elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Explainable Artificial Intelligence in Remote Sensing

Karmakar, Chandrabali und Dumitru, Corneliu Octavian und Datcu, Mihai (2020) Explainable Artificial Intelligence in Remote Sensing. Phi-week, 2020-09-28 - 2020-10-02, Frascati, Italy.

Dieses Archiv kann nicht den Volltext zur Verfügung stellen.

Offizielle URL: https://phiweek.esa.int/

Kurzfassung

Although artificial intelligence methods have achieved notable success in many sectors, there is an increasing demand towards explainability and trustworthiness of these methods. Currently, machine learning models such as deep learning are “opaque”, such “opacity” introduced by sub-symbolism. We attempt to explore explainable machine learning methods in understanding Earth observation data. Recently, there have been efforts towards explaining machine learning (X-ML) models, contributing to the paradigm of eXplainable Artificial Intelligence(XAI). The important conceptual propositions X-ML are interpretability, transparency and explainability. Here, we propose an explainable data mining approach based on Latent Dirichlet Allocation (LDA) which supports the idea of transparency, interpretability and explainability. Informally, transparency is the ability to understand the mechanism of each component of a method. Researchers delineate three levels of transparency: design transparency, algorithmic transparency and model transparency. Design transparency is concerned with clear logic behind design decision such as model parameters. Algorithmic transparency is the ability to understand how the algorithm works from a mathematical point of view. A model is called algorithmically transparent if input-out relation and the process can be written down as mathematical formula. Model transparency ensures traceability of the outcomes. We demonstrate of adherence of each step of our 5-step method to design, model and algorithmic transparency. The second aspect of explainable machine learning is interpretability, which is nothing but making sense of intermediate outcomes e.g., latent layers from the model in combination with the help of domain knowledge. We use a exploit the latent variables retrieved from the LDA to create a interpretable visualizations for non-visual Sentinel-1 data and demonstrate the idea of interpretability with the help of product quick-look and classification maps from another research. We define three levels of interpretability: low, medium and high. Low interpretability only uses the visualization, medium interpretability compares the visualization with the quick-look and high interpretability is achieved by comparing the visualization with the product quick-look and the classification map. The third aspect, explainability refers to the decision made by using features in the interpretable domain. We deliver explainable class similarity measures and semantic relations based on seamless latent variables retrieved from the LDA model. In general, the method proposes a LDA-based data mining approach as a contribution towards XAI in the remote sensing field.

elib-URL des Eintrags:https://elib.dlr.de/138123/
Dokumentart:Konferenzbeitrag (Poster)
Titel:Explainable Artificial Intelligence in Remote Sensing
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Karmakar, ChandrabaliChandrabali.Karmakar (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Dumitru, Corneliu OctavianCorneliu.Dumitru (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datcu, MihaiMihai.Datcu (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:2020
Referierte Publikation:Nein
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Status:veröffentlicht
Stichwörter:XAI, LDA, machine learning, Sentinels
Veranstaltungstitel:Phi-week
Veranstaltungsort:Frascati, Italy
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:28 September 2020
Veranstaltungsende:2 Oktober 2020
Veranstalter :ESA
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Vorhaben hochauflösende Fernerkundungsverfahren (alt)
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > EO Data Science
Hinterlegt von: Dumitru, Corneliu Octavian
Hinterlegt am:26 Nov 2020 13:58
Letzte Änderung:24 Apr 2024 20:40

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.