Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression

João E. Pereira-Pires; João M. N. Silva; José M. Fonseca; André Mora; Raffaella Guida

doi:10.1109/IGARSS52108.2023.10282639

Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression

João E. Pereira-Pires, João M. N. Silva, José M. Fonseca, André Mora, Raffaella Guida

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

2 Citations (Scopus)

Abstract

The knowledge of the Forest Height (FH) is important for monitoring the forests, and it can be used as a proxy variable of other forest parameters as the aboveground biomass. It is also important for understanding the climate change and prepare the wildfire seasons. The most effective way to map the FH is through field campaigns or airborne laser scanning, but both are expensive and not scalable. Alternatively, spaceborne Synthetic Aperture Radar (SAR) data may be used. However, it often relies on the acquisition of large ground truth datasets. In this paper, a new Regression Methodology (RM) that makes use of SAR data and a Stacking Regressor that minimises the amount of data needed to map the FH of a region is presented. Tested on a total of 16 regions between Portugal and Spain, plus one in California, the RM achieved a R2 between 42.12%-62.62%, and a RMSE between 0.96m-4.49m.

Original language	English
Title of host publication	IGARSS 2023
Subtitle of host publication	2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Place of Publication	Massachusetts
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1353-1356
Number of pages	4
ISBN (Electronic)	979-8-3503-2010-7
ISBN (Print)	979-8-3503-3174-5
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10282639
Publication status	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Publication series

Name	IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Volume	2023-July
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23

Keywords

ALOS-2
Climate Change
Forest Height
Mediterranean Forests
Sentinel-1
Stacking Regressor
Synthetic Aperture Radar
Wildfires

UN SDGs

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

Access to Document

10.1109/IGARSS52108.2023.10282639

Cite this

Pereira-Pires, J. E., Silva, J. M. N., Fonseca, J. M., Mora, A., & Guida, R. (2023). Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression. In IGARSS 2023: 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 1353-1356). (IEEE International Symposium on Geoscience and Remote Sensing (IGARSS); Vol. 2023-July). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IGARSS52108.2023.10282639

Pereira-Pires, João E. ; Silva, João M. N. ; Fonseca, José M. et al. / Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression. IGARSS 2023: 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Massachusetts : Institute of Electrical and Electronics Engineers (IEEE), 2023. pp. 1353-1356 (IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)).

@inproceedings{c2cf935747454dc5850c7eded2eff364,

title = "Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression",

abstract = "The knowledge of the Forest Height (FH) is important for monitoring the forests, and it can be used as a proxy variable of other forest parameters as the aboveground biomass. It is also important for understanding the climate change and prepare the wildfire seasons. The most effective way to map the FH is through field campaigns or airborne laser scanning, but both are expensive and not scalable. Alternatively, spaceborne Synthetic Aperture Radar (SAR) data may be used. However, it often relies on the acquisition of large ground truth datasets. In this paper, a new Regression Methodology (RM) that makes use of SAR data and a Stacking Regressor that minimises the amount of data needed to map the FH of a region is presented. Tested on a total of 16 regions between Portugal and Spain, plus one in California, the RM achieved a R2 between 42.12%-62.62%, and a RMSE between 0.96m-4.49m.",

keywords = "ALOS-2, Climate Change, Forest Height, Mediterranean Forests, Sentinel-1, Stacking Regressor, Synthetic Aperture Radar, Wildfires",

author = "Pereira-Pires, {Jo{\~a}o E.} and Silva, {Jo{\~a}o M. N.} and Fonseca, {Jos{\'e} M.} and Andr{\'e} Mora and Raffaella Guida",

note = "Funding Information: info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00066%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00239%2F2020/PT# info:eu-repo/grantAgreement/FCT/OE/2020.05015.BD/PT# Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10282639",

language = "English",

isbn = "979-8-3503-3174-5",

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

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1353--1356",

booktitle = "IGARSS 2023",

address = "United States",

}

Pereira-Pires, JE, Silva, JMN, Fonseca, JM , Mora, A & Guida, R 2023, Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression. in IGARSS 2023: 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. IEEE International Symposium on Geoscience and Remote Sensing (IGARSS), vol. 2023-July, Institute of Electrical and Electronics Engineers (IEEE), Massachusetts, pp. 1353-1356, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10282639

Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression. / Pereira-Pires, João E.; Silva, João M. N.; Fonseca, José M. et al.
IGARSS 2023: 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Massachusetts: Institute of Electrical and Electronics Engineers (IEEE), 2023. p. 1353-1356 (IEEE International Symposium on Geoscience and Remote Sensing (IGARSS); Vol. 2023-July).

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

TY - GEN

T1 - Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression

AU - Pereira-Pires, João E.

AU - Silva, João M. N.

AU - Fonseca, José M.

AU - Mora, André

AU - Guida, Raffaella

N1 - Funding Information: info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00066%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00239%2F2020/PT# info:eu-repo/grantAgreement/FCT/OE/2020.05015.BD/PT# Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - The knowledge of the Forest Height (FH) is important for monitoring the forests, and it can be used as a proxy variable of other forest parameters as the aboveground biomass. It is also important for understanding the climate change and prepare the wildfire seasons. The most effective way to map the FH is through field campaigns or airborne laser scanning, but both are expensive and not scalable. Alternatively, spaceborne Synthetic Aperture Radar (SAR) data may be used. However, it often relies on the acquisition of large ground truth datasets. In this paper, a new Regression Methodology (RM) that makes use of SAR data and a Stacking Regressor that minimises the amount of data needed to map the FH of a region is presented. Tested on a total of 16 regions between Portugal and Spain, plus one in California, the RM achieved a R2 between 42.12%-62.62%, and a RMSE between 0.96m-4.49m.

AB - The knowledge of the Forest Height (FH) is important for monitoring the forests, and it can be used as a proxy variable of other forest parameters as the aboveground biomass. It is also important for understanding the climate change and prepare the wildfire seasons. The most effective way to map the FH is through field campaigns or airborne laser scanning, but both are expensive and not scalable. Alternatively, spaceborne Synthetic Aperture Radar (SAR) data may be used. However, it often relies on the acquisition of large ground truth datasets. In this paper, a new Regression Methodology (RM) that makes use of SAR data and a Stacking Regressor that minimises the amount of data needed to map the FH of a region is presented. Tested on a total of 16 regions between Portugal and Spain, plus one in California, the RM achieved a R2 between 42.12%-62.62%, and a RMSE between 0.96m-4.49m.

KW - ALOS-2

KW - Climate Change

KW - Forest Height

KW - Mediterranean Forests

KW - Sentinel-1

KW - Stacking Regressor

KW - Synthetic Aperture Radar

KW - Wildfires

UR - http://www.scopus.com/inward/record.url?scp=85178345809&partnerID=8YFLogxK

U2 - 10.1109/IGARSS52108.2023.10282639

DO - 10.1109/IGARSS52108.2023.10282639

M3 - Conference contribution

AN - SCOPUS:85178345809

SN - 979-8-3503-3174-5

T3 - IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

SP - 1353

EP - 1356

BT - IGARSS 2023

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Massachusetts

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

Pereira-Pires JE, Silva JMN, Fonseca JM , Mora A, Guida R. Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression. In IGARSS 2023: 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Massachusetts: Institute of Electrical and Electronics Engineers (IEEE). 2023. p. 1353-1356. (IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)). doi: 10.1109/IGARSS52108.2023.10282639

Forest Height Estimation Using Multi-Frequency Sar and a Stacking Regression

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this