Visibility forecast for airport operations by LSTM neural network

Tuo Deng, Aijie Cheng, Wei Han, Hai Xiang Lin

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

3 Citations (Scopus)

Abstract

Visibility forecast is a meteorological problems which has direct impact to daily lives. For instance, timely prediction of low visibility situations is very important for the safe operation in airports and highways. In this paper, we investigate the use of Long Short-Term Memory(LSTM) model to predict visibility. By adjusting the loss function and network structure, we optimize the original LSTM model to make it more suitable for practical applications, which is superior to previous models in short-term low visibility prediction. In addition, there is a”time delay problem” when the number of hours time ahead we try to forecast becomes larger, this problem is persistent given the limited amount of available training data. We report our attempt of applying re-sampling to deal with the time delay problem, and we find that this method can improve the accuracy of visibility prediction, especially for the low visibility case.

Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Agents and Artificial Intelligence, ICAART 2019
EditorsAna Rocha, Luc Steels, Jaap van den Herik
PublisherSciTePress
Pages466-473
Number of pages8
Volume2
ISBN (Electronic)978-989-758-350-6
DOIs
Publication statusPublished - 2019
EventICAART 2019: 11th International Conference on Agents and Artificial Intelligence - Prague, Czech Republic
Duration: 19 Feb 201921 Feb 2019
Conference number: 11
http://www.icaart.org/?y=2019

Conference

ConferenceICAART 2019
CountryCzech Republic
CityPrague
Period19/02/1921/02/19
Internet address

Keywords

  • Atmospheric Visibility
  • Time Series Forecast

Fingerprint Dive into the research topics of 'Visibility forecast for airport operations by LSTM neural network'. Together they form a unique fingerprint.

Cite this