scholarly journals Evaluation of Microwave-Optical-Infrared Satellite Imagery for Land Cover Mapping

2021 ◽  
Vol 2114 (1) ◽  
pp. 012090
Author(s):  
Ghufran ameer ◽  
Nawal Kh. Gazal
Keyword(s):  
Land Cover ◽  
Satellite Imagery ◽  
Point Of View ◽  
Land Cover Mapping ◽  
Land Use Land Cover ◽  
Atmospheric Scattering ◽  
Optical Wavelengths ◽  
Almost All ◽  
Fusion Feature ◽  
Sentinel 2

Abstract Satellite images are vital tool in various applications like land use, land cover mapping and geographic information system (GIS) etc. A variety of factors involved in the process of image acquisition, introduce geometric distortions, which are removed by pre-processing of the digital imagery. Geometric correction is the process of rectification of geometric errors introduced in the imagery during the process of its acquisition. From practical point of view, the Sentinel-1 images are to be depended as source of microwave satellite imagery. While, Sentinel-2 are to be used for providing the study with the required visible-infrared images. The study includes performing different digital image processing and analysis techniques, such as: geometric and radiometric corrections, spatial merge (fusion), feature extraction with using different spatial filtering techniques and spectral classification to reveal which LULC image presents better accuracy results. The microwave portion of the spectrum covers the range from approximately 1cm to 1m in wavelength. Because of their long wavelengths, compared to the visible and infrared, microwaves have special properties that are important for remote sensing. Longer wavelength microwave radiation can penetrate through cloud cover, haze, dust, and all but the heaviest rainfall as the longer wavelengths are not susceptible to atmospheric scattering which affects shorter optical wavelengths. This property allows detection of microwave energy under almost all weather and environmental conditions so that data can be collected at any time.

scholarly journals Land Use Land Cover Classification with U-Net: Advantages of Combining Sentinel-1 and Sentinel-2 Imagery

2021 ◽  
Vol 13 (18) ◽  
pp. 3600
Author(s):  
Jonathan V. Solórzano ◽  
Jean François Mas ◽  
Yan Gao ◽  
José Alberto Gallardo-Cruz
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Secondary Forest ◽  
Secondary Forests ◽  
Land Use Land Cover ◽  
Algorithm Selection ◽  
Old Growth ◽  
The Difference ◽  
Almost All ◽  
Sentinel 2

The U-net is nowadays among the most popular deep learning algorithms for land use/land cover (LULC) mapping; nevertheless, it has rarely been used with synthetic aperture radar (SAR) and multispectral (MS) imagery. On the other hand, the discrimination between plantations and forests in LULC maps has been emphasized, especially for tropical areas, due to their differences in biodiversity and ecosystem services provision. In this study, we trained a U-net using different imagery inputs from Sentinel-1 and Sentinel-2 satellites, MS, SAR and a combination of both (MS + SAR); while a random forests algorithm (RF) with the MS + SAR input was also trained to evaluate the difference in algorithm selection. The classification system included ten classes, including old-growth and secondary forests, as well as old-growth and young plantations. The most accurate results were obtained with the MS + SAR U-net, where the highest overall accuracy (0.76) and average F1-score (0.58) were achieved. Although MS + SAR and MS U-nets gave similar results for almost all of the classes, for old-growth plantations and secondary forest, the addition of the SAR band caused an F1-score increment of 0.08–0.11 (0.62 vs. 0.54 and 0.45 vs. 0.34, respectively). Consecutively, in comparison with the MS + SAR RF, the MS + SAR U-net obtained higher F1-scores for almost all the classes. Our results show that using the U-net with a combined input of SAR and MS images enabled a higher F1-score and accuracy for a detailed LULC map, in comparison with other evaluated methods.

Optical and Radar Data Analysis for Land Use Land Cover Mapping in Peru

2019 ◽  
Vol 3 (1) ◽  
pp. 14-27
Author(s):  
Barry Haack ◽  
Ron Mahabir
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Window Size ◽  
Radar Data ◽  
Optical Data ◽  
Land Cover Mapping ◽  
Land Use Land Cover ◽  
Texture Image ◽  
Site Class ◽  
Spectral Signatures

This analysis determined the best individual band and combinations of various numbers of bands for land use land cover mapping for three sites in Peru. The data included Landsat Thematic Mapper (TM) optical data, PALSAR L-band dual-polarized radar, and derived radar texture images. Spectral signatures were first obtained for each site class and separability between classes determined using divergence measures. Results show that the best single band for analysis was a TM band, which was different for each site. For two of the three sites, the second best band was a radar texture image from a large window size. For all sites the best three bands included two TM bands and a radar texture image. The original PALSAR bands were of limited value. Finally upon further analysis it was determined that no more than six bands were needed for viable classification at each study site.

scholarly journals Land Use Land Cover map segmentation using Remote Sensing: A Case study of Ajoy river watershed, India

2020 ◽  
Vol 30 (1) ◽  
pp. 273-286
Author(s):  
Kalyan Mahata ◽  
Rajib Das ◽  
Subhasish Das ◽  
Anasua Sarkar
Keyword(s):  
Land Use ◽  
Image Segmentation ◽  
Cellular Automata ◽  
Land Cover ◽  
Satellite Imagery ◽  
Current Model ◽  
Discrete Dynamical System ◽  
Land Use Land Cover ◽  
Data Set ◽  
Validity Indices

Abstract Image segmentation in land cover regions which are overlapping in satellite imagery, is one crucial challenge. To detect true belonging of one pixel becomes a challenging problem while classifying mixed pixels in overlapping regions. In current work, we propose one new approach for image segmentation using a hybrid algorithm of K-Means and Cellular Automata algorithms. This newly implemented unsupervised model can detect cluster groups using hybrid 2-Dimensional Cellular-Automata model based on K-Means segmentation approach. This approach detects different land use land cover areas in satellite imagery by existing K-Means algorithm. Since it is a discrete dynamical system, cellular automaton realizes uniform interconnecting cells containing states. In the second stage of current model, we experiment with a 2-dimensional cellular automata to rank allocations of pixels among different land-cover regions. The method is experimented on the watershed area of Ajoy river (India) and Salinas (California) data set with true class labels using two internal and four external validity indices. The segmented areas are then compared with existing FCM, DBSCAN and K-Means methods and verified with the ground truth. The statistical analysis results also show the superiority of the new method.

scholarly journals Land Use/Land Cover Mapping of Sambar Watershed by Using Remote Sensing and GIS

2021 ◽  
Vol 10 (9) ◽  
pp. 578-585
Author(s):  
B. Varpe Shriniwas D. Payal Sandip
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Remote Sensing And Gis ◽  
Rapid Expansion ◽  
Water Bodies ◽  
Land Cover Mapping ◽  
Fallow Land ◽  
Land Use Land Cover ◽  
Barren Land

In the present study, an effort has been made to study in detail of Land Use/Land Cover Mapping for Sambar watershed by using Remote Sensing and GIS technique was carried out during the year of 2020-2021 in Parbhani district. In this research the Remote Sensing and Geographical Information system technique was used for identifying the land use/land cover classes with the help of ArcGIS 10.8 software. The Sambar watershed is located in 19º35ʹ78.78˝ N and 76º87ʹ88.44˝ E in the Parbhani district of Marathwada region in Maharashtra. It is covered a total area 97.01 km2. The land use/land cover map and its classes were identified by the Supervised Classification Method in ArcGIS 10.8 software by using the Landsat 8 satellite image. Total six classes are identified namely as Agricultural area, Forest area, Urban area, Barren land, Water bodies and Fallow land. The Agricultural lands are well distributed throughout the watershed area and it covers 4135 ha. (43 per cent). Forest occupies 502 ha area and sharing about 5 per cent of the total land use land cover of the study area. The Urban land occupies 390 ha. area (4 per cent) and there was a rapid expansion of settlement area. Barren land occupies 3392 ha. area (35 per cent). A water bodies occupy 630 ha. area (6 per cent) and the Fallow land occupies 650 ha (7 per cent) but well-developed dendritic drainage pattern and good water availability is in the Sambar watershed.

Land cover mapping in Latvia using hyperspectral airborne and simulated Sentinel-2 data

2016 ◽  
Author(s):  
Dainis Jakovels ◽  
Jevgenijs Filipovs ◽  
Agris Brauns ◽  
Juris Taskovs ◽  
Gatis Erins
Keyword(s):  
Land Cover ◽  
Land Cover Mapping ◽  
Sentinel 2
Sign in / Sign up

Export Citation Format

Share Document