Wyniki wyszukiwania - BazTech

1

Klasyfikacja pokrycia terenu z wykorzystaniem obrazów Sentinel-2A przetworzonych za pomocą metody głównych składowych (PCA)

Kałużna Urszula, Będkowski Krzysztof

Teledetekcja Środowiska

|

2020

|

T. 61

19--37

PL

Celem badań jest ocena możliwości realizacji klasyfikacji nadzorowanej z wykorzystaniem obrazów (komponentów) uzyskiwanych w wyniku przetworzenia oryginalnych obrazów Sentinel-2A za pomocą metody głównych składowych (PCA). Klasyfikację wykonano w ośmiu wariantach, z wykorzystaniem algorytmów najmniejszej odległości (MD, Minimum Distance) oraz największego prawdopodobieństwa (ML, Maximum Likelihood), przy czym zastosowano oryginalne kanały 2, 3, 4, 8 Sentinel-2A oraz różną liczbę komponentów. Wyniki klasyfikacji oceniono poprzez porównanie z danymi o pokryciu terenu według Ewidencji Gruntów i Budynków (EGiB). Przeprowadzenie klasyfikacji na ograniczonej do dwóch liczbie komponentów uzyskanych w procedurze PCA tylko nieznacznie zmieniło wyniki w porównaniu do klasyfikacji na oryginalnych, nieprzetworzonych kanałach Sentinel-2A. Najbardziej zbliżone do danych EGiB rezultaty uzyskano stosując klasyfikację ML kanałów oryginalnych, nieprzetworzonych lub używając wszystkich komponentów PCA. Podjęta próba porównania pokrycia terenu ustalonego za pomocą klasyfikacji obrazów satelitarnych z klasami pokrycia, które zostały wyodrębnione z mapy EGiB wykazała, że przetworzenie mapy z postaci wektorowej na rastrową wpływa istotnie na uzyskiwane wyniki.

EN

The aim of the research is to assess the feasibility of supervised classification using images (components) obtained through processing the original Sentinel-2A images by means of the principal component method (PCA). The classification was performed in eight variants, using the algorithms of the minimum distance (MD) and the maximum likelihood (ML), with the original channels 2, 3, 4, 8 of Sentinel-2A and a various number of components. The results of the classification were assessed by comparing them to the land coverage data of Land and Buildings Register (Ewidencja Gruntów i Budynków – EGiB). Performing the classification on a number of PCA components limited to two only slightly altered the results compared to the classification on the original, raw Sentinel-2A channels. The results most similar to the EGiB data were obtained using the ML classification of the original channels, i.e. raw channels or using all PCA components. The attempt to compare the land coverage established by the classification of satellite images to the coverage classes that were extracted from the EGiB map revealed that processing the map from vector to raster form significantly influences the obtained results.

2

Using Sentinel-2A to identify the change in dry marginal agricultural land occupation

Indarto Indarto, Putra Bayu T. W., Mandala Marga

Journal of Water and Land Development

|

2020

|

no. 47

89--95

EN

Dry marginal agricultural land (DryMAL) potentially use as an alternative resource for crop production. DryMAL defined as land having low natural fertility due to its intrinsic properties and forming environmental factors. This study uses Sentinel-2A imagery to map the spatial extent, compare the result of the classification, and identify the change in DryMAL occupation. The area of study (461.9 km2) is part of Situbondo Regency and is located at the eastern part of East Java, Indonesia. Sentinel-2A image captured in dry-season of 2018 use for this study. Then, supervised image classification using a maximum likelihood algorithm use for image treatment and processing. Furthermore, 450 ground control points for training areas collected during the field surveys. Five bands use in the classification process. The maps produced from the classification process were then compared to the land-use map from the year 2000. The change in DryMAL occupation from 2000 to 2018 was calculated by comparing the classified and land-use map. Supervised classification yielded an overall accuracy of 95.8% and a kappa accuracy of 93.2%. The classification produced six (6) classes of land use: (1) forest, (2) pavement or built-up area, (3) irrigated paddy field, (4) non-irrigated rural area, (5) dry marginal land and (6) water body. Globally, during the last two decades, regional development led by the Regency occupied more DryMAL area for developing plantation. The effort reduces the amount of non-irrigated and converting to the plantation, pavement areas, and irrigated paddy-field.

3

Use of the Sentinel-2A multispectral image for litho-structural and alteration mapping in Al Glo'a map sheet (1/50,000) (Bou Azzer-El Graara inlier, Central Anti-Atlas, Morocco)

El Atillah Abdessamad, El Morjani Zine El Abidine, Souhassou Mustapha

Artificial Satellites : Journal of Planetary Geodesy

|

2019

|

Vol. 54, No. 3

73--96

EN

The discovery of natural resources remains the main mission of Earth observation satellites, especially in geographical areas that have a very difficult accessibility as those of the Bou Azzer-El Graara inlier (Central Anti-Atlas, Morocco). This work investigates the use of different satellite data, such as Sentinel-2A's multispectral imagery, in order to direct the prospection program in an efficient manner, saving both time and cost. The image processing methods of Landsat 7, 8, and “Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)” (30 m/15 m) were used to create methods for Sentinel-2A images (10 m). The red, green, blue (RGB) image 12.8.2, 11/12.11/2.11/8, principal component (PC) 1,2,3(11.12.2), and other new images were the result of principal component analysis (PCA), and classification by the Iterative Self-Organizing Data Analysis Technique (ISODATA) and K-Means allowed realization of a lithological cartography as well as maps of lineaments through directional filters and the ratio of 11/12 for hydrothermal alteration zone mapping. The assembly of lithological, structural, and hydrothermal alteration data gave an idea of the mineralogy of the study area. Validity of the results was tested by comparison with the field data and the geological maps of the studied site (62% for the hydrothermal alteration zone, 81% for the lithological map, and 74% for the structural map).