{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:26:33Z","timestamp":1774603593226,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2018,2,16]],"date-time":"2018-02-16T00:00:00Z","timestamp":1518739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Mapping of surficial geology is an important requirement for broadening the geoscience database of northern Canada. Surficial geology maps are an integral data source for mineral and energy exploration. Moreover, they provide information such as the location of gravels and sands, which are important for infrastructure development. Currently, surficial geology maps are produced through expert interpretation of aerial photography and field data. However, interpretation is known to be subjective, labour-intensive and difficult to repeat. The expert knowledge required for interpretation can be challenging to maintain and transfer. In this research, we seek to assess the potential of deep neural networks to aid surficial geology mapping by providing an objective surficial materials initial layer that experts can modify to speed map development and improve consistency between mapped areas. Such an approach may also harness expert knowledge in a way that is transferable to unmapped areas. For this purpose, we assess the ability of convolution neural networks (CNN) to predict surficial geology classes under two sampling scenarios. In the first scenario, a CNN uses samples collected over the area to be mapped. In the second, a CNN trained over one area is then applied to locations where the available samples were not used in training the network. The latter case is important, as a collection of in situ training data can be costly. The evaluation of the CNN was carried out using aerial photos, Landsat reflectance, and high-resolution digital elevation data over five areas within the South Rae geological region of Northwest Territories, Canada. The results are encouraging, with the CNN generating average accuracy of 76% when locally trained. For independent test areas (i.e., trained over one area and applied over other), accuracy dropped to 59\u201370% depending on the classes selected for mapping. In the South Rae region, significant confusion was found between till veneer and till blanket as well as glaciofluvial subclasses (esker, terraced, and hummocky ice-contact). Merging these classes respectively increased accuracy for independent test area to 68% on average. Relative to the more widely used Random Forest machine learning algorithm, this represents an improvement in accuracy of 4%. Furthermore, the CNN produced better results for less frequent classes with distinct spatial structure.<\/jats:p>","DOI":"10.3390\/rs10020307","type":"journal-article","created":{"date-parts":[[2018,2,20]],"date-time":"2018-02-20T03:54:22Z","timestamp":1519098862000},"page":"307","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Assessment of Convolution Neural Networks for Surficial Geology Mapping in the South Rae Geological Region, Northwest Territories, Canada"],"prefix":"10.3390","volume":"10","author":[{"given":"Rasim","family":"Latifovic","sequence":"first","affiliation":[{"name":"Natural Resources Canada, Canadian Centre for Remote Sensing, 560 Rochester, Ottawa, ON K1A 0E4, Canada"}]},{"given":"Darren","family":"Pouliot","sequence":"additional","affiliation":[{"name":"Environment and Climate Change Canada, Landscape Science and Technology, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada"}]},{"given":"Janet","family":"Campbell","sequence":"additional","affiliation":[{"name":"Natural Resources Canada, Geological Survey of Canada, 601 Booth Street, Ottawa, ON K1A 0E8, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2018,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Harris, J. (2008). Remote Predictive Mapping: An Aid for Northern Mapping [1 DVD].","DOI":"10.4095\/225997"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Morris, K.P. (1990). Automatic Detection of Three-Dimensional Geological Features from Remotely Sensed Imagery and Digital Terrain Models. Remote Sensing: An Operational Technology for the Mining and Petroleum Industries, Springer.","DOI":"10.1007\/978-94-010-9744-4_7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"6876","DOI":"10.1080\/01431161.2012.693219","article-title":"Remote predictive mapping of bedrock geology using image classification of Landsat and SPOT data, western Minto Inlier, Victoria Island, Northwest Territories, Canada","volume":"33","author":"Behnia","year":"2012","journal-title":"Int. J. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Grunsky, E., Harris, J.R., and McMartin, I. (2006). Predictive Mapping of Surficial Materials, Schultz Lake Area (NTS 66A), Nunavut, Canada [1 DVD].","DOI":"10.4095\/221968"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Brown, O., Harris, J.R., Utting, D., and Little, E.C. (2007). Remote Predictive Mapping of Surficial Materials on Northern Baffin Island: Developing and Testing Techniques Using Landsat TM and Digital Elevation Data.","DOI":"10.4095\/223434"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"281","DOI":"10.5589\/m12-020","article-title":"Surficial materials mapping in Nunavut, Canada, with multi-beam RADARSAT-2 dual-polarization C-HH and C-HV, Landsat-7 ETM+, and DEM data","volume":"38","author":"LaRocque","year":"2012","journal-title":"Can. J. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Byatt, J., LaRocque, A., Leblon, B., Harris, J., and McMartin, I. (2017). Mapping Surficial Materials in Nunavut Using RADARSAT-2 C-HH and C-HV, Landsat-8 OLI, DEM and Slope Data. [unpublished Master of Science Forestry thesis, University of New Brunswick]. Available online: https:\/\/unbscholar.lib.unb.ca\/islandora\/object\/unbscholar%3A8312.","DOI":"10.1080\/07038992.2018.1545566"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Stevens, C.W., Kerr, D.E., Wolfe, S.A., and Eagles, S. (2013). Predictive Surficial Material and Surficial Geology Derived from LANDSAT 7, Hearne Lake, NTS 85I, Northwest Territories.","DOI":"10.4095\/292394"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Olthof, I., Kerr, D., Wolfe, S., and Eagles, S. (2014). Predictive Surficial Materials and Surficial Geology from LANDSAT-7, Upper Carp Lake, NTS 85-P, Northwest Territories.","DOI":"10.4095\/293970"},{"key":"ref_10","unstructured":"Campbell, J., Harris, J., Huntley, D., McMartin, I., Wityk, U., Dredge, L.A., and Eagles, S. (2013). Remote Predictive Mapping of Surficial Earth Materials: Wager Bay North Area, Nunavut."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breimann","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"69","DOI":"10.5589\/m12-013","article-title":"A robust, cross validation classification method (RCM) for improved mapping accuracy and confidence metrics","volume":"38","author":"Harris","year":"2012","journal-title":"Can. J. Remote Sens."},{"key":"ref_13","unstructured":"(2018, February 14). MIT Technology Review. Available online: https:\/\/www.technologyreview.com\/lists\/technologies\/2013\/."},{"key":"ref_14","unstructured":"Krizhevsky, A., Sutskever, I., and Hinto, G. (2012, January 3\u20136). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_15","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2018, February 14). Deep Residual Learning for Image Recognition. Available online: https:\/\/arxiv.org\/abs\/1512.03385."},{"key":"ref_16","unstructured":"Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L. (arXiv, 2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. Computer Vision and Pattern Recognition (cs.CV), arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep Learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_18","unstructured":"Touretzky, D. (1989, January 27\u201330). Handwritten Digit Recognition with a Back-Propagation Network. Proceedings of the Advances in Neural Information Processing Systems (NIPS 1989), Denver, CO, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_20","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11\u201313). Deep sparse rectifier neural networks. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Lauderdale, FL, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Pehrsson, S.J., Currie, M., Ashton, K.E., Harper, C.T., Paul, D., Pana, D., Berman, R.G., Bostock, H., Corkery, T., and Jefferson, C.W. (2014). Bedrock Geology Compilation South Rae and Western Hearne Provinces, Churchill Province, Northwest Territories, Saskatchewan, Nunavut, Manitoba, and Alberta.","DOI":"10.4095\/292232"},{"key":"ref_22","unstructured":"Ecoregions Working Group (1989). Ecoclimatic Regions of Canada, First Approximation."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Campbell, J.E., and Eagles, S. (2014). Report of 2014 Activities for the Geologic and Metallogenic Framework of the South Rae Craton, Southeast Northwest Territories: Reconnaissance Surficial and Bedrock Fieldwork in the GEM 2 South Rae Project Area.","DOI":"10.4095\/295463"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Pehrsson, S., Campbell, J., Martel, E., McCurdy, M., Agosta-Gongora, P., Theissen, E., Jamieson, D., Lauzon, G., Buller, G., and Falck, H. (2015). Report of 2015 Activities for the Geologic and Metallogenic Framework of the South Rae Craton, Southeast Northwest Territories: GEM 2 South Rae Quaternary and bedrock Project.","DOI":"10.4095\/297387"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Campbell, J.E., Lauzon, G., Dyke, A., and Haiblen, A. (2016). Report of 2016 Activities for the Regional Surficial Geological Mapping of the South Rae Craton, Southeast NWT: GEM 2 South Rae Quaternary and Bedrock Project.","DOI":"10.4095\/299391"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Latifovic, R., Pouliot, D., Sun, L., Schwarz, J., and Parkinson, W. (2015). Moderate Resolution Time Series Data Management and Analysis: Automated Large Area Mosaicking and Quality Contro.","DOI":"10.4095\/296204"},{"key":"ref_27","unstructured":"(2018, February 14). National Forestry Database. Available online: http:\/\/nfdp.ccfm.org."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/S0034-4257(96)00067-3","article-title":"NDWI\u2014A normalized difference water index for remote sensing of vegetation liquid water from space","volume":"58","author":"Gao","year":"1996","journal-title":"Remote Sens. Environ."},{"key":"ref_29","unstructured":"Jensen, J.R. (2005). Introductory Digital Image Processing: A Remote Sensing Perspective, Prentice Hall. [3rd ed.]."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1741","DOI":"10.1080\/01431160110106113","article-title":"Derivation of a tasselled cap transformation based on Landsat 7 at-satellite reflectance","volume":"23","author":"Huang","year":"2002","journal-title":"Int. J. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/0034-4257(85)90102-6","article-title":"A TM Tasseled Cap Equivalent Transformation for Reflectance Factor Data","volume":"17","author":"Crist","year":"1985","journal-title":"Remote Sens. Environ."},{"key":"ref_32","unstructured":"(2018, February 14). National Air Photo Library, Natural Resources Canada, Available online: http:\/\/www.nrcan.gc.ca\/earth-sciences\/geomatics\/satellite-imagery-air-photos\/9265."},{"key":"ref_33","unstructured":"(2018, February 14). Polar Geospatial Center. Available online: https:\/\/www.pgc.umn.edu\/data\/arcticdem\/."},{"key":"ref_34","unstructured":"Dyke, A.S., and Campbell, J.E. (2018). Surficial Geology, Abitau Lake, Northwest Territories, NTS 75-B, in press."},{"key":"ref_35","unstructured":"(2018, February 14). Open Source Computer Vision Library. Available online: http:\/\/opencv.org."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_37","unstructured":"Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/2\/307\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:55:21Z","timestamp":1760194521000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/2\/307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,16]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2018,2]]}},"alternative-id":["rs10020307"],"URL":"https:\/\/doi.org\/10.3390\/rs10020307","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,16]]}}}