Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil

Monitoring the height of secondary forest regrowth is essential for assessing ecosystem recovery, but current methods rely on field surveys, airborne or UAV LiDAR, and 3D reconstruction from high-resolution UAV imagery, which are often costly or limited by logistical constraints. Here, we address th...

Full description

Saved in:
Bibliographic Details
Main Authors: Fabien H. Wagner, Fábio Marcelo Breunig, Rafaelo Balbinot, Emanuel Araújo Silva, Messias Carneiro Soares, Marco Antonio Kramm, Mayumi C. M. Hirye, Griffin Carter, Ricardo Dalagnol, Stephen C. Hagen, Sassan Saatchi
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2718
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770833616044032
author Fabien H. Wagner
Fábio Marcelo Breunig
Rafaelo Balbinot
Emanuel Araújo Silva
Messias Carneiro Soares
Marco Antonio Kramm
Mayumi C. M. Hirye
Griffin Carter
Ricardo Dalagnol
Stephen C. Hagen
Sassan Saatchi
author_facet Fabien H. Wagner
Fábio Marcelo Breunig
Rafaelo Balbinot
Emanuel Araújo Silva
Messias Carneiro Soares
Marco Antonio Kramm
Mayumi C. M. Hirye
Griffin Carter
Ricardo Dalagnol
Stephen C. Hagen
Sassan Saatchi
author_sort Fabien H. Wagner
collection DOAJ
description Monitoring the height of secondary forest regrowth is essential for assessing ecosystem recovery, but current methods rely on field surveys, airborne or UAV LiDAR, and 3D reconstruction from high-resolution UAV imagery, which are often costly or limited by logistical constraints. Here, we address the challenge of scaling up canopy height monitoring by evaluating a recent deep learning model, trained on data from the Amazon and Atlantic Forests, developed to extract canopy height from RGB-NIR Planet NICFI imagery. The research questions are as follows: (i) How are canopy height estimates from the model affected by slope and orientation in natural forests, based on a large and well-balanced experimental design? (ii) How effectively does the model capture the growth trajectories of <i>Pinus</i> and <i>Eucalyptus</i> plantations over an eight-year period following planting? We find that the model closely tracks <i>Pinus</i> growth at the parcel scale, with predictions generally within one standard deviation of UAV-derived heights. For <i>Eucalyptus</i>, while growth is detected, the model consistently underestimates height, by more than 10 m in some cases, until late in the cycle when the canopy becomes less dense. In stable natural forests, the model reveals seasonal artifacts driven by topographic variables (slope × aspect × day of year), for which we propose strategies to reduce their influence. These results highlight the model’s potential as a cost-effective and scalable alternative to field-based and LiDAR methods, enabling broad-scale monitoring of forest regrowth and contributing to innovation in remote sensing for forest dynamics assessment.
format Article
id doaj-art-0d5a18bd884a42f2b37f8138ba1a4e83
institution DOAJ
issn 2072-4292
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-0d5a18bd884a42f2b37f8138ba1a4e832025-08-20T03:02:51ZengMDPI AGRemote Sensing2072-42922025-08-011715271810.3390/rs17152718Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, BrazilFabien H. Wagner0Fábio Marcelo Breunig1Rafaelo Balbinot2Emanuel Araújo Silva3Messias Carneiro Soares4Marco Antonio Kramm5Mayumi C. M. Hirye6Griffin Carter7Ricardo Dalagnol8Stephen C. Hagen9Sassan Saatchi10CTrees, Pasadena, CA 91105, USADepartment of Forestry, Federal University of Santa Maria (UFSM FW), Frederico Westphalen 98400-000, RS, BrazilDepartment of Forestry, Federal University of Santa Maria (UFSM FW), Frederico Westphalen 98400-000, RS, BrazilDepartment of Forestry, Federal University of Santa Maria (UFSM FW), Frederico Westphalen 98400-000, RS, BrazilDepartment of Forestry, Federal University of Santa Maria (UFSM FW), Frederico Westphalen 98400-000, RS, BrazilDepartment of Forestry, Federal University of Santa Maria (UFSM FW), Frederico Westphalen 98400-000, RS, BrazilCTrees, Pasadena, CA 91105, USACTrees, Pasadena, CA 91105, USACTrees, Pasadena, CA 91105, USACTrees, Pasadena, CA 91105, USACTrees, Pasadena, CA 91105, USAMonitoring the height of secondary forest regrowth is essential for assessing ecosystem recovery, but current methods rely on field surveys, airborne or UAV LiDAR, and 3D reconstruction from high-resolution UAV imagery, which are often costly or limited by logistical constraints. Here, we address the challenge of scaling up canopy height monitoring by evaluating a recent deep learning model, trained on data from the Amazon and Atlantic Forests, developed to extract canopy height from RGB-NIR Planet NICFI imagery. The research questions are as follows: (i) How are canopy height estimates from the model affected by slope and orientation in natural forests, based on a large and well-balanced experimental design? (ii) How effectively does the model capture the growth trajectories of <i>Pinus</i> and <i>Eucalyptus</i> plantations over an eight-year period following planting? We find that the model closely tracks <i>Pinus</i> growth at the parcel scale, with predictions generally within one standard deviation of UAV-derived heights. For <i>Eucalyptus</i>, while growth is detected, the model consistently underestimates height, by more than 10 m in some cases, until late in the cycle when the canopy becomes less dense. In stable natural forests, the model reveals seasonal artifacts driven by topographic variables (slope × aspect × day of year), for which we propose strategies to reduce their influence. These results highlight the model’s potential as a cost-effective and scalable alternative to field-based and LiDAR methods, enabling broad-scale monitoring of forest regrowth and contributing to innovation in remote sensing for forest dynamics assessment.https://www.mdpi.com/2072-4292/17/15/2718LiDARUAVcanopy height modelsdeep learningtime serieshigh-resolution satellite images
spellingShingle Fabien H. Wagner
Fábio Marcelo Breunig
Rafaelo Balbinot
Emanuel Araújo Silva
Messias Carneiro Soares
Marco Antonio Kramm
Mayumi C. M. Hirye
Griffin Carter
Ricardo Dalagnol
Stephen C. Hagen
Sassan Saatchi
Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
Remote Sensing
LiDAR
UAV
canopy height models
deep learning
time series
high-resolution satellite images
title Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
title_full Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
title_fullStr Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
title_full_unstemmed Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
title_short Monitoring the Early Growth of <i>Pinus</i> and <i>Eucalyptus</i> Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Riqueza, Brazil
title_sort monitoring the early growth of i pinus i and i eucalyptus i plantations using a planet nicfi based canopy height model a case study in riqueza brazil
topic LiDAR
UAV
canopy height models
deep learning
time series
high-resolution satellite images
url https://www.mdpi.com/2072-4292/17/15/2718
work_keys_str_mv AT fabienhwagner monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT fabiomarcelobreunig monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT rafaelobalbinot monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT emanuelaraujosilva monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT messiascarneirosoares monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT marcoantoniokramm monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT mayumicmhirye monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT griffincarter monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT ricardodalagnol monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT stephenchagen monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil
AT sassansaatchi monitoringtheearlygrowthofipinusiandieucalyptusiplantationsusingaplanetnicfibasedcanopyheightmodelacasestudyinriquezabrazil