Estimating ecoacoustic activity in the Amazon rainforest through Information Theory quantifiers

Abstract

Automatic monitoring of biodiversity by acoustic sensors has become an indispensable tool to assess environmental stress at an early stage. Due to the difficulty in recognizing the Amazon's high acoustic diversity and the large amounts of raw audio data recorded by the sensors, the labeling and manual inspection of this data is not feasible. Therefore, we propose an ecoacoustic index that allows us to quantify the complexity of an audio segment and correlate this measure with the biodiversity of the soundscape. The approach uses unsupervised methods to avoid the problem of labeling each species individually. The proposed index, named the Ecoacoustic Global Complexity Index (EGCI), makes use of Entropy, Divergence and Statistical Complexity. A distinguishing feature of this index is the mapping of each audio segment, including those of varied lengths, as a single point in a 2Dplane, supporting us in understanding the ecoacoustic dynamics of the rainforest. The main results show a regularity in the ecoacoustic richness of a floodplain, considering different temporal granularities, be it between hours of the day or between consecutive days of the monitoring program. We observed that this regularity does a good job of characterizing the soundscape of the environmental protection area of Mamirauá , in the Amazon, differentiating between species richness and environmental phenomena.

Identifying Acoustic Features to Distinguish Highly and Moderately Altered Soundscapes in Colombia

“…This resulted in a data matrix of 20 observations (rows) and 42 features (columns). Regarding the Pastures problem, these data are associated with the study in [16] and are available to be downloaded from the ARBIMON platform 3 . In this work, we considered a subset of this dataset, specifically those corresponding to La Pradera, a livestock farm in the piedmont of the Colombian Orinoco in the department of Meta.…”

“…In this work, we consider the acoustic features surveyed by Eldridge and Guyot, as well as the Ecoacoustic Global Complexity Index (EGCI) recently proposed by Colonna et al [3]. For the latter, we also use a Python implementation which is available in [2].…”

“…• Coffee: The ranking of the features for this problem is the following one: 10,11,12,15,19,20,21,28,29,18,25,5,22,23,27,30,31,32,13,16,17,34,35,36,39,42,2,24,9,26,1,4,14,3,38,8,37,6,7,33, 40 and 41. The top-ranked feature for discriminating between the two classes of this case is the main value of the Bio Acoustic Index, followed by the Normalized Difference Sound Index and then the minimum of the RMS Energy.…”

Generalized weighted permutation entropy analysis of SPEI index in Serbia as a proxy of corn production

“…The GWPE method was recently introduced (Stosic et al, 2022) as a generalization of the Permutation entropy–PE (Bandt & Pompe, 2002), complexity‐entropy causality plane–CECP (Rosso et al, 2007) and their weighted variants (Fadlallah et al, 2013), which have been extensively applied over the last decades in diverse phenomenological studies (Colonna et al, 2020; de Carvalho Barreto et al, 2023; Deng et al, 2015; Garland et al, 2018; Sigaki et al, 2019).…”

Busca por evidências de dinâmica caótica nas flutuações turbulentas de densidade em plasmas

“…Este método permite relacionar a natureza dinâmica do processo com a posic ¸ão relativa da representac ¸ão da série temporal no plano formado por duas medidas estatísticas: a complexidade de Jensen-Shannon e a entropia normalizada de Shannon, calculadas a partir da distribuic ¸ão de probabilidades dos estados de ordenac ¸ão dos pontos na série temporal [9]. O método já foi aplicado em diversas áreas, como: física de plasmas [10][11][12][13], análise de séries temporais financeiras [14,15], neurociência [16,17], dentre outras [17][18][19]. Na área de física de plasmas, essa metodologia foi utilizada recentemente para analisar os sinais turbulentos dos tokamaks DIII-D [20] e Alcator C-Mod [21].…”