Search Results

You are looking at 101 - 110 of 832 items for :

  • Deep learning x
  • All content x
Clear All
Cong Wang, Ping Wang, Di Wang, Jinyi Hou, and Bing Xue

extrapolation problem as a video prediction problem and used deep learning techniques to model changes between radar images. Han et al. (2017) translated the convective system nowcasting problems into classification problems. They made radar reflectivity and environmental field information into 3 km × 3 km grids and trained a support vector machine (SVM) classifier for prediction. Herman and Schumacher (2018) used NOAA’s second-generation Global Ensemble Forecast System Reforecast dataset to train a

Restricted access
Faisal Hossain, Matt Bonnema, Margaret Srinivasan, Ed Beighley, Alice Andral, Bradley Doorn, Indu Jayaluxmi, Susantha Jayasinghe, Yasir Kaheil, Bareerah Fatima, Nicholas Elmer, Luciana Fenoglio, Jerad Bales, Fabien Lefevre, Sébastien Legrand, Damien Brunel, and Pierre-Yves Le Traon

that hackathons tailored to enable rapid prototyping of real-world solutions for EAs using SWOT data are now timely. 6) Programs that encourage deeper engagement for EAs at academic or research centers for immersive learning or training in the United States/France are required for EA organizations and future SWOT user communities. 7) Close and more frequent mentoring support for EAs is needed as projects mature and they begin facing new challenges with data structure and processing. EAs will

Free access
Yonggang Liu, Robert H. Weisberg, and Ruoying He

circulation and its air–sea interactions ( Weisberg et al. 2004 ). a. Self-organizing map and its applications in meteorology and oceanography Techniques for pattern detection in large oceanographic datasets are becoming increasingly important as datasets grow in size and complexity. The self-organizing map (SOM), an artificial neural network based on unsupervised learning, is an effective software tool of feature extraction ( Kohonen 1982 , 2001 ). It provides a nonlinear cluster analysis, mapping high

Full access
Richard L. Bankert and Robert H. Wade

-only Advanced Very High Resolution Radiometer (AVHRR) classifier described in Tag et al. (2000) . Also, all visible and infrared channels (excluding the 13.3- μ m channel from GOES-12 ) were used in the classifier development. An instance-based classification algorithm employs a machine learning technique in which training datasets are stored in their entirety and a distance function is used to make predictions. For most purposes, operational users rely on the availability of near-real-time cloud

Full access
F. Chevallier, F. Chéruy, N. A. Scott, and A. Chédin

depends on the distance of f to the allowed functions g on B. Given a norm ‖·‖ on B and given ζ, the maximum error that we tolerate, we want: ∃ θ ∈ R p , ∀ x ∈ A,   ‖ f ( x ) − g ( θ , x )‖ < ζ. (2) The learning phase is devoted to the optimization of the MLP. That is, according to the representativity of the learning set, the algorithm selects a vector θ among all of the possible θ ’s. The so-called back-propagation algorithm enables us to derive the parameters in an iterative way

Full access
Tobias Becker and Cathy Hohenegger

strong near the boundary layer, and decrease with height in the free troposphere (e.g., Lin and Arakawa 1997 ; Kuang and Bretherton 2006 ). Reasons are versatile: first, only those updrafts with weaker entrainment rates remain positively buoyant and grow deeper; second, updraft size increases with height, and larger updrafts are thought to have smaller entrainment rates (e.g., Morton et al. 1956 ); and third, updraft velocity increases with height, which is thought to imply that more vertical

Restricted access
Nikolas O. Aksamit, Themistoklis Sapsis, and George Haller

satellite altimetry measurements, researchers actively study global ocean currents and mesoscale features in the ocean, ranging in size from 10 to 200 km ( Stewart 2008 ), in near–real time from an Eulerian perspective. These data have allowed a better understanding of the role of prominent circulation features in the deep ocean, like the Gulf Stream and the Pacific Gyre, as well as smaller coherent structures like the Agulhas rings ( Wang et al. 2015 ). In shallower waters, or at the interface of two

Free access
Robert R. Hoffman, John W. Coffey, Kenneth M. Ford, and Joseph D. Novak

, research in the emerging field of expertise studies has revealed the key features of expert learning and cognition that distinguish novices, apprentices, journeymen, and experts in terms of the ways that their practice is an “art” or “craft” ( Glaser 1987 ; Ericsson et al. 2006 ; Hoffman 1998 ). Key features include logical reasoning on the basis of systematically derived techniques, the formation of conceptual or mental models, the ability of experts to perceive meaningful patterns that nonexperts

Full access
K. M. Kwong, Max H. Y. Wong, James N. K. Liu, and P. W. Chan

provides a rich library of behaviors to aid computer systems, such as weather forecasting ( Kwong et al. 2008 ; Wong et al. 2008 ; Glushkov et al. 2009 ), communications ( Lawrance and Ohama 2003 ), and robot control ( Arsenio 2004 ) or laser control ( Karim 2009 ). Neural networks mimic the flexible nature of biological systems and offer a wide range of potential applications. Scientists have started using neural network architectures and learning algorithms involving chaos for the storage in memory

Full access
E. Bouws and G. J. Komen

discussed. For a certain choice of dissipation parameters, a good balancecan be obtained. This is in agreement with the steadiness of the observed wave conditions.1. Introduction Recent interest in the modeling of wind waves onshallow water (Vincent, 1982; Sanders and Bruinsma,1983) has shown that our knowledge of the variousprocesses contributing to the evolution of the wavespectrum is still fragmentary. As in deep water, windinput, nonlinear transfer, dissipation and advectionare important, but, in

Full access