Starting from the evaluation of presence-only data, and according to stochastic processes theory, we propose a classification method for unknown larval fish specimens, which is based on Local Indicators of Spatio-Temporal Association (LISTA). LISTA functions are typically used to evaluate the presence of clustered local second-order structures in spatio-temporal data. Here, these tools were applied to classification of two rare species of mesopelagic fish larvae belonging to the genus Vinciguerria (V. attenuata and V. poweriae), detected in the Strait of Sicily, from 1998 to 2016. To evaluate the dependence of larval fish abundance spatio-temporal distributions from covariates, with the aim of understanding their impact on the reproducing activity of Vinciguerria spp., we fit a thinned inhomogeneous multitype spatio-temporal Poisson point process model. According to the goodness-of-fit evaluation, based on second-order diagnostics, the spatio-temporal Poisson point process model perfectly fits larval fish abundance’ presence-only data, after the classification procedure. We classify units representing spatio-temporal events by a LISTA functions-based classification procedure of local interaction. In addition, a stochastic processes’ model for the evaluation of presence-only data from an inferential point of view is estimated, accounting for covariates and sampling bias correction. The modeling analysis is carried out before and after the classification procedure, with the aim to evaluate the difference in terms of interpretation and diagnostics.

Giada Lo Galbo, G.A. (2025). Larval fish abundance classification and modeling through spatio-temporal point processes approach. ENVIRONMENTAL AND ECOLOGICAL STATISTICS.

Larval fish abundance classification and modeling through spatio-temporal point processes approach

Giada Lo Galbo
Data Curation
;
Giada Adelfio
Secondo
Conceptualization
;
Angela Cuttitta
Membro del Collaboration Group
;
Bernardo Patti
Membro del Collaboration Group
;
Marco Torri
Membro del Collaboration Group
2025-01-01

Abstract

Starting from the evaluation of presence-only data, and according to stochastic processes theory, we propose a classification method for unknown larval fish specimens, which is based on Local Indicators of Spatio-Temporal Association (LISTA). LISTA functions are typically used to evaluate the presence of clustered local second-order structures in spatio-temporal data. Here, these tools were applied to classification of two rare species of mesopelagic fish larvae belonging to the genus Vinciguerria (V. attenuata and V. poweriae), detected in the Strait of Sicily, from 1998 to 2016. To evaluate the dependence of larval fish abundance spatio-temporal distributions from covariates, with the aim of understanding their impact on the reproducing activity of Vinciguerria spp., we fit a thinned inhomogeneous multitype spatio-temporal Poisson point process model. According to the goodness-of-fit evaluation, based on second-order diagnostics, the spatio-temporal Poisson point process model perfectly fits larval fish abundance’ presence-only data, after the classification procedure. We classify units representing spatio-temporal events by a LISTA functions-based classification procedure of local interaction. In addition, a stochastic processes’ model for the evaluation of presence-only data from an inferential point of view is estimated, accounting for covariates and sampling bias correction. The modeling analysis is carried out before and after the classification procedure, with the aim to evaluate the difference in terms of interpretation and diagnostics.
2025
Giada Lo Galbo, G.A. (2025). Larval fish abundance classification and modeling through spatio-temporal point processes approach. ENVIRONMENTAL AND ECOLOGICAL STATISTICS.
File in questo prodotto:
File Dimensione Formato  
s10651-025-00650-0.pdf

accesso aperto

Tipologia: Versione Editoriale
Dimensione 5.75 MB
Formato Adobe PDF
5.75 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/672144
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact