Search Results

You are looking at 31 - 40 of 832 items for :

  • Deep learning x
  • All content x
Clear All
John Bjørnar Bremnes

relations to the ensemble forecasts can be allowed for. By using the continuous ranked probability score as loss function and an estimation method developed for deep-learning problems ( Goodfellow et al. 2016 ) they demonstrated that the parameters could be efficiently estimated and skillful probabilistic forecasts could be made. The method proposed in this article can be seen as a generalization of the work by Rasp and Lerch (2018) and also as a way to deal with challenges in quantile regression

Open access
Yumeng Tao, Xiaogang Gao, Kuolin Hsu, Soroosh Sorooshian, and Alexander Ihler

key to making the best use of these datasets is promoting advanced methods that assist in the extraction of valuable information from the raw data ( Nasrollahi et al. 2013 ; Sorooshian et al. 2011 ). In recent years, multiple novel techniques for deep learning have been developed in the scientific discipline of machine learning, which is a breakthrough for dealing with large and complex datasets, especially for feature extraction from a large amount of image data ( Bengio 2009 ; Hinton et al

Full access
Amy McGovern, Ryan Lagerquist, David John Gagne II, G. Eli Jergensen, Kimberly L. Elmore, Cameron R. Homeyer, and Travis Smith

Machine learning model interpretation and visualization focusing on meteorological domains are introduced and analyzed. Machine learning (ML) and deep learning (DL; LeCun et al. 2015 ) have recently achieved breakthroughs across a variety of fields, including the world’s best Go player ( Silver et al. 2016 , 2017 ), medical diagnosis ( Rakhlin et al. 2018 ), and galaxy classification ( Dieleman et al. 2015 ). Simple forms of ML (e.g., linear regression) have been used in meteorology since at

Full 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
Mojtaba Sadeghi, Ata Akbari Asanjan, Mohammad Faridzad, Phu Nguyen, Kuolin Hsu, Soroosh Sorooshian, and Dan Braithwaite

related and co-related factors. Therefore, applying more advanced data-driven methodologies for automatically extracting features from the input data will enhance precipitation estimation accuracy. Recent advances in the field of machine learning (ML) offer exciting opportunities to expand our knowledge about the Earth system ( Lary et al. 2016 ). Among the different machine learning methods, the deep neural network (DNN) method is a fast-growing branch characterized by its flexibility and capacity to

Full access
Casey E. Davenport

via careful instructional design. Importantly, if extraneous load is reduced, then more effort can be put toward deeper, long-term understanding (i.e., a higher germane load; Sweller et al. 1998 ; Paas et al. 2003 ). One proven method to reduce extraneous cognitive load and enhance student learning is known as worked examples . In essence, worked examples represent an expert-constructed guide that provides in-depth, step-by-step explanations of how to solve a problem or perform a complex task

Open access
Stephan Rasp and Sebastian Lerch

parameters without having to specify appropriate link functions, and the ease of adding station information into a global model by using embeddings. The network model parameters are estimated by optimizing the CRPS, a nonstandard choice in the machine learning literature tailored to probabilistic forecasting. Furthermore, the rapid pace of development in the deep learning community provides flexible and efficient modeling techniques and software libraries. The presented approach can therefore be easily

Open access
Buo-Fu Chen, Boyo Chen, Hsuan-Tien Lin, and Russell L. Elsberry

various life stages, environments, and basins. In addition, only a few features (usually less than 10) may be finally used in the regression models. This collaborative study between meteorologists and data scientists proposes a deep-learning model to address the need for an automated, objective, and end-to-end intensity estimation technique. Since AlexNet, which established the baseline architecture of convolutional neural networks for image recognition used today, was proposed in 2012 ( Krizhevsky

Full access
Kirkwood A. Cloud, Brian J. Reich, Christopher M. Rozoff, Stefano Alessandrini, William E. Lewis, and Luca Delle Monache

-scale meteorological predictors, along with information describing the atmospheric flow stability and the uncertainty in initial conditions, to predict forecast intensity error in operational prediction schemes. A18 also addressed intensity prediction with the analog ensemble method. More recently, machine learning has gained increasing prominence in postprocessing. Evolutionary programming, simple neural networks, and deep learning have shown significant promise as postprocessing tools (e.g., Gagne et al. 2014

Full access