Search Results

You are looking at 1 - 10 of 83 items for :

  • Deep learning x
  • Journal of Applied Meteorology and Climatology x
  • All content x
Clear All
Yingkai Sha, David John Gagne II, Gregory West, and Roland Stull

. Second, these SD methods do not incorporate elevation as a predictor and may generate less accurate precipitation patterns in complex terrain. Convolutional neural networks (CNNs) are types of deep-learning methods that can learn nonlinear relationships with low generalization error across domains ( Zhang et al. 2017 ), and thus have the potential to overcome the limitation of traditional SD methods. In the first part of this research ( Sha et al. 2020 , hereinafter Part I ), CNNs with UNet

Open access
Yingkai Sha, David John Gagne II, Gregory West, and Roland Stull

what operational meteorological centers can currently offer. Statistical downscaling (SD), a postprocessing technique that can generate localized meteorological information conditioned on coarse numerical model outputs or reanalysis data, has the potential to resolve this challenge and, thus, has received attention since the 1990s ( Wilby and Wigley 1997 ; Wilby et al. 1999 ; Dibike and Coulibaly 2005 ; Glotter et al. 2014 ). Convolutional neural networks (CNNs) are types of deep-learning models

Open access
Christina Kumler-Bonfanti, Jebb Stewart, David Hall, and Mark Govett

popular and widely used CNNs, were trained with millions of images and are highly accurate ( Krizhevsky et al. 2017 ; Simonyan and Zisserman 2015 ). Deep learning (DL) is a term used to describe the optimization of NNs with multiple layers. Deep networks tend to be large relative to other ML models and their training typically requires powerful graphics processing unit (GPU) acceleration in order to make training practical. In comparison with other approaches, deep CNNs are particularly effective for

Restricted access
Kyle A. Hilburn, Imme Ebert-Uphoff, and Steven D. Miller

. Miller , 2020 : Evaluating Geostationary Lightning Mapper flash rates within intense convective storms . J. Geophys. Res. Atmos. , 125 , e2020JD032827, https://doi.org/10.1029/2020JD032827 . 10.1029/2020JD032827 Samsi , S. , C. J. Mattioli , and M. S. Veillette , 2019 : Distributed deep learning for precipitation nowcasting. IEEE High Performance Extreme Computing Conf. , Waltham, MA, IEEE, https://doi.org/10.1109/HPEC.2019.8916416 . 10.1109/HPEC.2019.8916416 Sawada , Y. , K

Open access
Alex M. Haberlie and Walker S. Ashley

-tree predictions ( Gagne et al. 2017 ). In addition, this study uses the XGBoost algorithm ( Chen and Guestrin 2016 ). XGBoost is an extension of GB that uses additional methods that reduce model overfitting. These algorithms can rival the performance of more complex algorithms (e.g., deep neural networks; Krizhevsky et al. 2012 ) in machine-learning competitions ( Chen and Guestrin 2016 ), with less time spent on tuning model hyperparameters. Gagne et al. (2017 , their section 2.4) provide a detailed

Full access
Lisa M. PytlikZillig, Qi Hu, Kenneth G. Hubbard, Gary D. Lynne, and Roger H. Bruning

explanations are essential for enhancing their ownership of the new knowledge they are developing. In addition, explanation also can facilitate the learning of new skills, deeper learning, and better integration of new knowledge with prior knowledge ( Ainsworth and Loizou 2003 ; Chi et al. 1989 , 1994 ; Renkl 2002 ; Roscoe and Chi 2008 ; Roy and Chi 2005 ). Meanwhile, peer discussion can enhance many important outcomes, including understanding, critical thinking, and construction of complex knowledge

Full access
Paul M. Tag and James E. Peak

714JOURNAL OF APPLIED METEOROLOGYVo~.u~ 35Machine Learning of Maritime Fog Forecast Rules PAUL M. TAGNaval Research Laboratory, Monterey, California JAMF~S E. PEAKComputer Sciences Corporation, Monterey, California(Manuscript received 1 May 1995, in final form 19 October 1995)ABSTRACT In recent years, the field of artificial intelligence has contributed significantly to the science of meteorology,most notably in the now familiar form of expert systems. Expert systems have

Full access
Andrew E. Mercer, Alexandria D. Grimes, and Kimberly M. Wood

learning method could benefit from considering multiple processes simultaneously as opposed to the best-separating field presented here (a task outside of the scope of this project). Typically, the best-separating GFSA fields were consistent among multiple RI definitions, revealing humidity across a deep vertical layer, low-level instability, and midlevel vorticity as potentially important separating fields for RI/non-RI environments. Ultimately, the improved separability offered by the presented

Restricted 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
John F. Griffiths

1428 JOURNAL OF APPLIED METEOROLOGY VOLUME20The Learning Process Related to Architecture and the Atmosphere JOHN F. GRIFFITHSTexas .4&M University, College Station 77843(Manuscript received 9 February 1981, in final form 18 March 1981)ABSTRACT There has been a rapidly growing awareness in the past few years of the role that the atmospheric scientistcan play in assisting the architect to achieve

Full access