elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

A Qualitative Study of Machine Learning Practices and Engineering Challenges in Earth Observation

Jentzsch, Sophie F. and Hochgeschwender, Nico (2021) A Qualitative Study of Machine Learning Practices and Engineering Challenges in Earth Observation. it - Information Technology. de Gruyter. doi: 10.1515/itit-2020-0045. ISSN 1611-2776.

[img] PDF - Only accessible within DLR - Preprint version (submitted draft)
353kB
[img] PDF - Published version
716kB

Official URL: https://www.degruyter.com/document/doi/10.1515/itit-2020-0045/html

Abstract

Machine Learning (ML) is ubiquitously on the advance. Like many domains, Earth Observation (EO) alsoincreasingly relies on ML applications, where ML methods are applied to process vast amounts of heterogeneous and continuous data streams to answer socially and en-vironmentally relevant questions. However, developing such ML-based EO systems remains challenging: Development processes and employed workflows are often barely structured and poorly reported. The application of ML methodsand techniques is considered to be opaque and the lack of transparency is contradictory to the responsible development of ML-based EO applications. To improve this situation a better understanding of the current practices and engineering-related challenges in developing ML-based EO applications is required. In this paper, we report observations from an exploratory study where five experts shared their view on ML-engineering in semi-structured interviews. We analysed these interviews with coding techniques as often applied in the domain of empirical software engineering. The interviews provide informative insights into the practical development of ML applications and reveal several engineering challenges. Inaddition, interviewees participated in a novel workflow sketching task, which provided a tangible reflection of implicit processes. Overall, the results confirm a gap between theoretical conceptions and real practices in ML development even though workflows were sketched abstractly as textbook-like. The results pave the way for a large-scale investigation on requirements for ML engineering in EO.

Item URL in elib:https://elib.dlr.de/137731/
Document Type:Article
Title:A Qualitative Study of Machine Learning Practices and Engineering Challenges in Earth Observation
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Jentzsch, Sophie F.Sophie.Jentzsch (at) dlr.dehttps://orcid.org/0000-0001-6217-8814
Hochgeschwender, NicoNico.Hochgeschwender (at) dlr.dehttps://orcid.org/0000-0003-1306-7880
Date:15 July 2021
Journal or Publication Title:it - Information Technology
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI :10.1515/itit-2020-0045
Publisher:de Gruyter
ISSN:1611-2776
Status:Published
Keywords:Machine Learning, Artificial Intelligence, Earth Observation, Process Models.
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Tasks SISTEC
Location: Köln-Porz
Institutes and Institutions:Institute for Software Technology
Institut of Simulation and Software Technology
Institut of Simulation and Software Technology > Software for Space Systems and Interactive Visualisation
Deposited By: Jentzsch, Sophie Freya
Deposited On:01 Sep 2021 09:59
Last Modified:18 Oct 2021 11:42

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.