Search Results
You are looking at 1 - 10 of 11 items for
- Author or Editor: Vladimir Krasnopolsky x
- Refine by Access: All Content x
Abstract
The application of Special Sensor Microwave/Imager (SSM/I) multiparameter satellite retrievals in operational weather analysis and forecasting is addressed. More accurate multiparameter satellite retrievals are now available from an SSM/I neural network algorithm. It also provides greater areal coverage than some of the initial algorithms. These retrievals (ocean surface wind speed, columnar water vapor, and columnar liquid water), when observed together, provide a meteorologically consistent description of synoptic weather patterns over the oceans. Three SSM/I sensors are currently in orbit, which provide sufficient amounts of data to be used in a real-time operational environment. Several examples are presented to illustrate that important synoptic meteorological features such as fronts, storms, and convective areas can be identified and observed in the SSM/I fields retrieved by the new algorithm. The most recent version of the neural network algorithm retrieves simultaneously four geophysical parameters: ocean-surface wind speed, columnar water vapor, columnar liquid water, and sea surface temperature, allowing the knowledge of each variable to contribute directly to better accuracy in ocean surface wind speed retrievals. The neural network wind speed data were recently incorporated as a part of operational Global Data Assimilation System at the National Centers for Environmental Prediction.
Abstract
The application of Special Sensor Microwave/Imager (SSM/I) multiparameter satellite retrievals in operational weather analysis and forecasting is addressed. More accurate multiparameter satellite retrievals are now available from an SSM/I neural network algorithm. It also provides greater areal coverage than some of the initial algorithms. These retrievals (ocean surface wind speed, columnar water vapor, and columnar liquid water), when observed together, provide a meteorologically consistent description of synoptic weather patterns over the oceans. Three SSM/I sensors are currently in orbit, which provide sufficient amounts of data to be used in a real-time operational environment. Several examples are presented to illustrate that important synoptic meteorological features such as fronts, storms, and convective areas can be identified and observed in the SSM/I fields retrieved by the new algorithm. The most recent version of the neural network algorithm retrieves simultaneously four geophysical parameters: ocean-surface wind speed, columnar water vapor, columnar liquid water, and sea surface temperature, allowing the knowledge of each variable to contribute directly to better accuracy in ocean surface wind speed retrievals. The neural network wind speed data were recently incorporated as a part of operational Global Data Assimilation System at the National Centers for Environmental Prediction.
Abstract
This reply is aimed at clarifying and further discussing the methodological aspects of this neural network application for a better understanding of the technique by the journal readership. The similarities and differences of two approaches and their areas of application are discussed. These two approaches outline a new interdisciplinary field based on application of neural networks (and probably other modern machine or statistical learning techniques) to significantly speed up calculations of time-consuming components of atmospheric and oceanic numerical models.
Abstract
This reply is aimed at clarifying and further discussing the methodological aspects of this neural network application for a better understanding of the technique by the journal readership. The similarities and differences of two approaches and their areas of application are discussed. These two approaches outline a new interdisciplinary field based on application of neural networks (and probably other modern machine or statistical learning techniques) to significantly speed up calculations of time-consuming components of atmospheric and oceanic numerical models.
Abstract
A new approach based on a synergetic combination of statistical/machine learning and deterministic modeling within atmospheric models is presented. The approach uses neural networks as a statistical or machine learning technique for an accurate and fast emulation or statistical approximation of model physics parameterizations. It is applied to development of an accurate and fast approximation of an atmospheric longwave radiation parameterization for the NCAR Community Atmospheric Model, which is the most time consuming component of model physics. The developed neural network emulation is two orders of magnitude, 50–80 times, faster than the original parameterization. A comparison of the parallel 10-yr climate simulations performed with the original parameterization and its neural network emulations confirmed that these simulations produce almost identical results. The obtained results show the conceptual and practical possibility of an efficient synergetic combination of deterministic and statistical learning components within an atmospheric climate or forecast model. A developmental framework and practical validation criteria for neural network emulations of model physics components are outlined.
Abstract
A new approach based on a synergetic combination of statistical/machine learning and deterministic modeling within atmospheric models is presented. The approach uses neural networks as a statistical or machine learning technique for an accurate and fast emulation or statistical approximation of model physics parameterizations. It is applied to development of an accurate and fast approximation of an atmospheric longwave radiation parameterization for the NCAR Community Atmospheric Model, which is the most time consuming component of model physics. The developed neural network emulation is two orders of magnitude, 50–80 times, faster than the original parameterization. A comparison of the parallel 10-yr climate simulations performed with the original parameterization and its neural network emulations confirmed that these simulations produce almost identical results. The obtained results show the conceptual and practical possibility of an efficient synergetic combination of deterministic and statistical learning components within an atmospheric climate or forecast model. A developmental framework and practical validation criteria for neural network emulations of model physics components are outlined.
Abstract
An approach to calculating model physics using neural network emulations, previously proposed and developed by the authors, has been implemented in this study for both longwave and shortwave radiation parameterizations, or to the full model radiation, the most time-consuming component of model physics. The developed highly accurate neural network emulations of the NCAR Community Atmospheric Model (CAM) longwave and shortwave radiation parameterizations are 150 and 20 times as fast as the original/control longwave and shortwave radiation parameterizations, respectively. The full neural network model radiation was used for a decadal climate model simulation with the NCAR CAM. A detailed comparison of parallel decadal climate simulations performed with the original NCAR model radiation parameterizations and with their neural network emulations is presented. Almost identical results have been obtained for the parallel decadal simulations. This opens the opportunity of using efficient neural network emulations for the full model radiation for decadal and longer climate simulations as well as for weather prediction.
Abstract
An approach to calculating model physics using neural network emulations, previously proposed and developed by the authors, has been implemented in this study for both longwave and shortwave radiation parameterizations, or to the full model radiation, the most time-consuming component of model physics. The developed highly accurate neural network emulations of the NCAR Community Atmospheric Model (CAM) longwave and shortwave radiation parameterizations are 150 and 20 times as fast as the original/control longwave and shortwave radiation parameterizations, respectively. The full neural network model radiation was used for a decadal climate model simulation with the NCAR CAM. A detailed comparison of parallel decadal climate simulations performed with the original NCAR model radiation parameterizations and with their neural network emulations is presented. Almost identical results have been obtained for the parallel decadal simulations. This opens the opportunity of using efficient neural network emulations for the full model radiation for decadal and longer climate simulations as well as for weather prediction.
Abstract
Artificial intelligence (AI) techniques have had significant recent successes in multiple fields. These fields and the fields of satellite remote sensing and NWP share the same fundamental underlying needs, including signal and image processing, quality control mechanisms, pattern recognition, data fusion, forward and inverse problems, and prediction. Thus, modern AI in general and machine learning (ML) in particular can be positively disruptive and transformational change agents in the fields of satellite remote sensing and NWP by augmenting, and in some cases replacing, elements of the traditional remote sensing, assimilation, and modeling tools. And change is needed to meet the increasing challenges of Big Data, advanced models and applications, and user demands. Future developments, for example, SmallSats and the Internet of Things, will continue the explosion of new environmental data. ML models are highly efficient and in some cases more accurate because of their flexibility to accommodate nonlinearity and/or non-Gaussianity. With that efficiency, ML can help to address the demands put on environmental products for higher accuracy, for higher resolution—spatial, temporal, and vertical, for enhanced conventional medium-range forecasts, for outlooks and predictions on subseasonal to seasonal time scales, and for improvements in the process of issuing advisories and warnings. Using examples from satellite remote sensing and NWP, it is illustrated how ML can accelerate the pace of improvement in environmental data exploitation and weather prediction—first, by complementing existing systems, and second, where appropriate, as an alternative to some components of the NWP processing chain from observations to forecasts.
Abstract
Artificial intelligence (AI) techniques have had significant recent successes in multiple fields. These fields and the fields of satellite remote sensing and NWP share the same fundamental underlying needs, including signal and image processing, quality control mechanisms, pattern recognition, data fusion, forward and inverse problems, and prediction. Thus, modern AI in general and machine learning (ML) in particular can be positively disruptive and transformational change agents in the fields of satellite remote sensing and NWP by augmenting, and in some cases replacing, elements of the traditional remote sensing, assimilation, and modeling tools. And change is needed to meet the increasing challenges of Big Data, advanced models and applications, and user demands. Future developments, for example, SmallSats and the Internet of Things, will continue the explosion of new environmental data. ML models are highly efficient and in some cases more accurate because of their flexibility to accommodate nonlinearity and/or non-Gaussianity. With that efficiency, ML can help to address the demands put on environmental products for higher accuracy, for higher resolution—spatial, temporal, and vertical, for enhanced conventional medium-range forecasts, for outlooks and predictions on subseasonal to seasonal time scales, and for improvements in the process of issuing advisories and warnings. Using examples from satellite remote sensing and NWP, it is illustrated how ML can accelerate the pace of improvement in environmental data exploitation and weather prediction—first, by complementing existing systems, and second, where appropriate, as an alternative to some components of the NWP processing chain from observations to forecasts.
Nonlinear Wave Ensemble Averaging in the Gulf of Mexico Using Neural NetworksAbstract
Artificial neural networks (ANNs) applied to nonlinear wave ensemble averaging are developed and studied for Gulf of Mexico simulations. It is an approach that expands the conservative arithmetic ensemble mean (EM) from the NCEP Global Wave Ensemble Forecast System (GWES) to a nonlinear mapping that better captures the differences among the ensemble members and reduces the systematic and scatter errors of the forecasts. The ANNs have the 20 members of the GWES as input, and outputs are trained using observations from six buoys. The variables selected for the study are the 10-m wind speed (U10), significant wave height (Hs), and peak period (Tp) for the year of 2016. ANNs were built with one hidden layer using a hyperbolic tangent basis function. Several architectures with 12 different combinations of neurons, eight different filtering windows (time domain), and 100 seeds for the random initialization were studied and constructed for specific forecast days from 0 to 10. The results show that a small number of neurons are sufficient to reduce the bias, while 35–50 neurons produce the greatest reduction in both the scatter and systematic errors. The main advantage of the methodology using ANNs is not on short-range forecasts but at longer forecast ranges beyond 4 days. The nonlinear ensemble averaging using ANNs was able to improve the correlation coefficient on forecast day 10 from 0.39 to 0.61 for U10, from 0.50 to 0.76 for Hs, and from 0.38 to 0.63 for Tp, representing a gain of five forecast days when compared to the EM currently implemented.
Abstract
Artificial neural networks (ANNs) applied to nonlinear wave ensemble averaging are developed and studied for Gulf of Mexico simulations. It is an approach that expands the conservative arithmetic ensemble mean (EM) from the NCEP Global Wave Ensemble Forecast System (GWES) to a nonlinear mapping that better captures the differences among the ensemble members and reduces the systematic and scatter errors of the forecasts. The ANNs have the 20 members of the GWES as input, and outputs are trained using observations from six buoys. The variables selected for the study are the 10-m wind speed (U10), significant wave height (Hs), and peak period (Tp) for the year of 2016. ANNs were built with one hidden layer using a hyperbolic tangent basis function. Several architectures with 12 different combinations of neurons, eight different filtering windows (time domain), and 100 seeds for the random initialization were studied and constructed for specific forecast days from 0 to 10. The results show that a small number of neurons are sufficient to reduce the bias, while 35–50 neurons produce the greatest reduction in both the scatter and systematic errors. The main advantage of the methodology using ANNs is not on short-range forecasts but at longer forecast ranges beyond 4 days. The nonlinear ensemble averaging using ANNs was able to improve the correlation coefficient on forecast day 10 from 0.39 to 0.61 for U10, from 0.50 to 0.76 for Hs, and from 0.38 to 0.63 for Tp, representing a gain of five forecast days when compared to the EM currently implemented.
Abstract
The error characteristics of surface waves and winds produced by ensemble forecasts issued by the National Centers for Environmental Prediction are analyzed as a function of forecast range and severity. Eight error metrics are compared, separating the scatter component of the error from the systematic bias. Ensemble forecasts of extreme winds and extreme waves are compared to deterministic forecasts for long lead times, up to 10 days. A total of 29 metocean buoys is used to assess 1 year of forecasts (2016). The Global Wave Ensemble Forecast System (GWES) performs 10-day forecasts four times per day, with a spatial resolution of 0.5° and a temporal resolution of 3 h, using a 20-member ensemble plus a control member (deterministic) forecast. The largest errors in GWES, beyond forecast day 3, are found to be associated with winds above 14 m s−1 and waves above 5 m. Extreme percentiles after the day-8 forecast reach 30% of underestimation for both 10-m-height wind (U10) and significant wave height (Hs). The comparison of probabilistic wave forecasts with deterministic runs shows an impressive improvement of predictability on the scatter component of the errors. The error for surface winds drops from 5 m s−1 in the deterministic runs, associated with extreme events at longer forecast ranges, to values around 3 m s−1 using the ensemble approach. As a result, GWES waves are better predicted, with a reduction in error from 2 m to less than 1.5 m for Hs. Nevertheless, under extreme conditions, critical systematic and scatter errors are identified beyond the day-6 and day-3 forecasts, respectively.
Abstract
The error characteristics of surface waves and winds produced by ensemble forecasts issued by the National Centers for Environmental Prediction are analyzed as a function of forecast range and severity. Eight error metrics are compared, separating the scatter component of the error from the systematic bias. Ensemble forecasts of extreme winds and extreme waves are compared to deterministic forecasts for long lead times, up to 10 days. A total of 29 metocean buoys is used to assess 1 year of forecasts (2016). The Global Wave Ensemble Forecast System (GWES) performs 10-day forecasts four times per day, with a spatial resolution of 0.5° and a temporal resolution of 3 h, using a 20-member ensemble plus a control member (deterministic) forecast. The largest errors in GWES, beyond forecast day 3, are found to be associated with winds above 14 m s−1 and waves above 5 m. Extreme percentiles after the day-8 forecast reach 30% of underestimation for both 10-m-height wind (U10) and significant wave height (Hs). The comparison of probabilistic wave forecasts with deterministic runs shows an impressive improvement of predictability on the scatter component of the errors. The error for surface winds drops from 5 m s−1 in the deterministic runs, associated with extreme events at longer forecast ranges, to values around 3 m s−1 using the ensemble approach. As a result, GWES waves are better predicted, with a reduction in error from 2 m to less than 1.5 m for Hs. Nevertheless, under extreme conditions, critical systematic and scatter errors are identified beyond the day-6 and day-3 forecasts, respectively.
Abstract
Forecast skill from dynamical forecast models decreases quickly with projection time due to various errors. Therefore, postprocessing methods, from simple bias correction methods to more complicated multiple linear regression–based model output statistics, are used to improve raw model forecasts. Usually, these methods show clear forecast improvement over the raw model forecasts, especially for short-range weather forecasts. However, linear approaches have limitations because the relationship between predictands and predictors may be nonlinear. This is even truer for extended range forecasts, such as week-3–4 forecasts. In this study, neural network techniques are used to seek or model the relationships between a set of predictors and predictands, and eventually to improve week-3–4 precipitation and 2-m temperature forecasts made by the NOAA/NCEP Climate Forecast System. Benefitting from advances in machine learning techniques in recent years, more flexible and capable machine learning algorithms and availability of big datasets enable us not only to explore nonlinear features or relationships within a given large dataset, but also to extract more sophisticated pattern relationships and covariabilities hidden within the multidimensional predictors and predictands. Then these more sophisticated relationships and high-level statistical information are used to correct the model week-3–4 precipitation and 2-m temperature forecasts. The results show that to some extent neural network techniques can significantly improve the week-3–4 forecast accuracy and greatly increase the efficiency over the traditional multiple linear regression methods.
Abstract
Forecast skill from dynamical forecast models decreases quickly with projection time due to various errors. Therefore, postprocessing methods, from simple bias correction methods to more complicated multiple linear regression–based model output statistics, are used to improve raw model forecasts. Usually, these methods show clear forecast improvement over the raw model forecasts, especially for short-range weather forecasts. However, linear approaches have limitations because the relationship between predictands and predictors may be nonlinear. This is even truer for extended range forecasts, such as week-3–4 forecasts. In this study, neural network techniques are used to seek or model the relationships between a set of predictors and predictands, and eventually to improve week-3–4 precipitation and 2-m temperature forecasts made by the NOAA/NCEP Climate Forecast System. Benefitting from advances in machine learning techniques in recent years, more flexible and capable machine learning algorithms and availability of big datasets enable us not only to explore nonlinear features or relationships within a given large dataset, but also to extract more sophisticated pattern relationships and covariabilities hidden within the multidimensional predictors and predictands. Then these more sophisticated relationships and high-level statistical information are used to correct the model week-3–4 precipitation and 2-m temperature forecasts. The results show that to some extent neural network techniques can significantly improve the week-3–4 forecast accuracy and greatly increase the efficiency over the traditional multiple linear regression methods.
Abstract
Artificial intelligence (AI) and machine learning (ML) have become important tools for environmental scientists and engineers, both in research and in applications. Although these methods have become quite popular in recent years, they are not new. The use of AI methods began in the 1950s and environmental scientists were adopting them by the 1980s. Although an “AI winter” temporarily slowed the growth, a more recent resurgence has brought it back with gusto. This paper tells the story of the evolution of AI in the field through the lens of the AMS Committee on Artificial Intelligence Applications to Environmental Science. The environmental sciences possess a host of problems amenable to advancement by intelligent techniques. We review a few of the early applications along with the ML methods of the time and how their progression has impacted these sciences. While AI methods have changed from expert systems in the 1980s to neural networks and other data-driven methods, and more recently deep learning, the environmental problems tackled have remained similar. We discuss the types of applications that have shown some of the biggest advances due to AI usage and how they have evolved over the past decades, including topics in weather forecasting, probabilistic prediction, climate estimation, optimization problems, image processing, and improving forecasting models. We finish with a look at where AI as employed in environmental science appears to be headed and some thoughts on how it might be best blended with physical/dynamical modeling approaches to further advance our science.
Abstract
Artificial intelligence (AI) and machine learning (ML) have become important tools for environmental scientists and engineers, both in research and in applications. Although these methods have become quite popular in recent years, they are not new. The use of AI methods began in the 1950s and environmental scientists were adopting them by the 1980s. Although an “AI winter” temporarily slowed the growth, a more recent resurgence has brought it back with gusto. This paper tells the story of the evolution of AI in the field through the lens of the AMS Committee on Artificial Intelligence Applications to Environmental Science. The environmental sciences possess a host of problems amenable to advancement by intelligent techniques. We review a few of the early applications along with the ML methods of the time and how their progression has impacted these sciences. While AI methods have changed from expert systems in the 1980s to neural networks and other data-driven methods, and more recently deep learning, the environmental problems tackled have remained similar. We discuss the types of applications that have shown some of the biggest advances due to AI usage and how they have evolved over the past decades, including topics in weather forecasting, probabilistic prediction, climate estimation, optimization problems, image processing, and improving forecasting models. We finish with a look at where AI as employed in environmental science appears to be headed and some thoughts on how it might be best blended with physical/dynamical modeling approaches to further advance our science.
