KIT | KIT-Bibliothek | Impressum | Datenschutz

Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression

Riese, Felix M.; Keller, Sina

Abstract (englisch):
In this chapter, we present an entire workflow for hyperspectral regression based on supervised, semi-supervised, and unsupervised learning. Hyperspectral regression is defined as the estimation of continuous parameters like chlorophyll a, soil moisture, or soil texture based on hyperspectral input data. The main challenges in hyperspectral regression are the high dimensionality and strong correlation of the input data combined with small ground truth datasets as well as dataset shift. The presented workflow is divided into three levels. (1) At the data level, the data is pre-processed, dataset shift is addressed, and the dataset is split reasonably. (2) The feature level considers unsupervised dimensionality reduction, unsupervised clustering as well as manual feature engineering and feature selection. These unsupervised approaches include autoencoder (AE), t-distributed stochastic neighbor embedding (t-SNE) as well as uniform manifold approximation and projection (UMAP). (3) At the model level, the most commonly used supervised and semi-supervised machine learning models are presented. These models include random forests (RF), convolutional neural networks (CNN), and supervised self-organizing maps (SOM). ... mehr



Originalveröffentlichung
DOI: 10.1007/978-3-030-38617-7_7
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Buchaufsatz
Publikationsjahr 2020
Sprache Englisch
Identifikator ISBN: 978-3-030-38616-0
ISSN: 2191-6586
KITopen-ID: 1000118750
Erschienen in Hyperspectral Image Analysis : Advances in Machine Learning and Signal Processing. Hrsg.: S. Prasad
Verlag Springer Nature Switzerland AG, Cham, CH
Seiten 187–232
Serie Advances in Computer Vision and Pattern Recognition
Vorab online veröffentlicht am 28.04.2020
Externe Relationen Siehe auch
Nachgewiesen in Scopus
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page