Search Results

You are looking at 1 - 10 of 1,025 items for :

  • Deep learning x
  • Refine by Access: All Content x
Clear All
Zongsheng Zheng, Chenyu Hu, Zhaorong Liu, Jianbo Hao, Qian Hou, and Xiaoyi Jiang

about satellite cloud images. A subfield of machine learning—deep learning (DL), as an extremely generalized approach—has been applied to various domains, such as pattern recognition, computer vision, artificial intelligence, and so on ( Xiao et al. 2010 ; Hinton et al. 2012 ; LeCun et al. 2015 ). As one of most popular deep learning models, convolutional neural networks (CNNs) have been demonstrated as a promising tool for image classification due to its locally connected layers and feasibility

Restricted access
Joaquin Cuomo and V. Chandrasekar

learning models for weather nowcasting using radar echo data and compared them with existing models, particularly against two operational models. A common issue with deep learning approaches is that they tend to underestimate the intensity of reflectivity. To address this, we proposed the Composite model, which shows promising results on enhancing the predictions at higher reflectivity values. Although this ensemble can improve any base model, we believe that the primary focus should be put on

Restricted access
Kanghui Zhou, Yongguang Zheng, Wansheng Dong, and Tingbo Wang

a good ability to combine the multisource data, and over 99% of the 550 observed initiation of MCS events were detected within 50 km. Deep learning (DL) is a subset of machine learning algorithms that uses multilayer artificial neural networks to deliver state-of-the-art accuracy in many tasks ( Bengio 2009 ; Schmidhuber 2015 ). Similar to traditional machine learning algorithms like artificial neural networks and SVM, DL networks can model complex nonlinear systems. Moreover, these networks

Free access
Tao Song, Ying Li, Fan Meng, Pengfei Xie, and Danya Xu

observatories, and ground stations, the amount of ocean and air data continues to accumulate. Combining deep learning models with big data environments provides us with a new opportunity to predict the track of tropical cyclones. In recent years, data-driven deep learning algorithms have been successfully applied in image processing, natural language processing, target detection, and other fields. Deep learning technology has strong nonlinear fitting capabilities, which have shown great advantages in

Restricted access
Ryan Lagerquist, Amy McGovern, Cameron R. Homeyer, David John Gagne II, and Travis Smith

( Cintineo et al. 2018 ). Convolutional neural networks (CNN) are specially designed to learn from spatial grids and often contain many layers, which qualifies them as a deep-learning method (section 1.1.4 of Chollet 2018 ). In traditional ML, spatial grids must be transformed into scalar features, which become the direct inputs to the model. Examples are principal components, spatial statistics (such as means and standard deviations), and raw gridpoint values (where each value in the grid is treated as

Free access
Ryan Lagerquist, David Turner, Imme Ebert-Uphoff, Jebb Stewart, and Venita Hagerty

our work unique. First, we use U-net++ models ( Zhou et al. 2020 ), as opposed to the fully connected networks [sometimes called “dense” or “feed-forward”; see chapter 6 of Goodfellow et al. (2016 )] used in previous work. U-net++ models are a type of deep learning, which can exploit spatial patterns in gridded data to make better predictions. Second, we have built physical constraints and vertical nonlocality into the U-net++ models, allowing them to handle nonadjacent cloud layers and better

Restricted access
Jing-Yi Zhuo and Zhe-Min Tan

postprocessed guidance such as wind speed probabilities (e.g., DeMaria et al. 2013 ). Therefore, more accurate estimations of TC intensity and wind radii are still badly needed. Moreover, with the recent advances in the satellite observations of TCs, updating the analysis technique, especially objective algorithms that can interpret complex TC dynamics from the satellite observations, is of vital importance. Deep learning is a type of artificial intelligence algorithm that has revolutionized computer

Restricted access
Ruian Tie, Chunxiang Shi, Gang Wan, Lihua Kang, and Lingling Ge

observation data in China except for the sparse national meteorological stations. So HRCLDAS is impossible to back-calculate high-quality and high-resolution assimilation data before 2008. We believe that deep learning–based statistical downscaling provides a potential method for accurately reconstructing high-resolution data, which can be used to fill historical gaps in HRCLDAS. Currently, it is common practice to obtain fine-scale fields from coarse-scale fields by downscaling methods, including

Restricted access
John L. Cintineo, Michael J. Pavolonis, Justin M. Sieglaff, Anthony Wimmers, Jason Brunner, and Willard Bellon

thunderstorms into a single output, we utilize a deep-learning approach that mimics expert human pattern recognition of intense convection in satellite imagery. The goal of this approach is to quantify convective intensity automatically, saving forecasters time in identifying, diagnosing, and prioritizing threats. Deep learning is a branch of machine-learning methods based on artificial neural networks with feature learning, or the ability to automatically find salient features in data (e.g., Schmidhuber

Full access
Wenwei Xu, Karthik Balaguru, Andrew August, Nicholas Lalo, Nathan Hodas, Mark DeMaria, and David Judi

, air–sea interaction and other processes in the TC core are highly nonlinear, which suggests that nonlinear methods have the potential to improve statistically based intensity forecast models. In particular, deep learning (DL), or deep neural networks, are capable of learning highly complex and nonlinear relationships involving many predictors. DL has achieved remarkable success in computer vision and pattern recognition in recent years. Yet its application to TC intensity prediction has been rare

Open access