Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image

Bahareh Kalantar; Seyd Teymoor Seydi; Naonori Ueda; Vahideh Saeidi; Alfian Abdul Halin; Farzin Shabani

doi:10.1109/IGARSS46834.2022.9884203

Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image

Bahareh Kalantar, Seyd Teymoor Seydi, Naonori Ueda, Vahideh Saeidi, Alfian Abdul Halin, Farzin Shabani

College of Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

This study investigates the effectiveness of Convolutional Neural Networks (CNN) for land cover classification of hyperspectral PRISMA (PRecursore IperSpettrale della Missione Applicativa) images. Specifically, a deep ensemble learning framework is proposed, mainly to extract pertinent information for accurate classification. In this work, 1D, 2D and 3D CNNs map land cover into the eight classes of waterbody, agriculture under cultivation, agriculture cultivation, build up area, wetland, range, forest, and salt marsh. Comparison with a hybrid-CNN model showed a 2.37% improvement in overall accuracy at 99.93%.

Original language	English
Title of host publication	IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
Publisher	Institute of Electrical and Electronics Engineers
Pages	3612-3615
Number of pages	4
ISBN (Electronic)	9781665427920
DOIs	https://doi.org/10.1109/IGARSS46834.2022.9884203
Publication status	Published - 2022
Event	2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, Malaysia Duration: 17 Jul 2022 → 22 Jul 2022

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2022-July

Conference

Conference	2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Country/Territory	Malaysia
City	Kuala Lumpur
Period	17/07/22 → 22/07/22

Keywords

change detection
classification
CNN
GIS
Land cover
Remote sensing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IGARSS46834.2022.9884203Licence: In Copyright

Cite this

Kalantar, B., Seydi, S. T., Ueda, N., Saeidi, V., Halin, A. A., & Shabani, F. (2022). Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium (pp. 3612-3615). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS46834.2022.9884203

Kalantar, Bahareh ; Seydi, Seyd Teymoor ; Ueda, Naonori et al. / Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium. Institute of Electrical and Electronics Engineers, 2022. pp. 3612-3615 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{068259cad411458bb90ee73b0dcf2861,

title = "Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image",

abstract = "This study investigates the effectiveness of Convolutional Neural Networks (CNN) for land cover classification of hyperspectral PRISMA (PRecursore IperSpettrale della Missione Applicativa) images. Specifically, a deep ensemble learning framework is proposed, mainly to extract pertinent information for accurate classification. In this work, 1D, 2D and 3D CNNs map land cover into the eight classes of waterbody, agriculture under cultivation, agriculture cultivation, build up area, wetland, range, forest, and salt marsh. Comparison with a hybrid-CNN model showed a 2.37% improvement in overall accuracy at 99.93%.",

keywords = "change detection, classification, CNN, GIS, Land cover, Remote sensing",

author = "Bahareh Kalantar and Seydi, {Seyd Teymoor} and Naonori Ueda and Vahideh Saeidi and Halin, {Alfian Abdul} and Farzin Shabani",

year = "2022",

doi = "10.1109/IGARSS46834.2022.9884203",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "3612--3615",

booktitle = "IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium",

address = "United States",

note = "2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 ; Conference date: 17-07-2022 Through 22-07-2022",

}

Kalantar, B, Seydi, ST, Ueda, N, Saeidi, V, Halin, AA & Shabani, F 2022, Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image. in IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2022-July, Institute of Electrical and Electronics Engineers, pp. 3612-3615, 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022, Kuala Lumpur, Malaysia, 17/07/22. https://doi.org/10.1109/IGARSS46834.2022.9884203

Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image. / Kalantar, Bahareh; Seydi, Seyd Teymoor; Ueda, Naonori et al.
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium. Institute of Electrical and Electronics Engineers, 2022. p. 3612-3615 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image

AU - Kalantar, Bahareh

AU - Seydi, Seyd Teymoor

AU - Ueda, Naonori

AU - Saeidi, Vahideh

AU - Halin, Alfian Abdul

AU - Shabani, Farzin

PY - 2022

Y1 - 2022

N2 - This study investigates the effectiveness of Convolutional Neural Networks (CNN) for land cover classification of hyperspectral PRISMA (PRecursore IperSpettrale della Missione Applicativa) images. Specifically, a deep ensemble learning framework is proposed, mainly to extract pertinent information for accurate classification. In this work, 1D, 2D and 3D CNNs map land cover into the eight classes of waterbody, agriculture under cultivation, agriculture cultivation, build up area, wetland, range, forest, and salt marsh. Comparison with a hybrid-CNN model showed a 2.37% improvement in overall accuracy at 99.93%.

AB - This study investigates the effectiveness of Convolutional Neural Networks (CNN) for land cover classification of hyperspectral PRISMA (PRecursore IperSpettrale della Missione Applicativa) images. Specifically, a deep ensemble learning framework is proposed, mainly to extract pertinent information for accurate classification. In this work, 1D, 2D and 3D CNNs map land cover into the eight classes of waterbody, agriculture under cultivation, agriculture cultivation, build up area, wetland, range, forest, and salt marsh. Comparison with a hybrid-CNN model showed a 2.37% improvement in overall accuracy at 99.93%.

KW - change detection

KW - classification

KW - CNN

KW - GIS

KW - Land cover

KW - Remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85140371853&partnerID=8YFLogxK

U2 - 10.1109/IGARSS46834.2022.9884203

DO - 10.1109/IGARSS46834.2022.9884203

M3 - Conference contribution

AN - SCOPUS:85140371853

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3612

EP - 3615

BT - IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

PB - Institute of Electrical and Electronics Engineers

T2 - 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022

Y2 - 17 July 2022 through 22 July 2022

ER -

Kalantar B, Seydi ST, Ueda N, Saeidi V, Halin AA, Shabani F. Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium. Institute of Electrical and Electronics Engineers. 2022. p. 3612-3615. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS46834.2022.9884203

Deep Ensemble Learning for Land Cover Classification Based on Hyperspectral Prisma Image

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this