Visualization of Neural Network Predictions for Weather Forecasting

Recurrent 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...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 38; no. 1; pp. 209 - 220
Main Authors: Roesch, Isabelle, Günther, Tobias
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.02.2019
Subjects:
Artificial neural networks
Computer graphics
I.3.3 [Computer Graphics]: Picture/Image Generation‐Viewing algorithms
Interactive systems
Mathematical models
Neural networks
Parameters
Recurrent neural networks
scientific visualization
Time series
Training
visualization
Weather forecasting
Wind speed
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recurrent 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.13453