A quantitative comparison of regionalization methods

Aydin, Orhun; Janikas, Mark V.; Assunção, Renato M.; Lee, Ting‐Hwan

doi:10.1080/13658816.2021.1905819

Cited by 30 publications

(13 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, bioclimatic zones in the Old World are irregularly shaped and do not follow any clear spatial pattern. The impact of irregularly shaped regions on climatic regionalizations has already been analysed (Aydin et al, 2021) and, as in our study case, result in the delimitation of highly patchy and incompatible regions based on the different classification systems (Appendix S3).…”

Section: Selection Of Regionalization Systems To Characterize the Climatic Preferences Of Taxa: A Matter Of Where You Are And Who You Arementioning

confidence: 88%

Tropical-temperate dichotomy falls apart in the Asian Palmate Group of Araliaceae

Coca-de-la-Iglesia

Medina

Wen

et al. 2021

Preprint

View full text Add to dashboard Cite

PREMISE The use of climatic data on phylogenetic studies has greatly increased in the last decades. High-quality spatial data and accurate climatic information are essential to minimize errors in the climatic reconstructions to the past. However, despite the huge amount of already available biodiversity digital information, the process of compiling, cleaning, and comparing spatial data from different open data sources is a time-consuming task that sometimes ends up with low-quality geographical information. For this reason, researchers often resort qualitative approximations among which World bioclimatic classification systems or the experts' criteria are the most used. Our aim is to evaluate the climatic characterization of the genera of the Asian Palmate Group (AsPG) of the ginseng family (Araliaceae), one of the classical examples of tropical-temperate plant families. METHODS We compiled a curated worldwide spatial database of the AsPG genera. We then created five raster layers representing bioclimatic regionalizations of the World. Finally, we crossed the database with the layers to characterize the AsPG genera. RESULTS We found large disagreement in the climatic characterization of genera among regionalizations and little support for the tropical-temperate dichotomy. Both results are attributed to the complexity of delimiting tropical, subtropical and temperate climates in the World and to the distribution of the study group in regions with transitional climatic conditions. CONCLUSIONS The complexity in the climatic classification of this classical example tropical-temperate dichotomy, calls for a general revision in other families. In fact, we claim that to properly evaluate tropical-temperate transitions we cannot ignore the complexity of distribution ranges.

show abstract

Section: Selection Of Regionalization Systems To Characterize the Climatic Preferences Of Taxa: A Matter Of Where You Are And Who You Arementioning

confidence: 88%

Tropical-temperate dichotomy falls apart in the Asian Palmate Group of Araliaceae

Coca-de-la-Iglesia

Medina

Wen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Spatial matrices such as Gaussian kernel, fixed bandwidth, and distance lags that express different spatial proxy relationships can be embedded into the STICC method as well (Yan et al, 2017). In addition, recent studies regarding spatial clustering approaches mainly focus on two directions, either modifying existing algorithms to achieve better performances in classic spatial clustering tasks (Aydin et al, 2021;Liu et al, 2019), or developing domain-specific algorithms for a specific field such as cartography (Wolf, 2021), human mobility (Liu et al, 2021), and geodemography (Grekousis, 2021), while limited attention was paid on the proposed RGPD problem. We believe that this work is just a beginning for solving the RGPD problem.…”

Section: Implications For Geoai and Spatially Explicit Modelmentioning

confidence: 99%

STICC: A multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity

Kang,

Wu,

Gao

et al. 2022

Preprint

View full text Add to dashboard Cite

Spatial clustering has been widely used for spatial data mining and knowledge discovery. An ideal multivariate spatial clustering should consider both spatial contiguity and aspatial attributes.Existing spatial clustering approaches may face challenges for discovering repeated geographic patterns with spatial contiguity maintained. In this paper, we propose a Spatial Toeplitz Inverse Covariance-Based Clustering (STICC) method that considers both attributes and spatial relationships of geographic objects for multivariate spatial clustering. A subregion is created for each geographic object serving as the basic unit when performing clustering. A Markov random field is then constructed to characterize the attribute dependencies of subregions. Using a spatial consistency strategy, nearby objects are encouraged to belong to the same cluster. To test the performance of the proposed STICC algorithm, we apply it in two use cases. The comparison results with several baseline methods show that the STICC outperforms others significantly in terms of adjusted rand index and macro-F1 score. Join count statistics is also calculated and shows that the spatial contiguity is well preserved by STICC. Such a spatial clustering method may benefit various applications in the fields of geography, remote sensing, transportation, and urban planning, etc.

show abstract

“…First, they do not allow a strict control of the resulting number of regions, as post-processing may produce a different number of regions than previously specified. Second, to impose a fixed number of output regions, manual refinement or domain knowledge may be required, which cannot be exempt of subjectivity (Aydin et al 2021). Third, the shape of the regions is subject to the choice of the clustering algorithm (Duque et al 2007).…”

Section: Related Workmentioning

confidence: 99%

“…This includes the automatic zoning procedure (AZP) (Openshaw 1977, Openshaw andRao 1995), spatial 'k'luster analysis by tree edge removal (SKATER) (Assunção et al 2006), and regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP) (Guo 2008). A detailed comparison of these algorithms based on simulation experiments is provided in Aydin et al (2021).…”

Section: Introductionmentioning

confidence: 99%

A generalized regionalization framework for geographical modelling and its application in spatial regression

Guo¹,

Python²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

In presence of spatial heterogeneity, models applied to geographic data face a tradeoff between producing general results and capturing local variations. Modelling at a regional scale may allow the identification of solutions that optimize both accuracy and generality. However, most current regionalization algorithms assume homogeneity in the attributes to delineate regions without considering the processes that generate the attributes. In this paper, we propose a generalized regionalization framework based on a two-item objective function which favors solutions with the highest overall accuracy while minimizing the number of regions. We introduce three regionalization algorithms, which extend previous methods that account for spatially constrained clustering. The effectiveness of the proposed framework is examined in regression experiments on both simulated and real data. The results show that a spatially implicit algorithm extended with an automatic post-processing procedure outperforms spatially explicit approaches. Our suggested framework contributes to better capturing the processes associated with spatial heterogeneity with potential applications in a wide range of geographical models.

show abstract

A quantitative comparison of regionalization methods

Cited by 30 publications

References 39 publications

Tropical-temperate dichotomy falls apart in the Asian Palmate Group of Araliaceae

Tropical-temperate dichotomy falls apart in the Asian Palmate Group of Araliaceae

STICC: A multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity

A generalized regionalization framework for geographical modelling and its application in spatial regression

Contact Info

Product

Resources

About