier
Accurate cloud type identification and coverage analysis are crucial in understanding the Earth’s radiative budget. Traditional computer vision methods rely on low-level visual features of clouds for estimating cloud coverage or sky conditions. Several handcrafted approaches have been proposed; however, scope for improvement still exists. Newer deep neural networks (DNNs) have demonstrated superior performance for cloud segmentation and categorization. These methods, however, need expert engineering intervention in the preprocessing steps—in the traditional methods—or human assistance in assigning cloud or clear sky labels to a pixel for training DNNs. Such human mediation imposes considerable time and labor costs. We present the application of a new self-supervised learning approach to autonomously extract relevant features from sky images captured by ground-based cameras, for the classification and segmentation of clouds. We evaluate a joint embedding architecture that uses self-knowledge distillation plus regularization. We use two datasets to demonstrate the network’s ability to classify and segment sky images—one with ∼ 85,000 images collected from our ground-based camera and another with 400 labeled images from the WSISEG database. We find that this approach can discriminate full-sky images based on cloud coverage, diurnal variation, and cloud base height. Furthermore, it semantically segments the cloud areas without labels. The approach shows competitive performance in all tested tasks, suggesting a new alternative for cloud characterization.
{"title":"Let’s Unleash the Network Judgment: A Self-Supervised Approach for Cloud Image Analysis","authors":"Dario Dematties, B. Raut, Seongha Park, Robert C. Jackson, Sean Shahkarami, Yongho Kim, R. Sankaran, P. Beckman, S. Collis, N. Ferrier","doi":"10.1175/aies-d-22-0063.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0063.1","url":null,"abstract":"\u0000Accurate cloud type identification and coverage analysis are crucial in understanding the Earth’s radiative budget. Traditional computer vision methods rely on low-level visual features of clouds for estimating cloud coverage or sky conditions. Several handcrafted approaches have been proposed; however, scope for improvement still exists. Newer deep neural networks (DNNs) have demonstrated superior performance for cloud segmentation and categorization. These methods, however, need expert engineering intervention in the preprocessing steps—in the traditional methods—or human assistance in assigning cloud or clear sky labels to a pixel for training DNNs. Such human mediation imposes considerable time and labor costs. We present the application of a new self-supervised learning approach to autonomously extract relevant features from sky images captured by ground-based cameras, for the classification and segmentation of clouds. We evaluate a joint embedding architecture that uses self-knowledge distillation plus regularization. We use two datasets to demonstrate the network’s ability to classify and segment sky images—one with ∼ 85,000 images collected from our ground-based camera and another with 400 labeled images from the WSISEG database. We find that this approach can discriminate full-sky images based on cloud coverage, diurnal variation, and cloud base height. Furthermore, it semantically segments the cloud areas without labels. The approach shows competitive performance in all tested tasks,\u0000suggesting a new alternative for cloud characterization.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75463026","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 : 2023-02-22DOI: 10.1175/aies-d-22-0031.1
D. J. Fulton, Ben J. Clarke, G. Hegerl
We assess the suitability of unpaired image-to-image translation networks for bias correcting data simulated by global atmospheric circulation models. We use the UNIT neural network architecture to map between data from the HadGEM3-A-N216 model and ERA5 reanalysis data in a geographical area centred on the South Asian monsoon, which has well-documented serious biases in this model. The UNIT network corrects cross-variable correlations and spatial structures but creates bias corrections with less extreme values than the target distribution. By combining the UNIT neural network with the classical technique of quantile mapping, we can produce bias corrections that are better than either alone. The UNIT+QM scheme is shown to correct cross-variable correlations, spatial patterns, and all marginal distributions of single variables. The careful correction of such joint distributions is of high importance for compound extremes research.
{"title":"Bias correcting climate model simulations using unpaired image-to-image translation networks","authors":"D. J. Fulton, Ben J. Clarke, G. Hegerl","doi":"10.1175/aies-d-22-0031.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0031.1","url":null,"abstract":"\u0000We assess the suitability of unpaired image-to-image translation networks for bias correcting data simulated by global atmospheric circulation models. We use the UNIT neural network architecture to map between data from the HadGEM3-A-N216 model and ERA5 reanalysis data in a geographical area centred on the South Asian monsoon, which has well-documented serious biases in this model. The UNIT network corrects cross-variable correlations and spatial structures but creates bias corrections with less extreme values than the target distribution. By combining the UNIT neural network with the classical technique of quantile mapping, we can produce bias corrections that are better than either alone. The UNIT+QM scheme is shown to correct cross-variable correlations, spatial patterns, and all marginal distributions of single variables. The careful correction of such joint distributions is of high importance for compound extremes research.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77804866","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 : 2023-02-16DOI: 10.1175/aies-d-22-0053.1
Andrew P. Osborne, Jian Zhang, M. Simpson, K. Howard, S. Cocks
The Multi-Radar Multi-Sensor (MRMS) system produces a suite of hydrometeorological products that are widely used for applications such as flash flood warning operations, water resource management, and climatological studies. The MRMS radar-based quantitative precipitation estimation (QPE) products have greater challenges in the western United States compared to the eastern two-thirds of the CONUS due to terrain-related blockages and gaps in radar coverage. Further, orographic enhancement of precipitation often occurs, which is highly variable in space and time and difficult to accurately capture with physically-based approaches. A deep learning approach was applied in this study to understand the correlations between several interacting variables and to obtain a more accurate precipitation estimation in these scenarios. The model presented here is a convolutional neural network (CNN), which uses spatial information from small grids of several radar variables to predict an estimated precipitation value at the central grid point. Several case analyses are presented along with a year-long statistical evaluation. The CNN model 24-hour QPE shows higher accuracy than the MRMS radar QPE for several cool-season atmospheric river events. Areas of consistent improvement from the CNN model are highlighted in the discussion along with areas where the model can be further improved. The initial findings from this work help set the foundation for further exploration of machine learning techniques and products for precipitation estimation as part of the MRMS operational system.
{"title":"Application of Machine Learning Techniques to Im prove Multi-Radar Multi-Sensor (MRMS) Precipitation Estimates in the Western United States","authors":"Andrew P. Osborne, Jian Zhang, M. Simpson, K. Howard, S. Cocks","doi":"10.1175/aies-d-22-0053.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0053.1","url":null,"abstract":"\u0000The Multi-Radar Multi-Sensor (MRMS) system produces a suite of hydrometeorological products that are widely used for applications such as flash flood warning operations, water resource management, and climatological studies. The MRMS radar-based quantitative precipitation estimation (QPE) products have greater challenges in the western United States compared to the eastern two-thirds of the CONUS due to terrain-related blockages and gaps in radar coverage. Further, orographic enhancement of precipitation often occurs, which is highly variable in space and time and difficult to accurately capture with physically-based approaches. A deep learning approach was applied in this study to understand the correlations between several interacting variables and to obtain a more accurate precipitation estimation in these scenarios. The model presented here is a convolutional neural network (CNN), which uses spatial information from small grids of several radar variables to predict an estimated precipitation value at the central grid point. Several case analyses are presented along with a year-long statistical evaluation. The CNN model 24-hour QPE shows higher accuracy than the MRMS radar QPE for several cool-season atmospheric river events. Areas of consistent improvement from the CNN model are highlighted in the discussion along with areas where the model can be further improved. The initial findings from this work help set the foundation for further exploration of machine learning techniques and products for precipitation estimation as part of the MRMS operational system.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"100 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83509069","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 : 2023-02-16DOI: 10.1175/aies-d-22-0040.1
W. Pringle, Zachary Burnett, K. Sargsyan, S. Moghimi, E. Myers
This study proposes and assesses a methodology to obtain high-quality probabilistic predictions and uncertainty information of near-landfall tropical cyclone(TC)-driven storm tide and inundation with limited time and resources. Forecasts of TC track, intensity, and size are perturbed according to quasi-random Korobov sequences of historical forecast errors with assumed Gaussian and uniform statistical distributions. These perturbations are run in an ensemble of hydrodynamic storm tide model simulations. The resulting set of maximum water surface elevations are dimensionality reduced using Karhunen-Lo`eve expansions and then used as a training set to develop a Polynomial Chaos (PC) surrogate model from which global sensitivities and probabilistic predictions can be extracted. The maximum water surface elevation is extrapolated over dry points incorporating energy head loss with distance to properly train the surrogate for predicting inundation. We find that the surrogate constructed with 3rd order PCs using Elastic Net penalized regression with Leave-One-Out cross-validation provides the most robust fit across training and test sets. Probabilistic predictions of maximum water surface elevation and inundation area by the surrogate model at 48-hour lead time for three past U.S. landfalling hurricanes (Irma 2017, Florence 2018, and Laura 2020) are found to be reliable when compared to best-track hindcast simulation results, even when trained with as few as 19 samples. The maximum water surface elevation is most sensitive to perpendicular track-offset errors for all three storms. Laura is also highly sensitive to storm size and has the least reliable prediction.
{"title":"Efficient Probabilistic Prediction and Uncertainty Quantification of Tropical Cyclone-driven Storm Tides and Inundation","authors":"W. Pringle, Zachary Burnett, K. Sargsyan, S. Moghimi, E. Myers","doi":"10.1175/aies-d-22-0040.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0040.1","url":null,"abstract":"\u0000This study proposes and assesses a methodology to obtain high-quality probabilistic predictions and uncertainty information of near-landfall tropical cyclone(TC)-driven storm tide and inundation with limited time and resources. Forecasts of TC track, intensity, and size are perturbed according to quasi-random Korobov sequences of historical forecast errors with assumed Gaussian and uniform statistical distributions. These perturbations are run in an ensemble of hydrodynamic storm tide model simulations. The resulting set of maximum water surface elevations are dimensionality reduced using Karhunen-Lo`eve expansions and then used as a training set to develop a Polynomial Chaos (PC) surrogate model from which global sensitivities and probabilistic predictions can be extracted. The maximum water surface elevation is extrapolated over dry points incorporating energy head loss with distance to properly train the surrogate for predicting inundation. We find that the surrogate constructed with 3rd order PCs using Elastic Net penalized regression with Leave-One-Out cross-validation provides the most robust fit across training and test sets. Probabilistic predictions of maximum water surface elevation and inundation area by the surrogate model at 48-hour lead time for three past U.S. landfalling hurricanes (Irma 2017, Florence 2018, and Laura 2020) are found to be reliable when compared to best-track hindcast simulation results, even when trained with as few as 19 samples. The maximum water surface elevation is most sensitive to perpendicular track-offset errors for all three storms. Laura is also highly sensitive to storm size and has the least reliable prediction.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82664166","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 : 2023-02-14DOI: 10.1175/aies-d-22-0076.1
Mohamad Abed El Rahman Hammoud, Humam Alwassel, Bernard Ghanem, O. Knio, I. Hoteit
Backward-in-time predictions are needed to better understand the underlying dynamics of physical fluid flows and improve future forecasts. However, integrating fluid flows backward in time is challenging because of numerical instabilities caused by the diffusive nature of the fluid systems and nonlinearities of the governing equations. Although this problem has been long addressed using a non-positive diffusion coefficient when integrating backward, it is notoriously inaccurate. In this study, a physics-informed deep neural network (PI-DNN) is presented to predict past states of a dissipative dynamical system from snapshots of the subsequent evolution of the system state. The performance of the PI-DNN is investigated using several systematic numerical experiments and the accuracy of the backward-in-time predictions is evaluated in terms of different error metrics. The proposed PI-DNN can predict the previous state of the Rayleigh–Bénard convection with an 8-time step average normalized ℓ2-error of less than 2% for a turbulent flow at a Rayleigh number of 105.
{"title":"Physics-Informed Deep Neural Network for Backward-in-Time Prediction: Application to Rayleigh–Bénard Convection","authors":"Mohamad Abed El Rahman Hammoud, Humam Alwassel, Bernard Ghanem, O. Knio, I. Hoteit","doi":"10.1175/aies-d-22-0076.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0076.1","url":null,"abstract":"\u0000Backward-in-time predictions are needed to better understand the underlying dynamics of physical fluid flows and improve future forecasts. However, integrating fluid flows backward in time is challenging because of numerical instabilities caused by the diffusive nature of the fluid systems and nonlinearities of the governing equations. Although this problem has been long addressed using a non-positive diffusion coefficient when integrating backward, it is notoriously inaccurate. In this study, a physics-informed deep neural network (PI-DNN) is presented to predict past states of a dissipative dynamical system from snapshots of the subsequent evolution of the system state. The performance of the PI-DNN is investigated using several systematic numerical experiments and the accuracy of the backward-in-time predictions is evaluated in terms of different error metrics. The proposed PI-DNN can predict the previous state of the Rayleigh–Bénard convection with an 8-time step average normalized ℓ2-error of less than 2% for a turbulent flow at a Rayleigh number of 105.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78484282","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 : 2023-02-10DOI: 10.1175/aies-d-22-0044.1
M. D. Mallet, S. Alexander, A. Protat, S. Fiddes
Earth System models struggle to simulate clouds and their radiative effects over the Southern Ocean, partly due to a lack of measurements and targeted cloud microphysics knowledge. We have evaluated biases of downwelling shortwave radiation in the ERA5 climate reanalysis using 25 years (1995 - 2019) of summertime surface measurements, collected on the RSV Aurora Australis, the RV Investigator, and at Macquarie Island. During October - March daylight hours, the ERA5 simulation of SWdown exhibited large errors (mean bias = 54 Wm−2, mean absolute error = 82 Wm−2, root mean squared error = 132 Wm-2, R2 = 0.71). To determine whether we could improve these statistics, we bypassed ERA5’s radiative transfer model for SWdown with machine learning-based models using a number of ERA5’s grid-scale meteorological variables as predictors. These models were trained and tested with the surface measurements of SWdown using a 10-fold shuffle split. An XGBoost and a random forest-based model setup had the best performance relative to ERA5, both with a near complete reduction of the mean bias error, a decrease in the mean absolute error and root mean squared error by 25% ± 3 %, and an increase in the R2 value of 5% ± 1% over the 10 splits. Large improvements occurred at higher latitudes and cyclone cold-sectors, where ERA5 performed most poorly. We further interpret our methods using SHapley Additive exPlanations. Our results indicate that data-driven techniques could have an important role in simulating surface radiation fluxes and in improving reanalysis products.
{"title":"Reducing Southern Ocean shortwave radiation errors in the ERA5 reanalysis with machine learning and 25 years of surface observations","authors":"M. D. Mallet, S. Alexander, A. Protat, S. Fiddes","doi":"10.1175/aies-d-22-0044.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0044.1","url":null,"abstract":"\u0000Earth System models struggle to simulate clouds and their radiative effects over the Southern Ocean, partly due to a lack of measurements and targeted cloud microphysics knowledge. We have evaluated biases of downwelling shortwave radiation in the ERA5 climate reanalysis using 25 years (1995 - 2019) of summertime surface measurements, collected on the RSV Aurora Australis, the RV Investigator, and at Macquarie Island. During October - March daylight hours, the ERA5 simulation of SWdown exhibited large errors (mean bias = 54 Wm−2, mean absolute error = 82 Wm−2, root mean squared error = 132 Wm-2, R2 = 0.71). To determine whether we could improve these statistics, we bypassed ERA5’s radiative transfer model for SWdown with machine learning-based models using a number of ERA5’s grid-scale meteorological variables as predictors. These models were trained and tested with the surface measurements of SWdown using a 10-fold shuffle split. An XGBoost and a random forest-based model setup had the best performance relative to ERA5, both with a near complete reduction of the mean bias error, a decrease in the mean absolute error and root mean squared error by 25% ± 3 %, and an increase in the R2 value of 5% ± 1% over the 10 splits. Large improvements occurred at higher latitudes and cyclone cold-sectors, where ERA5 performed most poorly. We further interpret our methods using SHapley Additive exPlanations. Our results indicate that data-driven techniques could have an important role in simulating surface radiation fluxes and in improving reanalysis products.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84806755","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：