Vladimir M. Krasnopolsky

A neural network technique to improve computational efficiency of numerical oceanic models

A new generic approach to improve computational efficiency of certain processes in numerical environmental models is formulated. This approach is based on the application of neural network (NN) techniques. It can be used to accelerate the calculations and improve the accuracy of the parameterizations of several types of physical processes which generally require computations involving complex mathematical expressions, including differential and integral equations, rules, restrictions and highly nonlinear empirical relations based on physical or statistical models. It is shown that, from a mathematical point of view, such parameterizations can usually be considered as continuous mappings (continuous dependencies between two vectors). It is also shown that NNs are a generic tool for fast and accurate approximation of continuous mappings and, therefore, can be used to replace primary parameterization algorithms. In addition to fast and accurate approximation of the primary parameterization, NN also provides the entire Jacobian for very little computation cost. Three successful particular applications of the NN approach are presented here: (1) a NN approximation of the UNESCO equation of state of the seawater (density of the seawater); (2) an inversion of this equation (salinity of the seawater); and (3) a NN approximation for the nonlinear wave–wave interaction. The first application has been implemented in the National Centers for Environmental Prediction multi-scale oceanic forecast system, and the second one is being developed for wind wave models. The NN approach introduced in this paper can provide numerically efficient solutions to a wide range of problems in environmental numerical models where lengthy, complicated calculations, which describe physical processes, must be repeated frequently. � 2002 Elsevier Science Ltd. All rights reserved.

New approach to calculation of atmospheric model physics: accurate and fast neural network emulation of longwave radiation in a climate model

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 statist...

Computational intelligence in earth sciences and environmental applications: Issues and challenges

This paper introduces a generic theoretical framework for predictive learning, and relates it to data-driven and learning applications in earth and environmental sciences. The issues of data quality, selection of the error function, incorporation of the predictive learning methods into the existing modeling frameworks, expert knowledge, model uncertainty, and other application-domain specific problems are discussed. A brief overview of the papers in the Special Issue is provided, followed by discussion of open issues and directions for future research.

2006 Special issue: Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction

A new practical application of neural network (NN) techniques to environmental numerical modeling has been developed. Namely, a new type of numerical model, a complex hybrid environmental model based on a synergetic combination of deterministic and machine learning model components, has been introduced. Conceptual and practical possibilities of developing hybrid models are discussed in this paper for applications to climate modeling and weather prediction. The approach presented here uses NN as a statistical or machine learning technique to develop highly accurate and fast emulations for time consuming model physics components (model physics parameterizations). The NN emulations of the most time consuming model physics components, short and long wave radiation parameterizations or full model radiation, presented in this paper are combined with the remaining deterministic components (like model dynamics) of the original complex environmental model--a general circulation model or global climate model (GCM)--to constitute a hybrid GCM (HGCM). The parallel GCM and HGCM simulations produce very similar results but HGCM is significantly faster. The speed-up of model calculations opens the opportunity for model improvement. Examples of developed HGCMs illustrate the feasibility and efficiency of the new approach for modeling complex multidimensional interdisciplinary systems.

Decadal Climate Simulations Using Accurate and Fast Neural Network Emulation of Full, Longwave and Shortwave, Radiation*

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.

Domain check for input to NN emulating an inverse model

Multi-layer perceptrons are used in many fields of science and technology to emulate forward and inverse models. The paper proposes a necessary condition check for the validity of results obtained by inverse NNs. The solution consists of a combination of inverse and forward NNs that, in addition to the inversion, computes a quality measure for the inversion. Examples of such combined NNs from applications in the remote sensing area are discussed.

The Use of SSM/I Data in Operational Marine Analysis*

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 ...

Using ensemble of neural networks to learn stochastic convection parameterizations for climate and numerical weather prediction models from data simulated by a cloud resolving model

Anovel approach based on the neural network (NN) ensemble technique is formulated and used for development of aNNstochastic convection parameterization for climate and numerical weather prediction (NWP)models. This fast parameterization is built based on learning fromdata simulated by a cloud-resolvingmodel (CRM) initialized with and forced by the observed meteorological data available for 4-month boreal winter from November 1992 to February 1993. CRM-simulated data were averaged and processed to implicitly define a stochastic convection parameterization. This parameterization is learned from the data using an ensemble of NNs. The NN ensemble members are trained and tested. The inherent uncertainty of the stochastic convection parameterization derived following this approach is estimated. The newly developed NN convection parameterization has been tested in National Center of Atmospheric Research (NCAR) Community AtmosphericModel (CAM). It produced reasonable and promising decadal climate simulations for a large tropical Pacific region. The extent of the adaptive ability of the developed NN parameterization to the changes in the model environment is briefly discussed. This paper is devoted to a proof of concept and discusses methodology, initial results, and the major challenges of using the NN technique for developing convection parameterizations for climate and NWP models.

Neural Network Applications to Solve Forward and Inverse Problems in Atmospheric and Oceanic Satellite Remote Sensing

Vladimir M. Krasnopolsky (*) Science Application International Company at Environmental Modeling Center, National Centers for Environmental Prediction, National Oceanic and Atmospheric Administration, Camp Springs, Maryland, USA Earth System Science Interdisciplinary Center, University of Maryland, EMC/NCEP/NOAA, 5200 Auth Rd., Camp Springs, MD 20746, USA Phone: 301-763-8000 ext. 7262; fax 301-763-8545; email: vladimir.krasnopolsky@noaa.gov also presented in Chapter 10 by G. Yung. These applications and those that we discuss in Chapter 11, from the mathematical point of view, belong to the broad class of applications called approximation of mappings. A particular type of the NN, a Multi-Layer Perceptron (MLP) NN (Rumelhart et al. 1986) is usually employed to approximate mappings. We will start by introducing a remote sensing, mapping, and NN background.

Accurate and fast neural network emulations of model radiation for the NCEP coupled Climate Forecast System: climate simulations and seasonal predictions.

Abstract The approach to accurate and fast-calculating model physics using neural network emulations was previously developed by the authors for both longwave and shortwave radiation parameterizations or the full model radiation, which is the most time-consuming component of model physics. It was successfully tested for a moderate-resolution uncoupled NCAR Community Atmospheric Model (CAM) that is driven by climatological SST for a decadal climate simulation mode. In this study, the approach has been further developed and implemented into the NCEP coupled Climate Forecast System (CFS) with significantly higher resolution and time-dependent CO2. The higher complexity of NCEP CFS required further adjustments to the neural network emulation methodology. Validation of the approach for the NCEP CFS has been performed through a decadal climate simulation and seasonal predictions. The developed highly-accurate neural network emulations of longwave and shortwave radiation parameterizations are, on average, 16 and...