The Artificial Intelligence and Discrete Wavelet Transform Applied to the Forecasting of Plastic Waste Leakage in the Ocean
Artificial Intelligence and Discrete Wavelet Transform Applied to the Forecasting of Plastic Waste Leakage in the Ocean
Palabras clave:
Marine pollution, waste management, artificial neural networks, wavelet analysis, BrazilResumen
This study aimed to evaluate the forecasting of leak-prone plastic waste in the oceans (LPW) using artificial neural networks (ANN): Nonlinear Autoregressive (NAR); Nonlinear Autoregressive with Exogenous Inputs (NARX); Long Short-Term Memory (LSTM). The analysis focused on the 20 Brazilian municipalities with the highest LPW potential based on 2022 data. Methodologies included discrete wavelet transform, simple linear regression, Taylor diagrams, geospatial mapping, and others. The results indicated that São Paulo, Rio de Janeiro and the Southeast region exhibited the highest absolute LPW potential, followed by the Northeast and Central-West regions. In predictive modeling, the ANN-NARX achieved the highest accuracy, followed by the ANN-NAR and -LSTM. These findings can improve the monitoring and control of plastic waste leakage in the oceans.
Citas
Alencar, M.V., 2022. Improving the source-to-sea approach for marine litter in Brazil. PhD thesis in Oceanography, University of São Paulo, São Paulo. Available at: https://www.teses.usp.br/teses/disponiveis/21/21134/tde-19092022-144406/publico/Dissertacao_Alencar_Melanie_Corrigida.pdf. Accessed 30 January 2025.
Alencar, M.V., Gimenez, B.G., Sasahara, C., Elliff, C.I., Velis, C.A., Rodrigues, L.S., Conti, L.A., Gonçalves-Dias, S.L.F., Cetrulo, T.B., Scrich, V.M., Turra, A., 2023. Advancing plastic pollution hotspotting at the subnational level: Brazil as a case study in the Global South. Mar. Pollut. Bull. 194, 115382. https://doi.org/10.1016/j.marpolbul.2023.115382
Barbosa, A., De Castro Gonçalves, T., Simões, P., 2025. Improving municipal solid waste services: Insights into efficiency, productivity, and recycling in Brazil. Sustainability 17, 2519. https://doi.org/10.3390/su17062519
Carmo, N.R.M., 2022. Uso de redes neurais artificiais para previsão de GHI. Rev. Virtual Quím. 14, 56–60. https://doi.org/10.21577/1984-6835.20220013
Chamas, A., Moon, H., Zheng, J., Qiu, Y., Tabassum, T., Jang, J.H., Abu-Omar, M., Scott, S.L., Suh, S., 2020. Degradation rates of plastics in the environment. ACS Sustainable Chemistry & Engineering 8, 3494–3511. https://doi.org/10.1021/acssuschemeng.9b06635
Exame, 2023. Poluição plástica: 350 milhões de toneladas viram resíduos a cada ano, diz Credit Suisse. Available at: https://exame.com/esg/impacto-da-poluicao-plastica-no-mundo-e-medido-em-estudo-do-credit-suisse. Accessed 6 March 2025.
Fraga Filho, C.A.D., 2025. Analysis of Brazilian plastic waste management in the global context and case study of the city of Vitória, Espírito Santo. Environmental Science and Pollution Research 32, 5645–5684. https://doi.org/10.1007/s11356-024-35865-4
Guo, Q., He, Z., Wang, Z., 2025. Assessing the effectiveness of long short – term memory and artificial neural network in predicting daily ozone concentrations in Liaocheng City. Scientific reports, 15, 6798. https://doi.org/10.1038/s41598-025-91329-w
He, Z., Guo, Q., Wang, Z., Li, X., 2025.A Hybrid wavelet – based deep learning model for accurate prediction of daily surface PM2.5 concentrations in Guangzhou. Toxics, 13, 254. https://doi.org/10.3390/toxics13040254
Hopkins, W.G., 2009. A new view of statistics: correlation coefficient. New York: Internet Society for Sport Science. Available at: http://www.sportsci.org/resource/stats/correl.html (accessed 18 January 2025).
Islam, F., 2025. The effects of plastic and microplastic waste on the marine environment and the ocean. Eur. J. Environ. Earth Sci. 6, 508. https://doi.org/10.24018/ejgeo.2025.6.3.508
Izzaddin, A., Langousis, A., Totaro, V., Yaseen, M., & Iacobellis, V., 2024. A new diagram performance evaluation of complex models. Stochastic Environmental Research and Risk Assessment. https://doi.org/10.1007/s00477-024-02678-3
Meijer, L.J.J., Emmerik, T.V., Ent, R.V.D., Schmidt, C., Lebreton, L., 2021. More than 1000 rivers account for 80% of global riverine plastic emissions into the ocean. Science Advances 7, eaaz5803. Available at: https://www.science.org/doi/pdf/10.1126/sciadv.aaz5803 (accessed 11 July 2025).
Monitor Mercantil, 2023. O Brasil é um dos que mais produz lixo no mundo; apenas 4% dos resíduos sólidos são reciclados. Available at: https://monitormercantil.com.br/brasil-e-um-dos-que-mais-produzem-lixo-no-mundo-so-4-dos-residuos-solidos-so-reciclados (accessed 06 March 2025).
Nascimento, E.G.S., Melo, T.A.C., Moreira, D.M., 2023. A transformer-based deep neural network with wavelet transforms for forecasting wind speed and wind energy. Energy 278, 127678. https://doi.org/10.1016/j.energy.2023.127678
Nguyen, T.H., Nguyen, H.T., 2024. Advances in wavelet transform methods for non-stationary signal analysis: A review. Signal Processing, 215, 110145. https://doi.org/10.1016/j.sigpro.2024.110145
Nuwairan, M.A.L., Sabir, Z., Raja, M.A.Z., Aldhafeeri, A., 2022. An advance artificial neural network scheme to examine the waste plastic management in the ocean. AIP Advances 12, 045211. https://doi.org/10.1063/5.0085737
Pincelli, I., De Castilhos Júnior, A., Matias, M., Rutkowski, E., 2021. Post-consumer plastic packaging waste flow analysis for Brazil: The challenges moving towards a circular economy. Waste Manag. 126, 781–790. https://doi.org/10.1016/j.wasman.2021.04.005
Prakash, N., Zielinski, O., 2025. AI-enhanced real-time monitoring of marine pollution: Part 1 – A state-of-the-art and scoping review. Front. Mar. Sci. 1486615. https://doi.org/10.3389/fmars.2025.1486615
Prakash, N., Zielinski, O., 2025. AI-enhanced real-time monitoring of marine pollution: Part 2 — A spectral analysis approach. J. Mar. Sci. Eng. 13, 636. https://doi.org/10.3390/jmse13040636
Santos, I.G.S., 2024. Estatísticas de cinco variáveis meteorológicas no município de Craíbas no Estado de Alagoas. Tese (Doutorado em Meteorologia), Universidade Federal de Campina Grande, Paraíba. Available at: http://dspace.sti.ufcg.edu.br:8080/jspui/handle/riufcg/38015 (accessed 09 March 2025).
Santos, I.G.S., Oliveira-Júnior, J.F., Sousa, F.A.S., Barbosa, I.I., 2022. Previsão de focos de calor na região metropolitana de Maceió utilizando rede neural artificial. Revista Brasileira de Geografia Física 15(5), 2313–2326. https://doi.org/10.26848/rbgf.v15.5.p2313-2326
Santos, I.G.S., Lyra, R.F.F., Silva-Júnior, R.S., 2020. Comparativo de prognósticos da velocidade do vento utilizando o modelo WRF e rede neural artificial. Revista Brasileira de Meteorologia 35(Special issue), 1017–1027. https://doi.org/10.1590/0102-77863550103
Saraiva, S.V., Carvalho, F.O., Santos, C.A.G., Barreto, L.C., Freire, P.K.M.M., 2021. Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping. Applied Soft Computing 102, 107081. https://doi.org/10.1016/j.asoc.2021.107081
Simão, M., Videiro, P., Silva, P., De Freitas Assad, L., Sagrilo, L., 2020. Application of Taylor diagram in the evaluation of joint environmental distributions' performances. Marine Systems & Ocean Technology, 15, 151–159. https://doi.org/10.1007/s40868-020-00081-5
Smyl, S., 2020. A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2019.03.017
Taylor, K.E., 2001. Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research 126, 7183–7192. https://doi.org/10.1029/2000JD900719
Tian, Z., Chen, H., 2021. Multi-step short-term wind speed prediction based on integrated multi-model fusion. Applied Energy 298, 117248. https://doi.org/10.1016/j.apenergy.2021.117248
Velis, C.A., Wilson, D.C., Gavish, Y., Grimes, S.M., Whiteman, A., 2023. Socio-economic development drives solid waste management performance in cities: A global analysis using machine learning. Science of the Total Environment 872, 161913. https://doi.org/10.1016/j.scitotenv.2023.161913
Vergara, D., De La Hoz-M, J., Ariza-Echeverri, E., Fernández-Arias, P., Antón-Sancho, Á., 2025. Evaluating solutions to marine plastic pollution. Environments 12, 86. https://doi.org/10.3390/environments12030086
Zhang, B., 2025. Application of the Taylor Diagram in evaluating the performance of IOL formulas. J. Refract. Surg. 41 (1), e50–e55. https://doi.org/10.3928/1081597X-20241126-04
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 IWLDSON GUILHERME DA SILVA SANTOS
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Authors who publish in the Annals of Data Analysis retain
the copyright of their work and agree to license it under a Creative Commons Attribution-
NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license.
