A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon‐Ocean Feedback in Typhoon Forecast Models

Jiang, Guoqing; Xu, Jing; Wei, Jiangong

doi:10.1002/2018gl077004

Cited by 105 publications

(77 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is now predicted that deep learning is going to transform many industries as well as society through developments in health care, education, and business. Deep learning has been applied in fields like bioinformatics [27], medicine and health care [28], space information and weather forecasting [29], education [30], traffic and transportation [31,32], agriculture [33], robotics [34], and gaming [35].…”

Section: Applications Of Deep Learningmentioning

confidence: 99%

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

et al. 2019

View full text Add to dashboard Cite

In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of autoencoders (AE) for cell outage detection. First, we briefly introduce deep learning (DL) and also shed light on why it is a promising technique to make self organizing networks intelligent, cognitive, and intuitive so that they behave as fully self-configured, self-optimized, and self-healed cellular networks. The concept of SON is then explained with applications of intrusion detection and mobility load balancing. Our empirical study presents a framework for cell outage detection based on an autoencoder using simulated data obtained from a SON simulator. Finally, we provide a comparative analysis of the proposed framework with the existing frameworks.

show abstract

Section: Applications Of Deep Learningmentioning

confidence: 99%

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Buscombe and Carini, ; Buscombe et al ., ; Buscombe and Ritchie, ; Linville et al . ; Luo et al ., ; Jiang et al ., ; Reichstein et al ., ). The basic premise of applications such as these, compared to those of other machine learning subcategories, is that it circumvents the need (and the effort required) to make decisions about what extracted image features are important to a specific task, which tends to make the models both more subjective and more powerful.…”

Section: Introductionmentioning

confidence: 99%

SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry

Buscombe

2019

Earth Surf Processes Landf

View full text Add to dashboard Cite

I describe a configurable machine‐learning framework to estimate a suite of continuous and categorical sedimentological properties from photographic imagery of sediment, and to exemplify how machine learning can be a powerful and flexible tool for automated quantitative and qualitative measurements from remotely sensed imagery. The model is tested on a dataset consisting of 409 images and associated detailed label data. The data are from a much wider sedimentological spectrum than previous optical granulometry studies, consisting of both well‐ and poorly sorted sediment, terrigenous, carbonate, and volcaniclastic sands and gravels and their mixtures, and grain sizes spanning over two orders of magnitude. I demonstrate the model framework by configuring it in several ways, to estimate two categories (describing grain shape and population, respectively) and nine numeric grain size percentiles in pixels from a single input image. Grain size is then recovered using the physical size of a pixel. Finally, I demonstrate that the model can be configured and trained to estimate equivalent sieve diameters directly from image features, without the need for area‐to‐mass conversion formulas and without even knowing the scale of one pixel. Thus it is the only optical granulometry method proposed to date that does not necessarily require image scaling. The flexibility of the model framework should facilitate numerous application in the spatiotemporal monitoring of the grain size distribution, shape, mineralogy and other quantities of interest of sedimentary deposits as they evolve, as well as other texture‐based proxies extracted from remotely sensed imagery. © 2019 John Wiley & Sons, Ltd.

show abstract

“…The NN convection parameterization was tested in the NCAR Community Atmospheric Model (CAM) and produced reasonable and promising results for the tropical Pacific region. Jiang et al (2018) developed a deep NN-based algorithm or parameterization to be used in the WRF model to provide flow-dependent typhooninduced sea surface temperature cooling. Results based on four typhoon case studies showed that the algorithm reduced maximum wind intensity error by 60 %-70 % compared with using the WRF model.…”

Section: Introductionmentioning

confidence: 99%

Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model

Wang¹,

Balaprakash²,

Kotamarthi³

2019

Geosci. Model Dev.

View full text Add to dashboard Cite

Parameterizations for physical processes in weather and climate models are computationally expensive. We use model output from the Weather Research Forecast (WRF) climate model to train deep neural networks (DNNs) and evaluate whether trained DNNs can provide an accurate alternative to the physics-based parameterizations. Specifically, we develop an emulator using DNNs for a planetary boundary layer (PBL) parameterization in the WRF model. PBL parameterizations are used in atmospheric models to represent the diurnal variation in the formation and collapse of the atmospheric boundary layer -the lowest part of the atmosphere. The dynamics and turbulence, as well as velocity, temperature, and humidity profiles within the boundary layer are all critical for determining many of the physical processes in the atmosphere. PBL parameterizations are used to represent these processes that are usually unresolved in a typical climate model that operates at horizontal spatial scales in the tens of kilometers. We demonstrate that a domain-aware DNN, which takes account of underlying domain structure (e.g., nonlocal mixing), can successfully simulate the vertical profiles within the boundary layer of velocities, temperature, and water vapor over the entire diurnal cycle. Results also show that a single trained DNN from one location can produce predictions of wind speed, temperature, and water vapor profiles over nearby locations with similar terrain conditions with correlations higher than 0.9 when compared with the WRF simulations used as the training dataset.

show abstract

A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon‐Ocean Feedback in Typhoon Forecast Models

Cited by 105 publications

References 32 publications

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry

Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model

Contact Info

Product

Resources

About