Landscape similarity, retrieval, and machine mapping of physiographic units

Jasiewicz, Jarosław; Netzel, Paweł; Stepinski, T. F.

doi:10.1016/j.geomorph.2014.06.011

Cited by 45 publications

(26 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the early period of terrain classification using DEMs, Dikau et al (1991) presented unmanned landform classification maps. Research in the twenty-first century using only DEMs for terrain classification appears to be converging on two approaches; one is the classification of landform elements with reference to hydrological geomorphology and transportation of soils using high-resolution DEMs such as laser scanning data (e.g., van Asselen and Seijmonsbergen 2006; Drăguţ and Blaschke 2006;MacMillan et al 2003;del Val et al 2015), and the other is classification of physiographic regions using medium or small-scale DEMs (e.g., Jasiewicz et al 2014). In recent years, many studies have combined other parameters with DEMs; for example, Shafique et al (2012) produced a seismic site characterization map by combining terrain classification with Vs30 (average shear wave velocity for the top 30 m); Guida et al (2016) produced hydro-geomorphological scenario maps by combining API (air-photo interpretation) maps with flow accumulation data calculated from DEMs and hydro-chemographs from field surveys, and Martha et al (2010) extracted landslides using terrain classification with satellite images.…”

Section: Introductionmentioning

confidence: 99%

Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification

Iwahashi

Kamiya²,

Matsuoka

et al. 2018

Prog Earth Planet Sci

View full text Add to dashboard Cite

Polygon-based terrain classification data were created globally using 280 m digital elevation models (DEMs) interpolated from the multi-error-removed improved-terrain DEM (MERIT DEM). First, area segmentation was performed globally with the logarithmic value of slope gradient and the local convexity calculated from the DEM. Next, by adding surface texture, k-means clustering was performed globally and the polygons were grouped into 40 clusters. Then, we tried to reclassify these 40 clusters into geomorphologic terrain groups. In this study, we attempted reclassification and grouping using local information from Japan as a test case. The 40 clusters were compared with Japanese geological and geomorphological data and were then reclassified into 12 groups that had different geomorphological and geological characteristics. In addition, large shape landforms, mountains, and hills were subdivided by using the combined texture. Finally, 15 groups were created as terrain groups. Cross tabulations were performed with geological or lithological maps of California and Australia in order to investigate if the Japanese grouping of the clusters was also meaningful for other regions. The classification is improved from previous studies that used 1-km DEMs, especially for the representation of terrace shapes and landform elements smaller than 1 km. The results were generally suitable for distinguishing bedrock mountains, hills, large highland slopes, intermediate landforms (plateaus, terraces, large lowland slopes), and plains. On the other hand, the cross tabulations indicate that in the case of gentler landforms under different geologic provinces/climates, similar topographies may not always indicate similar formative mechanisms and lithology. This may be solved by locally replacing the legend; however, care is necessary for mixed areas where both depositional and erosional gentle plains exist. Moreover, the limit of the description of geometric signatures still appears in failure to detect narrow valley bottom plains, metropolitan areas, and slight rises in gentle plains. Therefore, both global and local perspectives regarding geologic province and climate are necessary for better grouping of the clusters, and additional parameters or higher resolution DEMs are necessary. Successful classification of terrain types of geomorphology may lead to a better understanding of terrain susceptibility to natural hazards and land development.

show abstract

Section: Introductionmentioning

confidence: 99%

Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification

Iwahashi

Kamiya²,

Matsuoka

et al. 2018

Prog Earth Planet Sci

View full text Add to dashboard Cite

show abstract

“…Comparative histogram-binning methods such as the Earth Mover's Distance (Rubner, Tomasi, & Guibas, 2000) use multidimensional histograms that describe colour and texture and define distance measures in these spaces to characterize similarity of images. Applications of these methods in geographic contexts, most notably for retrieval and characterization of satellite imagery, are increasing (Jasiewicz, Netzel, & Stepinski, 2014;Kranstauber, Smolla, & Safi, 2016;Shao, Zhou, Zhang, & Hou, 2014).…”

Section: Comparing Patterns In Spatial Latticesmentioning

confidence: 99%

Comparing spatial patterns

Long

Robertson

2017

Geography Compass

View full text Add to dashboard Cite

The comparison of spatial patterns is a fundamental task in geography and quantitative spatial modelling. With the growth of data being collected with a geospatial element, we are witnessing an increased interest in analyses requiring spatial pattern comparisons (e.g., model assessment and change analysis). In this paper, we review quantitative techniques for comparing spatial patterns, examining key methodological approaches developed both within and beyond the field of geography. We highlight the key challenges using examples from widely known datasets from the spatial analysis literature. Through these examples, we identify a problematic dichotomy between spatial pattern and process—a widespread issue in the age of big geospatial data. Further, we identify the role of complex topology, the interdependence of spatial configuration and composition, and spatial scale as key (research) challenges. Several areas ripe for geographic research are discussed to establish a consolidated research agenda for spatial pattern comparison grounded in quantitative geography. Hierarchical scaling and the modifiable areal unit problem are highlighted as ideas which can be exploited to identify pattern similarities across spatial and temporal scales. Increased use of “time‐aware” comparisons of spatial processes are suggested, which properly account for spatial evolution and pattern formation. Simulation‐based inference is identified as particularly promising for integrating spatial pattern comparison into existing modelling frameworks. To date, the literature on spatial pattern comparison has been fragmented, and we hope this work will provide a basis for others to build on in future studies.

show abstract

“…delineation of an image into regions characterized by different stationary (relatively small spatial gradient) patterns of pixel values. Examples include: classification of very high resolution (VHR) images of urban areas into different urban landscapes, such as informal settlements, industrial/commercial structures, and formal residential settlements [4,5]; classification of different landscape types [6,7] as well as different types of forest structures [8]; identification of physiographic units from digital elevation model (DEM) [9].…”

Section: Introductionmentioning

confidence: 99%

“…Data are modeled using a multidimensional histogram of categorical pattern primitive features and a dissimilarity between two blocks is calculated using Jensen-Shannon divergence or other histogram dissimilarity measure [12]. This implementation has been applied to search for similar landscape types in the National Land Cover Dataset (NLCD) [10] using query-by-example principle, to assessment land cover change over the conterminous United States using the NLCD [13], and to identification of physiographic units using DEM data [9].…”

Section: Introductionmentioning

confidence: 99%

Pattern-based Regionalization of Large Geospatial Datasets Using Complex Object-based Image Analysis

Stepinski

Niesterowicz

Jasiewicz

2015

Procedia Computer Science

Self Cite

View full text Add to dashboard Cite

Pattern-based regionalization -spatial classification of an image into sub-regions characterized by relatively stationary patterns of pixel values -is of significant interest for conservation, planing, as well as for academic research. A technique called the complex object-based image analysis (COBIA) is particularly well-suited for pattern-based regionalization of very large spatial datasets. In COBIA image is subdivided into a regular grid of local blocks of pixels (complex objects) at minimal computational cost. Further analysis is performed on those blocks which represent local patterns of pixel-based variable. A variant of COBIA presented here works on pixel-classified images, uses a histogram of co-occurrence pattern features as block attribute, and utilizes the Jensen-Shannon divergence to measure a distance between any two local patterns. In this paper the COBIA concept is utilized for unsupervised regionalization of land cover dataset (pixel-classified Landsat images) into landscape types -characteristic patterns of different land covers. This exploratory technique identifies and delineates landscape types using a combination of segmentation of a grid of local patterns with clustering of the segments. A test site with 3.5 × 10 8 pixels is regionalized in just few minutes using a standard desktop computer. Computational efficiency of presented approach allows for carrying out regionalizations of various high resolution spatial datasets on continental or global scales.

show abstract

Landscape similarity, retrieval, and machine mapping of physiographic units

Cited by 45 publications

References 31 publications

Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification

Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification

Comparing spatial patterns

Pattern-based Regionalization of Large Geospatial Datasets Using Complex Object-based Image Analysis

Contact Info

Product

Resources

About