Spatial Clustering Using Hierarchical SOM

Henriques, Roberto; Bação, Fernando; Lobo, Victor

doi:10.5772/51159

Cited by 8 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All prepared variables were subjected to an unsupervised clustering algorithm so that areas with commonalities are grouped together, resulting in clusters that are formed based on spatial similarities in biophysical or management related variables. Here we used a neural-network clustering algorithm called self-organizing map (SOM), that is particularly suited for non-linear and heterogeneous data [ 57 , 58 ]. Other, supervised clustering methods exist and can be the preferred method of choice when a-priori knowledge about the type and name of clusters exist [ 22 ].…”

Section: Methodsmentioning

confidence: 99%

“…However, the purpose of this work was to discover and let the data speak about emergent clusters using available global data. SOMs are able to reduce heterogeneous multi-dimensional sets of variables to a lower, two-dimensional space where topological properties are preserved among neighbours, making them ideal for the visual exploration and clustering of geographic data, such as data on food production [ 25 , 58 ]. We conducted all procedures and clustering separately for each variable grouping (biophysical lvl1 and management lvl2, S1 Fig in S1 File ).…”

Section: Methodsmentioning

confidence: 99%

“…We note that although these measures taken post hoc necessarily result in a loss of detail, (a) they more closely refine an essential set of global clusters of food production making labeling and interpretation more viable, (b) clusters of both level 1 and level 2 were ultimately combined across levels (see below) thus combining strengths of both biophysical and management data in mapping foodscapes in a hierarchical manner [ 58 ], and (c) all clusters were carefully visually assessed by experts with knowledge of regional centers of food production and eventually further refined (i.e. by separating nodes from another) if deemed necessary.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A global clustering of terrestrial food production systems

Jung,

Boucher,

Wood

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Food production is at the heart of global sustainability challenges, with unsustainable practices being a major driver of biodiversity loss, emissions and land degradation. The concept of foodscapes, defined as the characteristics of food production along biophysical and socio-economic gradients, could be a way addressing those challenges. By identifying homologues foodscapes classes possible interventions and leverage points for more sustainable agriculture could be identified. Here we provide a globally consistent approximation of the world’s foodscape classes. We integrate global data on biophysical and socio-economic factors to identify a minimum set of emergent clusters and evaluate their characteristics, vulnerabilities and risks with regards to global change factors. Overall, we find food production globally to be highly concentrated in a few areas. Worryingly, we find particularly intensively cultivated or irrigated foodscape classes to be under considerable climatic and degradation risks. Our work can serve as baseline for global-scale zoning and gap analyses, while also revealing homologous areas for possible agricultural interventions.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A global clustering of terrestrial food production systems

Jung,

Boucher,

Wood

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…All prepared variables were subjected to an unsupervised clustering algorithm so that areas with commonalities are grouped together, resulting in clusters that are formed based on spatial similarities in biophysical or management related variables. Here we used a neural-network clustering algorithm called self-organizing map (SOM), that is particularly suited for non-linear and heterogeneous data 57,58 . Other, supervised clustering methods exist and can be the preferred method of choice when a-priori knowledge about the type and name of clusters exist .…”

Section: Clustering and Post-hoc Processingmentioning

confidence: 99%

“…However, the purpose of this work was to discover and let the data speak about emergent clusters using available global data. SOMs are able to reduce heterogeneous multidimensional sets of variables to a lower, two-dimensional space where topological properties are preserved among neighbours, making them ideal for the visual exploration and clustering of geographic data, such as data on food production 25,58 . We conducted all procedures and clustering separately for each variable grouping (biophysical lvl1 and management lvl2).…”

Section: Clustering and Post-hoc Processingmentioning

confidence: 99%

A global clustering of terrestrial food production systems

Jung¹,

Boucher²,

Wood³

et al. 2022

Preprint

View full text Add to dashboard Cite

The production of food is at the heart of global sustainability challenges, with unsustainable practices being a major driver of biodiversity loss, greenhouse gas emissions, water overextraction, and land degradation. The concept of foodscapes, defined as the characteristics of food production along biophysical and socio-economic gradients, could provide an entry point into navigating this nexus. Further, identifying broad homologues of possible foodscape classes would help to design possible interventions and leverage points for more sustainable agriculture. Here we provide a globally consistent depiction of the world’s foodscapes approximated through distinct classes. We integrate the best available global data on biophysical and socio-economic factors to identify the minimum set of emergent clusters that determine these homologues production systems and evaluate their characteristics. We also explore and highlight vulnerabilities, risks and values affecting these depictions of the world's foodscapes. Overall, we find that food production globally is highly concentrated, with few foodscape classes producing much of the World’s food. Worryingly, we also find that many foodscape classes, particularly intensively cultivated or irrigated foodscape classes, are under considerable climatic and degradation risks. Our work can serve as baseline for global-scale zoning and gap analyses, while also revealing opportunities and homologous areas for possible agricultural interventions.

show abstract

Contextual contact tracing based on stochastic compartment modeling and spatial risk assessment

Mahmood

Mateu

Hernández-Orallo

2021

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

The current situation of COVID-19 highlights the paramount importance of infectious disease surveillance, which necessitates early monitoring for effective response. Policymakers are interested in data insights identifying high-risk areas as well as individuals to be quarantined, especially as the public gets back to their normal routine. We investigate both requirements by the implementation of disease outbreak modeling and exploring its induced dynamic spatial risk in form of risk assessment, along with its real-time integration back into the disease model. This paper implements a contact tracing-based stochastic compartment model as a baseline, to further modify the existing setup to include the spatial risk. This modification of each individual-level contact’s intensity to be dependent on its spatial location has been termed as Contextual Contact Tracing . The results highlight that the inclusion of spatial context tends to send more individuals into quarantine which reduces the overall spread of infection. With a simulated example of an induced spatial high-risk, it is highlighted that the new spatio-SIR model can act as a tool to empower the analyst with a capability to explore disease dynamics from a spatial perspective. We conclude that the proposed spatio-SIR tool can be of great help for policymakers to know the consequences of their decision prior to their implementation.

show abstract

Spatial Clustering Using Hierarchical SOM

Cited by 8 publications

References 58 publications

A global clustering of terrestrial food production systems

A global clustering of terrestrial food production systems

A global clustering of terrestrial food production systems

Contextual contact tracing based on stochastic compartment modeling and spatial risk assessment

Contact Info

Product

Resources

About