Show simple item record

dc.contributor.authorRoesch, Isabelleen_US
dc.contributor.authorGünther, Tobiasen_US
dc.contributor.editorChen, Min and Benes, Bedrichen_US
dc.date.accessioned2019-03-17T09:56:52Z
dc.date.available2019-03-17T09:56:52Z
dc.date.issued2019
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.13453
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13453
dc.description.abstractRecurrent neural networks are prime candidates for learning evolutions in multi‐dimensional time series data. The performance of such a network is judged by the loss function, which is aggregated into a scalar value that decreases during training. Observing only this number hides the variation that occurs within the typically large training and testing data sets. Understanding these variations is of highest importance to adjust network hyper‐parameters, such as the number of neurons, number of layers or to adjust the training set to include more representative examples. In this paper, we design a comprehensive and interactive system that allows users to study the output of recurrent neural networks on both the complete training data and testing data. We follow a coarse‐to‐fine strategy, providing overviews of annual, monthly and daily patterns in the time series and directly support a comparison of different hyper‐parameter settings. We applied our method to a recurrent convolutional neural network that was trained and tested on 25 years of climate data to forecast meteorological attributes, such as temperature, pressure and wind velocity. We further visualize the quality of the forecasting models, when applied to various locations on the Earth and we examine the combination of several forecasting models.Recurrent neural networks are prime candidates for learning evolutions in multi‐dimensional time series data. We describe a comprehensive and interactive system to visually analyse and compare time series predictions that were generated by convolutional and recurrent neural networks in the context of weather forecasting.en_US
dc.publisher© 2019 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectscientific visualization
dc.subjectvisualization
dc.subjectI.3.3 [Computer Graphics]: Picture/Image Generation‐Viewing algorithms
dc.titleVisualization of Neural Network Predictions for Weather Forecastingen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersArticles
dc.description.volume38
dc.description.number1
dc.identifier.doi10.1111/cgf.13453
dc.identifier.pages209-220


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record