FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186013623> ?p ?o ?g. }

• W3186013623 abstract "&lt;p&gt;During the last years, much progress has been reached with machine learning algorithms. Among the typical application fields of machine learning are many technical and commercial applications as well as Earth science analyses, where most often indirect and distorted detector data have to be converted to well-calibrated scientific data that are a prerequisite for a correct understanding of the desired physical quantities and their relationships.&lt;/p&gt;&lt;p&gt;However, the provision of sufficient calibrated data is not enough for the testing, training, and routine processing of most machine learning applications. In principle, one also needs a clear strategy for the selection of necessary and useful training data and an easily understandable quality control of the finally desired parameters.&lt;/p&gt;&lt;p&gt;At a first glance, one could guess that this problem could be solved by a careful selection of representative test data covering many typical cases as well as some counterexamples. Then these test data can be used for the training of the internal parameters of a machine learning application. At a second glance, however, many researchers found out that a simple stacking up of plain examples is not the best choice for many scientific applications.&lt;/p&gt;&lt;p&gt;To get improved machine learning results, we concentrated on the analysis of satellite images depicting the Earth&amp;#8217;s surface under various conditions such as the selected instrument type, spectral bands, and spatial resolution. In our case, such data are routinely provided by the freely accessible European Sentinel satellite products (e.g., Sentinel-1, and Sentinel-2). Our basic work then included investigations of how some additional processing steps &amp;#8211; to be linked with the selected training data &amp;#8211; can provide better machine learning results.&lt;/p&gt;&lt;p&gt;To this end, we analysed and compared three different approaches to find out machine learning strategies for the joint selection and processing of training data for our Earth observation images:&lt;/p&gt;&lt;ul&gt;&lt;li&gt;One can optimize the training data selection by adapting the data selection to the specific instrument, target, and application characteristics [1].&lt;/li&gt; &lt;li&gt;As an alternative, one can dynamically generate new training parameters by Generative Adversarial Networks. This is comparable to the role of a sparring partner in boxing [2].&lt;/li&gt; &lt;li&gt;One can also use a hybrid semi-supervised approach for Synthetic Aperture Radar images with limited labelled data. The method is split in: polarimetric scattering classification, topic modelling for scattering labels, unsupervised constraint learning, and supervised label prediction with constraints [3].&lt;/li&gt; &lt;/ul&gt;&lt;p&gt;We applied these strategies in the ExtremeEarth sea-ice monitoring project (http://earthanalytics.eu/). As a result, we can demonstrate for which application cases these three strategies will provide a promising alternative to a simple conventional selection of available training data.&lt;/p&gt;&lt;p&gt;[1] C.O. Dumitru et. al, &amp;#8220;Understanding Satellite Images: A Data Mining Module for Sentinel Images&amp;#8221;, Big Earth Data, 2020, 4(4), pp. 367-408.&lt;/p&gt;&lt;p&gt;[2] D. Ao et. al., &amp;#8220;Dialectical GAN for SAR Image Translation: From Sentinel-1 to TerraSAR-X&amp;#8221;, Remote Sensing, 2018, 10(10), pp. 1-23.&lt;/p&gt;&lt;p&gt;[3] Z. Huang, et. al., &quot;HDEC-TFA: An Unsupervised Learning Approach for Discovering Physical Scattering Properties of Single-Polarized SAR Images&quot;, IEEE Transactions on Geoscience and Remote Sensing, 2020, pp.1-18.&lt;/p&gt;" @default.
• W3186013623 created "2021-08-02" @default.
• W3186013623 creator A5002219929 @default.
• W3186013623 creator A5010440425 @default.
• W3186013623 creator A5020223046 @default.
• W3186013623 creator A5032370631 @default.
• W3186013623 creator A5036724690 @default.
• W3186013623 creator A5038250580 @default.
• W3186013623 date "2021-03-03" @default.
• W3186013623 modified "2023-09-27" @default.
• W3186013623 title "Improved Training for Machine Learning: The Additional Potential of Innovative Algorithmic Approaches." @default.
• W3186013623 doi "https://doi.org/10.5194/egusphere-egu21-4683" @default.
• W3186013623 hasPublicationYear "2021" @default.
• W3186013623 type Work @default.
• W3186013623 sameAs 3186013623 @default.
• W3186013623 citedByCount "0" @default.
• W3186013623 crossrefType "posted-content" @default.
• W3186013623 hasAuthorship W3186013623A5002219929 @default.
• W3186013623 hasAuthorship W3186013623A5010440425 @default.
• W3186013623 hasAuthorship W3186013623A5020223046 @default.
• W3186013623 hasAuthorship W3186013623A5032370631 @default.
• W3186013623 hasAuthorship W3186013623A5036724690 @default.
• W3186013623 hasAuthorship W3186013623A5038250580 @default.
• W3186013623 hasConcept C111472728 @default.
• W3186013623 hasConcept C11413529 @default.
• W3186013623 hasConcept C119857082 @default.
• W3186013623 hasConcept C138885662 @default.
• W3186013623 hasConcept C151730666 @default.
• W3186013623 hasConcept C154945302 @default.
• W3186013623 hasConcept C16910744 @default.
• W3186013623 hasConcept C178790620 @default.
• W3186013623 hasConcept C185592680 @default.
• W3186013623 hasConcept C199360897 @default.
• W3186013623 hasConcept C2775924081 @default.
• W3186013623 hasConcept C2777267654 @default.
• W3186013623 hasConcept C2779530757 @default.
• W3186013623 hasConcept C33347731 @default.
• W3186013623 hasConcept C41008148 @default.
• W3186013623 hasConcept C81917197 @default.
• W3186013623 hasConcept C86803240 @default.
• W3186013623 hasConceptScore W3186013623C111472728 @default.
• W3186013623 hasConceptScore W3186013623C11413529 @default.
• W3186013623 hasConceptScore W3186013623C119857082 @default.
• W3186013623 hasConceptScore W3186013623C138885662 @default.
• W3186013623 hasConceptScore W3186013623C151730666 @default.
• W3186013623 hasConceptScore W3186013623C154945302 @default.
• W3186013623 hasConceptScore W3186013623C16910744 @default.
• W3186013623 hasConceptScore W3186013623C178790620 @default.
• W3186013623 hasConceptScore W3186013623C185592680 @default.
• W3186013623 hasConceptScore W3186013623C199360897 @default.
• W3186013623 hasConceptScore W3186013623C2775924081 @default.
• W3186013623 hasConceptScore W3186013623C2777267654 @default.
• W3186013623 hasConceptScore W3186013623C2779530757 @default.
• W3186013623 hasConceptScore W3186013623C33347731 @default.
• W3186013623 hasConceptScore W3186013623C41008148 @default.
• W3186013623 hasConceptScore W3186013623C81917197 @default.
• W3186013623 hasConceptScore W3186013623C86803240 @default.
• W3186013623 hasLocation W31860136231 @default.
• W3186013623 hasOpenAccess W3186013623 @default.
• W3186013623 hasPrimaryLocation W31860136231 @default.
• W3186013623 hasRelatedWork W1009047 @default.
• W3186013623 hasRelatedWork W12563130 @default.
• W3186013623 hasRelatedWork W13704299 @default.
• W3186013623 hasRelatedWork W265079 @default.
• W3186013623 hasRelatedWork W3422034 @default.
• W3186013623 hasRelatedWork W435147 @default.
• W3186013623 hasRelatedWork W6296663 @default.
• W3186013623 hasRelatedWork W6655772 @default.
• W3186013623 hasRelatedWork W7608368 @default.
• W3186013623 hasRelatedWork W9972581 @default.
• W3186013623 isParatext "false" @default.
• W3186013623 isRetracted "false" @default.
• W3186013623 magId "3186013623" @default.
• W3186013623 workType "article" @default.