Processos pontuais espaciais univariados aplicados à distribuição de espécies arbóreas em florestas naturais

Abstract

The majority of forested areas worldwide (3.75 billion hectares) consist of naturally regene- rating forests, and approximately 1.11 billion hectares are native forests. Natural forests, en- compassing both naturally regenerating and native forests, establish internal distances at which

individuals of the same or different species must be for their survival, due to minimal human

intervention in reforestation efforts. These internal separation distances define distinct spa- tial distribution patterns of plants (random, clustered, and regular). Understanding the factors

responsible for these patterns is crucial for effective forest management. This study aimed to

investigate the spatial distribution pattern of the species Siparuna guianensis, Xylopia brasi- liensis, Copaifera langsdorffii, and Myrcia splendens, and to model these patterns to identify

directly linked factors. These species inhabit a 6.2-hectare fragment of Atlantic Forest located

at the Campus of the Federal University of Lavras (UFLA), Minas Gerais, Brazil. Forest inven- tories from 1987 to 2017 were utilized alongside non-parametric kernel methods to characterize

spatial configuration trends, and Linhom(r) and Jinhom(r) functions to characterize spatial distri- bution patterns. Poisson and Cox models were fitted using maximum pseudo-likelihood and

maximum likelihood Palm methods, validated through residual analysis, Akaike Information

Criterion, and Monte Carlo simulations (1000). Spatio-temporal dynamics (1987-2017) reve- aled low mortality among species, with slight mortality observed during 2015-2017 due to the

El Niño phenomenon recorded between 2015 and 2016. Despite this, Copaifera langsdorffii,

Myrcia splendens, and Siparuna guianensis showed limited growth. Spatial distribution pat- tern analysis indicated that Siparuna guianensis and Copaifera langsdorffii exhibited spatial

trends rather than spatial dependence, modeled through inhomogeneous Poisson models. The low abundance of Copaifera langsdorffii was influenced by factors such as soil acidity, effective

cation exchange capacity, organic matter content, and clay composition, while for Siparuna gui- anensis, negative influences included low germination capacity (<30%) and presence of alumi- num. In contrast, Xylopia brasiliensis and Myrcia splendens demonstrated intra-specific spatial

dependence. Cox models revealed that potential acidity and organic matter positively influ- enced Xylopia brasiliensis, whereas moisture, calcium, magnesium, and aluminum negatively

influenced the restricted abundance of Myrcia splendens in the southeast. This study contributes to understanding the spatio-temporal dynamics and spatial distribution patterns of the studied species, providing explanatory models for their distribution.