Browse
Abstract
The Atlantic Meridional Overturning Circulation (AMOC) is an important component of the global climate, known to be a tipping element, as it could collapse under global warming. The main objective of this study is to compute the probability that the AMOC collapses within a specified time window, using a rare-event algorithm called Trajectory-Adaptive Multilevel Splitting (TAMS). However, the efficiency and accuracy of TAMS depend on the choice of the score function. Although the definition of the optimal score function, called “committor function” is known, it is impossible in general to compute it a priori. Here, we combine TAMS with a Next-Generation Reservoir Computing technique that estimates the committor function from the data generated by the rare-event algorithm. We test this technique in a stochastic box model of the AMOC for which two types of transition exist, the so-called F(ast)-transitions and S(low)-transitions. Results for the F-transtions compare favorably with those in the literature where a physically-informed score function was used. We show that coupling a rare-event algorithm with machine learning allows for a correct estimation of transition probabilities, transition times, and even transition paths for a wide range of model parameters. We then extend these results to the more difficult problem of S-transitions in the same model. In both cases of F-transitions and S-transitions, we also show how the Next-Generation Reservoir Computing technique can be interpreted to retrieve an analytical estimate of the committor function.
Abstract
The Atlantic Meridional Overturning Circulation (AMOC) is an important component of the global climate, known to be a tipping element, as it could collapse under global warming. The main objective of this study is to compute the probability that the AMOC collapses within a specified time window, using a rare-event algorithm called Trajectory-Adaptive Multilevel Splitting (TAMS). However, the efficiency and accuracy of TAMS depend on the choice of the score function. Although the definition of the optimal score function, called “committor function” is known, it is impossible in general to compute it a priori. Here, we combine TAMS with a Next-Generation Reservoir Computing technique that estimates the committor function from the data generated by the rare-event algorithm. We test this technique in a stochastic box model of the AMOC for which two types of transition exist, the so-called F(ast)-transitions and S(low)-transitions. Results for the F-transtions compare favorably with those in the literature where a physically-informed score function was used. We show that coupling a rare-event algorithm with machine learning allows for a correct estimation of transition probabilities, transition times, and even transition paths for a wide range of model parameters. We then extend these results to the more difficult problem of S-transitions in the same model. In both cases of F-transitions and S-transitions, we also show how the Next-Generation Reservoir Computing technique can be interpreted to retrieve an analytical estimate of the committor function.
Abstract
Producing high-quality forecasts of key climate variables, such as temperature and precipitation, on subseasonal time scales has long been a gap in operational forecasting. This study explores an application of machine learning (ML) models as postprocessing tools for subseasonal forecasting. Lagged numerical ensemble forecasts (i.e., an ensemble where the members have different initialization dates) and observational data, including relative humidity, pressure at sea level, and geopotential height, are incorporated into various ML methods to predict monthly average precipitation and 2-m temperature 2 weeks in advance for the continental United States. For regression, quantile regression, and tercile classification tasks, we consider using linear models, random forests, convolutional neural networks, and stacked models (a multimodel approach based on the prediction of the individual ML models). Unlike previous ML approaches that often use ensemble mean alone, we leverage information embedded in the ensemble forecasts to enhance prediction accuracy. Additionally, we investigate extreme event predictions that are crucial for planning and mitigation efforts. Considering ensemble members as a collection of spatial forecasts, we explore different approaches to using spatial information. Trade-offs between different approaches may be mitigated with model stacking. Our proposed models outperform standard baselines such as climatological forecasts and ensemble means. In addition, we investigate feature importance, trade-offs between using the full ensemble or only the ensemble mean, and different modes of accounting for spatial variability.
Significance Statement
Accurately forecasting temperature and precipitation on subseasonal time scales—2 weeks–2 months in advance—is extremely challenging. These forecasts would have immense value in agriculture, insurance, and economics. Our paper describes an application of machine learning techniques to improve forecasts of monthly average precipitation and 2-m temperature using lagged physics-based predictions and observational data 2 weeks in advance for the entire continental United States. For lagged ensembles, the proposed models outperform standard benchmarks such as historical averages and averages of physics-based predictions. Our findings suggest that utilizing the full set of physics-based predictions instead of the average enhances the accuracy of the final forecast.
Abstract
Producing high-quality forecasts of key climate variables, such as temperature and precipitation, on subseasonal time scales has long been a gap in operational forecasting. This study explores an application of machine learning (ML) models as postprocessing tools for subseasonal forecasting. Lagged numerical ensemble forecasts (i.e., an ensemble where the members have different initialization dates) and observational data, including relative humidity, pressure at sea level, and geopotential height, are incorporated into various ML methods to predict monthly average precipitation and 2-m temperature 2 weeks in advance for the continental United States. For regression, quantile regression, and tercile classification tasks, we consider using linear models, random forests, convolutional neural networks, and stacked models (a multimodel approach based on the prediction of the individual ML models). Unlike previous ML approaches that often use ensemble mean alone, we leverage information embedded in the ensemble forecasts to enhance prediction accuracy. Additionally, we investigate extreme event predictions that are crucial for planning and mitigation efforts. Considering ensemble members as a collection of spatial forecasts, we explore different approaches to using spatial information. Trade-offs between different approaches may be mitigated with model stacking. Our proposed models outperform standard baselines such as climatological forecasts and ensemble means. In addition, we investigate feature importance, trade-offs between using the full ensemble or only the ensemble mean, and different modes of accounting for spatial variability.
Significance Statement
Accurately forecasting temperature and precipitation on subseasonal time scales—2 weeks–2 months in advance—is extremely challenging. These forecasts would have immense value in agriculture, insurance, and economics. Our paper describes an application of machine learning techniques to improve forecasts of monthly average precipitation and 2-m temperature using lagged physics-based predictions and observational data 2 weeks in advance for the entire continental United States. For lagged ensembles, the proposed models outperform standard benchmarks such as historical averages and averages of physics-based predictions. Our findings suggest that utilizing the full set of physics-based predictions instead of the average enhances the accuracy of the final forecast.
Abstract
Combining strengths from deep learning and extreme value theory can help describe complex relationships between variables where extreme events have significant impacts (e.g., environmental or financial applications). Neural networks learn complicated nonlinear relationships from large datasets under limited parametric assumptions. By definition, the number of occurrences of extreme events is small, which limits the ability of the data-hungry, nonparametric neural network to describe rare events. Inspired by recent extreme cold winter weather events in North America caused by atmospheric blocking, we examine several probabilistic generative models for the entire multivariate probability distribution of daily boreal winter surface air temperature. We propose metrics to measure spatial asymmetries, such as long-range anticorrelated patterns that commonly appear in temperature fields during blocking events. Compared to vine copulas, the statistical standard for multivariate copula modeling, deep learning methods show improved ability to reproduce complicated asymmetries in the spatial distribution of ERA5 temperature reanalysis, including the spatial extent of in-sample extreme events.
Abstract
Combining strengths from deep learning and extreme value theory can help describe complex relationships between variables where extreme events have significant impacts (e.g., environmental or financial applications). Neural networks learn complicated nonlinear relationships from large datasets under limited parametric assumptions. By definition, the number of occurrences of extreme events is small, which limits the ability of the data-hungry, nonparametric neural network to describe rare events. Inspired by recent extreme cold winter weather events in North America caused by atmospheric blocking, we examine several probabilistic generative models for the entire multivariate probability distribution of daily boreal winter surface air temperature. We propose metrics to measure spatial asymmetries, such as long-range anticorrelated patterns that commonly appear in temperature fields during blocking events. Compared to vine copulas, the statistical standard for multivariate copula modeling, deep learning methods show improved ability to reproduce complicated asymmetries in the spatial distribution of ERA5 temperature reanalysis, including the spatial extent of in-sample extreme events.
Abstract
We use a spectral-based approach that employs principal component analysis along with a relatively shallow artificial neural network (NN) to substantially reduce noise and other artifacts in terrestrial chlorophyll solar-induced fluorescence (SIF) retrievals. SIF is a very small emission at red and far-red wavelengths that is difficult to measure and is highly sensitive to random errors and systematic artifacts. Our approach relies upon an assumption that a trained NN can effectively reconstruct the total SIF signal from a relatively small number of leading principal components of the satellite-observed far-red radiance spectra without using information from the trailing modes that contain most of the random errors. We test the approach with simulated reflectance spectra produced with a full atmospheric and surface radiative transfer model using different observing and geophysical parameters and various noise levels. The resulting noisy and noise-reduced retrieved SIF values are compared with true values to assess performance. We then apply our noise reduction approach to SIF derived from two different satellite spectrometers. For evaluation, since the truth in this case is unknown, we compare SIF retrievals from two independent sensors with each other. We also compare the noise-reduced SIF temporal variations with those from an independent gross primary product (GPP) product that should display similar variations. Results show that our noise reduction approach improves the capture of SIF seasonal and interannual variability. Our approach should be applicable to many noisy data products derived from spectral measurements. Our methodology does not replace the original retrieval algorithms; rather, the original noisy retrievals are needed as the target for the NN training process.
Significance Statement
The purpose of this study is to document and demonstrate a machine learning algorithm that is used to effectively reduce noise and artifacts in a satellite data product, solar-induced fluorescence (SIF) from chlorophyll. This is important because SIF retrievals are typically noisy, and the noise limits their ability to be used for diagnosing plant health and productivity. Our results show substantial improvement in SIF retrievals that may lead to new applications. Our approach can be similarly applied to other noisy satellite data products.
Abstract
We use a spectral-based approach that employs principal component analysis along with a relatively shallow artificial neural network (NN) to substantially reduce noise and other artifacts in terrestrial chlorophyll solar-induced fluorescence (SIF) retrievals. SIF is a very small emission at red and far-red wavelengths that is difficult to measure and is highly sensitive to random errors and systematic artifacts. Our approach relies upon an assumption that a trained NN can effectively reconstruct the total SIF signal from a relatively small number of leading principal components of the satellite-observed far-red radiance spectra without using information from the trailing modes that contain most of the random errors. We test the approach with simulated reflectance spectra produced with a full atmospheric and surface radiative transfer model using different observing and geophysical parameters and various noise levels. The resulting noisy and noise-reduced retrieved SIF values are compared with true values to assess performance. We then apply our noise reduction approach to SIF derived from two different satellite spectrometers. For evaluation, since the truth in this case is unknown, we compare SIF retrievals from two independent sensors with each other. We also compare the noise-reduced SIF temporal variations with those from an independent gross primary product (GPP) product that should display similar variations. Results show that our noise reduction approach improves the capture of SIF seasonal and interannual variability. Our approach should be applicable to many noisy data products derived from spectral measurements. Our methodology does not replace the original retrieval algorithms; rather, the original noisy retrievals are needed as the target for the NN training process.
Significance Statement
The purpose of this study is to document and demonstrate a machine learning algorithm that is used to effectively reduce noise and artifacts in a satellite data product, solar-induced fluorescence (SIF) from chlorophyll. This is important because SIF retrievals are typically noisy, and the noise limits their ability to be used for diagnosing plant health and productivity. Our results show substantial improvement in SIF retrievals that may lead to new applications. Our approach can be similarly applied to other noisy satellite data products.
Abstract
The safe and efficient execution of offshore operations requires short-term (1–6 h ahead) high-quality probabilistic forecasts of metocean variables. The development areas for offshore wind projects, potentially in high depths, make it difficult to gather measurement data. This paper explores the use of deep learning for wind speed forecasting at an unobserved offshore location. The proposed convolutional architecture jointly exploits coastal measurements and numerical weather predictions to emulate multivariate probabilistic short-term forecasts. We explore both Gaussian and non-Gaussian neural representations using normalizing flows. We benchmark these approaches with respect to state-of-the-art data-driven schemes, including analog methods and quantile forecasting. The performance of the models and resulting forecast quality are analyzed in terms of probabilistic calibration, probabilistic and deterministic metrics, and as a function of weather situations. We report numerical experiments for a real case study off the French Mediterranean coast. Our results highlight the role of regional numerical weather prediction and coastal in situ measurement in the performance of postprocessing. For single-valued forecasts, a 40% decrease in RMSE is observed compared to the direct use of numerical weather predictions. Significant skill improvements are also obtained for the probabilistic forecasts, in terms of various scores, as well as an acceptable probabilistic calibration. The proposed architecture can process a large amount of heterogeneous input data and offers a versatile probabilistic framework for multivariate forecasting.
Abstract
The safe and efficient execution of offshore operations requires short-term (1–6 h ahead) high-quality probabilistic forecasts of metocean variables. The development areas for offshore wind projects, potentially in high depths, make it difficult to gather measurement data. This paper explores the use of deep learning for wind speed forecasting at an unobserved offshore location. The proposed convolutional architecture jointly exploits coastal measurements and numerical weather predictions to emulate multivariate probabilistic short-term forecasts. We explore both Gaussian and non-Gaussian neural representations using normalizing flows. We benchmark these approaches with respect to state-of-the-art data-driven schemes, including analog methods and quantile forecasting. The performance of the models and resulting forecast quality are analyzed in terms of probabilistic calibration, probabilistic and deterministic metrics, and as a function of weather situations. We report numerical experiments for a real case study off the French Mediterranean coast. Our results highlight the role of regional numerical weather prediction and coastal in situ measurement in the performance of postprocessing. For single-valued forecasts, a 40% decrease in RMSE is observed compared to the direct use of numerical weather predictions. Significant skill improvements are also obtained for the probabilistic forecasts, in terms of various scores, as well as an acceptable probabilistic calibration. The proposed architecture can process a large amount of heterogeneous input data and offers a versatile probabilistic framework for multivariate forecasting.
Abstract
Machine learning (ML) has rapidly transitioned from a niche activity to a mainstream tool for environmental research applications including atmospheric science cloud microphysics studies. Two recently developed cloud particle probes measure the light scattered in the near forward direction and save digital images of the scattering light. Scattering pattern images collected by the Particle Phase Discriminator mark 2, Karlsruhe edition (PPD-2K), and the Small Ice Detector, version 3 (SID-3) provide valuable information for particle shape and size characterization. Since different particle shapes have distinctly different light scattering characteristics, the images are ideally suited for ML. Here, results of a ML project to characterize ice particle shapes sampled by the PPD-2K in ice fog and diamond dust during a 3-yr project in Fairbanks, Alaska. About 2.15 million light-scattering pattern images were collected during 3 years of measurements with the PPD-2K. Visual Geometry Group (VGG) convolutional neural network (CNN) was trained to categorize light-scattering patterns into eight categories. Initial training images (120 each category) were selected by human visual examination of data, and the training dataset was augmented using an automated iterative method for image identification of further images which were all visually inspected by a human. Results were well correlated to similar categories identified from previously developed classification algorithms. ML identifies characteristics not included in automated analysis such as sublimation. Of the 2.15 million images analyzed, 1.3% were categorized as spherical (liquid), 43.5% were categorized as having rough surfaces, 15.3% were pristine, 16.3% were categorized as sublimating, and the remaining 23.6% did not fit into any of those categories (irregular or saturated).
Significance Statement
The shapes and sizes of cloud particles can be extremely important for understanding the conditions that exist in the cloud. In this study, we show that more information about cloud particle characteristics can be identified by using machine learning than by traditional means. To demonstrate this, data are analyzed from a 3-yr study of ice fog and diamond dust events in Fairbanks, Alaska. The Particle Phase Discriminator instrument collected 2.15 million light-scattering pattern images of cloud particles during ground-based measurements. Neither traditional techniques nor machine learning were able to identify all categories, but a combination of both techniques led to a more complete view of ice particle shapes.
Abstract
Machine learning (ML) has rapidly transitioned from a niche activity to a mainstream tool for environmental research applications including atmospheric science cloud microphysics studies. Two recently developed cloud particle probes measure the light scattered in the near forward direction and save digital images of the scattering light. Scattering pattern images collected by the Particle Phase Discriminator mark 2, Karlsruhe edition (PPD-2K), and the Small Ice Detector, version 3 (SID-3) provide valuable information for particle shape and size characterization. Since different particle shapes have distinctly different light scattering characteristics, the images are ideally suited for ML. Here, results of a ML project to characterize ice particle shapes sampled by the PPD-2K in ice fog and diamond dust during a 3-yr project in Fairbanks, Alaska. About 2.15 million light-scattering pattern images were collected during 3 years of measurements with the PPD-2K. Visual Geometry Group (VGG) convolutional neural network (CNN) was trained to categorize light-scattering patterns into eight categories. Initial training images (120 each category) were selected by human visual examination of data, and the training dataset was augmented using an automated iterative method for image identification of further images which were all visually inspected by a human. Results were well correlated to similar categories identified from previously developed classification algorithms. ML identifies characteristics not included in automated analysis such as sublimation. Of the 2.15 million images analyzed, 1.3% were categorized as spherical (liquid), 43.5% were categorized as having rough surfaces, 15.3% were pristine, 16.3% were categorized as sublimating, and the remaining 23.6% did not fit into any of those categories (irregular or saturated).
Significance Statement
The shapes and sizes of cloud particles can be extremely important for understanding the conditions that exist in the cloud. In this study, we show that more information about cloud particle characteristics can be identified by using machine learning than by traditional means. To demonstrate this, data are analyzed from a 3-yr study of ice fog and diamond dust events in Fairbanks, Alaska. The Particle Phase Discriminator instrument collected 2.15 million light-scattering pattern images of cloud particles during ground-based measurements. Neither traditional techniques nor machine learning were able to identify all categories, but a combination of both techniques led to a more complete view of ice particle shapes.
Abstract
Convective initiation (CI) nowcasting remains a challenging problem for both numerical weather prediction models and existing nowcasting algorithms. In this study, an object-based probabilistic deep learning model is developed to predict CI based on multichannel infrared GOES-16 satellite observations. The data come from patches surrounding potential CI events identified in Multi-Radar Multi-Sensor Doppler weather radar products over the Great Plains region from June and July 2020 and June 2021. An objective radar-based approach is used to identify these events. The deep learning model significantly outperforms the classical logistic model at lead times up to 1 h, especially on the false alarm ratio. Through case studies, the deep learning model exhibits dependence on the characteristics of clouds and moisture at multiple altitudes. Model explanation further reveals that the contribution of features to model predictions is significantly dependent on the baseline, a reference point against which the prediction is compared. Under a moist baseline, moisture gradients in the lower and middle troposphere contribute most to correct CI forecasts. In contrast, under a clear-sky baseline, correct CI forecasts are dominated by cloud-top features, including cloud-top glaciation, height, and cloud coverage. Our study demonstrates the advantage of using different baselines in further understanding model behavior and gaining scientific insights.
Abstract
Convective initiation (CI) nowcasting remains a challenging problem for both numerical weather prediction models and existing nowcasting algorithms. In this study, an object-based probabilistic deep learning model is developed to predict CI based on multichannel infrared GOES-16 satellite observations. The data come from patches surrounding potential CI events identified in Multi-Radar Multi-Sensor Doppler weather radar products over the Great Plains region from June and July 2020 and June 2021. An objective radar-based approach is used to identify these events. The deep learning model significantly outperforms the classical logistic model at lead times up to 1 h, especially on the false alarm ratio. Through case studies, the deep learning model exhibits dependence on the characteristics of clouds and moisture at multiple altitudes. Model explanation further reveals that the contribution of features to model predictions is significantly dependent on the baseline, a reference point against which the prediction is compared. Under a moist baseline, moisture gradients in the lower and middle troposphere contribute most to correct CI forecasts. In contrast, under a clear-sky baseline, correct CI forecasts are dominated by cloud-top features, including cloud-top glaciation, height, and cloud coverage. Our study demonstrates the advantage of using different baselines in further understanding model behavior and gaining scientific insights.
Abstract
The complexity of growing spatiotemporal resolution of climate simulations produces a variety of climate patterns under different projection scenarios. This paper proposes a new data-driven climate classification workflow via an unsupervised deep learning technique that can dimensionally reduce the vast volume of spatiotemporal numerical climate projection data into a compact representation. We aim to identify distinct zones that capture multiple climate variables as well as their future changes under different climate change scenarios. Our approach leverages convolutional autoencoders combined with k-means clustering (standard autoencoder) and online clustering based on the Sinkhorn–Knopp algorithm (clustering autoencoder) across the conterminous United States (CONUS) to capture unique climate patterns in a data-driven fashion from the Geophysical Fluid Dynamics Laboratory Earth System Model with GOLD component (GFDL-ESM2G). The developed approach compresses 70 years of GFDL-ESM2G simulation at 0.125° spatial resolution across the CONUS under multiple warming scenarios to a lower-dimensional space by a factor of 660 000 and then tested on 150 years of GFDL-ESM2G simulation data. The results show that five climate clusters capture physically reasonable and spatially stable climatological patterns matched to known climate classes defined by human experts. Results also show that using a clustering autoencoder can reduce the computational time for clustering by up to 9.2 times when compared to using a standard autoencoder. Our five unique climate patterns resulting from the deep learning–based clustering of the lower-dimensional space thereby enable us to provide insights on hydrometeorology and its spatial heterogeneity across the conterminous United States immediately without downloading large climate datasets.
Significance Statement
This paper presents a data-driven climate classification approach using unsupervised deep learning to dimensionally reduce climate model outputs and to identify distinct climate regions for their future changes. Our approach compresses climate information for 70 years of Geophysical Fluid Dynamics Laboratory Earth System Model data across the conterminous United States (CONUS) at 0.125° spatial resolution. The results reveal that five climate clusters capture reasonable and stable climatological patterns matched to known climate patterns. The embedded clustering process in deep learning provides ×9.2 times faster execution than the k-means clustering technique. These results give us insight about climate spatial patterns and heterogeneity of hydrological patterns across the conterminous United States without downloading large climate datasets.
Abstract
The complexity of growing spatiotemporal resolution of climate simulations produces a variety of climate patterns under different projection scenarios. This paper proposes a new data-driven climate classification workflow via an unsupervised deep learning technique that can dimensionally reduce the vast volume of spatiotemporal numerical climate projection data into a compact representation. We aim to identify distinct zones that capture multiple climate variables as well as their future changes under different climate change scenarios. Our approach leverages convolutional autoencoders combined with k-means clustering (standard autoencoder) and online clustering based on the Sinkhorn–Knopp algorithm (clustering autoencoder) across the conterminous United States (CONUS) to capture unique climate patterns in a data-driven fashion from the Geophysical Fluid Dynamics Laboratory Earth System Model with GOLD component (GFDL-ESM2G). The developed approach compresses 70 years of GFDL-ESM2G simulation at 0.125° spatial resolution across the CONUS under multiple warming scenarios to a lower-dimensional space by a factor of 660 000 and then tested on 150 years of GFDL-ESM2G simulation data. The results show that five climate clusters capture physically reasonable and spatially stable climatological patterns matched to known climate classes defined by human experts. Results also show that using a clustering autoencoder can reduce the computational time for clustering by up to 9.2 times when compared to using a standard autoencoder. Our five unique climate patterns resulting from the deep learning–based clustering of the lower-dimensional space thereby enable us to provide insights on hydrometeorology and its spatial heterogeneity across the conterminous United States immediately without downloading large climate datasets.
Significance Statement
This paper presents a data-driven climate classification approach using unsupervised deep learning to dimensionally reduce climate model outputs and to identify distinct climate regions for their future changes. Our approach compresses climate information for 70 years of Geophysical Fluid Dynamics Laboratory Earth System Model data across the conterminous United States (CONUS) at 0.125° spatial resolution. The results reveal that five climate clusters capture reasonable and stable climatological patterns matched to known climate patterns. The embedded clustering process in deep learning provides ×9.2 times faster execution than the k-means clustering technique. These results give us insight about climate spatial patterns and heterogeneity of hydrological patterns across the conterminous United States without downloading large climate datasets.
