End-to-End Prediction of Lightning Events from Geostationary Satellite Images
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Sebastian Brodehl
- Richard Mueller
- Elmar Schoemer
- Peter Spichtinger
- Michael Wand
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000839746100001&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.3390/rs14153760
- eISSN
- 2072-4292
- Externe Identifier
- Clarivate Analytics Document Solution ID: 3S7AY
- Ausgabe der Veröffentlichung
- 15
- Zeitschrift
- REMOTE SENSING
- Schlüsselwörter
- neural networks
- satellite images
- class imbalance
- feature attribution
- lightning prediction
- nowcasting
- short-term forecasts
- machine learning
- meteorology
- Artikelnummer
- ARTN 3760
- Datum der Veröffentlichung
- 2022
- Status
- Published
- Titel
- End-to-End Prediction of Lightning Events from Geostationary Satellite Images
- Sub types
- Article
- Ausgabe der Zeitschrift
- 14
Data source: Web of Science (Lite)
- Other metadata sources:
-
- Abstract
- <jats:p>While thunderstorms can pose severe risks to property and life, forecasting remains challenging, even at short lead times, as these often arise in meta-stable atmospheric conditions. In this paper, we examine the question of how well we could perform short-term (up to 180 min) forecasts using exclusively multi-spectral satellite images and past lighting events as data. We employ representation learning based on deep convolutional neural networks in an “end-to-end” fashion. Here, a crucial problem is handling the imbalance of the positive and negative classes appropriately in order to be able to obtain predictive results (which is not addressed by many previous machine-learning-based approaches). The resulting network outperforms previous methods based on physically based features and optical flow methods (similar to operational prediction models) and generalizes across different years. A closer examination of the classifier performance over time and under masking of input data indicates that the learned model actually draws most information from structures in the visible spectrum, with infrared imaging sustaining some classification performance during the night.</jats:p>
- Autoren
- Sebastian Brodehl
- Richard Müller
- Elmar Schömer
- Peter Spichtinger
- Michael Wand
- DOI
- 10.3390/rs14153760
- eISSN
- 2072-4292
- Ausgabe der Veröffentlichung
- 15
- Zeitschrift
- Remote Sensing
- Sprache
- en
- Online publication date
- 2022
- Paginierung
- 3760 - 3760
- Status
- Published online
- Herausgeber
- MDPI AG
- Herausgeber URL
- http://dx.doi.org/10.3390/rs14153760
- Datum der Datenerfassung
- 2022
- Titel
- End-to-End Prediction of Lightning Events from Geostationary Satellite Images
- Ausgabe der Zeitschrift
- 14
Data source: Crossref
- Autoren
- Sebastian Brodehl
- Richard Müller
- Elmar Schömer
- Peter Spichtinger
- Michael Wand
- Zeitschrift
- Remote. Sens.
- Artikelnummer
- 15
- Paginierung
- 3760 - 3760
- Datum der Veröffentlichung
- 2022
- Titel
- End-to-End Prediction of Lightning Events from Geostationary Satellite Images.
- Ausgabe der Zeitschrift
- 14
Data source: DBLP
- Beziehungen:
- Property of