Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches

Samet Aksoy; Shouq Zuhter Hasan Al Shwayyat; Sule Nur Topgul; Elif Sertel; Cem Unsalan; Jari Salo; Anton Holmstrom; Jorgen Wallerman; Mats Nilsson; Johan E.S. Fransson

doi:10.1109/IGARSS52108.2023.10282899

Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches

Samet Aksoy, Shouq Zuhter Hasan Al Shwayyat, Sule Nur Topgul, Elif Sertel, Cem Unsalan, Jari Salo, Anton Holmstrom, Jorgen Wallerman, Mats Nilsson, Johan E.S. Fransson

Geomatik Mühendisliği Bölümü

Araştırma sonucu: ???type-name??? › Konferans katkısı › bilirkişi

1 Atıf (Scopus)

Özet

This paper presents the first results of the ongoing development of new forest mapping methods for the Swedish national forest mapping case using Airborne Laser Scanning (ALS) data, utilizing the recent findings in machine learning (ML) and Artificial Intelligence (AI) techniques. We used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) as ML models. In addition, Neural networks (NN) based approaches were utilized in this study. ALS derived features were used to estimate the stem volume (V), above-ground biomass (AGB), basal area (B), tree height (H), stem diameter (D), and forest stand age (A). XGBoost ML algorithm outperformed RF 1 % to 3 % in the R² metric. NN model performed similar to ML model, however it is superior in the estimation of V, AGB, and B parameters.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	2661-2664
Sayfa sayısı	4
ISBN (Elektronik)	9798350320107
DOI'lar	https://doi.org/10.1109/IGARSS52108.2023.10282899
Yayın durumu	Yayınlandı - 2023
Etkinlik	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Süre: 16 Tem 2023 → 21 Tem 2023

Yayın serisi

Adı	International Geoscience and Remote Sensing Symposium (IGARSS)
Hacim	2023-July

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Ülke/Bölge	United States
Şehir	Pasadena
Periyot	16/07/23 → 21/07/23

Bibliyografik not

Publisher Copyright:
© 2023 IEEE.

BM SKH

Bu sonuç, aşağıdaki Sürdürülebilir Kalkınma Hedefine/Hedeflerine katkıda bulunur

Belgeye Erişim

10.1109/IGARSS52108.2023.10282899

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Aksoy, S., Hasan Al Shwayyat, S. Z., Nur Topgul, S., Sertel, E., Unsalan, C., Salo, J., Holmstrom, A., Wallerman, J., Nilsson, M., & Fransson, J. E. S. (2023). Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 2661-2664). (International Geoscience and Remote Sensing Symposium (IGARSS); Hac. 2023-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS52108.2023.10282899

Aksoy, Samet ; Hasan Al Shwayyat, Shouq Zuhter ; Nur Topgul, Sule et al. / Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches. IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 2661-2664 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{af1693615a6b4e52a007d95eb5dda40f,

title = "Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches",

abstract = "This paper presents the first results of the ongoing development of new forest mapping methods for the Swedish national forest mapping case using Airborne Laser Scanning (ALS) data, utilizing the recent findings in machine learning (ML) and Artificial Intelligence (AI) techniques. We used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) as ML models. In addition, Neural networks (NN) based approaches were utilized in this study. ALS derived features were used to estimate the stem volume (V), above-ground biomass (AGB), basal area (B), tree height (H), stem diameter (D), and forest stand age (A). XGBoost ML algorithm outperformed RF 1 % to 3 % in the R² metric. NN model performed similar to ML model, however it is superior in the estimation of V, AGB, and B parameters.",

keywords = "Artificial Intelligence, Forest, global, machine learning, map",

author = "Samet Aksoy and {Hasan Al Shwayyat}, {Shouq Zuhter} and {Nur Topgul}, Sule and Elif Sertel and Cem Unsalan and Jari Salo and Anton Holmstrom and Jorgen Wallerman and Mats Nilsson and Fransson, {Johan E.S.}",

note = "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/IGARSS52108.2023.10282899",

language = "English",

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

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2661--2664",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

}

Aksoy, S, Hasan Al Shwayyat, SZ, Nur Topgul, S, Sertel, E, Unsalan, C, Salo, J, Holmstrom, A, Wallerman, J, Nilsson, M & Fransson, JES 2023, Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), hac. 2023-July, Institute of Electrical and Electronics Engineers Inc., pp. 2661-2664, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10282899

Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches. / Aksoy, Samet; Hasan Al Shwayyat, Shouq Zuhter; Nur Topgul, Sule et al.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2661-2664 (International Geoscience and Remote Sensing Symposium (IGARSS); Hac. 2023-July).

Araştırma sonucu: ???type-name??? › Konferans katkısı › bilirkişi

TY - GEN

T1 - Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches

AU - Aksoy, Samet

AU - Hasan Al Shwayyat, Shouq Zuhter

AU - Nur Topgul, Sule

AU - Sertel, Elif

AU - Unsalan, Cem

AU - Salo, Jari

AU - Holmstrom, Anton

AU - Wallerman, Jorgen

AU - Nilsson, Mats

AU - Fransson, Johan E.S.

PY - 2023

Y1 - 2023

N2 - This paper presents the first results of the ongoing development of new forest mapping methods for the Swedish national forest mapping case using Airborne Laser Scanning (ALS) data, utilizing the recent findings in machine learning (ML) and Artificial Intelligence (AI) techniques. We used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) as ML models. In addition, Neural networks (NN) based approaches were utilized in this study. ALS derived features were used to estimate the stem volume (V), above-ground biomass (AGB), basal area (B), tree height (H), stem diameter (D), and forest stand age (A). XGBoost ML algorithm outperformed RF 1 % to 3 % in the R² metric. NN model performed similar to ML model, however it is superior in the estimation of V, AGB, and B parameters.

AB - This paper presents the first results of the ongoing development of new forest mapping methods for the Swedish national forest mapping case using Airborne Laser Scanning (ALS) data, utilizing the recent findings in machine learning (ML) and Artificial Intelligence (AI) techniques. We used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) as ML models. In addition, Neural networks (NN) based approaches were utilized in this study. ALS derived features were used to estimate the stem volume (V), above-ground biomass (AGB), basal area (B), tree height (H), stem diameter (D), and forest stand age (A). XGBoost ML algorithm outperformed RF 1 % to 3 % in the R² metric. NN model performed similar to ML model, however it is superior in the estimation of V, AGB, and B parameters.

KW - Artificial Intelligence

KW - Forest

KW - global

KW - machine learning

KW - map

UR - http://www.scopus.com/inward/record.url?scp=85178366425&partnerID=8YFLogxK

U2 - 10.1109/IGARSS52108.2023.10282899

DO - 10.1109/IGARSS52108.2023.10282899

M3 - Conference contribution

AN - SCOPUS:85178366425

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2661

EP - 2664

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

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

Y2 - 16 July 2023 through 21 July 2023

ER -

Aksoy S, Hasan Al Shwayyat SZ, Nur Topgul S, Sertel E, Unsalan C, Salo J et al. Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2661-2664. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS52108.2023.10282899

Forest Biophysical Parameter Estimation via Machine Learning and Neural Network Approaches

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

BM SKH

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap