From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery

Accurate, detailed, and up-to-date tree species distribution information is essential for effective forest management and environmental research. However, existing tree species maps face limitations in resolution and update cycle, making it difficult to meet modern demands. To overcome these limitat...

Full description

Saved in:
Bibliographic Details
Main Authors: Taebin Choe, Seungpyo Jeon, Byeongcheol Kim, Seonyoung Park
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115477634809856
author Taebin Choe
Seungpyo Jeon
Byeongcheol Kim
Seonyoung Park
author_facet Taebin Choe
Seungpyo Jeon
Byeongcheol Kim
Seonyoung Park
author_sort Taebin Choe
collection DOAJ
description Accurate, detailed, and up-to-date tree species distribution information is essential for effective forest management and environmental research. However, existing tree species maps face limitations in resolution and update cycle, making it difficult to meet modern demands. To overcome these limitations, this study proposes a novel framework that utilizes existing medium-resolution national tree species maps as ‘weak labels’ and fuses multi-temporal Sentinel-2 and PlanetScope satellite imagery data. Specifically, a super-resolution (SR) technique, using PlanetScope imagery as a reference, was first applied to Sentinel-2 data to enhance its resolution to 2.5 m. Then, these enhanced Sentinel-2 bands were combined with PlanetScope bands to construct the final multi-spectral, multi-temporal input data. Deep learning (DL) model training data was constructed by strategically sampling information-rich pixels from the national tree species map. Applying the proposed methodology to Sobaeksan and Jirisan National Parks in South Korea, the performance of various machine learning (ML) and deep learning (DL) models was compared, including traditional ML (linear regression, random forest) and DL architectures (multilayer perceptron (MLP), spectral encoder block (SEB)—linear, and SEB-transformer). The MLP model demonstrated optimal performance, achieving over 85% overall accuracy (OA) and more than 81% accuracy in classifying spectrally similar and difficult-to-distinguish species, specifically <i>Quercus mongolica</i> (QM) and <i>Quercus variabilis</i> (QV). Furthermore, while spectral and temporal information were confirmed to contribute significantly to tree species classification, the contribution of spatial (texture) information was experimentally found to be limited at the 2.5 m resolution level. This study presents a practical method for creating high-resolution tree species maps scalable to the national level by fusing existing tree species maps with Sentinel-2 and PlanetScope imagery without requiring costly separate field surveys. Its significance lies in establishing a foundation that can contribute to various fields such as forest resource management, biodiversity conservation, and climate change research.
format Article
id doaj-art-175c7f02218b4c81a31b50abb2a7e86d
institution OA Journals
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-175c7f02218b4c81a31b50abb2a7e86d2025-08-20T02:36:33ZengMDPI AGRemote Sensing2072-42922025-06-011713222210.3390/rs17132222From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite ImageryTaebin Choe0Seungpyo Jeon1Byeongcheol Kim2Seonyoung Park3Department of Applied Artificial Intelligence, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaDepartment of Applied Artificial Intelligence, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaDepartment of Applied Artificial Intelligence, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaDepartment of Applied Artificial Intelligence, Seoul National University of Science and Technology, 232 Gongneung-ro, Nowon-gu, Seoul 01811, Republic of KoreaAccurate, detailed, and up-to-date tree species distribution information is essential for effective forest management and environmental research. However, existing tree species maps face limitations in resolution and update cycle, making it difficult to meet modern demands. To overcome these limitations, this study proposes a novel framework that utilizes existing medium-resolution national tree species maps as ‘weak labels’ and fuses multi-temporal Sentinel-2 and PlanetScope satellite imagery data. Specifically, a super-resolution (SR) technique, using PlanetScope imagery as a reference, was first applied to Sentinel-2 data to enhance its resolution to 2.5 m. Then, these enhanced Sentinel-2 bands were combined with PlanetScope bands to construct the final multi-spectral, multi-temporal input data. Deep learning (DL) model training data was constructed by strategically sampling information-rich pixels from the national tree species map. Applying the proposed methodology to Sobaeksan and Jirisan National Parks in South Korea, the performance of various machine learning (ML) and deep learning (DL) models was compared, including traditional ML (linear regression, random forest) and DL architectures (multilayer perceptron (MLP), spectral encoder block (SEB)—linear, and SEB-transformer). The MLP model demonstrated optimal performance, achieving over 85% overall accuracy (OA) and more than 81% accuracy in classifying spectrally similar and difficult-to-distinguish species, specifically <i>Quercus mongolica</i> (QM) and <i>Quercus variabilis</i> (QV). Furthermore, while spectral and temporal information were confirmed to contribute significantly to tree species classification, the contribution of spatial (texture) information was experimentally found to be limited at the 2.5 m resolution level. This study presents a practical method for creating high-resolution tree species maps scalable to the national level by fusing existing tree species maps with Sentinel-2 and PlanetScope imagery without requiring costly separate field surveys. Its significance lies in establishing a foundation that can contribute to various fields such as forest resource management, biodiversity conservation, and climate change research.https://www.mdpi.com/2072-4292/17/13/2222tree species classificationdeep learningremote sensingSentinel-2PlanetScopesuper-resolution
spellingShingle Taebin Choe
Seungpyo Jeon
Byeongcheol Kim
Seonyoung Park
From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
Remote Sensing
tree species classification
deep learning
remote sensing
Sentinel-2
PlanetScope
super-resolution
title From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
title_full From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
title_fullStr From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
title_full_unstemmed From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
title_short From Coarse to Crisp: Enhancing Tree Species Maps with Deep Learning and Satellite Imagery
title_sort from coarse to crisp enhancing tree species maps with deep learning and satellite imagery
topic tree species classification
deep learning
remote sensing
Sentinel-2
PlanetScope
super-resolution
url https://www.mdpi.com/2072-4292/17/13/2222
work_keys_str_mv AT taebinchoe fromcoarsetocrispenhancingtreespeciesmapswithdeeplearningandsatelliteimagery
AT seungpyojeon fromcoarsetocrispenhancingtreespeciesmapswithdeeplearningandsatelliteimagery
AT byeongcheolkim fromcoarsetocrispenhancingtreespeciesmapswithdeeplearningandsatelliteimagery
AT seonyoungpark fromcoarsetocrispenhancingtreespeciesmapswithdeeplearningandsatelliteimagery