Search Results

You are looking at 71 - 80 of 830 items for :

  • Deep learning x
  • All content x
Clear All
Christine J. Kirchhoff, Joseph J. Barsugli, Gillian L. Galford, Ambarish V. Karmalkar, Kelly Lombardo, Scott R. Stephenson, Mathew Barlow, Anji Seth, Guiling Wang, and Austin Frank

representatives from all SCAs listed except Maryland and Delaware. LEARNING FROM GLOBAL AND NATIONAL ASSESSMENTS. Years of research on global and national CAs offers a number of important lessons. First, research on global assessments ( Farrell and Jäger 2006 ) and the U.S. National CA (NCA) ( Mitchell et al. 2006 ) suggests that involving recognized experts enhances assessment credibility as does using accepted data, methods/tools, numerical models, and scientific peer review. Credibility of CAs can be

Full access
Travis A. O’Brien, Ashley E. Payne, Christine A. Shields, Jonathan Rutz, Swen Brands, Christopher Castellano, Jiayi Chen, William Cleveland, Michael J. DeFlorio, Naomi Goldenson, Irina V. Gorodetskaya, Héctor Inda Díaz, Karthik Kashinath, Brian Kawzenuk, Sol Kim, Mikhail Krinitskiy, Juan M. Lora, Beth McClenny, Allison Michaelis, John P. O’Brien, Christina M. Patricola, Alexandre M. Ramos, Eric J. Shearer, Wen-Wen Tung, Paul A. Ullrich, Michael F. Wehner, Kevin Yang, Rudong Zhang, Zhenhai Zhang, and Yang Zhou

, L20401 , https://doi.org/10.1029/2010GL044696 . 10.1029/2010GL044696 Kurth , T. , and Coauthors , 2018 : Exascale deep learning for climate analytics . Proc. Int. Conf. for High Performance Computing, Networking, Storage, and Analysis , Piscataway, NJ, IEEE, 51, https://dl.acm.org/doi/10.5555/3291656.3291724 . Mudigonda , M. , and Coauthors , 2017 : Segmenting and tracking extreme climate events using neural networks . 31st Conf. on Neural Information Processing System , Long Beach

Full access
Gert-Jan Steeneveld and Jordi Vilà-Guerau de Arellano

An active learning approach is a successful method in teaching atmospheric modelling of the atmospheric environment at the master’s level. Numerical weather prediction (NWP) has rapidly developed from basic single-layer barotropic models in the 1950s to very advanced high-resolution Earth system models. Bauer et al. (2015) explained in detail why weather forecasting has undergone a key silent revolution in society, where the current-day global models show skill for lead times up to 7 days

Full access
G. L. Mullendore and J. S. Tilley

The University of North Dakota partnered with field campaign investigators to provide undergraduate students with an experiential learning opportunity that uniquely integrated classroom activities, operational forecasting, and a large multiagency field campaign. It is crucial for the next generation of scientists, who will deal increasingly with research areas that cross not only disciplinary but also methodological boundaries, to gain as much cross-disciplinary and cross

Full access
Hongbo Liu, Janina V. Büscher, Kevin Köser, Jens Greinert, Hong Song, Ying Chen, and Timm Schoening

; Osterloff et al. 2016a ; Rimavicius and Gelzinis 2017 ; Nilssen et al. 2017 ). Osterloff et al. (2019) successfully linked the polyp activity determined by machine learning to other sensor time series (current, water depth, temperature) to find relationships. The potential of deep learning methods to utilize the enormous number of images taken by conventional red–green–blue (RGB) cameras has also been investigated ( King et al. 2018 ). Underwater hyperspectral imaging (UHI) and multispectral (MS

Open access
Ben Orlove

In recent weeks, people around the world have expressed deep disappointment that the United Nations Climate Change Conference in Copenhagen, Denmark, held in December 2009, did not produce a firm agreement that would reduce greenhouse gas emissions and help the world adapt to present and future impacts of climate change. As commentators have stressed, international agreements are often difficult to establish and the failure of this conference can be traced to many sources. The consensus process

Full access
Ariel E. Cohen, Richard L. Thompson, Steven M. Cavallo, Roger Edwards, Steven J. Weiss, John A. Hart, Israel L. Jirak, William F. Bunting, Jaret W. Rogers, Steven F. Piltz, Alan E. Gerard, Andrew D. Moore, Daniel J. Cornish, Alexander C. Boothe, and Joel B. Cohen

death. As an integral member of the weather enterprise, academia not only lays the foundation for learning within the university classroom, but also plays a key role in fostering research development. As such, under the broader umbrella of academia, the university classroom can be considered as an incubator for R2O. Specifically, the classroom setting provides knowledge, guidance, and practice for students to successfully 1) conduct operationally relevant research as a part of their academic and

Open access
Jun Yang, Weitao Lyu, Ying Ma, Yijun Zhang, Qingyong Li, Wen Yao, and Tianshu Lu

training method for limited sample data and realized the application of the convolutional architecture for fast feature embedding (“Caffe”) deep-learning framework ( Jia et al. 2014 ) in the classification of total-sky cloud images. In this paper, we adopted the trained network parameters and deep-learning model provided by Zhang to perform cloud-type classification. The entire TCIS image set is used to assess the classification accuracy, and Table 1 shows the confusion matrix of the classification

Full access
Michael Sprenger, Sebastian Schemm, Roger Oechslin, and Johannes Jenkner

statistical methods with NWP-based forecasts is to apply the Widmer index to the model output. In a more modern terminology, this directly leads to a machine learning (ML) approach for foehn prediction (see Hastie et al. 2009 ). Other names, which essentially mean the same thing, are applied predictive modeling, artificial intelligence, and statistical learning ( Kuhn and Johnson 2013 ). There are many ML methods that could be ( Hastie et al. 2009 ), and indeed have been, applied within a meteorological

Full access
Noah D. Brenowitz, Tom Beucler, Michael Pritchard, and Christopher S. Bretherton

, including a machine-learning parameterization, should capture the dependence of convection to these parameters. One such parameter is the LTS: LTS = θ ⁡ ( 700   hPa ) − SST , where θ is the potential temperature and SST is the sea surface temperature. Low LTS indicates the lower troposphere is conditionally unstable, favoring deep convection. A second controlling parameter is the midtropospheric moisture, defined by Q = ∫ 850 hPa 550 hPa q T   d p g . Cumulus updrafts entrain surrounding air as they

Restricted access