Pub Date : 2023-09-27DOI: 10.1175/aies-d-23-0029.1
Maruti K. Mudunuru, James Ang, Mahantesh Halappanavar, Simon D. Hammond, Maya B. Gokhale, James C. Hoe, Tushar Krishna, Sarat S. Sreepathi, Matthew R. Norman, Ivy B. Peng, Philip W. Jones
Abstract Recently, the U.S. Department of Energy (DOE), Office of Science, Biological and Environmental Research (BER), and Advanced Scientific Computing Research (ASCR) programs organized and held the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop series. From this workshop, a critical conclusion that the DOE BER and ASCR community came to is the requirement to develop a new paradigm for Earth system predictability focused on enabling artificial intelligence (AI) across the field, lab, modeling, and analysis activities, called ModEx. The BER’s ‘Model-Experimentation’, ModEx, is an iterative approach that enables process models to generate hypotheses. The developed hypotheses inform field and laboratory efforts to collect measurement and observation data, which are subsequently used to parameterize, drive, and test model (e.g., process-based) predictions. A total of 17 technical sessions were held in this AI4ESP workshop series. This paper discusses the topic of the ‘AI Architectures and Co-design’ session and associated outcomes. The AI Architectures and Co-design session included two invited talks, two plenary discussion panels, and three breakout rooms that covered specific topics, including: (1) DOE high-performance computing (HPC) Systems, (2) Cloud HPC Systems, and (3) Edge computing and Internet of Things (IoT). We also provide forward-looking ideas and perspectives on potential research in this co-design area that can be achieved by synergies with the other 16 session topics. These ideas include topics such as: (1) reimagining co-design, (2) data acquisition to distribution, (3) heterogeneous HPC solutions for integration of AI/ML and other data analytics like uncertainty quantification with earth system modeling and simulation, and (4) AI-enabled sensor integration into earth system measurements and observations. Such perspectives are a distinguishing aspect of this paper.
{"title":"Perspectives on AI Architectures and Co-design for Earth System Predictability","authors":"Maruti K. Mudunuru, James Ang, Mahantesh Halappanavar, Simon D. Hammond, Maya B. Gokhale, James C. Hoe, Tushar Krishna, Sarat S. Sreepathi, Matthew R. Norman, Ivy B. Peng, Philip W. Jones","doi":"10.1175/aies-d-23-0029.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0029.1","url":null,"abstract":"Abstract Recently, the U.S. Department of Energy (DOE), Office of Science, Biological and Environmental Research (BER), and Advanced Scientific Computing Research (ASCR) programs organized and held the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop series. From this workshop, a critical conclusion that the DOE BER and ASCR community came to is the requirement to develop a new paradigm for Earth system predictability focused on enabling artificial intelligence (AI) across the field, lab, modeling, and analysis activities, called ModEx. The BER’s ‘Model-Experimentation’, ModEx, is an iterative approach that enables process models to generate hypotheses. The developed hypotheses inform field and laboratory efforts to collect measurement and observation data, which are subsequently used to parameterize, drive, and test model (e.g., process-based) predictions. A total of 17 technical sessions were held in this AI4ESP workshop series. This paper discusses the topic of the ‘AI Architectures and Co-design’ session and associated outcomes. The AI Architectures and Co-design session included two invited talks, two plenary discussion panels, and three breakout rooms that covered specific topics, including: (1) DOE high-performance computing (HPC) Systems, (2) Cloud HPC Systems, and (3) Edge computing and Internet of Things (IoT). We also provide forward-looking ideas and perspectives on potential research in this co-design area that can be achieved by synergies with the other 16 session topics. These ideas include topics such as: (1) reimagining co-design, (2) data acquisition to distribution, (3) heterogeneous HPC solutions for integration of AI/ML and other data analytics like uncertainty quantification with earth system modeling and simulation, and (4) AI-enabled sensor integration into earth system measurements and observations. Such perspectives are a distinguishing aspect of this paper.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135477336","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 : 2023-09-27DOI: 10.1175/aies-d-23-0044.1
Stephanie M. Ortland, Michael J. Pavolonis, John L. Cintineo
Abstract This paper presents the Thunderstorm Nowcasting Tool (ThunderCast), a 24-hour, year round model for predicting the location of convection that is likely to initiate or remain a thunderstorm in the next 0-60 minutes in the continental United States, adapted from existing deep learning convection applications. ThunderCast utilizes a U-Net convolutional neural network for semantic segmentation trained on 320 km by 320 km data patches with four inputs and one target dataset. The inputs are satellite bands from the Geostationary Operational Environmental Satellite (GOES-16) Advanced Baseline Imager (ABI) in the visible, shortwave infrared, and longwave infrared spectrum, and the target is Multi-Radar Multi-Sensor (MRMS) radar reflectivity at the - 10°C isothermin the atmosphere. On a pixel-by-pixel basis, ThunderCast has high accuracy, recall, and specificity but is subject to false positive predictions resulting in low precision. However, the number of false positives decreases when buffering the target values with a 15×15 km centered window indicating ThunderCast’s predictions are useful within a buffered area. To demonstrate the initial prediction capabilities of ThunderCast, three case studies are presented: a mesoscale convective vortex, sea breeze convection, and monsoonal convection in the southwestern United States. The case studies illustrate that the ThunderCast model effectively nowcasts the location of newly initiated and ongoing active convection, within the next 60 minutes, under a variety of geographic and meteorological conditions.
{"title":"The Development and Initial Capabilities of ThunderCast, a Deep-Learning Model for Thunderstorm Nowcasting in the United States","authors":"Stephanie M. Ortland, Michael J. Pavolonis, John L. Cintineo","doi":"10.1175/aies-d-23-0044.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0044.1","url":null,"abstract":"Abstract This paper presents the Thunderstorm Nowcasting Tool (ThunderCast), a 24-hour, year round model for predicting the location of convection that is likely to initiate or remain a thunderstorm in the next 0-60 minutes in the continental United States, adapted from existing deep learning convection applications. ThunderCast utilizes a U-Net convolutional neural network for semantic segmentation trained on 320 km by 320 km data patches with four inputs and one target dataset. The inputs are satellite bands from the Geostationary Operational Environmental Satellite (GOES-16) Advanced Baseline Imager (ABI) in the visible, shortwave infrared, and longwave infrared spectrum, and the target is Multi-Radar Multi-Sensor (MRMS) radar reflectivity at the - 10°C isothermin the atmosphere. On a pixel-by-pixel basis, ThunderCast has high accuracy, recall, and specificity but is subject to false positive predictions resulting in low precision. However, the number of false positives decreases when buffering the target values with a 15×15 km centered window indicating ThunderCast’s predictions are useful within a buffered area. To demonstrate the initial prediction capabilities of ThunderCast, three case studies are presented: a mesoscale convective vortex, sea breeze convection, and monsoonal convection in the southwestern United States. The case studies illustrate that the ThunderCast model effectively nowcasts the location of newly initiated and ongoing active convection, within the next 60 minutes, under a variety of geographic and meteorological conditions.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135477093","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 : 2023-09-21DOI: 10.1175/aies-d-23-0015.1
Nicolaas J. Annau, Alex J. Cannon, Adam H. Monahan
Abstract This paper explores the application of emerging machine learning methods from image super-resolution (SR) to the task of statistical downscaling. We specifically focus on convolutional neural network-based Generative Adversarial Networks (GANs). Our GANs are conditioned on low-resolution (LR) inputs to generate high-resolution (HR) surface winds emulating Weather Research and Forecasting (WRF) model simulations over North America. Unlike traditional SR models, where LR inputs are idealized coarsened versions of the HR images, WRF emulation involves using non-idealized LR and HR pairs resulting in shared-scale mismatches due to internal variability. Our study builds upon current SR-based statistical downscaling by experimenting with a novel frequency-separation (FS) approach from the computer vision field. To assess the skill of SR models, we carefully select evaluation metrics, and focus on performance measures based on spatial power spectra. Our analyses reveal how GAN configurations influence spatial structures in the generated fields, particularly biases in spatial variability spectra. Using power spectra to evaluate the FS experiments reveals that successful applications of FS in computer vision do not translate to climate fields. However, the FS experiments demonstrate the sensitivity of power spectra to a commonly used GAN-based SR objective function, which helps interpret and understand its role in determining spatial structures. This result motivates the development of a novel partial frequency-separation scheme as a promising configuration option. We also quantify the influence on GAN performance of non-idealized LR fields resulting from internal variability. Furthermore, we conduct a spectra-based feature-importance experiment allowing us to explore the dependence of the spatial structure of generated fields on different physically relevant LR covariates.
{"title":"Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales","authors":"Nicolaas J. Annau, Alex J. Cannon, Adam H. Monahan","doi":"10.1175/aies-d-23-0015.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0015.1","url":null,"abstract":"Abstract This paper explores the application of emerging machine learning methods from image super-resolution (SR) to the task of statistical downscaling. We specifically focus on convolutional neural network-based Generative Adversarial Networks (GANs). Our GANs are conditioned on low-resolution (LR) inputs to generate high-resolution (HR) surface winds emulating Weather Research and Forecasting (WRF) model simulations over North America. Unlike traditional SR models, where LR inputs are idealized coarsened versions of the HR images, WRF emulation involves using non-idealized LR and HR pairs resulting in shared-scale mismatches due to internal variability. Our study builds upon current SR-based statistical downscaling by experimenting with a novel frequency-separation (FS) approach from the computer vision field. To assess the skill of SR models, we carefully select evaluation metrics, and focus on performance measures based on spatial power spectra. Our analyses reveal how GAN configurations influence spatial structures in the generated fields, particularly biases in spatial variability spectra. Using power spectra to evaluate the FS experiments reveals that successful applications of FS in computer vision do not translate to climate fields. However, the FS experiments demonstrate the sensitivity of power spectra to a commonly used GAN-based SR objective function, which helps interpret and understand its role in determining spatial structures. This result motivates the development of a novel partial frequency-separation scheme as a promising configuration option. We also quantify the influence on GAN performance of non-idealized LR fields resulting from internal variability. Furthermore, we conduct a spectra-based feature-importance experiment allowing us to explore the dependence of the spatial structure of generated fields on different physically relevant LR covariates.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136136403","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}
Abstract In this study, we introduce a self-supervised deep neural network approach to classify satellite images into independent classes of cloud systems. The driving question of the work is to understand whether our algorithm can capture cloud variability and identify distinct cloud regimes. Ultimately, we want to achieve generalization such that the algorithm can be applied to unseen data and thus help automatically extract relevant information important to atmospheric science and renewable energy applications from the ever-increasing satellite data stream. We use cloud optical depth (COD) retrieved from post-processed high-resolution Meteosat Second Generation (MSG) satellite data as input for the network. The network’s architecture is based on the DeepCluster version 2 and consists of a convolutional neural network and a multilayer perceptron, followed by a k-means algorithm. We explore the network’s training capabilities by analyzing the centroids and feature vectors found from progressive minimization of the cross entropy loss function. By making use of additional MSG retrieval products based on multi-channel information, we derive the optimum number of classes to determine independent cloud regimes. We test the network capabilities on COD data from 2013 and find that the trained neural network gives insights into the cloud systems’ persistence and transition probability. The generalization on the 2015 data shows good skills of our algorithm with unseen data, but results depend on the spatial scale of cloud systems.
{"title":"Understanding cloud systems structure and organization using a machine’s self-learning approach","authors":"Dwaipayan Chatterjee, Claudia Acquistapace, Hartwig Deneke, Susanne Crewell","doi":"10.1175/aies-d-22-0096.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0096.1","url":null,"abstract":"Abstract In this study, we introduce a self-supervised deep neural network approach to classify satellite images into independent classes of cloud systems. The driving question of the work is to understand whether our algorithm can capture cloud variability and identify distinct cloud regimes. Ultimately, we want to achieve generalization such that the algorithm can be applied to unseen data and thus help automatically extract relevant information important to atmospheric science and renewable energy applications from the ever-increasing satellite data stream. We use cloud optical depth (COD) retrieved from post-processed high-resolution Meteosat Second Generation (MSG) satellite data as input for the network. The network’s architecture is based on the DeepCluster version 2 and consists of a convolutional neural network and a multilayer perceptron, followed by a k-means algorithm. We explore the network’s training capabilities by analyzing the centroids and feature vectors found from progressive minimization of the cross entropy loss function. By making use of additional MSG retrieval products based on multi-channel information, we derive the optimum number of classes to determine independent cloud regimes. We test the network capabilities on COD data from 2013 and find that the trained neural network gives insights into the cloud systems’ persistence and transition probability. The generalization on the 2015 data shows good skills of our algorithm with unseen data, but results depend on the spatial scale of cloud systems.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135060032","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 : 2023-09-14DOI: 10.1175/aies-d-23-0017.1
Charlotte Cambier van Nooten, Koert Schreurs, Jasper S. Wijnands, Hidde Leijnse, Maurice Schmeits, Kirien Whan, Yuliya Shapovalova
Abstract Precipitation nowcasting is essential for weather-dependent decision-making, but it remains a challenging problem despite active research. The combination of radar data and deep learning methods have opened a new avenue for research. Radar data is well-suited for precipitation nowcasting due to the high space-time resolution of the precipitation field. On the other hand, deep learning methods allow the exploitation of possible nonlinearities in the precipitation process. Thus far, deep learning approaches have demonstrated equal or better performance than optical flow methods for low-intensity precipitation, but nowcasting high-intensity events remains a challenge. In this study, we have built a deep generative model with various extensions to improve nowcasting of heavy precipitation intensities. Specifically, we consider different loss functions and how the incorporation of temperature data as an additional feature affects the model’s performance. Using radar data from KNMI and 5-90 minutes lead times, we demonstrate that the deep generative model with the proposed loss function and temperature feature outperforms other state-of-the-art models and benchmarks. Our model, with both loss function and feature extensions, is skilful at nowcasting precipitation the high rainfall intensities, up to 60 minutes lead time.
{"title":"Improving precipitation nowcasting for high-intensity events using deep generative models with balanced loss and temperature data: a case study in the Netherlands","authors":"Charlotte Cambier van Nooten, Koert Schreurs, Jasper S. Wijnands, Hidde Leijnse, Maurice Schmeits, Kirien Whan, Yuliya Shapovalova","doi":"10.1175/aies-d-23-0017.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0017.1","url":null,"abstract":"Abstract Precipitation nowcasting is essential for weather-dependent decision-making, but it remains a challenging problem despite active research. The combination of radar data and deep learning methods have opened a new avenue for research. Radar data is well-suited for precipitation nowcasting due to the high space-time resolution of the precipitation field. On the other hand, deep learning methods allow the exploitation of possible nonlinearities in the precipitation process. Thus far, deep learning approaches have demonstrated equal or better performance than optical flow methods for low-intensity precipitation, but nowcasting high-intensity events remains a challenge. In this study, we have built a deep generative model with various extensions to improve nowcasting of heavy precipitation intensities. Specifically, we consider different loss functions and how the incorporation of temperature data as an additional feature affects the model’s performance. Using radar data from KNMI and 5-90 minutes lead times, we demonstrate that the deep generative model with the proposed loss function and temperature feature outperforms other state-of-the-art models and benchmarks. Our model, with both loss function and feature extensions, is skilful at nowcasting precipitation the high rainfall intensities, up to 60 minutes lead time.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134911383","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 : 2023-09-13DOI: 10.1175/aies-d-22-0095.1
Jordan Richards, Raphaël Huser, Emanuele Bevacqua, Jakob Zscheischler
Abstract Extreme wildfires continue to be a significant cause of human death and biodiversity destruction within countries that encompass the Mediterranean Basin. Recent worrying trends in wildfire activity (i.e., occurrence and spread) suggest that wildfires are likely to be highly impacted by climate change. In order to facilitate appropriate risk mitigation, it is imperative to identify the main drivers of extreme wildfires and assess their spatio-temporal trends, with a view to understanding the impacts of the changing climate on fire activity. To this end, we analyse the monthly burnt area due to wildfires over a region encompassing most of Europe and the Mediterranean Basin from 2001 to 2020, and identify high fire activity during this period in eastern Europe, Algeria, Italy and Portugal. We build an extreme quantile regression model with a high-dimensional predictor set describing meteorological conditions, land cover usage, and orography, for the domain. To model the complex relationships between the predictor variables and wildfires, we make use of a hybrid statistical deep-learning framework that allows us to disentangle the effects of vapour-pressure deficit (VPD), air temperature, and drought on wildfire activity. Our results highlight that whilst VPD, air temperature, and drought significantly affect wildfire occurrence, only VPD affects wildfire spread. Furthermore, to gain insights into the effect of climate trends on wildfires in the near future, we focus on the extreme wildfires in August 2001 and perturb VPD and temperature according to their observed trends. We find that, on average over Europe, trends in temperature (median over Europe: +0.04K per year) lead to a relative increase of 17.1% and 1.6% in the expected frequency and severity, respectively, of wildfires in August 2001; similar analyses using VPD (median over Europe: +4.82Pa per year) give respective increases of 1.2% and 3.6%. Our analysis finds evidence suggesting that global warming can lead to spatially non-uniform changes in wildfire activity.
{"title":"Insights into the drivers and spatio-temporal trends of extreme Mediterranean wildfires with statistical deep-learning","authors":"Jordan Richards, Raphaël Huser, Emanuele Bevacqua, Jakob Zscheischler","doi":"10.1175/aies-d-22-0095.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0095.1","url":null,"abstract":"Abstract Extreme wildfires continue to be a significant cause of human death and biodiversity destruction within countries that encompass the Mediterranean Basin. Recent worrying trends in wildfire activity (i.e., occurrence and spread) suggest that wildfires are likely to be highly impacted by climate change. In order to facilitate appropriate risk mitigation, it is imperative to identify the main drivers of extreme wildfires and assess their spatio-temporal trends, with a view to understanding the impacts of the changing climate on fire activity. To this end, we analyse the monthly burnt area due to wildfires over a region encompassing most of Europe and the Mediterranean Basin from 2001 to 2020, and identify high fire activity during this period in eastern Europe, Algeria, Italy and Portugal. We build an extreme quantile regression model with a high-dimensional predictor set describing meteorological conditions, land cover usage, and orography, for the domain. To model the complex relationships between the predictor variables and wildfires, we make use of a hybrid statistical deep-learning framework that allows us to disentangle the effects of vapour-pressure deficit (VPD), air temperature, and drought on wildfire activity. Our results highlight that whilst VPD, air temperature, and drought significantly affect wildfire occurrence, only VPD affects wildfire spread. Furthermore, to gain insights into the effect of climate trends on wildfires in the near future, we focus on the extreme wildfires in August 2001 and perturb VPD and temperature according to their observed trends. We find that, on average over Europe, trends in temperature (median over Europe: +0.04K per year) lead to a relative increase of 17.1% and 1.6% in the expected frequency and severity, respectively, of wildfires in August 2001; similar analyses using VPD (median over Europe: +4.82Pa per year) give respective increases of 1.2% and 3.6%. Our analysis finds evidence suggesting that global warming can lead to spatially non-uniform changes in wildfire activity.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135739847","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 : 2023-09-06DOI: 10.1175/aies-d-23-0016.1
Lei Meng, Laiyin Zhu
Snow is an important component of Earth’s climate system and snowfall intensity and variation often significantly impact society, the environment, and ecosystems. Understanding monthly and seasonal snowfall intensity and variations is challenging because of multiple controlling mechanisms at different spatial and temporal scales. Using a 65-year of in-situ snowfall observation, we evaluated seven machine learning algorithms for modeling monthly and seasonal snowfall in the Lower Peninsula of Michigan (LPM) based on selected environmental and climatic variables. Our results show that the Bayesian Additive Regression Trees (BART) has the best fitting (R2 = 0.88) and out-of-sample estimation skills (R2 = 0.58) for the monthly mean snowfall followed by the Random Forest model. The BART also demonstrates strong estimation skills for large monthly snowfall amounts. Both BART and the Random Forest models suggest that topography, local/regional environmental factors, and teleconnection indices can significantly improve the estimation of monthly and seasonal snowfall amounts in the LPM. These statistical models based on machine learning algorithms can incorporate variables at multiple scales and address nonlinear responses of snowfall variations to environmental/climatic changes. It demonstrated that the multiscale machine learning techniques provide a reliable and computationally efficient approach to modeling snowfall intensity and variability.
{"title":"Statistical modeling of monthly and seasonal Michigan snowfall based on machine learning: A multiscale approach","authors":"Lei Meng, Laiyin Zhu","doi":"10.1175/aies-d-23-0016.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0016.1","url":null,"abstract":"\u0000Snow is an important component of Earth’s climate system and snowfall intensity and variation often significantly impact society, the environment, and ecosystems. Understanding monthly and seasonal snowfall intensity and variations is challenging because of multiple controlling mechanisms at different spatial and temporal scales. Using a 65-year of in-situ snowfall observation, we evaluated seven machine learning algorithms for modeling monthly and seasonal snowfall in the Lower Peninsula of Michigan (LPM) based on selected environmental and climatic variables. Our results show that the Bayesian Additive Regression Trees (BART) has the best fitting (R2 = 0.88) and out-of-sample estimation skills (R2 = 0.58) for the monthly mean snowfall followed by the Random Forest model. The BART also demonstrates strong estimation skills for large monthly snowfall amounts. Both BART and the Random Forest models suggest that topography, local/regional environmental factors, and teleconnection indices can significantly improve the estimation of monthly and seasonal snowfall amounts in the LPM. These statistical models based on machine learning algorithms can incorporate variables at multiple scales and address nonlinear responses of snowfall variations to environmental/climatic changes. It demonstrated that the multiscale machine learning techniques provide a reliable and computationally efficient approach to modeling snowfall intensity and variability.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81092449","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 : 2023-08-31DOI: 10.1175/aies-d-23-0005.1
Elias C. Massoud, Forrest Hoffman, Zheng Shi, Jinyun Tang, Elie Alhajjar, Mallory Barnes, R. Braghiere, Zoe Cardon, Nathan Collier, Octavia Crompton, P. Dennedy‐Frank, S. Gautam, Miquel A Gonzalez-Meler, Julia K. Green, Charles Koven, Paul Levine, Natasha MacBean, J. Mao, Richard Tran Mills, U. Mishra, M. Mudunuru, Alexandre A. Renchon, Sarah Scott, E. Siirila‐Woodburn, Matthias Sprenger, C. Tague, Yaoping Wang, Chonggang Xu, C. Zarakas
In November 2021, the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop was held, which involved hundreds of researchers from dozens of institutions (Hickmon et al., 2022). There were 17 sessions held at the workshop, including one on Ecohydrology. The Ecohydrology session included various break-out rooms that addressed specific topics, including: 1) Soils & Belowground, 2) Watersheds, 3) Hydrology, 4) Ecophysiology & Plant Hydraulics, 5) Ecology, 6) Extremes, Disturbance & Fire, and Land Use & Land Cover Change, and 7) Uncertainty Quantification Methods & Techniques. In this paper, we investigate and report on the potential application of Artificial Intelligence and Machine Learning (AI/ML) in Ecohydrology, highlight outcomes of the Ecohydrology session at the AI4ESP workshop, and provide visionary perspectives for future research in this area.
2021年11月，举办了地球系统可预测性人工智能(AI4ESP)研讨会，来自数十个机构的数百名研究人员参加了该研讨会(Hickmon et al.， 2022)。研讨会共举行了17场会议，其中一场是关于生态水文学的。生态水文学会议包括不同的分组会议，讨论具体的主题，包括:1)土壤与地下，2)流域，3)水文学，4)生态生理学与植物水力学，5)生态学，6)极端，扰动与火灾，土地利用与土地覆盖变化，以及7)不确定性量化方法与技术。在本文中，我们调查和报告了人工智能和机器学习(AI/ML)在生态水文学中的潜在应用，重点介绍了AI4ESP研讨会上生态水文学会议的成果，并为该领域的未来研究提供了有远见的展望。
{"title":"Perspectives on Artificial Intelligence for Predictions in Ecohydrology","authors":"Elias C. Massoud, Forrest Hoffman, Zheng Shi, Jinyun Tang, Elie Alhajjar, Mallory Barnes, R. Braghiere, Zoe Cardon, Nathan Collier, Octavia Crompton, P. Dennedy‐Frank, S. Gautam, Miquel A Gonzalez-Meler, Julia K. Green, Charles Koven, Paul Levine, Natasha MacBean, J. Mao, Richard Tran Mills, U. Mishra, M. Mudunuru, Alexandre A. Renchon, Sarah Scott, E. Siirila‐Woodburn, Matthias Sprenger, C. Tague, Yaoping Wang, Chonggang Xu, C. Zarakas","doi":"10.1175/aies-d-23-0005.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0005.1","url":null,"abstract":"\u0000In November 2021, the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop was held, which involved hundreds of researchers from dozens of institutions (Hickmon et al., 2022). There were 17 sessions held at the workshop, including one on Ecohydrology. The Ecohydrology session included various break-out rooms that addressed specific topics, including: 1) Soils & Belowground, 2) Watersheds, 3) Hydrology, 4) Ecophysiology & Plant Hydraulics, 5) Ecology, 6) Extremes, Disturbance & Fire, and Land Use & Land Cover Change, and 7) Uncertainty Quantification Methods & Techniques. In this paper, we investigate and report on the potential application of Artificial Intelligence and Machine Learning (AI/ML) in Ecohydrology, highlight outcomes of the Ecohydrology session at the AI4ESP workshop, and provide visionary perspectives for future research in this area.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90907591","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 : 2023-08-17DOI: 10.1175/aies-d-23-0004.1
Lauren Hoffman, M. Mazloff, S. Gille, D. Giglio, C. Bitz, P. Heimbach, Kayli Matsuyoshi
Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea-ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea-ice motion. The ML models are built to predict present-day sea-ice velocity given present-day wind velocity and previous-day sea-ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea-ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and convolutional neural network (CNN). We quantify the spatio-temporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea-ice velocity with a correlation up to 0.81 between predicted and observed sea-ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally; lower values occur in shallow coastal regions and during times of minimum sea-ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea-ice velocity on one-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.
{"title":"Machine learning for daily forecasts of Arctic sea-ice motion: an attribution assessment of model predictive skill","authors":"Lauren Hoffman, M. Mazloff, S. Gille, D. Giglio, C. Bitz, P. Heimbach, Kayli Matsuyoshi","doi":"10.1175/aies-d-23-0004.1","DOIUrl":"https://doi.org/10.1175/aies-d-23-0004.1","url":null,"abstract":"\u0000Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea-ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea-ice motion. The ML models are built to predict present-day sea-ice velocity given present-day wind velocity and previous-day sea-ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea-ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and convolutional neural network (CNN). We quantify the spatio-temporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea-ice velocity with a correlation up to 0.81 between predicted and observed sea-ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally; lower values occur in shallow coastal regions and during times of minimum sea-ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea-ice velocity on one-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87544730","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 : 2023-08-10DOI: 10.1175/aies-d-22-0070.1
M. Keller, C. Piatko, M. Clemens-Sewall, Rebecca E. Eager, Kevin Foster, Christopher Gifford, Derek M. Rollend, Jennifer Sleeman
Ships inside the Arctic basin require high-resolution (one to five kilometers), near-term (days to semi-monthly) forecasts for guidance on scales of interest to their operations where forecast model predictions are insufficient due to their coarse spatial and temporal resolutions. Deep learning techniques offer the capability of rapid assimilation and analysis of multiple sources of information for improved forecasting. Data from the National Oceanographic and Atmospheric Administration’s Global Forecast System, Multi-scale Ultra-high Resolution Sea Surface Temperature, and the National Snow and Ice Data Center’s Multisensor Analyzed Sea-Ice Extent (MASIE) were used to develop the sea-ice extent deep learning forecast model, over the freeze-up periods of 2016, 2018, 2019, and 2020 in the Beaufort Sea. Sea-ice extent forecasts were produced for one to seven days in the future. The approach was novel for sea-ice extent forecasting in using forecast data as model input to aid in the prediction of sea-ice extent. Model accuracy was assessed against a persistence model. While the average accuracy of the persistence model dropped from 97% to 90% for forecast days one to seven, the deep learning model accuracy dropped only to 93%. A k (four)-fold cross-validation study found that on all except the first day, the deep learning model, which includes a U-Net architecture with a Resnet-18 backbone, does better than the persistence model. Skill scores improve the farther out in time to 0.27. The model demonstrated success in predicting changes in ice extent of significance for navigation in the Amundsen Gulf. Extensions to other Arctic seas, seasons, and sea-ice parameters are under development.
{"title":"Short-Term (Seven-Day) Beaufort Sea-Ice Extent Forecasting with Deep Learning","authors":"M. Keller, C. Piatko, M. Clemens-Sewall, Rebecca E. Eager, Kevin Foster, Christopher Gifford, Derek M. Rollend, Jennifer Sleeman","doi":"10.1175/aies-d-22-0070.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0070.1","url":null,"abstract":"\u0000Ships inside the Arctic basin require high-resolution (one to five kilometers), near-term (days to semi-monthly) forecasts for guidance on scales of interest to their operations where forecast model predictions are insufficient due to their coarse spatial and temporal resolutions. Deep learning techniques offer the capability of rapid assimilation and analysis of multiple sources of information for improved forecasting. Data from the National Oceanographic and Atmospheric Administration’s Global Forecast System, Multi-scale Ultra-high Resolution Sea Surface Temperature, and the National Snow and Ice Data Center’s Multisensor Analyzed Sea-Ice Extent (MASIE) were used to develop the sea-ice extent deep learning forecast model, over the freeze-up periods of 2016, 2018, 2019, and 2020 in the Beaufort Sea. Sea-ice extent forecasts were produced for one to seven days in the future. The approach was novel for sea-ice extent forecasting in using forecast data as model input to aid in the prediction of sea-ice extent. Model accuracy was assessed against a persistence model. While the average accuracy of the persistence model dropped from 97% to 90% for forecast days one to seven, the deep learning model accuracy dropped only to 93%. A k (four)-fold cross-validation study found that on all except the first day, the deep learning model, which includes a U-Net architecture with a Resnet-18 backbone, does better than the persistence model. Skill scores improve the farther out in time to 0.27. The model demonstrated success in predicting changes in ice extent of significance for navigation in the Amundsen Gulf. Extensions to other Arctic seas, seasons, and sea-ice parameters are under development.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81822472","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：