Use of guided regularized random forest for biophysical parameter retrieval

E. Izquierdo-Verdiguier; R. Zurita-Milla

doi:10.1109/IGARSS.2018.8517920

Use of guided regularized random forest for biophysical parameter retrieval

E. Izquierdo-Verdiguier, R. Zurita-Milla

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

8 Citations (Scopus)

86 Downloads (Pure)

Abstract

This paper introduces a feature selection method based on random forest -the Guided Regularized Random Forest (GRRF)- which can be used in classification and regression tasks. The method is based on the regularization of the information gain in the random forest nodes to obtain a subset of relevant and non-redundant features. The proposed method is used as a preliminary step In the process of retrieving biophysical parameters from a hyperspectral image.Preliminary experiments show that we can reduce the RMSE of the retrievals by around 7% for the Leaf Area Index and around 8% for the fraction of vegetation cover when compared to the results using random forest features.

Original language	English
Title of host publication	2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
Subtitle of host publication	Proceedings
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	5776-5779
Number of pages	4
ISBN (Electronic)	9781538671504
DOIs	https://doi.org/10.1109/IGARSS.2018.8517920
Publication status	Published - 5 Nov 2018
Event	38th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018: Observing, Understanding and Forcasting the Dynamics of Our Planet - Feria Valencia Convention & Exhibition Center, Valencia, Spain Duration: 22 Jul 2018 → 27 Jul 2018 Conference number: 38 https://www.igarss2018.org/

Publication series

Name	IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Publisher	IEEE
Volume	2018
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	38th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
Abbreviated title	2018
Country/Territory	Spain
City	Valencia
Period	22/07/18 → 27/07/18
Internet address	https://www.igarss2018.org/

Keywords

Biophysical parameter retrieval
Feature selection
Hyperspectral images
Random forest
22/3 OA procedure

Access to Document

10.1109/IGARSS.2018.8517920

ArticleFinal published version, 2.27 MBLicence: Taverne

Cite this

Izquierdo-Verdiguier, E., & Zurita-Milla, R. (2018). Use of guided regularized random forest for biophysical parameter retrieval. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018: Proceedings (pp. 5776-5779). Article 8517920 (IEEE International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018). IEEE. https://doi.org/10.1109/IGARSS.2018.8517920

@inproceedings{9faab72713be415bbdb1f3496673003a,

title = "Use of guided regularized random forest for biophysical parameter retrieval",

abstract = "This paper introduces a feature selection method based on random forest -the Guided Regularized Random Forest (GRRF)- which can be used in classification and regression tasks. The method is based on the regularization of the information gain in the random forest nodes to obtain a subset of relevant and non-redundant features. The proposed method is used as a preliminary step In the process of retrieving biophysical parameters from a hyperspectral image.Preliminary experiments show that we can reduce the RMSE of the retrievals by around 7% for the Leaf Area Index and around 8% for the fraction of vegetation cover when compared to the results using random forest features.",

keywords = "Biophysical parameter retrieval, Feature selection, Hyperspectral images, Random forest, 22/3 OA procedure",

author = "E. Izquierdo-Verdiguier and R. Zurita-Milla",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE; 38th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 : Observing, Understanding and Forcasting the Dynamics of Our Planet, 2018 ; Conference date: 22-07-2018 Through 27-07-2018",

year = "2018",

month = nov,

day = "5",

doi = "10.1109/IGARSS.2018.8517920",

language = "English",

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

publisher = "IEEE",

pages = "5776--5779",

booktitle = "2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018",

address = "United States",

url = "https://www.igarss2018.org/",

}

Izquierdo-Verdiguier, E & Zurita-Milla, R 2018, Use of guided regularized random forest for biophysical parameter retrieval. in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018: Proceedings., 8517920, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2018, IEEE, Piscataway, NJ, pp. 5776-5779, 38th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018, Valencia, Spain, 22/07/18. https://doi.org/10.1109/IGARSS.2018.8517920

Use of guided regularized random forest for biophysical parameter retrieval. / Izquierdo-Verdiguier, E.; Zurita-Milla, R.
2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018: Proceedings. Piscataway, NJ: IEEE, 2018. p. 5776-5779 8517920 (IEEE International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018).

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

TY - GEN

T1 - Use of guided regularized random forest for biophysical parameter retrieval

AU - Izquierdo-Verdiguier, E.

AU - Zurita-Milla, R.

N1 - Conference code: 38

PY - 2018/11/5

Y1 - 2018/11/5

N2 - This paper introduces a feature selection method based on random forest -the Guided Regularized Random Forest (GRRF)- which can be used in classification and regression tasks. The method is based on the regularization of the information gain in the random forest nodes to obtain a subset of relevant and non-redundant features. The proposed method is used as a preliminary step In the process of retrieving biophysical parameters from a hyperspectral image.Preliminary experiments show that we can reduce the RMSE of the retrievals by around 7% for the Leaf Area Index and around 8% for the fraction of vegetation cover when compared to the results using random forest features.

AB - This paper introduces a feature selection method based on random forest -the Guided Regularized Random Forest (GRRF)- which can be used in classification and regression tasks. The method is based on the regularization of the information gain in the random forest nodes to obtain a subset of relevant and non-redundant features. The proposed method is used as a preliminary step In the process of retrieving biophysical parameters from a hyperspectral image.Preliminary experiments show that we can reduce the RMSE of the retrievals by around 7% for the Leaf Area Index and around 8% for the fraction of vegetation cover when compared to the results using random forest features.

KW - Biophysical parameter retrieval

KW - Feature selection

KW - Hyperspectral images

KW - Random forest

KW - 22/3 OA procedure

U2 - 10.1109/IGARSS.2018.8517920

DO - 10.1109/IGARSS.2018.8517920

M3 - Conference contribution

AN - SCOPUS:85058883322

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

SP - 5776

EP - 5779

BT - 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018

PB - IEEE

CY - Piscataway, NJ

T2 - 38th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018

Y2 - 22 July 2018 through 27 July 2018

ER -

Use of guided regularized random forest for biophysical parameter retrieval

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this