Search Results

You are looking at 1 - 10 of 86 items for :

  • Deep learning x
  • Journal of Atmospheric and Oceanic Technology x
  • All content x
Clear All
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
Veljko Petković, Marko Orescanin, Pierre Kirstetter, Christian Kummerow, and Ralph Ferraro

observations and storm morphology, little, if any, room has been left for a potentially novel physically based approach to emerge. However, recent advances in deep learning methods with neural networks may offer perhaps not new but for the first time fully applicable models that could better exploit the information content in PMW observations. This study seeks to investigate such a possibility through the use of deep learning for both retrieving precipitation types and improving the performance of PMW

Full access
Tao Song, Zihe Wang, Pengfei Xie, Nisheng Han, Jingyu Jiang, and Danya Xu

optimization of machine-learning methods may be hard, and overfitting is really a tough problem to be solved ( Jiang et al. 2018 ; Siahkoohi et al. 2019 ). In recent decades, deep-learning methods, especially recurrent neural network (RNN), have been widely used for time series data processing and value prediction. RNN introduces the recurrent unit structure and allows the internal connection between the hidden units, so it is suitable for analyzing and processing time series data ( Krizhevsky et al. 2012

Free access
Momme C. Hell, Bruce D. Cornelle, Sarah T. Gille, Arthur J. Miller, and Peter D. Bromirski

conventional wave observations. We use these data as a training set to develop a new method to characterize ocean swell observations. Feature comparison in geophysical data is often challenging because the observations are noisy, and the models are too simple. As we outline below, the combination of optimization and Monte Carlo methods enables us to improve our model understanding of the data, while we use the model to identify the relevant data. This is a “machine learning” approach that is constrained by

Full access
Andrew Geiss and Joseph C. Hardin

features), and similar precipitating features occur across many different PPI scans depending on the regional weather, for instance, the presence of a cold front and corresponding heavy precipitation in an extratropical cyclone. By learning common sub-pixel-scale features in the context of large-scale weather in PPI scans, a neural network can outperform interpolation schemes. Though introduced in the late 1980s, deep CNNs have become very popular since about 2010 for various image processing tasks

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

Abstract

We present a novel approach for the automated quality control (QC) of precipitation for a sparse station observation network within the complex terrain of British Columbia, Canada. Our QC approach uses Convolutional Neural Networks (CNNs) to classify bad observation values, incorporating a multi-classifier ensemble to achieve better QC performance. We train CNNs using human QC’d labels from 2016 to 2017 with gridded precipitation and elevation analyses as inputs. Based on the classification evaluation metrics, our QC approach shows reliable and robust performance across different geographical environments (e.g., coastal and inland mountains), with 0.927 Area Under Curve (AUC) and type I/type II error lower than 15%. Based on the saliency-map-based interpretation studies, we explain the success of CNN-based QC by showing that it can capture the precipitation patterns around, and upstream of the station locations. This automated QC approach is an option for eliminating bad observations for various applications, including the pre-processing of training datasets for machine learning. It can be used in conjunction with human QC to improve upon what could be accomplished with either method alone.

Open access
Min Wang, Shudao Zhou, Zhong Yang, and Zhanhua Liu

application and low recognition accuracy. Therefore, we need to find a method that can automatically learn different cloud features. The convolutional neural network (CNN) has achieved great success in large-scale image classification tasks. The CNN is a deep, feedforward artificial neural network that has the ability to perform in-depth learning. After in-depth learning, it is possible to express features that are difficult to express in general, fully mine the association between data, extract the

Restricted access
Qian Li, Shaoen Tang, Xuan Peng, and Qiang Ma

learning, which can utilize large-scale datasets effectively to complete recognition or classification tasks, has achieved significant progress and been widely used in machine vision. Especially deep convolutional neural networks (DCNNs) are receiving more and more attention because of its ability of automatic learning multiscale representative features of the image with multilayer convolution structures. Chaabani et al. (2017) trained an artificial neural network from image to estimate the

Open access
Xining Zhang and Hao Dai

) , Dixit and Londhe (2016) , and Dixit et al. (2015) added the wavelet into the neural network. From other papers on wave height prediction by machine learning methods, for example, a neural network, it is easy to find that the models used in these methods generally have shallow architecture, that is, the hidden layer number is 1. In addition, the hidden layer has fewer neurons. To approach sufficiently arbitrary multivariate nonlinear functions, the neural network should have deep enough levels or

Full access
A. Hicks and B. M. Notaroš

they are capable of transferring learning from one dataset to another and are not limited to specific parameters inherent either to the dataset (e.g., resolution, color, or size) or capturing method (e.g., hardware imperfections reflected in data). Therefore, a classifier properly trained with a CNN can be utilized by a variety of image-capturing in situ devices. Research into deep learning has extended their ability to process complex data without major changes to the algorithm. Finally, CNNs are

Full access