Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, Vol. 20, No. 2, pp. 75-93

Use of convolutional neural networks for geospatial modelling of species structure and taxation characteristics of forests (case study of Khanty-Mansi Autonomous Okrug – Yugra)

M.D. Moskovchenko 1 
1 Tyumen State University, Tyumen, Russia
Accepted: 30.03.2023
DOI: 10.21046/2070-7401-2023-20-2-75-93
Until recently, forest inventory data was the only reliable data source in forestry. Nowadays, correction of forest inventory data became possible, including correction at the local per-community level, using remote sensing data and geospatial modeling methods. This study assessed the possibility of using convolutional neural networks for geospatial modelling of the species structure and taxation characteristics of forests on the example of the territory of Khanty-Mansi Autonomous Okrug – Yugra. Forest inventory data of the Khanty-Mansi Autonomous Okrug – Yugra was used as a target variable, remote sensing data (Sentinel-2 satellite imagery), digital elevation model ASTER GDEM, ESA WorldCover landcover data and Global Forest Change dataset were used as independent variables. The model of the vegetation of the Khanty-Mansi Autonomous Okrug (of its dominant species, ground cover and forest site index classes) based on DeepLab architecture achieved an accuracy of 88 % on both train, validation and test datasets and made it possible to create an up-to-date digital map of vegetation in the region with a resolution of 10 m. Using the pre-trained models for modelling forest characteristics in the territories of adjacent regions — Yamalo-Nenets Autonomous Okrug (modeling accuracy was 85 %) and the Krasnoyarsk Krai (modeling accuracy was from 62 to 67 %) — showed that they can be used in adjacent territories of the other regions of Western Siberia but are not applicable for modeling forest characteristics in Eastern Siberia.
Keywords: neural networks, modelling, U-Net, DEEPLAB, forest management, forest mapping, Western Siberia
Full text

References:

  1. Bartalev S. A., Egorov V. A., Ershov D. V., Isaev A. S., Loupian E. A., Plotnikov D. E., Uvarov I. A., Mapping of Russia’s vegetation cover using MODIS satellite spectroradiometer data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2011, Vol. 8, No. 4, pp. 285–302 (in Russian).
  2. Bondur V. G., Voronova O. S., Cherepanova E. V., Tsidilina M. N., Zima A. L., The spatiotemporal analysis of multiannual wildfires and trace gas and aerosol emissions in Russia based of satellite data, Issledovanie Zemli iz kosmosa, 2020, No. 4, pp. 3–17 (in Russian), DOI: 10.31857/s0205961420040028.
  3. Gavrilyuk E. A., Gornov A. V., Ershov D. V., Estimation of spatial trees species distribution in Bryansk Forest Nature Reserve based on multitemporal Landsat data, Bull. Bryansk dpt. of RBS, 2018, No. 3(15), pp. 13–23 (in Russian), DOI: 10.22281/2307-4353-2018-3-13-23.
  4. Gavrilyuk E. A., Koroleva N. V., Karpukhina D. A., Sochilova E. N., Ershov D. V., Geospatial modeling of biometric and structural forest attributes in the Bryansk oblast based on satellite imagery and selective inventory data, Lesovedenie, 2021, No. 6, pp. 609–626 (in Russian), DOI: 10.31857/S002411482106005X.
  5. Ershov D. V., Gavrilyuk E. A., Belova E. I., Nikitina A. D., Determination of the species structure of a forest area using orthophotoimages from unmanned aerial vehicles, Aktual’nye problemy sovremennogo lesovodstva: Vtorye mezhdunarodnye chteniya pamyati G. F. Morozova. K stoletiyu pamyati klassika russkogo lesovodstva (1920–2020 gg.) (Actual problems of modern forestry: Second international readings in memory of G. F. Morozov. On the centenary of the memory of the classic of Russian forestry (1920–2020)), Simferopol, 2020, pp. 141–152 (in Russian).
  6. Zuev V. V., Korotkova E. M., Pavlinsky A. V., Climate-related changes in the vegetation cover of the taiga and tundra of Western Siberia in 1982–2015 according to satellite observations, Issledovanie Zemli iz kosmosa, 2019, No. 6, pp. 66–76 (in Russian), DOI: 10.31857/S0205-96142019666-76.
  7. Kornienko S. G., Characteristics of anthropogenic transformations of landscapes in the area of Bovanenkovo gas field based on Landsat satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2022, Vol. 19, No. 2, pp. 106–129 (in Russian), DOI: 10.21046/2070-7401-2022-19-2-106-129.
  8. Luganskii N. A., Zalesov S. V., Luganskii V. N., Lesovedenie (Forest science), Ekaterinburg: Uralslkii gosudarstvennyi lesotekhnicheskii universitet, 2010, 432 p. (in Russian).
  9. Osobo okhranyaemye prirodnye territorii i lesa Khanty-Mansiiskogo avtonomnogo okruga: atlas (Protected areas and forests of Khanty-Mansi Autonomous Okrug, Atlas), Khanty-Mansiisk; Ekaterinburg: IzdatNaukaServis, 2006, 120 p. (in Russian).
  10. Platonov E. P., Practice of use of the earths of wood fund for the subsoil industry in the Khanty-Mansiysk autonomous okrug — Yugra, Nedropol’zovanie XXI vek, 2011, No. 2, pp. 60–63 (in Russian).
  11. Savel’ev A. A., Biokhorologicheskoe raznoobrazie i modelirovanie prostranstvennoi struktury rastitel’nogo pokrova: Geoinformatsionnyi podkhod: Avtoref. diss. dokt. biol. nauk (Biochorological diversity and modeling of the spatial structure of vegetation cover: Geoinformatic approach, Ext. abstract Dr. biol. sci. thesis), Kazan, 2004, 24 p. (in Russian).
  12. Sochilova E. N., Surkov N. V., Ershov D. V., Khamedov V. A. (2018a), Assessment of biomass of forest species using satellite images of high spatial resolution (on the example of the forest of Khanty-Mansi autonomous okrug), Forest science issues, 2018, Vol. 2, No. 52, pp. 1–19, DOI: 10.31509/2658-607x-2019-2-2-1-20.
  13. Sochilova E. N., Surkov N. V., Ershov D. V., Egorov V. A., Bartalev S. S., Bartalev S. A. (2018b), Mapping of forest site index classes in Primorskiy Krai based on satellite images and terrain characteristics, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 5, pp. 96–109 (in Russian), DOI: 10.21046/2070-7401-2018-15-5-96-109.
  14. Filipchuk A. N., Malysheva N. V., Zolina T. A., Yugov A. N., The boreal forest of Russia: Opportunities for the effects of climate change mitigation, Lesokhozyaistvennaya informatsiya, 2020, No. 1, pp. 92–114 (in Russian), DOI 10.24419/LHI.2304-3083.2020.1.10.
  15. Khamedov V. A., Kopylov V. N., Polishchuk Yu. M., Sugaipova A. N., Shimov S. V., Forestry mapping of Khanty-Mansi autonomous okrug on base of middle resolution space images, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2009, Vol. 6, No. 2, pp. 474–478 (in Russian).
  16. Chollet F., Deep learning with Python, Shelter Island, New York: Manning, 2018, 386 p.
  17. Abadi M., Agarwal A., Barham P., Brevdo E., Chen Z., Citro C., Corrado G. S., Davis A., Dean J., Devin M., Ghemawat S., Goodfellow I., Harp A., Irving G., Isard M., Jia Y., Jozefowicz R., Kaiser L., Kudlur M., Levenberg J., Mane D., Monga R., Moore S., Murray D., Olah C., Schuster M., Shlens J., Steiner D., Sutskever I., Talwar K., Tucker P., Vanhoucke V., Vasudevan V., Viegas F., Vinyals O., Warden P., Wattenberg M., Wicke M., Yu Y., Zheng X., Tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint, arXiv:1603.04467, 2016, DOI: 10.48550/arXiv.1603.04467.
  18. ASTER GlobalDigital Elevation Model V003, NASA EOSDIS Land Processes DAAC, NASA/METI/AIST/Japan Spacesystems, U. S./Japan ASTER Science Team, 2018, https://doi.org/10.5067/ASTER/ASTGTM.003.
  19. Chen L. C., Papandreou G., Schroff F., Adam H., Rethinking Atrous Convolution for Semantic Image Segmentation, arXiv preprint, arXiv:1706.05587, 2017, DOI: 10.48550/arXiv.1706.05587.
  20. Cheng K., Wang J., Forest Type Classification Based on Integrated Spectral-Spatial-Temporal Features and Random Forest Algorithm — A Case Study in the Qinling Mountains, Forests, 2019, Vol. 10, No. 7, Art. No. 559, DOI: 10.3390/f10070559.
  21. Cheng K., Wang J., Yan X., Mapping Forest Types in China with 10 m Resolution Based on Spectral – Spatial – Temporal Features, Remote Sensing, 2021, Vol. 13, No 5, Art. No. 973, DOI: 10.3390/rs13050973.
  22. Das S., Singh T. P., Forest Type, Diversity and Biomass Estimation in Tropical Forests of Western Ghat of Maharashtra Using Geospatial Techniques, Small-scale Forestry, 2016, Vol. 15, pp. 517–532, DOI: 10.1007/s11842-016-9337-y.
  23. Drusch M., Del Bello U., Carlier S., Colin O., Fernandez V., Gascon F., Hoersch B., Isola C., Laberinti P., Martimort P., Meygret A., Spoto F., Sy O., Marchese F., Bargellini P., Sentinel-2: ESA’s optical high-resolution mission for GMES operational services, Remote Sensing of Environment, 2012, Vol. 120, pp. 25–36, DOI: 10.1016/j.rse.2011.11.026.
  24. Flood N., Watson F., Collett L., Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia, Intern. J. Applied Earth Observation and Geoinformation, 2019, Vol. 82, Art. No. 101897, DOI: 10.1016/j.jag.2019.101897.
  25. Hansen M. C., Potapov P. V., Moore R., Hancher M., Turubanova S. A., Tyukavina A., Thau D., Stehman S. V., Goetz S. J., Loveland T. R., Kommareddy A., Egorov A., Chini L., Justice C. O., Townshend J. R. G., High-resolution global maps of 21st-century forest cover change, Science, 2013, Vol. 342, Issue 6160, pp. 850–853, DOI: 10.1126/science.12446.
  26. Harris C. R., Millman K. J., van der Walt S. J., Gommers R., Virtanen P., Cournapeau D., Wieser E., Taylor J., Berg S., Smith N. J., Kern R., Picus M., Hoyer S., van Kerkwijk M. H., Brett M., Haldane A., del Rio J. F., Wiebe M., Peterson P., Gerard-Marchant P., Sheppard K., Reddy T., Weckesser W., Abbasi H., Gohlke C., Oliphant T. E., Array programming with NumPy, Nature, 2020, Vol. 585, No. 7825, pp. 357–362, DOI: 10.1038/s41586-020-2649-2.
  27. Huang H., Lin L., Tong R., Hu H., Zhang Q., Iwamoto Y., Han X., Chen Y., Wu J., UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation, IEEE Intern. Conf. Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 1055–1059, DOI: 10.1109/icassp40776.2020.9053405.
  28. Hunter J. D., Matplotlib: A 2D graphics environment, Computing in Science and Engineering, 2007, Vol. 9, No. 3, pp. 90–95, DOI: 10.1109/MCSE.2007.55.
  29. Kirpotin S. N., Callaghan T. V., Peregon A. M., Babenko A. S., Berman D. I., Bulakhova N. A., Byzaakay A. A., Chernykh T. M., Chursin V., Interesova E. A., Gureev S. P., Kerchev I. A., Kharuk V. I., Khovalyg A. O., Kolpashchikov L. A., Krivets S. A., Kvasnikova Z. N., Kuzhevskaia I. V., Merzlyakov O. E., Nekhoroshev O. G., Popkov V. K., Pyak A. I., Valevich T. O., Volkov I. V., Volkova I. I., Impacts of environmental change on biodiversity and vegetation dynamics in Siberia, Ambio, 2021, Vol. 50, pp. 1926–1952, DOI: 10.1007/s13280-021-01570-6.
  30. Lanaras C., Bioucas-Dias J., Galliani S., Baltsavias E., Schindler K., Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network, ISPRS J. Photogrammetry and Remote Sensing, 2018, Vol. 146, pp. 305–319, DOI: 10.1016/j.isprsjprs.2018.09.018.
  31. LeCun Y., Bose B., Denker J. S., Henderson D., Howard R. E., Hubbard W., Jackel L. D., Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1989, No. 1, pp. 541–551, DOI: 10.1162/neco.1989.1.4.541.
  32. Lenczner G., Chan-Hon-Tong A., Le Saux B., Luminari N., Le Besnerais G., DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing, IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 2022, No. 15, pp. 3376–3389, DOI: 10.1109/jstars.2022.3166551.
  33. Liu M., Fu B., Xie S., He H., Lan F., Li Y., Lou P., Fan D., Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm, Ecological Indicators, 2021, Vol. 125, Art. No. 107562, DOI: 10.1016/j.ecolind.2021.107562.
  34. Louis J., Debaecker V., Pflug B., Main-Khorn M., Bieniarz J., Mueller-Wilm U., Cadau E., Gascon F., Sentinel-2 Sen2Cor: L2A processor for users, Proc. Living Planet Symp., 2016, Vol. SP-740, pp. 1–8.
  35. Miles V. V., Esau I., Spatial heterogeneity of greening and browning between and within bioclimatic zones in northern West Siberia, Environmental Research Letters, 2016, Vol. 11, No. 11, Art. No. 115002, DOI: 10.1088/1748-9326/11/11/115002.
  36. Omer G., Mutanga O., Abdel-Rahman E. M., Adam E., Performance of support vector machines and artificial neural network for mapping endangered tree species using WorldView-2 data in Dukuduku forest, South Africa, IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 2015, Vol. 8, No. 10, pp. 4825–4840, DOI: 10.1109/JSTARS.2015.2461136.
  37. Ronneberger O., Fischer P., Brox T., U-net: Convolutional networks for biomedical image segmentation, Intern. Conf. Medical Image Computing and Computer-Assisted Intervention, Cham: Springer, 2015, pp. 234–241, DOI: 10.1007/978-3-319-24574-4_28.
  38. Scepanovic S., Antropov O., Laurila P., Rauste Y., Ignatenko V., Praks J., Wide-area land cover mapping with Sentinel-1 imagery using deep learning semantic segmentation models, IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 2021, Vol. 14, pp. 10357–10374, DOI: 10.1109/JSTARS.2021.3116094.
  39. Sundelius C., Deep Fusion of Imaging Modalities for Semantic Segmentation of Satellite Imagery: Master of Science Thesis in Electrical Engineering, Linköping, 2017, 88 p.
  40. van Rossum G., Python reference manual, Amsterdam, Netherlands: Centre for Mathematics and Computer Science, 1995, No. R 9525.
  41. Wasser L., Joseph M. B., McGlinchy J., Palomino J., Korinek N., Holdgraf C., Head T., EarthPy: A Python package that makes it easier to explore and plot raster and vector data using open source Python tools, J. Open Source Software, 2019, Vol. 4, No. 43, Art. No. 1886, DOI: 10.21105/joss.01886.
  42. Wei S., Zhang H., Wang C., Wang Y., Xu L., Multi-temporal SAR data large-scale crop mapping based on U-Net model, Remote Sensing, 2019, Vol. 11, No. 1, Art. No. 68, DOI: 10.3390/rs11010068.
  43. Xi Y., Ren C., Tian Q., Ren Y., Dong X., Zhang Z., Exploitation of Time Series Sentinel-2 Data and Different Machine Learning Algorithms for Detailed Tree Species Classification, IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 2021, Vol. 14, pp. 7589–7603, DOI: 10.1109/JSTARS.2021.3098817.