Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery
Canopy height models (CHMs) with sufficient resolution to distinguish individual trees are useful for a variety of applications. However, standard techniques to acquire such data, such as airborne lidar surveying, are often prohibitively expensive. Deep learning techniques for generating CHMs from h...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada47e |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591741040984064 |
|---|---|
| author | Charles J Abolt Javier E Santos Adam L Atchley Lucas Wells Daithi Martin Russell A Parsons Rodman R Linn |
| author_facet | Charles J Abolt Javier E Santos Adam L Atchley Lucas Wells Daithi Martin Russell A Parsons Rodman R Linn |
| author_sort | Charles J Abolt |
| collection | DOAJ |
| description | Canopy height models (CHMs) with sufficient resolution to distinguish individual trees are useful for a variety of applications. However, standard techniques to acquire such data, such as airborne lidar surveying, are often prohibitively expensive. Deep learning techniques for generating CHMs from high-resolution imagery are an attractive option to reduce costs. To date, success with these methods has been demonstrated using multichannel aerial photography and specialized satellite data products derived from multiple sensors, neither of which is commonly available at temporal resolutions finer than one year. Here we demonstrate a method to generate sub-meter resolution CHMs in three forests in California using a more abundant data source: sub-meter resolution, panchromatic satellite imagery from a single sensor. We show that phenology and species composition play important roles in model transferability; when trained using imagery from a single conifer forest in autumn, the model performs well on autumn imagery from a second conifer forest several hundred kilometers distant with no re-training. With modest additions to the training dataset, the same model generates minimally biased estimates of canopy height in both conifer and deciduous forests during multiple seasons. Because the model operates on satellite data with global coverage and a relatively short return interval, we propose its suitability to extrapolate tree-level canopy height data to remote regions and conduct high-temporal resolution monitoring of forest structure. We furthermore demonstrate the workflow’s applicability to fire modeling by conducting simulations in forests populated by trees measured using both this approach and airborne lidar surveying. We find minimal differences in fire behavior relative to a baseline case in which only statistical distributions of tree height and crown area are known. This result underscores the value of forest structural information derived from our workflow for improving the fidelity of wildland fire simulations, among other ecological applications. |
| format | Article |
| id | doaj-art-e9372b4a9f77490b8f6223b5d3293220 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-e9372b4a9f77490b8f6223b5d32932202025-01-22T07:06:11ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101501310.1088/2632-2153/ada47eDeep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imageryCharles J Abolt0https://orcid.org/0000-0001-6052-199XJavier E Santos1https://orcid.org/0000-0002-2404-3975Adam L Atchley2https://orcid.org/0000-0003-2203-1994Lucas Wells3https://orcid.org/0000-0001-9210-8112Daithi Martin4Russell A Parsons5https://orcid.org/0000-0001-5091-8993Rodman R Linn6https://orcid.org/0000-0002-5746-4880Earth and Environmental Sciences Division, Los Alamos National Laboratory , Los Alamos, NM, United States of AmericaEarth and Environmental Sciences Division, Los Alamos National Laboratory , Los Alamos, NM, United States of AmericaEarth and Environmental Sciences Division, Los Alamos National Laboratory , Los Alamos, NM, United States of AmericaSilvx Labs , Missoula, MT, United States of AmericaSilvx Labs , Missoula, MT, United States of AmericaUSFS RMRS Fire Sciences Laboratory , Missoula, MT, United States of AmericaEarth and Environmental Sciences Division, Los Alamos National Laboratory , Los Alamos, NM, United States of AmericaCanopy height models (CHMs) with sufficient resolution to distinguish individual trees are useful for a variety of applications. However, standard techniques to acquire such data, such as airborne lidar surveying, are often prohibitively expensive. Deep learning techniques for generating CHMs from high-resolution imagery are an attractive option to reduce costs. To date, success with these methods has been demonstrated using multichannel aerial photography and specialized satellite data products derived from multiple sensors, neither of which is commonly available at temporal resolutions finer than one year. Here we demonstrate a method to generate sub-meter resolution CHMs in three forests in California using a more abundant data source: sub-meter resolution, panchromatic satellite imagery from a single sensor. We show that phenology and species composition play important roles in model transferability; when trained using imagery from a single conifer forest in autumn, the model performs well on autumn imagery from a second conifer forest several hundred kilometers distant with no re-training. With modest additions to the training dataset, the same model generates minimally biased estimates of canopy height in both conifer and deciduous forests during multiple seasons. Because the model operates on satellite data with global coverage and a relatively short return interval, we propose its suitability to extrapolate tree-level canopy height data to remote regions and conduct high-temporal resolution monitoring of forest structure. We furthermore demonstrate the workflow’s applicability to fire modeling by conducting simulations in forests populated by trees measured using both this approach and airborne lidar surveying. We find minimal differences in fire behavior relative to a baseline case in which only statistical distributions of tree height and crown area are known. This result underscores the value of forest structural information derived from our workflow for improving the fidelity of wildland fire simulations, among other ecological applications.https://doi.org/10.1088/2632-2153/ada47eforestryopticallidarfireCNN |
| spellingShingle | Charles J Abolt Javier E Santos Adam L Atchley Lucas Wells Daithi Martin Russell A Parsons Rodman R Linn Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery Machine Learning: Science and Technology forestry optical lidar fire CNN |
| title | Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery |
| title_full | Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery |
| title_fullStr | Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery |
| title_full_unstemmed | Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery |
| title_short | Deep-learning-based canopy height model generation from sub-meter resolution panchromatic satellite imagery |
| title_sort | deep learning based canopy height model generation from sub meter resolution panchromatic satellite imagery |
| topic | forestry optical lidar fire CNN |
| url | https://doi.org/10.1088/2632-2153/ada47e |
| work_keys_str_mv | AT charlesjabolt deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT javieresantos deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT adamlatchley deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT lucaswells deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT daithimartin deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT russellaparsons deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery AT rodmanrlinn deeplearningbasedcanopyheightmodelgenerationfromsubmeterresolutionpanchromaticsatelliteimagery |