528.7; 528.8

В целях городского планирования и управления необходимы точные данные о городской территории и ее функциональном зонировании. Классификация городских территорий возможна с использованием данных дистанционного зондирования Земли. В настоящее время для этого используются преимущественно снимки в оптическом диапазоне, применение которых имеет некоторое ограничение по точности. Нами для территории города Кабул (Исламская Республика Афганистан) использована комбинация оптических и радиолокационных данных для повышения точности классификации функциональных зон. Для достижения поставленной цели использовались программные продукты SNAP, ENVI и ArcGIS, при помощи которых обрабатывались снимки Sentinel-1, Sentinel-2, а также Landsat 8 OLI. После объединения снимков была осуществлена их классификация методом машины опорных векторов (SVM). Также использовались спектральные индексы (NDVI, NDBI). Комбинированные наборы данных Sentinel-1A и Sentinel-2B позволяют повысить точность выделения функциональных зон города (общую точность классификации 96.8% и коэффициент Каппа 0.95), тогда как точность комбинированных наборов данных Landsat 8 и Sentinel-2B составляет 93.7% при коэффициенте Каппа 0,91. Таким образом, сочетание радиолокационных и оптических данных позволяет повысить точность классификации городских территорий и функциональных зон в их пределах.

For urban planning and management, an accurate map of the earth's urban area and its functional zoning is necessary. Classification of urban areas is possible using remote sensing data. Currently, images in the optical range are mainly used for this having some limitations in accuracy. For the territory of Kabul (Islamic Republic of Afghanistan), we used a combination of optical and radar data to increase the accuracy of the classification of functional zones. To achieve this goal, the software products SNAP, ENVI, and ArcGIS were used, with the help of which Sentinel-1, Sentinel-2, and Landsat 8 OLI images were processed. After combining the images, they were classified using a support vector machine (SVM). Spectral indices (NDVI, NDBI) were also used. The combined Sentinel-1A and Sentinel-2B datasets improve the accuracy of identifying functional areas of the city (96.8% overall classification accuracy and 0.95 Kappa coefficient), while the accuracy of the combined Landsat 8 and Sentinel-2B datasets is 93.7% with a Kappa coefficient of 0.91. That is, the combination of radar and optical data allows for improved classification of urban areas.

аспирант, Московский государственный университет геодезии и картографии

доктор географических наук, заведующий кафедрой географии Московского государственного университета геодезии и картографии

Godinho S., N. Guiomar, and A. Gil. Using a stochastic gradient boosting algorithm to analyse the effectiveness of Landsat 8 data for montado land cover mapping: Application in southern Portugal. International Journal of Applied Earth Observation and Geoinformation. 2016. 49. Pp. 151-162.

Chen B., B. Huang, and B. Xu. Multi-source remotely sensed data fusion for improving land cover classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2017. 124. Pp. 27-39.

Carrasco L., et al. Evaluating combinations of temporally aggregated Sentinel-1, Sentinel-2 and Landsat 8 for land cover mapping with Google Earth Engine. Remote Sensing. 2019. 11(3). Pp. 288.

Drusch M., et al. Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote sensing of Environment, 2012. 120. Pp. 25-36.

Veloso A., et al. Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote sensing of environment. 2017. 199. Pp. 415-426.

Chen B., et al. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Sci. Bull. 2019. 64(370-373). Pp. 3.

Lu D., M. Batistella, and E. Moran. Land-cover classification in the Brazilian Amazon with the integration of Landsat ETM+ and Radarsat data. International Journal of Remote Sensing. 2007. 28(24). Pp. 5447-5459.

Jiang L., et al. Synergistic use of optical and InSAR data for urban impervious surface mapping: a case study in Hong Kong. International Journal of Remote Sensing. 2009. 30(11). Pp. 2781-2796.

Shao Z., W. Wu, and S. Guo. IHS-GTF: A fusion method for optical and synthetic aperture radar data. Remote Sensing. 2020. 12(17). Pp. 2796.

Zhang H., Y. Zhang, and H. Lin. A comparison study of impervious surfaces estimation using optical and SAR remote sensing images. International Journal of Applied Earth Observation and Geoinformation. 2012. 18. Pp. 148-156.

Balzter H., et al. Mapping CORINE land cover from Sentinel-1A SAR and SRTM digital elevation model data using random forests. Remote Sensing. 2015. 7(11). Pp. 14876-14898.

Bao Y., et al. Surface soil moisture retrievals over partially vegetated areas from the synergy of Sentinel-1 and Landsat 8 data using a modified water-cloud model. International journal of applied earth observation and geoinformation. 2018. 72. Pp. 76-85.

Erinjery J.J., M. Singh, and R. Kent. Mapping and assessment of vegetation types in the tropical rainforests of the Western Ghats using multispectral Sentinel-2 and SAR Sentinel-1 satellite imagery. Remote Sensing of Environment. 2018. 216. Pp. 345-354.

Colson D., G.P. Petropoulos, and K.P. Ferentinos. Exploring the potential of Sentinels-1 & 2 of the Copernicus Mission in support of rapid and cost-effective wildfire assessment. International journal of applied earth observation and geoinformation. 2018. 73. Pp. 262-276.

Weng Q. Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends. Remote Sensing of Environment. 2012. 117. Pp. 34-49.

Haas J. and Y. Ban. Sentinel-1A SAR and sentinel-2A MSI data fusion for urban ecosystem service mapping. Remote Sensing Applications: Society and Environment. 2017. 8. Pp. 41-53.

Pavanelli J.A.P., et al. PALSAR-2/ALOS-2 and OLI/LANDSAT-8 data integration for land use and land cover mapping in northern Brazilian Amazon. Boletim de Ciencias Geodesicas. 2018. 24. Pp. 250-269.

Chaturvedi V., M. Kuffer, and D. Kohli. Analysing urban development patterns in a conflict zone: A case study of Kabul. Remote sensing. 2020. 12(21). Pp. 3662.

Sahak A.S., et al. Seasonal monitoring of urban heat island based on the relationship between land surface temperature and land use/ cover: a case study of Kabul City, Afghanistan. Earth Science Informatics. 2023. 16(1). Pp. 845-861.

Sahak A.S., et al. Evaluating the Impact of Land Use/Land Cover Changes on the Surface Urban Heat Island intensity: The case study of Kabul city. Afghanistan. 2022.

Suhet B.H., Sentinel-2 User Handbook. 24 July 2015: European Space Agency European Commission. Pp. 50-54.

Ihlen V., Landsat 8 (L8) Data Users Handbook, ed. K. Zanter. Vol. 5. 2019, EROS Sioux Falls, South Dakota, United States: Department of the Interior U.S. Geological Survey. 114.

Li H., et al. Mapping urban bare land automatically from Landsat imagery with a simple index. Remote sensing. 2017. 9(3). Pp. 249.