PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data

Forest height inversion based on polarimetric interferometric synthetic aperture radar data has demonstrated significant potential for producing large-scale high-resolution forest height maps and has been the subject of extensive research in recent decades. Machine learning and deep learning (DL) te...

Full description

Saved in:
Bibliographic Details
Main Authors: Dandan Li, Hailiang Lu, Mercedes E. Paoletti, Juan M. Haut, Juntao Gu, Chao Li, Weipeng Jing
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11103723/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737121347141632
author Dandan Li
Hailiang Lu
Mercedes E. Paoletti
Juan M. Haut
Juntao Gu
Chao Li
Weipeng Jing
author_facet Dandan Li
Hailiang Lu
Mercedes E. Paoletti
Juan M. Haut
Juntao Gu
Chao Li
Weipeng Jing
author_sort Dandan Li
collection DOAJ
description Forest height inversion based on polarimetric interferometric synthetic aperture radar data has demonstrated significant potential for producing large-scale high-resolution forest height maps and has been the subject of extensive research in recent decades. Machine learning and deep learning (DL) techniques frequently utilize the height of the forest derived from light detection and ranging (LiDAR) as labels, exhibiting superior inversion accuracy. Nevertheless, due to the complex terrain of forest areas, it is difficult to ensure the inversion accuracy when training in a specific forested scene and then applying it to other areas. Meanwhile, the lack of training samples imposes additional constraints on the efficacy of supervised DL-based methods. Given this context, an unsupervised framework for forest height inversion that can be used with several existing DL models and does not require previous knowledge from LiDAR data is very appealing. In this article, we delve into this framework by introducing a novel terrain compensation strategy, which allows the framework to be adapted to different forest terrain scenarios. Furthermore, a more efficient network architecture called ResUnet++ is used to extensively extract forest height information from pseudo-labels, resulting in the novel adaptive polarimetric interferometric deep-learning-based framework (<monospace>PIDLF+</monospace>). Three study sites with different terrain characteristics, i.e., Lop&#x00E9;, Pongara, and Rabi, were selected for validation. The experiments show that the proposed <monospace>PIDLF+</monospace> works well in different forest terrains and improves accuracy. It achieved a root-mean-square error (RMSE) of 8.69 m and a coefficient of determination (<inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula>) of 0.94 in the Lop&#x00E9; site, an RMSE of 11.31 m and an <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> of 0.90 in the Pongara site, and an RMSE of 8.86 m and an <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> of 0.92 in the Rabi site.
format Article
id doaj-art-c9f3d1edb33749f6b72d1db2c5795b6d
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-c9f3d1edb33749f6b72d1db2c5795b6d2025-08-20T03:07:01ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118200542007110.1109/JSTARS.2025.359420111103723PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR DataDandan Li0https://orcid.org/0009-0004-7847-4449Hailiang Lu1https://orcid.org/0000-0003-0094-184XMercedes E. Paoletti2https://orcid.org/0000-0003-1030-3729Juan M. Haut3https://orcid.org/0000-0001-6701-961XJuntao Gu4Chao Li5https://orcid.org/0000-0003-1932-7698Weipeng Jing6https://orcid.org/0000-0001-7933-6946College of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaDepartment of Technology of Computers and Communications, University of Extremadura, C&#x00E1;ceres, SpainDepartment of Technology of Computers and Communications, University of Extremadura, C&#x00E1;ceres, SpainHeilongjiang Cyberspace Research Center, Harbin, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaCollege of Computer and Control Engineering, Northeast Forestry University, Harbin, ChinaForest height inversion based on polarimetric interferometric synthetic aperture radar data has demonstrated significant potential for producing large-scale high-resolution forest height maps and has been the subject of extensive research in recent decades. Machine learning and deep learning (DL) techniques frequently utilize the height of the forest derived from light detection and ranging (LiDAR) as labels, exhibiting superior inversion accuracy. Nevertheless, due to the complex terrain of forest areas, it is difficult to ensure the inversion accuracy when training in a specific forested scene and then applying it to other areas. Meanwhile, the lack of training samples imposes additional constraints on the efficacy of supervised DL-based methods. Given this context, an unsupervised framework for forest height inversion that can be used with several existing DL models and does not require previous knowledge from LiDAR data is very appealing. In this article, we delve into this framework by introducing a novel terrain compensation strategy, which allows the framework to be adapted to different forest terrain scenarios. Furthermore, a more efficient network architecture called ResUnet++ is used to extensively extract forest height information from pseudo-labels, resulting in the novel adaptive polarimetric interferometric deep-learning-based framework (<monospace>PIDLF+</monospace>). Three study sites with different terrain characteristics, i.e., Lop&#x00E9;, Pongara, and Rabi, were selected for validation. The experiments show that the proposed <monospace>PIDLF+</monospace> works well in different forest terrains and improves accuracy. It achieved a root-mean-square error (RMSE) of 8.69 m and a coefficient of determination (<inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula>) of 0.94 in the Lop&#x00E9; site, an RMSE of 11.31 m and an <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> of 0.90 in the Pongara site, and an RMSE of 8.86 m and an <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> of 0.92 in the Rabi site.https://ieeexplore.ieee.org/document/11103723/Deep learning (DL)forest height estimation<inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX">$L$</tex-math> </inline-formula>-bandpolarimetric interferometric synthetic aperture radar (PolInSAR)terrain slope
spellingShingle Dandan Li
Hailiang Lu
Mercedes E. Paoletti
Juan M. Haut
Juntao Gu
Chao Li
Weipeng Jing
PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL)
forest height estimation
<inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX">$L$</tex-math> </inline-formula>-band
polarimetric interferometric synthetic aperture radar (PolInSAR)
terrain slope
title PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
title_full PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
title_fullStr PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
title_full_unstemmed PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
title_short PIDLF+: A Novel Adaptive PIDLF for Forestry Height Mapping Based on Single-Baseline PolInSAR Data
title_sort pidlf a novel adaptive pidlf for forestry height mapping based on single baseline polinsar data
topic Deep learning (DL)
forest height estimation
<inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX">$L$</tex-math> </inline-formula>-band
polarimetric interferometric synthetic aperture radar (PolInSAR)
terrain slope
url https://ieeexplore.ieee.org/document/11103723/
work_keys_str_mv AT dandanli pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT hailianglu pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT mercedesepaoletti pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT juanmhaut pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT juntaogu pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT chaoli pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata
AT weipengjing pidlfanoveladaptivepidlfforforestryheightmappingbasedonsinglebaselinepolinsardata