Applying data mining techniques for spatial distribution analysis of plant species co-occurrences

Abstract

The continuous growth of biodiversity databases has led to a search for techniques that can assist researchers. This paper presents a method for the analysis of occurrences of pairs and groups of species that aims to identify patterns in co-occurrences through the application of association rules of data mining. We propose, implement and evaluate a tool to help ecologists formulate and validate hypotheses regarding cooccurrence between two or more species. To validate our approach, we analyzed the occurrence of species with a dataset from the 50-ha Forest Dynamics Project on Barro Colorado Island (BCI). Three case studies were developed based on this tropical forest to evaluate patterns of positive and negative correlation. Our tool can be used to point co-occurrence in a multi-scale form and for multi-species, simultaneously, accelerating the identification process for the Spatial Point Pattern Analysis. This paper demonstrates that data mining, which has been used successfully in applications such as business and consumer profile analysis, can be a useful resource in ecology.

How do similarities in spatial distributions and interspecific associations affect the coexistence of Quercus species in the Baotianman National Nature Reserve, Henan, China

“…In HP, the points are distributed in accordance with an intensity function λ( x , y ) that varies with location ( x , y ) (Wiegand & Moloney, ; Zhu, Getzin, Wiegand, Ren, & Ma, ; Hypotheses 1, Table ). g ( r ) is related to the derivative of the K function (Equation ): A is the area of the study region, n is the number of the points of species, d ij is the distance between focus point i and the other point j , I r is a counter variable ( I r ( d ij ) = 1 if d ij < r , and I r ( d ij ) = 0 otherwise), and w ij is a weighting factor to correct for the edge effects (Silva et al., ; Wiegand & Moloney, ).…”

“…A is the area of the study region, n is the number of the points of species, d ij is the distance between focus point i and the other point j, I r is a counter variable (I r (d ij ) = 1 if d ij < r, and I r (d ij ) = 0 otherwise), and w ij is a weighting factor to correct for the edge effects (Silva et al, 2016;Wiegand & Moloney, 2004).…”

Jabot - Sistema de Gerenciamento de Coleções Botânicas: a experiência de uma década de desenvolvimento e avanços

“…Bancos de dados da biodiversidade são cada vez mais consultados para diversos estudos e pesquisas, bem como para tomada de decisões por parte de gestores públicos (Briggs 2006;Sarukhán & Jiménez 2016). Eles auxiliam na geração de conhecimento, facilitando o monitoramento e a elaboração de ações de conservação da biodiversidade (Pougy et al 2014), a produção de listas de espécies ameaçadas (Silveira & Straube 2008;Martinelli & Moraes 2013;Martinelli et al 2014), a modelagem de distribuição de espécies (Barros et al 2012), a análise de co-ocorrência (Silva et al 2016) entre muitas outras possibilidades. De modo a facilitar o acesso e a integração de dados, diversos sistemas de informação especialistas no Rodriguésia 68(2): 391-410.…”

Market basket analysis of grasshopper (Orthoptera: Acrididae) assemblages in eastern Wyoming: a 17‐year case study using associative analysis for ecological insights into grasshopper outbreaks

“…The confidence interval (i.e. In a large database with multiple items where relationships of those items are of interest, MBA can be utilised to find not only common, but also rare or surprising, associations (Samecka-Cymerman et al, 2010;Silva et al, 2016). MBA uses all elements within the dataset, thus eliminating investigator bias, and the reiterative calculations ignore redundant rules (Tan et al, 2006).…”

“…MBA uses all elements within the dataset, thus eliminating investigator bias, and the reiterative calculations ignore redundant rules (Tan et al, 2006). In a large database with multiple items where relationships of those items are of interest, MBA can be utilised to find not only common, but also rare or surprising, associations (Samecka-Cymerman et al, 2010;Silva et al, 2016). This method identifies the likelihood of one item, or right-hand sets (rhs) being in a basket if several other items are already in the basket, or left-hand sets (lhs).…”