The Use of Remote Sensing and Landscape Metrics to Describe Structures and Changes in Urban Land Uses

10.1068/a3496 ◽  
2002 ◽  
Vol 34 (8) ◽  
pp. 1443-1458 ◽  
Author(s):  
Martin Herold ◽  
Joseph Scepan ◽  
Keith C Clarke
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Urban Growth ◽  
Landscape Metrics ◽  
Urban Land ◽  
Urban Land Use ◽  
Urban Region ◽  
Santa Barbara

Remote sensing technology has great potential for acquisition of detailed and accurate land-use information for management and planning of urban regions. However, the determination of land-use data with high geometric and thematic accuracy is generally limited by the availability of adequate remote sensing data, in terms of spatial and temporal resolution, and digital image analysis techniques. This study introduces a methodology using information on image spatial form—landscape metrics—to describe urban land-use structures and land-cover changes that result from urban growth. The analysis is based on spatial analysis of land-cover structures mapped from digitally classified aerial photographs of the urban region Santa Barbara, CA. Landscape metrics were calculated for segmented areas of homogeneous urban land use to allow a further characterization of the land use of these areas. The results show a useful separation and characterization of three urban land-use types: commercial development, high-density residential, and low-density residential. Several important structural land-cover features were identified for this study. These were: the dominant general land cover (built up or vegetation), the housing density, the mean structure and plot size, and the spatial aggregation of built-up areas. For two test areas in the Santa Barbara region, changes (urban growth) in the urban spatial land-use structure can be described and quantified with landscape metrics. In order to discriminate more accurately between the three land-cover types of interest, the landscape metrics were further refined into what are termed ‘landscape metric signatures’ for the land-use categories. The analysis shows the importance of the spatial measurements as second-order image information that can contribute to more detailed mapping of urban areas and towards a more accurate characterization of spatial urban growth pattern.

scholarly journals An Ensemble Learning Approach for Urban Land Use Mapping Based on Remote Sensing Imagery and Social Sensing Data

2020 ◽  
Vol 12 (19) ◽  
pp. 3254
Author(s):  
Zhou Huang ◽  
Houji Qi ◽  
Chaogui Kang ◽  
Yuelong Su ◽  
Yu Liu
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Ensemble Learning ◽  
Urban Land ◽  
Urban Land Use ◽  
Learning Approach ◽  
Land Use Classification ◽  
Remote Sensing Imagery ◽  
Sensing Data

Urban land use mapping is crucial for effective urban management and planning due to the rapid change of urban processes. State-of-the-art approaches rely heavily on the socioeconomic, topographical, infrastructural and land cover information of urban environments via feeding them into ad hoc classifiers for land use classification. Yet, the major challenge lies in the lack of a universal and reliable approach for the extraction and combination of physical and socioeconomic features derived from remote sensing imagery and social sensing data. This article proposes an ensemble-learning-approach-based solution of integrating a rich body of features derived from high resolution satellite images, street-view images, building footprints, points-of-interest (POIs) and social media check-ins for the urban land use mapping task. The proposed approach can statistically differentiate the importance of input feature variables and provides a good explanation for the relationships between land cover, socioeconomic activities and land use categories. We apply the proposed method to infer the land use distribution in fine-grained spatial granularity within the Fifth Ring Road of Beijing and achieve an average classification accuracy of 74.2% over nine typical land use types. The results also indicate that our model outperforms several alternative models that have been widely utilized as baselines for land use classification.

scholarly journals A regional spatial-retrofitting approach to geovisualise regional urban growth: An application to the Golden Horseshoe in Canada

2021 ◽  
Author(s):  
Eric Vaz ◽  
Amy Buckland ◽  
Kevin Worthington
Keyword(s):  
Decision Making ◽  
Land Use ◽  
Urban Growth ◽  
Urban Land ◽  
Urban Land Use ◽  
Urban Region ◽  
Web Environment ◽  
Urban Land Use Change ◽  
Spatio Temporal ◽  
Share Information

Understanding urban change in particular for larger regions has been a great demur in both regional planning and geography. One of the main challenges has been linked to the potential of modelling urban change. The absence of spatial data and size of areas of study limit the traditional urban monitoring approaches, which also do not take into account visualization techniques that share information with the community. This is the case of the Golden Horseshoe in southern Ontario in Canada, one of the fastest growing regions in North America. An unprecedented change on the urban environment has been witnessed, leading to an increased importance of awareness for future planning in the region. With a population greater than 8 million, the Golden Horseshoe is steadily showing symptoms of becoming a mega-urban region, joining surrounding cities into a single and diversified urban landscape. However, little effort has been done to understand these changes, nor to share information with policy makers, stakeholders and investors. These players are in need of the most diverse information on urban land use, which is seldom available from a single source. The spatio-temporal effect of the growth of this urban region could very well be the birth of yet another North American megacity. Therefore, from a spatial perspective there is demand for joint collaboration and adoption of a regional science perspective including land use and spatio-temporal configurations. This calls forth a novel technique that allows for assessment of urban and regional change, and supports decision-making without having the usual concerns of locational data availability. It is this sense, that we present a spatial-retrofitting model, with the objective of (i) retrofitting spatial land use based on current land use and land cover, and assessing proportional change in the past, leading to four spatial timestamps of the Golden Horseshoe’s land use, while (ii) integrating this in a multi-user open source web environment to facilitate synergies for decision-making. This combined approach is referred to as a regional-spatial-retrofitting approach (RSRA), where the conclusions permit accurate assessment of land use in past time frames based on Landsat imagery. The RSRA also allows for a collective vision of regional urban growth supporting local governance through a decision-making process adhering to Volunteered Geographic Information Systems. Urban land use change can be refined by means of contribution from end-users through a web environment, leading to a constant understanding and monitoring of urban land use and urban land use change.

Reviewing the Pertinence of Sentinel-1 SAR for Urban Land Use Land Cover Classification

2020 ◽  
Vol 11 (5) ◽  
pp. 529-535
Author(s):  
Dan Abudu ◽  
Nigar Sultana Parvin ◽  
Geoffrey Andogah
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Urban Areas ◽  
Land Use Changes ◽  
Land Cover Classification ◽  
Urban Land ◽  
Urban Land Use ◽  
Land Use Land Cover ◽  
Sensing Technology

Conventional approaches for urban land use land cover classification and quantification of land use changes have often relied on the ground surveys and urban censuses of urban surface properties. Advent of Remote Sensing technology supporting metric to centimetric spatial resolutions with simultaneous wide coverage, significantly reduced huge operational costs previously encountered using ground surveys. Weather, sensor’s spatial resolution and the complex compositions of urban areas comprising concrete, metallic, water, bare- and vegetation-covers, limits Remote Sensing ability to accurately discriminate urban features. The launch of Sentinel-1 Synthetic Aperture Radar, which operates at metric resolution and microwave frequencies evades the weather limitations and has been reported to accurately quantify urban compositions. This paper assessed the feasibility of Sentinel-1 SAR data for urban land use land cover classification by reviewing research papers that utilised these data. The review found that since 2014, 11 studies have specifically utilised the datasets.

Sign in / Sign up

Export Citation Format

Share Document