EchoSystem: An Integrated Platform for Bioacoustic and Micrometeorological Monitoring
Resumo
Biodiversity loss driven by factors such as deforestation, wildfires, and urban expansion highlights the need for effective environmental monitoring strategies. This work presents EchoWeb, an open-source web platform for the processing and analysis of bioacoustic and micrometeorological data, and its integration within EchoSystem, a complete end-to-end monitoring ecosystem. EchoWeb supports acoustic index computation, spectrogram visualization, and structured organization of scientific results through a web-based interface. A case study conducted near the Federal University of Amazonas demonstrates its applicability in real-world conditions. Simulation experiments based on Poisson arrival processes and log-normal workload distributions show that the main system bottleneck lies in the audio processing stage. Results further indicate that scaling the number of audio-worker instances significantly reduces end-to-end response time and improves system throughput.
Referências
A. L. Albernaz, M. C. Thalês, M. Gordo, D. Lagroteria, T. V. Sobroza, W. E. Magnusson, P. M. Fearnside, L. Jerusalinsky, R. B. de Azevedo, R. B. Castro, D. Campista, W. R. Spironello, and M. Noronha. Conservation of an endangered amazonian primate: priority areas for the pied tamarin (saguinus bicolor) in manaus, brazil. Journal for Nature Conservation, 89:127069, 2026. ISSN 1617-1381. DOI: 10.1016/j.jnc.2025.127069.
G. B. Anderson, M. L. Bell, and R. D. Peng. Methods to calculate the heat index as an exposure metric in environmental health research. Environmental health perspectives, 121(10):1111, 2013.
R. D. Beason, R. Riesch, and J. Koricheva. Aurita: an affordable, autonomous recording device for acoustic monitoring of audible and ultrasonic frequencies. Bioacoustics, 28 (4):381–396, 2019. DOI: 10.1080/09524622.2018.1463293.
Y. Cheng. Application of the poisson distribution in enterprise web application performance testing. In Proceedings of the 2025 3rd International Conference on Mathematics and Machine Learning, pages 35–40, 2025.
J. G. Colonna, T. V. Sobroza, M. Gordo, E. F. Nakamura, and A. C. Frery. One-class bioacoustic detector for monitoring the critically endangered pied tamarin (saguinus bicolor). bioRxiv, 2025. DOI: 10.1101/2025.10.11.681843.
K. Darras, N. Pérez, and T. Hanf-Dressler. Biosounds: an open-source, online platform for ecoacoustics. F1000Research, 9:1224, 2020. DOI: 10.12688/f1000research.26369.1.
A. F. Giraldo-Forero, P. A. Rodríguez-Marín, C. Isaza-Narváez, and J. M. Daza-Rojas. Ecoacoustic bank: A software for ecoacoustics data management. SoftwareX, 27: 101822, 2024. ISSN 2352-7110. DOI: 10.1016/j.softx.2024.101822.
M. Harchol-Balter. Performance modeling and design of computer systems: queueing theory in action. Cambridge University Press, 2013.
A. P. Hill, P. Prince, E. Piña Covarrubias, C. P. Doncaster, J. L. Snaddon, and A. Rogers. Audiomoth: Evaluation of a smart open acoustic device for monitoring biodiversity and the environment. Methods in Ecology and Evolution, 9(5):1199–1211, 2018. DOI: 10.1111/2041-210X.12955.
ICMBio. Estudo sauim-de-coleira. [link], 2025. Accessed on January 27, 2025.
M. Joyce. Biophonyai: Gpu-accelerated bioacoustic analysis platform, 2025. URL [link].
S. Kahl, C. M. Wood, M. Eibl, and H. Klinck. Birdnet: A deep learning solution for avian diversity monitoring. Ecological Informatics, 61:101236, 2021. ISSN 1574-9541. DOI: 10.1016/j.ecoinf.2021.101236.
K. Kandananond. Applying 2k factorial design to assess the performance of ann and svm methods for forecasting stationary and non-stationary time series. Procedia Computer Science, 22:60–69, 2013.
M. G. Lawrence. The relationship between relative humidity and the dewpoint temperature in moist air: A simple conversion and applications. Bulletin of the American Meteorological Society, 86(2):225–234, 2005.
R. M. May, K. H. Goebbert, J. E. Thielen, J. R. Leeman, M. D. Camron, Z. Bruick, E. C. Bruning, R. P. Manser, S. C. Arms, and P. T. Marsh. Metpy: A meteorological python library for data analysis and visualization. Bulletin of the American Meteorological Society, 103(10):E2273 – E2284, 2022. DOI: 10.1175/BAMS-D-21-0125.1.
P. Mendes, R. Stoll, and J. Colonna. Echologger: sistema embarcado para cálculo do índice de riqueza acústica no monitoramento ambiental não invasivo. In Anais do XVII Simpósio Brasileiro de Computação Ubíqua e Pervasiva, pages 151–160, 2025. DOI: 10.5753/sbcup.2025.9242.
M. Mitzenmacher. Dynamic models for file sizes and double pareto distributions. Internet mathematics, 1(3):305–333, 2004.
D. C. Montgomery. Design and analysis of experiments. John wiley & sons, 2017. S. L. Pimm, C. N. Jenkins, R. Abell, T. M. Brooks, J. L. Gittleman, L. N. Joppa, P. H.
Raven, C. M. Roberts, and J. O. Sexton. The biodiversity of species and their rates of extinction, distribution, and protection. science, 344(6187):1246752, 2014. DOI: 10.1126/science.1246752.
L. S. M. Sugai, T. S. F. Silva, J. Ribeiro, José Wagner, and D. Llusia. Terrestrial passive acoustic monitoring: Review and perspectives. BioScience, 69(1):15–25, 11 2018. ISSN 0006-3568. DOI: 10.1093/biosci/biy147.
Wildlife Acoustics. Kaleidoscope Pro User Guide. Wildlife Acoustics, Maynard, MA, 2024. Software documentation.
Wildlife Acoustics. Song meter sm5, 2026. Accessed on February 22, 2026. [link].
C. M. Wood, F. Günther, A. Rex, D. F. Hofstadter, H. Reers, S. Kahl, M. Z. Peery, and H. Klinck. Real-time acoustic monitoring facilitates the proactive management of biological invasions. Biological Invasions, 26:3989–3996, 2024. DOI: 10.1007/s10530-024-03426-y.
