scholarly journals Experiment of Multispectral Images using Spectral Angle Mapper Algorithm for Land Cover Classification

2019 ◽  
Vol 8 (6S4) ◽  
pp. 96-99
Keyword(s):  
Land Cover ◽  
Satellite Images ◽  
Water Bodies ◽  
Classification Algorithms ◽  
Multispectral Images ◽  
Rapid Urbanization ◽  
Spectral Angle Mapper ◽  
Time Period ◽  
Steep Decline ◽  
Spectral Angle

Urbanization plays a key role in the health of the water bodies in any region. In a rapidly growing country like India, especially Bangalore district, rapid urbanization has seen a steep decline in the number of water bodies the region is famous for. In this paper, Land Use and Land Cover change is analysed for the remotely sensed images of Bangalore District using Spectral Angle Mapper Algorithm. Data for the purpose of analysis was obtained from BHUVAN (NRSC, ISRO). The study area is Bangalore District and data was collected from the time period 2008-2016. The major classes used in the classification are Land(Built-up), water bodies (Lakes), Vegetation (Gardens), Soil (Barren and fertile). The satellite images and the accompanying classification algorithms indicate that the percentage of water bodies have drastically shrunk (from 2.9% in 2008to1.8% in 2016) in the area of study. The results of this study can be used by the civic authorities to implement decisions to conserve the water bodies in the area.

scholarly journals Variations in ecosystem service value in response to land use/land cover changes in Central Asia over 1995-2035

2019 ◽  
Author(s):  
Jiangyue Li ◽  
Hongxing Chen ◽  
Chi Zhang ◽  
Tao Pan
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Central Asia ◽  
Ecosystem Service ◽  
Water Bodies ◽  
Land Cover Changes ◽  
Land Use Land Cover ◽  
Ecosystem Service Value ◽  
Rapid Urbanization ◽  
Service Value

Acute farmland expansion and rapid urbanization in Central Asia have accelerated land use/land cover changes, which has significant effect onecosystemservice. However, the spatio-temporal changes in ecosystem service values in Central Asia are not well understood. Here, based on land use products with 300-m resolution for the years of 1995, 2005 and 2015 and transfer methodology, we predicted LUCC for 2025 and 2035 using CA-Markov, assessed changes in ecosystem service value in response to LUCC dynamics, and explored the elasticity for the response of ESV to LULC changes. We found significant expansions of cropland and urban and shrinking of water bodies and bare land during 1995-2035. Overall ESVs had an increasing trend from 1995-2035, which was mainly due to the increasing cropland and construction land. The combined valueofecosystemservices of cropland, grassland, water bodies accounted for over 90% of the total ESVs. However, LULC analysis showed that the area of water body reduced by 21.80% from 1995 to 2015 and continued to decrease by 21.14% from 2015 to 2035, indicating that approximately 63.37 billion US$ of ESVs lost in Central Asia. Biodiversity, food production and water regulation were major service functions, accounting for 80.52% of the total ESVs . Our results demonstrated that theeffective land-usepolicies should be made to control farmland expansion and protect water bodies, grassland and forestland for better sustainable ecosystem services.

scholarly journals Remote Sensing and GIS based Land Use Land Cover Analysis in Chandel District, Manipur, India

2021 ◽  
Vol 889 (1) ◽  
pp. 012046
Author(s):  
Ashangbam Inaoba Singh ◽  
Kanwarpreet Singh
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Supervised Classification ◽  
Geographical Area ◽  
Temporal Trends ◽  
Water Bodies ◽  
Landsat 8 ◽  
Rapid Urbanization ◽  
Barren Area ◽  
Landsat 7

Abstract Rapid urbanization has dramatically altered land use and land cover (LULC). The focus of this research is on the examination of the last two decades. The research was conducted in the Chandel district of Manipur, India. The LULC of Chandel (encompassing a 3313 km2 geographical area) was mapped using remotely sensed images from LANDSAT4-5, LANDSAT 7 ETM+, and LANDSAT 8 (OLI) to focus on spatial and temporal trends between years 2000 and 2021. The LULC maps with six major classifications viz., Thickly Vegetated Area (TVA), Sparsely Vegetated Area (SVA), Agriculture Area (AA), Population Area (PA), Water Bodies (WB), and Barren Area (BA) of the were generated using supervised classification approach. For the image classification procedure, interactive supervised classification is adopted to calculate the area percentage. The results interpreted that the TVA covers approximately 65% of the total mapped area in year 2002, which has been decreased up to 60% in 2007, 56% in 2011, 55 % in 2017, and 52% in 2021. The populated area also increases significantly in these two decades. The change and increase in the PA has been observed from year 2000 (8%) to 2021 (11%). Water Bodies remain same throughout the study period. Deforestation occurs as a result of the rapid rise of the population and the extension of the territory.

scholarly journals Land Use and Land Cover Change Detection and Prediction in the Kathmandu District of Nepal Using Remote Sensing and GIS

2020 ◽  
Vol 12 (9) ◽  
pp. 3925 ◽  
Author(s):  
Sonam Wangyel Wang ◽  
Belay Manjur Gebru ◽  
Munkhnasan Lamchin ◽  
Rijan Bhakta Kayastha ◽  
Woo-Kyun Lee
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Land Cover Change ◽  
Agricultural Land ◽  
Water Bodies ◽  
Geographical Information ◽  
Land Cover Changes ◽  
Rapid Urbanization ◽  
Urbanized Areas

Understanding land use and land cover changes has become a necessity in managing and monitoring natural resources and development especially urban planning. Remote sensing and geographical information systems are proven tools for assessing land use and land cover changes that help planners to advance sustainability. Our study used remote sensing and geographical information system to detect and predict land use and land cover changes in one of the world’s most vulnerable and rapidly growing city of Kathmandu in Nepal. We found that over a period of 20 years (from 1990 to 2010), the Kathmandu district has lost 9.28% of its forests, 9.80% of its agricultural land and 77% of its water bodies. Significant amounts of these losses have been absorbed by the expanding urbanized areas, which has gained 52.47% of land. Predictions of land use and land cover change trends for 2030 show worsening trends with forest, agriculture and water bodies to decrease by an additional 14.43%, 16.67% and 25.83%, respectively. The highest gain in 2030 is predicted for urbanized areas at 18.55%. Rapid urbanization—coupled with lack of proper planning and high rural-urban migration—is the key driver of these changes. These changes are associated with loss of ecosystem services which will negatively impact human wellbeing in the city. We recommend city planners to mainstream ecosystem-based adaptation and mitigation into urban plans supported by strong policy and funds.

scholarly journals Fusion Methods and Multi-classifiers to Improve Land Cover Estimation Using Remote Sensing Analysis

2021 ◽  
Author(s):  
Hayder Dibs ◽  
Hashim Ali Hasab ◽  
Ammar Shaker Mahmoud ◽  
Nadhir Al-Ansari
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Spatial Resolution ◽  
Kappa Coefficient ◽  
Support Vector ◽  
Land Use Land Cover ◽  
Multispectral Imagery ◽  
Spectral Angle Mapper ◽  
Spectral Angle

AbstractAdopting a low spatial resolution remote sensing imagery to get an accurate estimation of Land Use Land Cover is a difficult task to perform. Image fusion plays a big role to map the Land Use Land Cover. Therefore, This study aims to find out a refining method for the Land Use Land Cover estimating using these steps; (1) applying a three pan-sharpening fusion approaches to combine panchromatic imagery that has high spatial resolution with multispectral imagery that has low spatial resolution, (2) employing five pixel-based classifier approaches on multispectral imagery and fused images; artificial neural net, support vector machine, parallelepiped, Mahalanobis distance and spectral angle mapper, (3) make a statistical comparison between image classification results. The Landsat-8 image was adopted for this research. There are twenty Land Use Land Cover thematic maps were generated in this study. A suitable and reliable Land Use Land Cover method was presented based on the most accurate results. The results validation was performed by adopting a confusion matrix method. A comparison made between the images classification results of multispectral imagery and all fused images levels. It proved the Land Use Land Cover map produced by Gram–Schmidt Pan-sharpening and classified by support vector machine method has the most accurate result among all other multispectral imagery and fused images that classified by the other classifiers, it has an overall accuracy about (99.85%) and a kappa coefficient of about (0.98). However, the spectral angle mapper algorithm has the lowest accuracy compared to all other adopted methods, with overall accuracy of 53.41% and the kappa coefficient of about 0.48. The proposed procedure is useful in the industry and academic side for estimating purposes. In addition, it is also a good tool for analysts and researchers, who could interest to extend the technique to employ different datasets and regions.

scholarly journals LAND USE AND LAND COVER CLASSIFICATION USING HYPERSPECTRAL IMAGERY: EVALUATING THE PERFORMANCE OF SPECTRAL ANGLE MAPPER, SUPPORT VECTOR MACHINE AND RANDOM FOREST

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1841-1847 ◽  
Author(s):  
L. E. Christovam ◽  
G. G. Pessoa ◽  
M. H. Shimabukuro ◽  
M. L. B. T. Galo
Keyword(s):  
Land Use ◽  
Support Vector Machine ◽  
Random Forest ◽  
Land Cover ◽  
Principal Components ◽  
Classification Model ◽  
Support Vector ◽  
Classification Models ◽  
Spectral Angle Mapper ◽  
Spectral Angle

<p><strong>Abstract.</strong> Land Use and Land Cover (LULC) information is an important data source for modeling environmental variables, so it is essential to develop high quality LULC maps. The hundreds of continuous spectral bands gathered with hyperspectral sensors provide high spectral detail and consequently confirm hyperspectral remote sensing as an appropriate option for many LULC applications. Despite increased spectral detail, issues like high dimensionality, huge volume of data and redundant information, mean that hyperspectral image classification is a complex task. It is therefore essential to develop classification approaches that deals with these issues. Since classification results are directly dependent on the dataset used, it is fundamental to compare and validate the classification approaches in public datasets. With this in mind, aiming to provide a baseline, four classification models in the relatively new hyperspectral HyRANK dataset were evaluated. The classification models were defined with three well-known classification algorithms: Spectral Angle Mapper (SAM), Support Vector Machine (SVM) and Random Forest (RF). A classification model with SAM and another with RF were defined with the 176 surface reflectance bands. A dimensionality reduction with principal component analysis was carried out and a classification model with SVM and another with RF were defined using 14 principal components as features. The results show that SVM and RF algorithms outperformed by far the SAM in terms of accuracy, and that the RF is slightly better than the SVM in this respect. It is also possible to see from the results that the use of principal components as features provided an improvement in the accuracy of the RF and an improvement of 28% in the time spent fitting the classification model.</p>

scholarly journals Examples of Object-Oriented Classification Performed on High-Resolution Satellite Images

2004 ◽  
Vol 11 (1) ◽  
pp. 349-358 ◽  
Author(s):  
Stanisław Lewiński ◽  
Karol Zaremski
Keyword(s):  
Land Cover ◽  
Satellite Images ◽  
Satellite Image ◽  
Object Oriented ◽  
Unsupervised Classification ◽  
Automatic Classification ◽  
Classification Algorithms ◽  
Visual Interpretation ◽  
Vistula River ◽  
High Resolution Satellite Images

Abstract Information about the types of land cover and its use is obtained by the visual interpretation of the color composite of satellite images or by the use of automatic classification algorithms. For obvious reasons, the automatic classification methods make it possible to obtain information quicker and much faster than the traditional interpretation method. The commonly used automatic methods of satellite image classification, based on supervised or unsupervised classification algorithms, are the most accurate when used with low resolution images. In the case of images with 1-meter-sized pixels, showing a diversity of land cover forms, it is not possible to obtain satisfactory results. New classification techniques, based on object-oriented classification algorithms, have been developing for a couple of years now. In contrast to the traditional methods, the new operating procedure does not involve the classification of single pixels, but of entire objects, into which the content of the satellite image is divided. Aside from the spectral values of the pixels, the shape of the objects created by the pixels and the relationships between the objects, are also considered during the analysis. Similar to visual interpretation, variation in the texture of the image can also be taken into account in this case. The aim of this article is to present the possibility of using high density satellite images in object-oriented classification. The classification presented is that of a high-rise built area in Wrocław and of bridges on the Vistula River in Warsaw.

scholarly journals AUTOMATED RECOGNITION OF VEGETATION AND WATER BODIES ON THE TERRITORY OF MEGACITIES IN SATELLITE IMAGES OF VISIBLE AND IR BANDS

2018 ◽  
Vol IV-3 ◽  
pp. 167-172 ◽  
Author(s):  
Dmitry k. Mozgovoy ◽  
Volodymyr V. Hnatushenko ◽  
Volodymyr V. Vasyliev
Keyword(s):  
Satellite Images ◽  
Landscape Planning ◽  
Urban Ecosystems ◽  
Water Bodies ◽  
Multispectral Images ◽  
Automated Recognition ◽  
Large Cities ◽  
Wide Range ◽  
High Degree ◽  
Ir Bands

Vegetation and water bodies are a fundamental element of urban ecosystems, and water mapping is critical for urban and landscape planning and management. A methodology of automated recognition of vegetation and water bodies on the territory of megacities in satellite images of sub-meter spatial resolution of the visible and IR bands is proposed. By processing multispectral images from the satellite SuperView-1A, vector layers of recognized plant and water objects were obtained. Analysis of the results of image processing showed a sufficiently high accuracy of the delineation of the boundaries of recognized objects and a good separation of classes. The developed methodology provides a significant increase of the efficiency and reliability of updating maps of large cities while reducing financial costs. Due to the high degree of automation, the proposed methodology can be implemented in the form of a geo-information web service functioning in the interests of a wide range of public services and commercial institutions.

Sign in / Sign up

Export Citation Format

Share Document