{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T23:50:40Z","timestamp":1774655440625,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Environment and Climate Change Canada"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Forest roads provide access to remote wooded areas, serving as key transportation routes and contributing to human impact on the local environment. However, large animals, such as bears (Ursus sp.), moose (Alces alces), and caribou (Rangifer tarandus caribou), are affected by their presence. Many publicly available road layers are outdated or inaccurate, making the assessment of landscape objectives difficult. To address these gaps in road location data, we employ CubeSat Imagery from the Planet constellation to predict the occurrence of road probabilities using a SegNet Convolutional Neural Network. Our research examines the potential of a pre-trained neural network (VGG-16 trained on ImageNet) transferred to the remote sensing domain. The classification is refined through post-processing, which considers spatial misalignment and road width variability. On a withheld test subset, we achieve an overall accuracy of 99.1%, a precision of 76.1%, and a recall of 91.2% (F1-Score: 83.0%) after considering these effects. We investigate the performance with respect to canopy coverage using a spectral greenness index, topography (slope and aspect), and land cover metrics. Results found that predictions are best in flat areas, with low to medium canopy coverage, and in the forest (coniferous and deciduous) land cover classes. The results are vectorized into a drivable road network, allowing for vector-based routing and coverage analyses. Our approach digitized 14,359 km of roads in a 23,500 km2 area in British Columbia, Canada. Compared to a governmental dataset, our method missed 10,869 km but detected an additional 5774 km of roads connected to the network. Finally, we use the detected road locations to investigate road age by accessing an archive of Landsat data, allowing spatiotemporal modelling of road access to remote areas. This provides important information on the development of the road network over time and the calculation of impacts, such as cumulative effects on wildlife.<\/jats:p>","DOI":"10.3390\/rs16061083","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T05:56:07Z","timestamp":1710914167000},"page":"1083","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Extraction of Forest Road Information from CubeSat Imagery Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8229-1160","authenticated-orcid":false,"given":"Lukas","family":"Winiwarter","sequence":"first","affiliation":[{"name":"Integrated Remote Sensing Studio, Faculty of Forestry, University of British Columbia, Vancouver Campus, Vancouver, BC V6T 1Z4, Canada"},{"name":"Department of Geodesy and Geoinformation, TU Wien, 1040 Vienna, Austria"},{"name":"Unit of Geometry and Surveying, Faculty of Engineering Sciences, University of Innsbruck, 6020 Innsbruck, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0151-9037","authenticated-orcid":false,"given":"Nicholas C.","family":"Coops","sequence":"additional","affiliation":[{"name":"Integrated Remote Sensing Studio, Faculty of Forestry, University of British Columbia, Vancouver Campus, Vancouver, BC V6T 1Z4, Canada"}]},{"given":"Alex","family":"Bastyr","sequence":"additional","affiliation":[{"name":"Integrated Remote Sensing Studio, Faculty of Forestry, University of British Columbia, Vancouver Campus, Vancouver, BC V6T 1Z4, Canada"}]},{"given":"Jean-Romain","family":"Roussel","sequence":"additional","affiliation":[{"name":"Centre de Recherche sur les Mat\u00e9riaux Renouvelables, D\u00e9partement des Sciences du Bois et de la For\u00eat, Universit\u00e9 Laval, Qu\u00e9bec, QC G1V 0A6, Canada"}]},{"given":"Daisy Q. R.","family":"Zhao","sequence":"additional","affiliation":[{"name":"Integrated Remote Sensing Studio, Faculty of Forestry, University of British Columbia, Vancouver Campus, Vancouver, BC V6T 1Z4, Canada"}]},{"given":"Clayton T.","family":"Lamb","sequence":"additional","affiliation":[{"name":"Department of Biology, University of British Columbia, Okanagan Campus, Kelowna, BC V1V 1V7, Canada"}]},{"given":"Adam T.","family":"Ford","sequence":"additional","affiliation":[{"name":"Department of Biology, University of British Columbia, Okanagan Campus, Kelowna, BC V1V 1V7, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Barrington-Leigh, C., and Millard-Ball, A. (2017). The World\u2019s User-Generated Road Map Is More than 80% Complete. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0180698"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bennett, V.J., Smith, W.P., and Betts, M.G. (2011). Toward Understanding the Ecological Impact of Transportation Corridors.","DOI":"10.2737\/PNW-GTR-846"},{"key":"ref_3","first-page":"102031","article-title":"Maintaining Accurate, Current, Rural Road Network Data: An Extraction and Updating Routine Using RapidEye, Participatory GIS and Deep Learning","volume":"87","author":"Kearney","year":"2020","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4043","DOI":"10.3390\/rs6054043","article-title":"Object-Based Classification of Abandoned Logging Roads under Heavy Canopy Using LiDAR","volume":"6","author":"Sherba","year":"2014","journal-title":"Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"van der Ree, R., Smith, D.J., and Grilo, C. (2015). Handbook of Road Ecology, John Wiley & Sons, Ltd.","DOI":"10.1002\/9781118568170"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1406","DOI":"10.1111\/1365-2664.13056","article-title":"Effects of Habitat Quality and Access Management on the Density of a Recovering Grizzly Bear Population","volume":"55","author":"Lamb","year":"2018","journal-title":"J. Appl. Ecol."},{"key":"ref_7","unstructured":"Rowland, M.M., Wisdom, M.J., Johnson, B.K., and Penninger, M.A. (2004, January 16). Effects of Roads on Elk: Implications for Management in Forested Ecosystems. Proceedings of the Transactions of the 69th North American Wildlife and Natural Resources Conference, Spokane, WA, USA."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1111\/1365-2656.13130","article-title":"Corridors or Risk? Movement along, and Use of, Linear Features Varies Predictably among Large Mammal Predator and Prey Species","volume":"89","author":"Dickie","year":"2020","journal-title":"J. Anim. Ecol."},{"key":"ref_9","unstructured":"B.C. Ministry of Forests (2002). Forest Road Engineering Guidebook."},{"key":"ref_10","first-page":"501","article-title":"Forest Road Status Assessment Using Airborne Laser Scanning","volume":"66","author":"Waga","year":"2020","journal-title":"For. Sci."},{"key":"ref_11","first-page":"103020","article-title":"Correction, Update, and Enhancement of Vectorial Forestry Road Maps Using ALS Data, a Pathfinder, and Seven Metrics","volume":"114","author":"Roussel","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_12","unstructured":"(2023, April 24). BC Ministry of Forests Resource Roads Spatial Data Update\u2014Province of British Columbia, Available online: https:\/\/www2.gov.bc.ca\/gov\/content\/data\/geographic-data-services\/topographic-data\/roads\/resource-roads."},{"key":"ref_13","unstructured":"(2024, March 15). Microsoft RoadDetections\u2014GitHub 2023. Available online: https:\/\/github.com\/microsoft\/RoadDetections."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"110077","DOI":"10.1016\/j.measurement.2021.110077","article-title":"A Multi-Constraint Combined Method for Road Extraction from Airborne Laser Scanning Data","volume":"186","author":"Yadav","year":"2021","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","article-title":"Road Extraction by Deep Residual U-Net","volume":"15","author":"Zhang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Oehmcke, S., Thrys\u00f8e, C., Borgstad, A., Salles, M.A.V., Brandt, M., and Gieseke, F. (2019, January 9\u201312). Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9006251"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5875","DOI":"10.1080\/10106049.2021.1926555","article-title":"Forest Road Detection Using Deep Learning Models","volume":"37","author":"Sevim","year":"2022","journal-title":"Geocarto Int."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.1080\/01431161.2020.1862438","article-title":"Forest Roads Extraction through a Convolution Neural Network Aided Method","volume":"42","author":"Zhang","year":"2021","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hormese, J., and Saravanan, C. (2018, January 11\u201312). A Comparison of Convolutional Neural Network Architectures for Road Classification from Satellite Images. Proceedings of the 2018 International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.","DOI":"10.1109\/ICIRCA.2018.8597408"},{"key":"ref_20","first-page":"126","article-title":"A Holistic Framework for Forestry and Rural Road Detection Based on Satellite Imagery and Deep Semantic Segmentation","volume":"Volume 12786","author":"Kelesakis","year":"2023","journal-title":"Proceedings of the Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023)"},{"key":"ref_21","first-page":"103267","article-title":"Vectorial and Topologically Valid Segmentation of Forestry Road Networks from ALS Data","volume":"118","author":"Roussel","year":"2023","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_22","unstructured":"(2023, January 31). BC Ministry of Environment Caribou in BC Range by Ecotype, Available online: https:\/\/www.env.gov.bc.ca\/wld\/speciesconservation\/caribou_by_ecotype.html#_."},{"key":"ref_23","unstructured":"(2023, January 31). Environment Canada Working Together to Recover Boreal Caribou. Available online: https:\/\/publications.gc.ca\/collections\/collection_2010\/ec\/En14-16-2010-eng.pdf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Frazier, A.E., and Hemingway, B.L. (2021). A Technical Review of Planet Smallsat Data: Practical Considerations for Processing and Using PlanetScope Imagery. Remote Sens., 13.","DOI":"10.3390\/rs13193930"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1080\/17538947.2016.1187673","article-title":"Mass Data Processing of Time Series Landsat Imagery: Pixels to Data Products for Forest Monitoring","volume":"9","author":"Hermosilla","year":"2016","journal-title":"Int. J. Digit. Earth"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1080\/07038992.2014.945827","article-title":"Pixel-Based Image Compositing for Large-Area Dense Time Series Applications and Science","volume":"40","author":"White","year":"2014","journal-title":"Can. J. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1109\/LGRS.2005.857030","article-title":"A Landsat Surface Reflectance Dataset for North America, 1990\u20132000","volume":"3","author":"Masek","year":"2006","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Schmidt, G., Jenkerson, C.B., Masek, J., Vermote, E., and Gao, F. (2013). Landsat Ecosystem Disturbance Adaptive Processing System (LEDAPS) Algorithm Description, Open-File Report 2013\u20131057.","DOI":"10.3133\/ofr20131057"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.rse.2014.11.005","article-title":"An Integrated Landsat Time Series Protocol for Change Detection and Generation of Annual Gap-Free Surface Reflectance Composites","volume":"158","author":"Hermosilla","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_30","unstructured":"Winiwarter, L. (2024, March 15). lwiniwar\/roadCNN: Release for publication. Zenodo. Available online: https:\/\/zenodo.org\/records\/10727576."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"111716","DOI":"10.1016\/j.rse.2020.111716","article-title":"Deep Learning in Environmental Remote Sensing: Achievements and Challenges","volume":"241","author":"Yuan","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_32","unstructured":"Mnih, V. (2013). Machine Learning for Aerial Image Labeling. [Ph.D. Thesis, University of Toronto]."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D., and Raskar, R. (2018, January 18\u201323). DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1007\/s11220-018-0191-1","article-title":"Transfer Learning for Classification of Optical Satellite Image","volume":"19","author":"Zou","year":"2018","journal-title":"Sens. Imaging"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liang, Y., Monteiro, S.T., and Saber, E.S. (2016, January 18\u201320). Transfer Learning for High Resolution Aerial Image Classification. Proceedings of the 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA.","DOI":"10.1109\/AIPR.2016.8010600"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sonogashira, M., Shonai, M., and Iiyama, M. (2020). High-Resolution Bathymetry by Deep-Learning-Based Image Superresolution. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0235487"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Meesad, P., Sodsee, S., and Unger, H. (2018). Recent Advances in Information and Communication Technology 2017, Springer International Publishing.","DOI":"10.1007\/978-3-319-60663-7"},{"key":"ref_41","unstructured":"Rouault, E., Warmerdam, F., Schwehr, K., Kiselev, A., Butler, H., \u0141oskot, M., Szekeres, T., Tourigny, E., Landa, M., and Miara, I. (2024, March 15). GDAL 2024. Available online: https:\/\/github.com\/OSGeo\/gdal\/blob\/master\/CITATION."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Abrams, M., Crippen, R., and Fujisada, H. (2020). ASTER Global Digital Elevation Model (GDEM) and ASTER Global Water Body Dataset (ASTWBD). Remote Sens., 12.","DOI":"10.3390\/rs12071156"},{"key":"ref_43","unstructured":"(2024, March 15). NASA\/METI\/AIST\/Japan Spacesystems and U.S.\/Japan ASTER Science Team ASTER Global Digital Elevation Model V003, Available online: https:\/\/lpdaac.usgs.gov\/products\/ast14demv003\/#citation."},{"key":"ref_44","unstructured":"Roussel, J.-R. (2024, March 14). Vecnet: Vectorization of Road Networks From Rasters and Airborne Laser Scanning. R Package Version 0.1.2. Available online: https:\/\/github.com\/Jean-Romain\/vecnet."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3138\/D327-0323-2JUT-016M","article-title":"Least-Cost Path in GIS Using an Accumulated Cost Surface and Slopelines","volume":"31","author":"Douglas","year":"1994","journal-title":"Cartographica"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1080\/136588198241554","article-title":"On Applying Viewshed Analysis for Determining Least-Cost Paths on Digital Elevation Models","volume":"12","author":"Stucky","year":"1998","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Surface-Evans, S.L., and White, D.A. (2012). Least Cost Analysis of Social Landscapes: Archaeological Case Studies, University of Utah Press.","DOI":"10.1353\/book41407"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/s40823-016-0006-9","article-title":"Least-Cost Modelling and Landscape Ecology: Concepts, Applications, and Opportunities","volume":"1","author":"Etherington","year":"2016","journal-title":"Curr. Landsc. Ecol. Rep."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"12314","DOI":"10.3390\/rs70912314","article-title":"A Phenology-Based Method for Monitoring Woody and Herbaceous Vegetation in Mediterranean Forests from NDVI Time Series","volume":"7","author":"Helman","year":"2015","journal-title":"Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.rse.2013.01.010","article-title":"Evaluation of the Potential of MODIS Satellite Data to Predict Vegetation Phenology in Different Biomes: An Investigation Using Ground-Based NDVI Measurements","volume":"132","author":"Hmimina","year":"2013","journal-title":"Remote Sens. Environ."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/0034-4257(79)90013-0","article-title":"Red and Photographic Infrared Linear Combinations for Monitoring Vegetation","volume":"8","author":"Tucker","year":"1979","journal-title":"Remote Sens. Environ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2897","DOI":"10.1016\/j.rse.2010.07.008","article-title":"Detecting Trends in Forest Disturbance and Recovery Using Yearly Landsat Time Series: 1. LandTrendr\u2014Temporal Segmentation Algorithms","volume":"114","author":"Kennedy","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Gao, L., Song, W., Dai, J., and Chen, Y. (2019). Road Extraction from High-Resolution Remote Sensing Imagery Using Refined Deep Residual Convolutional Neural Network. Remote Sens., 11.","DOI":"10.3390\/rs11050552"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Xu, Y., Xie, Z., Feng, Y., and Chen, Z. (2018). Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning. Remote Sens., 10.","DOI":"10.3390\/rs10091461"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"4853","DOI":"10.1109\/JSTARS.2015.2443552","article-title":"An Object-Based Method for Road Network Extraction in VHR Satellite Images","volume":"8","author":"Miao","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Zhou, T., Sun, C., and Fu, H. (2019). Road Information Extraction from High-Resolution Remote Sensing Images Based on Road Reconstruction. Remote Sens., 11.","DOI":"10.3390\/rs11010079"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"2154598","DOI":"10.1080\/07038992.2022.2154598","article-title":"Automated Forest Harvest Detection With a Normalized PlanetScope Imagery Time Series","volume":"49","author":"Keay","year":"2023","journal-title":"Can. J. Remote Sens."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Boulanger, J., and Stenhouse, G.B. (2014). The Impact of Roads on the Demography of Grizzly Bears in Alberta. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0115535"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/6\/1083\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:16:32Z","timestamp":1760105792000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/6\/1083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,20]]},"references-count":58,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["rs16061083"],"URL":"https:\/\/doi.org\/10.3390\/rs16061083","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,20]]}}}