Browse
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.
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.
Abstract
We construct a novel multi-input multioutput autoencoder (MIMO-AE) to capture the nonlinear relationship of Southern California precipitation and tropical Pacific Ocean sea surface temperature. The MIMO-AE is trained on both monthly tropical Pacific sea surface temperature (TP-SST) and Southern California precipitation (SC-PRECIP) anomalies simultaneously. The covariability of the two fields in the MIMO-AE shared nonlinear latent space can be condensed into an index, termed the MIMO-AE index. We use a transfer learning approach to train a MIMO-AE on the combined dataset of 100 yr of output from a historical simulation with the Energy Exascale Earth Systems Model, version 1, and a segment of observational data. We further use long short-term memory networks to assess subseasonal predictability of SC-PRECIP using the MIMO-AE index. We find that the MIMO-AE index provides enhanced predictability of SC-PRECIP for a lead time of up to 4 months as compared with the Niño-3.4 index and the El Niño–Southern Oscillation longitudinal index.
Significance Statement
Traditional El Niño–Southern Oscillation indices, like the Niño-3.4 index, although well predicted themselves, fail to offer reliable subseasonal-to-seasonal predictions of western U.S. precipitation. Here, we use a machine learning approach called a multi-input, multioutput autoencoder to capture the relationship between tropical Pacific Ocean and Southern California precipitation and project it onto a new index, which we call the MIMO-AE index. Using machine learning–based time series predictions, we find that the MIMO-AE index offers enhanced predictability of Southern California precipitation up to a lead time of 4 months as compared with other ENSO indices.
Abstract
We construct a novel multi-input multioutput autoencoder (MIMO-AE) to capture the nonlinear relationship of Southern California precipitation and tropical Pacific Ocean sea surface temperature. The MIMO-AE is trained on both monthly tropical Pacific sea surface temperature (TP-SST) and Southern California precipitation (SC-PRECIP) anomalies simultaneously. The covariability of the two fields in the MIMO-AE shared nonlinear latent space can be condensed into an index, termed the MIMO-AE index. We use a transfer learning approach to train a MIMO-AE on the combined dataset of 100 yr of output from a historical simulation with the Energy Exascale Earth Systems Model, version 1, and a segment of observational data. We further use long short-term memory networks to assess subseasonal predictability of SC-PRECIP using the MIMO-AE index. We find that the MIMO-AE index provides enhanced predictability of SC-PRECIP for a lead time of up to 4 months as compared with the Niño-3.4 index and the El Niño–Southern Oscillation longitudinal index.
Significance Statement
Traditional El Niño–Southern Oscillation indices, like the Niño-3.4 index, although well predicted themselves, fail to offer reliable subseasonal-to-seasonal predictions of western U.S. precipitation. Here, we use a machine learning approach called a multi-input, multioutput autoencoder to capture the relationship between tropical Pacific Ocean and Southern California precipitation and project it onto a new index, which we call the MIMO-AE index. Using machine learning–based time series predictions, we find that the MIMO-AE index offers enhanced predictability of Southern California precipitation up to a lead time of 4 months as compared with other ENSO indices.
Abstract
This paper presents a novel application of convolutional neural network (CNN) models for filtering the intraseasonal variability of the tropical atmosphere. In this deep learning filter, two convolutional layers are applied sequentially in a supervised machine learning framework to extract the intraseasonal signal from the total daily anomalies. The CNN-based filter can be tailored for each field similarly to fast Fourier transform filtering methods. When applied to two different fields (zonal wind stress and outgoing longwave radiation), the index of agreement between the filtered signal obtained using the CNN-based filter and a conventional weight-based filter is between 95% and 99%. The advantage of the CNN-based filter over the conventional filters is its applicability to time series with the length comparable to the period of the signal being extracted.
Significance Statement
This study proposes a new method for discovering hidden connections in data representative of tropical atmosphere variability. The method makes use of an artificial intelligence (AI) algorithm that combines a mathematical operation known as convolution with a mathematical model built to reflect the behavior of the human brain known as artificial neural network. Our results show that the filtered data produced by the AI-based method are consistent with the results obtained using conventional mathematical algorithms. The advantage of the AI-based method is that it can be applied to cases for which the conventional methods have limitations, such as forecast (hindcast) data or real-time monitoring of tropical variability in the 20–100-day range.
Abstract
This paper presents a novel application of convolutional neural network (CNN) models for filtering the intraseasonal variability of the tropical atmosphere. In this deep learning filter, two convolutional layers are applied sequentially in a supervised machine learning framework to extract the intraseasonal signal from the total daily anomalies. The CNN-based filter can be tailored for each field similarly to fast Fourier transform filtering methods. When applied to two different fields (zonal wind stress and outgoing longwave radiation), the index of agreement between the filtered signal obtained using the CNN-based filter and a conventional weight-based filter is between 95% and 99%. The advantage of the CNN-based filter over the conventional filters is its applicability to time series with the length comparable to the period of the signal being extracted.
Significance Statement
This study proposes a new method for discovering hidden connections in data representative of tropical atmosphere variability. The method makes use of an artificial intelligence (AI) algorithm that combines a mathematical operation known as convolution with a mathematical model built to reflect the behavior of the human brain known as artificial neural network. Our results show that the filtered data produced by the AI-based method are consistent with the results obtained using conventional mathematical algorithms. The advantage of the AI-based method is that it can be applied to cases for which the conventional methods have limitations, such as forecast (hindcast) data or real-time monitoring of tropical variability in the 20–100-day range.
Abstract
Digital twins are a transformative technology that can significantly strengthen climate adaptation and mitigation decision-making. Through provision of dynamic, virtual representations of physical systems, making intelligent use of multi-disciplinary data, and high-fidelity simulations they equip decision-makers with the information they need, when they need it, marking a step-change in how we extract value from data and models. While digital twins are commonplace in some industrial sectors, they are an emerging concept in the environmental sciences and practical demonstrations are limited, partly due the challenges of representing complex environmental systems. Collaboration on challenges of mutual interest will unlock digital twins’ potential. To bridge the current gap between digital twins for industrial sectors and those of the environment, we identify the need for ‘environment-aware’ digital twins (EA-DT) that are a federation of digital twins of environmentally-sensitive systems with weather, climate, and environmental information systems. As weather extremes become more frequent and severe, the importance of building weather, climate, and environmental information into digital twins of critical systems such as cities, ports, flood barriers, energy grids, and transport networks increases. Delivering societal benefits will also require significant advances in climate-related decision-making, which lags behind other applications. Progress relies on moving beyond heuristics, and driving advances in the decision sciences informed by new theoretical insights, machine learning and artificial intelligence. To support the use of EA-DTs, we propose a new ontology that stimulates thinking about application and best-practice for decision-making so that we are resilient to the challenges of today's weather and tomorrow's climate.
Abstract
Digital twins are a transformative technology that can significantly strengthen climate adaptation and mitigation decision-making. Through provision of dynamic, virtual representations of physical systems, making intelligent use of multi-disciplinary data, and high-fidelity simulations they equip decision-makers with the information they need, when they need it, marking a step-change in how we extract value from data and models. While digital twins are commonplace in some industrial sectors, they are an emerging concept in the environmental sciences and practical demonstrations are limited, partly due the challenges of representing complex environmental systems. Collaboration on challenges of mutual interest will unlock digital twins’ potential. To bridge the current gap between digital twins for industrial sectors and those of the environment, we identify the need for ‘environment-aware’ digital twins (EA-DT) that are a federation of digital twins of environmentally-sensitive systems with weather, climate, and environmental information systems. As weather extremes become more frequent and severe, the importance of building weather, climate, and environmental information into digital twins of critical systems such as cities, ports, flood barriers, energy grids, and transport networks increases. Delivering societal benefits will also require significant advances in climate-related decision-making, which lags behind other applications. Progress relies on moving beyond heuristics, and driving advances in the decision sciences informed by new theoretical insights, machine learning and artificial intelligence. To support the use of EA-DTs, we propose a new ontology that stimulates thinking about application and best-practice for decision-making so that we are resilient to the challenges of today's weather and tomorrow's climate.
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.
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.
Abstract
There is a need for long-term observations of cloud and precipitation fall speeds in validating and improving rainfall forecasts from climate models. To this end, the U.S. Department of Energy Atmospheric Radiation Measurement (ARM) user facility Southern Great Plains (SGP) site at Lamont, Oklahoma, 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 the ARM 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 images 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 10 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.
Abstract
There is a need for long-term observations of cloud and precipitation fall speeds in validating and improving rainfall forecasts from climate models. To this end, the U.S. Department of Energy Atmospheric Radiation Measurement (ARM) user facility Southern Great Plains (SGP) site at Lamont, Oklahoma, 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 the ARM 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 images 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 10 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.
Abstract
Geostationary satellite imagers provide historical and near-real-time observations of cloud-top patterns that are commonly associated with severe convection. Environmental conditions favorable for severe weather are thought to be represented well by reanalyses. Predicting exactly where convection and costly storm hazards like hail will occur using models or satellite imagery alone, however, is extremely challenging. The multivariate combination of satellite-observed cloud patterns with reanalysis environmental parameters, linked to Next Generation Weather Radar (NEXRAD) estimated maximum expected size of hail (MESH) using a deep neural network (DNN), enables estimation of potentially severe hail likelihood for any observed storm cell. These estimates are made where satellites observe cold clouds, indicative of convection, located in favorable storm environments. We seek an approach that can be used to estimate climatological hailstorm frequency and risk throughout the historical satellite data record. Statistical distributions of convective parameters from satellite and reanalysis show separation between nonsevere and severe hailstorm classes for predictors that include overshooting cloud-top temperature and area characteristics, vertical wind shear, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN to produce a likelihood estimate with a critical success index of 0.511 and Heidke skill score of 0.407, which is exceptional among analogous hail studies. Furthermore, applications of the DNN to case studies demonstrate good qualitative agreement between hail likelihood and MESH. These hail classifications are aggregated across an 11-yr Geostationary Operational Environmental Satellite (GOES) image database from GOES-12/13 to derive a hail frequency and severity climatology, which denotes the central Great Plains, the Midwest, and northwestern Mexico as being the most hail-prone regions within the domain studied.
Abstract
Geostationary satellite imagers provide historical and near-real-time observations of cloud-top patterns that are commonly associated with severe convection. Environmental conditions favorable for severe weather are thought to be represented well by reanalyses. Predicting exactly where convection and costly storm hazards like hail will occur using models or satellite imagery alone, however, is extremely challenging. The multivariate combination of satellite-observed cloud patterns with reanalysis environmental parameters, linked to Next Generation Weather Radar (NEXRAD) estimated maximum expected size of hail (MESH) using a deep neural network (DNN), enables estimation of potentially severe hail likelihood for any observed storm cell. These estimates are made where satellites observe cold clouds, indicative of convection, located in favorable storm environments. We seek an approach that can be used to estimate climatological hailstorm frequency and risk throughout the historical satellite data record. Statistical distributions of convective parameters from satellite and reanalysis show separation between nonsevere and severe hailstorm classes for predictors that include overshooting cloud-top temperature and area characteristics, vertical wind shear, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN to produce a likelihood estimate with a critical success index of 0.511 and Heidke skill score of 0.407, which is exceptional among analogous hail studies. Furthermore, applications of the DNN to case studies demonstrate good qualitative agreement between hail likelihood and MESH. These hail classifications are aggregated across an 11-yr Geostationary Operational Environmental Satellite (GOES) image database from GOES-12/13 to derive a hail frequency and severity climatology, which denotes the central Great Plains, the Midwest, and northwestern Mexico as being the most hail-prone regions within the domain studied.
Abstract
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.
Abstract
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.
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.
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.
