Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network
Based on modern satellite products Planet with high spatial resolution 3 meters, authors of this paper improved the neural network methodology for constructing land cover classification maps based on satellite data of high spatial resolution using the latest architectures of convolutional neural net...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Anhalt University of Applied Sciences
2022-03-01
|
| Series: | Proceedings of the International Conference on Applied Innovations in IT |
| Subjects: | |
| Online Access: | https://icaiit.org/paper.php?paper=10th_ICAIIT_1/3_6 |
| _version_ | 1797825330692489216 |
|---|---|
| author | Andrii Shelestov Bohdan Yailymov Hanna Yailymova Leonid Shumilo Mykola Lavreniuk Alla Lavreniuk Sergiy Sylantyev Nataliia Kussul |
| author_facet | Andrii Shelestov Bohdan Yailymov Hanna Yailymova Leonid Shumilo Mykola Lavreniuk Alla Lavreniuk Sergiy Sylantyev Nataliia Kussul |
| author_sort | Andrii Shelestov |
| collection | DOAJ |
| description | Based on modern satellite products Planet with high spatial resolution 3 meters, authors of this paper improved the neural network methodology for constructing land cover classification maps based on satellite data of high spatial resolution using the latest architectures of convolutional neural networks. The process of information
features formation for types of land cover is described and the method of land cover type classification on the basis of satellite data of high spatial resolution is improved. A method for filtering artificial objects and other types of land cover using a probabilistic channel is proposed, and a convolutional neural network architecture
to classify high-resolution spatial satellite data is developed. The problem of building density maps for the quarters of the city atlas construction is solved and the metrics for estimating the accuracy of classification map construction methods are analyzed. This will make it possible to obtain high-precision building maps to
calculate the building area by functional segments of the Urban Atlas and monitor the development of the city in time. This will make it possible to create the first geospatial analogue of the product Copernicus Urban Atlas for Kyiv using high spatial resolution data. This Urban Atlas will be the first such product in Ukraine,
which can be further extended to other cities in Ukraine. As a further development, the authors plan to create a methodology for combining satellite and in-situ air quality monitoring data in the city based on the developed Urban Atlas, which will provide high-precision layers of PM10 and PM2.5 concentrations with high
spatial and temporal resolution of Ukraine. |
| first_indexed | 2024-03-13T10:52:31Z |
| format | Article |
| id | doaj.art-9d8c41193ef64184b4e2b3de0c68ef02 |
| institution | Directory Open Access Journal |
| issn | 2199-8876 |
| language | English |
| last_indexed | 2024-03-13T10:52:31Z |
| publishDate | 2022-03-01 |
| publisher | Anhalt University of Applied Sciences |
| record_format | Article |
| series | Proceedings of the International Conference on Applied Innovations in IT |
| spelling | doaj.art-9d8c41193ef64184b4e2b3de0c68ef022023-05-17T08:30:03ZengAnhalt University of Applied SciencesProceedings of the International Conference on Applied Innovations in IT2199-88762022-03-0110112513210.25673/76943Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural NetworkAndrii Shelestov0https://orcid.org/0000-0001-9256-4097Bohdan Yailymov1https://orcid.org/0000-0002-2635-9842Hanna Yailymova2https://orcid.org/0000-0001-6116-8294Leonid Shumilo3https://orcid.org/0000-0002-7395-7933Mykola Lavreniuk4https://orcid.org/0000-0003-2183-8833Alla Lavreniuk5https://orcid.org/0000-0002-5791-0377Sergiy Sylantyev6https://orcid.org/0000-0001-8532-1396Nataliia Kussul7https://orcid.org/0000-0002-9704-9702Institute of Physics and Technology, NTUU "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy avenue, Kyiv, UkraineDepartment of Space Information Technologies and System, Space Research Institute NAS Ukraine an SSA Ukraine, 40 Glushkov avenue, Kyiv, UkraineInstitute of Physics and Technology, NTUU "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy avenue, Kyiv, UkraineDepartment of Geography, The University of Maryland, College Park, Maryland, USADepartment of Space Information Technologies and System, Space Research Institute NAS Ukraine an SSA Ukraine, 40 Glushkov avenue, Kyiv, UkraineInstitute of Physics and Technology, NTUU "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy avenue, Kyiv, UkraineDepartment of Space Information Technologies and System, Space Research Institute NAS Ukraine an SSA Ukraine, 40 Glushkov avenue, Kyiv, UkraineInstitute of Physics and Technology, NTUU "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy avenue, Kyiv, UkraineBased on modern satellite products Planet with high spatial resolution 3 meters, authors of this paper improved the neural network methodology for constructing land cover classification maps based on satellite data of high spatial resolution using the latest architectures of convolutional neural networks. The process of information features formation for types of land cover is described and the method of land cover type classification on the basis of satellite data of high spatial resolution is improved. A method for filtering artificial objects and other types of land cover using a probabilistic channel is proposed, and a convolutional neural network architecture to classify high-resolution spatial satellite data is developed. The problem of building density maps for the quarters of the city atlas construction is solved and the metrics for estimating the accuracy of classification map construction methods are analyzed. This will make it possible to obtain high-precision building maps to calculate the building area by functional segments of the Urban Atlas and monitor the development of the city in time. This will make it possible to create the first geospatial analogue of the product Copernicus Urban Atlas for Kyiv using high spatial resolution data. This Urban Atlas will be the first such product in Ukraine, which can be further extended to other cities in Ukraine. As a further development, the authors plan to create a methodology for combining satellite and in-situ air quality monitoring data in the city based on the developed Urban Atlas, which will provide high-precision layers of PM10 and PM2.5 concentrations with high spatial and temporal resolution of Ukraine.https://icaiit.org/paper.php?paper=10th_ICAIIT_1/3_6convolution neural networkprobability classificationland cover mapurban atlassmart city |
| spellingShingle | Andrii Shelestov Bohdan Yailymov Hanna Yailymova Leonid Shumilo Mykola Lavreniuk Alla Lavreniuk Sergiy Sylantyev Nataliia Kussul Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network Proceedings of the International Conference on Applied Innovations in IT convolution neural network probability classification land cover map urban atlas smart city |
| title | Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network |
| title_full | Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network |
| title_fullStr | Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network |
| title_full_unstemmed | Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network |
| title_short | Advanced Method of Land Cover Classification Based on High Spatial Resolution Data and Convolutional Neural Network |
| title_sort | advanced method of land cover classification based on high spatial resolution data and convolutional neural network |
| topic | convolution neural network probability classification land cover map urban atlas smart city |
| url | https://icaiit.org/paper.php?paper=10th_ICAIIT_1/3_6 |
| work_keys_str_mv | AT andriishelestov advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT bohdanyailymov advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT hannayailymova advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT leonidshumilo advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT mykolalavreniuk advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT allalavreniuk advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT sergiysylantyev advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork AT nataliiakussul advancedmethodoflandcoverclassificationbasedonhighspatialresolutiondataandconvolutionalneuralnetwork |