{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:27:05Z","timestamp":1779294425828,"version":"3.51.4"},"reference-count":53,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T00:00:00Z","timestamp":1713398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universidad de Antioquia, Instituto Tecnol\u00f3gico Metropolitano de Medell\u00edn, Alexander von Humboldt Institute for Research on Biological Resources and Colombian National Fund for Science, Technology and Innovation, Francisco Jose de Caldas\u2014MINCIENCIAS (Colombia)","award":["11585269779"],"award-info":[{"award-number":["11585269779"]}]},{"name":"Colombian National Fund for Science, Technology and Innovation, Francisco Jose de Caldas\u2014MINCIENCIAS","award":["11585269779"],"award-info":[{"award-number":["11585269779"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Passive acoustic monitoring (PAM) through acoustic recorder units (ARUs) shows promise in detecting early landscape changes linked to functional and structural patterns, including species richness, acoustic diversity, community interactions, and human-induced threats. However, current approaches primarily rely on supervised methods, which require prior knowledge of collected datasets. This reliance poses challenges due to the large volumes of ARU data. In this work, we propose a non-supervised framework using autoencoders to extract soundscape features. We applied this framework to a dataset from Colombian landscapes captured by 31 audiomoth recorders. Our method generates clusters based on autoencoder features and represents cluster information with prototype spectrograms using centroid features and the decoder part of the neural network. Our analysis provides valuable insights into the distribution and temporal patterns of various sound compositions within the study area. By utilizing autoencoders, we identify significant soundscape patterns characterized by recurring and intense sound types across multiple frequency ranges. This comprehensive understanding of the study area\u2019s soundscape allows us to pinpoint crucial sound sources and gain deeper insights into its acoustic environment. Our results encourage further exploration of unsupervised algorithms in soundscape analysis as a promising alternative path for understanding and monitoring environmental changes.<\/jats:p>","DOI":"10.3390\/s24082597","type":"journal-article","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T10:30:52Z","timestamp":1713436252000},"page":"2597","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Soundscape Characterization Using Autoencoders and Unsupervised Learning"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6046-4622","authenticated-orcid":false,"given":"Daniel Alexis","family":"Nieto-Mora","sequence":"first","affiliation":[{"name":"M\u00e1quinas Inteligentes y Reconocimiento de Patrones (MIRP), Instituto Tecnol\u00f3gico Metropolitano ITM, Medell\u00edn 050034, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4729-5104","authenticated-orcid":false,"given":"Maria Cristina","family":"Ferreira de Oliveira","sequence":"additional","affiliation":[{"name":"Instituto de Ci\u00eancias Matem\u00e1ticas e de Computa\u00e7\u00e3o, Universidade de S\u00e3o Paulo, S\u00e3o Carlos 13566-590, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-9377","authenticated-orcid":false,"given":"Camilo","family":"Sanchez-Giraldo","sequence":"additional","affiliation":[{"name":"Grupo Herpetol\u00f3gico de Antioquia, Institute of Biology, Universidad de Antioquia-UdeA, Medell\u00edn 050010, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7115-3870","authenticated-orcid":false,"given":"Leonardo","family":"Duque-Mu\u00f1oz","sequence":"additional","affiliation":[{"name":"M\u00e1quinas Inteligentes y Reconocimiento de Patrones (MIRP), Instituto Tecnol\u00f3gico Metropolitano ITM, Medell\u00edn 050034, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1044-9429","authenticated-orcid":false,"given":"Claudia","family":"Isaza-Narv\u00e1ez","sequence":"additional","affiliation":[{"name":"SISTEMIC, Facultad de Ingenier\u00eda, Universidad de Antioquia-UdeA, Medell\u00edn 050010, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7037-6925","authenticated-orcid":false,"given":"Juan David","family":"Mart\u00ednez-Vargas","sequence":"additional","affiliation":[{"name":"GIDITIC, Universidad EAFIT, Medell\u00edn 050022, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108831","DOI":"10.1016\/j.ecolind.2022.108831","article-title":"Soundscape classification with convolutional neural networks reveals temporal and geographic patterns in ecoacoustic data","volume":"138","author":"Quinn","year":"2022","journal-title":"Ecol. Indic."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101160","DOI":"10.1016\/j.ecoinf.2020.101160","article-title":"Data selection in frog chorusing recognition with acoustic indices","volume":"60","author":"Gan","year":"2020","journal-title":"Ecol. Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106559","DOI":"10.1016\/j.ecolind.2020.106559","article-title":"Automatic detection of dolphin whistles and clicks based on entropy approach","volume":"117","author":"Siddagangaiah","year":"2020","journal-title":"Ecol. Indic."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e02056","DOI":"10.1002\/eap.2056","article-title":"Modeling avian full annual cycle distribution and population trends with citizen science data","volume":"30","author":"Fink","year":"2020","journal-title":"Ecol. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"106717","DOI":"10.1016\/j.ecolind.2020.106717","article-title":"Spatial replication and habitat context matters for assessments of tropical biodiversity using acoustic indices","volume":"119","author":"Mitchell","year":"2020","journal-title":"Ecol. Indic."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1093\/biosci\/biab073","article-title":"A Comprehensive Overview of Technologies for Species and Habitat Monitoring and Conservation","volume":"71","author":"Magrath","year":"2021","journal-title":"BioScience"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1111\/2041-210X.13101","article-title":"Emerging opportunities and challenges for passive acoustics in ecological assessment and monitoring","volume":"10","author":"Gibb","year":"2019","journal-title":"Methods Ecol. Evol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"118253","DOI":"10.1109\/ACCESS.2023.3326367","article-title":"Improving Bearing Fault Identification by Using Novel Hybrid Involution-Convolution Feature Extraction With Adversarial Noise Injection in Conditional GANs","volume":"11","author":"Irfan","year":"2023","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Shinde, P.P., and Shah, S. (2018, January 16\u201318). A Review of Machine Learning and Deep Learning Applications. Proceedings of the 2018 4th International Conference on Computing, Communication Control and Automation, ICCUBEA 2018, Pune, India.","DOI":"10.1109\/ICCUBEA.2018.8697857"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1111\/2041-210X.13599","article-title":"A machine learning approach for classifying and quantifying acoustic diversity","volume":"12","author":"Keen","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106852","DOI":"10.1016\/j.ecolind.2020.106852","article-title":"Automated species identification of frog choruses in environmental recordings using acoustic indices","volume":"119","author":"Brodie","year":"2020","journal-title":"Ecol. Indic."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2799","DOI":"10.1111\/2041-210X.14003","article-title":"Domain-specific neural networks improve automated bird sound recognition already with small amount of local data","volume":"13","author":"Lauha","year":"2022","journal-title":"Methods Ecol. Evol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101688","DOI":"10.1016\/j.ecoinf.2022.101688","article-title":"Passive acoustic monitoring of animal populations with transfer learning","volume":"70","author":"Dufourq","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhan, H., Hao, Z., and Gao, X. (2023). Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models. Forests, 14.","DOI":"10.3390\/f14020206"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102449","DOI":"10.1016\/j.ecoinf.2023.102449","article-title":"Towards Interpretable Learned Representations for Ecoacoustics Using Variational Auto-Encoding","volume":"80","author":"Gibb","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hilasaca, L.H., Ribeiro, M.C., and Minghim, R. (2021). Visual active learning for labeling: A case for soundscape ecology data. Information, 12.","DOI":"10.3390\/info12070265"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1111\/2041-210X.13960","article-title":"soundscape IR: A source separation toolbox for exploring acoustic diversity in soundscapes","volume":"13","author":"Sun","year":"2022","journal-title":"Methods Ecol. Evol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.ecolind.2018.03.026","article-title":"Estimating animal acoustic diversity in tropical environments using unsupervised multiresolution analysis","volume":"90","author":"Ulloa","year":"2018","journal-title":"Ecol. Indic."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101237","DOI":"10.1016\/j.ecoinf.2021.101237","article-title":"Acoustic auto-encoders for biodiversity assessment","volume":"62","author":"Rowe","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"101184","DOI":"10.1016\/j.ecoinf.2020.101184","article-title":"Soundscape segregation based on visual analysis and discriminating features","volume":"61","author":"Dias","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Best, P., Paris, S., Glotin, H., and Marxer, R. (2023). Deep audio embeddings for vocalisation clustering. PLoS ONE, 18.","DOI":"10.1101\/2023.03.10.531956"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"120089","DOI":"10.1016\/j.eswa.2023.120089","article-title":"Explainable automated anuran sound classification using improved one-dimensional local binary pattern and Tunable Q Wavelet Transform techniques","volume":"225","author":"Akbal","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"106635","DOI":"10.1016\/j.engappai.2023.106635","article-title":"Uncertainty clustering internal validity assessment using Fr\u00e9chet distance for unsupervised learning","volume":"124","author":"Rendon","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"121923","DOI":"10.1016\/j.eswa.2023.121923","article-title":"Unified embedding and clustering","volume":"238","author":"Allaoui","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e20275","DOI":"10.1016\/j.heliyon.2023.e20275","article-title":"Systematic review of machine learning methods applied to ecoacoustics and soundscape monitoring","volume":"9","year":"2023","journal-title":"Heliyon"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hershey, S., Chaudhuri, S., Ellis, D.P., Gemmeke, J.F., Jansen, A., Moore, R.C., Plakal, M., Platt, D., Saurous, R.A., and Seybold, B. (2017, January 5\u20139). CNN architectures for large-scale audio classification. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref_27","first-page":"e-910","article-title":"H\u00e1bitat y espectro ac\u00fastico como factores determinantes de la ocupaci\u00f3n de anuros neotropicales","volume":"23","author":"Bedoya","year":"2022","journal-title":"Biota Colomb."},{"key":"ref_28","first-page":"319","article-title":"Environmental sound as a mirror of landscape ecological integrity in monitoring programs","volume":"19","author":"Daza","year":"2021","journal-title":"Perspect. Ecol. Conserv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.ecolind.2016.12.018","article-title":"Automatic identification of rainfall in acoustic recordings","volume":"75","author":"Bedoya","year":"2017","journal-title":"Ecol. Indic."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"108077","DOI":"10.1016\/j.apacoust.2021.108077","article-title":"Sound-spectrogram based automatic bird species recognition using MLP classifier","volume":"180","author":"Pahuja","year":"2021","journal-title":"Appl. Acoust."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"107375","DOI":"10.1016\/j.apacoust.2020.107375","article-title":"Multispecies bioacoustic classification using transfer learning of deep convolutional neural networks with pseudo-labeling","volume":"166","author":"Zhong","year":"2020","journal-title":"Appl. Acoust."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e68837","DOI":"10.7554\/eLife.68837","article-title":"Fast and accurate annotation of acoustic signals with deep neural networks","volume":"10","author":"Steinfath","year":"2021","journal-title":"eLife"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mushtaq, Z., and Su, S.F. (2020). Efficient classification of environmental sounds through multiple features aggregation and data enhancement techniques for spectrogram images. Symmetry, 12.","DOI":"10.3390\/sym12111822"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"8463","DOI":"10.1016\/j.eswa.2015.07.002","article-title":"Audio parameterization with robust frame selection for improved bird identification","volume":"42","author":"Ventura","year":"2015","journal-title":"Expert Syst. Appl."},{"key":"ref_35","first-page":"468","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Int. Encycl. Educ."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"100145","DOI":"10.1016\/j.dche.2024.100145","article-title":"Robust reduced-order machine learning modeling of high-dimensional nonlinear processes using noisy data","volume":"11","author":"Tan","year":"2024","journal-title":"Digit. Chem. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Vincent, P., and Larochelle, H. (2008, January 5\u20139). (Denoising AE) Extracting and Composing Robust Features with Denoising. Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland.","DOI":"10.1145\/1390156.1390294"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MGRS.2018.2853555","article-title":"A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images","volume":"6","author":"Dong","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Kammoun, A., Ravier, P., and Buttelli, O. (2024). Impact of PCA Pre-Normalization Methods on Ground Reaction Force Estimation Accuracy. Sensors, 24.","DOI":"10.3390\/s24041137"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Siddique, M.F., Ahmad, Z., Ullah, N., and Kim, J. (2023). A Hybrid Deep Learning Approach: Integrating Short-Time Fourier Transform and Continuous Wavelet Transform for Improved Pipeline Leak Detection. Sensors, 23.","DOI":"10.3390\/s23198079"},{"key":"ref_41","first-page":"187","article-title":"Visualizing Data using t-SNE Laurens","volume":"219","author":"Geoffrey","year":"2008","journal-title":"Ann. Oper. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., and Melville, J. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv.","DOI":"10.21105\/joss.00861"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Urrutia, R., Espejo, D., Evens, N., S\u00fchn, T., Boese, A., Hansen, C., Fuentealba, P., Illanes, A., and Poblete, V. (2023). Clustering Methods for Vibro-Acoustic Sensing Features as a Potential Approach to Tissue Characterisation in Robot-Assisted Interventions. Sensors, 23.","DOI":"10.3390\/s23239297"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"15","DOI":"10.20982\/tqmp.09.1.p015","article-title":"The k-means clustering technique: General considerations and implementation in Mathematica","volume":"9","author":"Morissette","year":"2013","journal-title":"Tutor. Quant. Methods Psychol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"80716","DOI":"10.1109\/ACCESS.2020.2988796","article-title":"Unsupervised K-means clustering algorithm","volume":"8","author":"Sinaga","year":"2020","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Khan, A., Hao, J., Dong, Z., and Li, J. (2023). Adaptive Deep Clustering Network for Retinal Blood Vessel and Foveal Avascular Zone Segmentation. Appl. Sci., 13.","DOI":"10.3390\/app132011259"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","article-title":"K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data","volume":"322","author":"Ikotun","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, J., and Wang, J. (2023). Efficient Detection of Forest Fire Smoke in UAV Aerial Imagery Based on an Improved Yolov5 Model and Transfer Learning. Remote Sens., 15.","DOI":"10.3390\/rs15235527"},{"key":"ref_49","first-page":"320","article-title":"Comparisons Between Data Clustering Algorithms","volume":"5","year":"2008","journal-title":"Int. Arab. J. Inf. Technol."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1111\/2041-210X.13711","article-title":"scikit-maad: An open-source and modular toolbox for quantitative soundscape analysis in Python","volume":"12","author":"Ulloa","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1002\/rse2.162","article-title":"Ecoacoustics in the rain: Understanding acoustic indices under the most common geophonic source in tropical rainforests","volume":"6","author":"Bedoya","year":"2020","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"227","DOI":"10.4028\/www.scientific.net\/AMR.951.227","article-title":"Automatic method for determining cluster number based on silhouette coefficient","volume":"951","author":"Zhou","year":"2014","journal-title":"Adv. Mater. Res."},{"key":"ref_53","first-page":"2","article-title":"What do insects, anurans, birds, and mammals have to say about soundscape indices in a tropical savanna","volume":"2","author":"Ferreira","year":"2018","journal-title":"J. Ecoacoust."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/8\/2597\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:30:11Z","timestamp":1760106611000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/8\/2597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,18]]},"references-count":53,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["s24082597"],"URL":"https:\/\/doi.org\/10.3390\/s24082597","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,18]]}}}