{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T10:50:04Z","timestamp":1778669404089,"version":"3.51.4"},"reference-count":68,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2020,6,19]],"date-time":"2020-06-19T00:00:00Z","timestamp":1592524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020","doi-asserted-by":"publisher","award":["654462"],"award-info":[{"award-number":["654462"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["254711"],"award-info":[{"award-number":["254711"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The world\u2019s oceans are under stress from climate change, acidification and other human activities, and the UN has declared 2021\u20132030 as the decade for marine science. To monitor the marine waters, with the purpose of detecting discharges of tracers from unknown locations, large areas will need to be covered with limited resources. To increase the detectability of marine gas seepage we propose a deep probabilistic learning algorithm, a Bayesian Convolutional Neural Network (BCNN), to classify time series of measurements. The BCNN will classify time series to belong to a leak\/no-leak situation, including classification uncertainty. The latter is important for decision makers who must decide to initiate costly confirmation surveys and, hence, would like to avoid false positives. Results from a transport model are used for the learning process of the BCNN and the task is to distinguish the signal from a leak hidden within the natural variability. We show that the BCNN classifies time series arising from leaks with high accuracy and estimates its associated uncertainty. We combine the output of the BCNN model, the posterior predictive distribution, with a Bayesian decision rule showcasing how the framework can be used in practice to make optimal decisions based on a given cost function.<\/jats:p>","DOI":"10.3390\/a13060145","type":"journal-article","created":{"date-parts":[[2020,6,19]],"date-time":"2020-06-19T10:43:58Z","timestamp":1592563438000},"page":"145","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Binary Time Series Classification with Bayesian Convolutional Neural Networks When Monitoring for Marine Gas Discharges"],"prefix":"10.3390","volume":"13","author":[{"given":"Kristian","family":"Gundersen","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Bergen, 5020 Bergen, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5757-4345","authenticated-orcid":false,"given":"Guttorm","family":"Alendal","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Bergen, 5020 Bergen, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Oleynik","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Bergen, 5020 Bergen, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9489-1657","authenticated-orcid":false,"given":"Nello","family":"Blaser","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Bergen, 5020 Bergen, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1038\/nature11397","article-title":"An index to assess the health and benefits of the global ocean","volume":"488","author":"Halpern","year":"2012","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.marpol.2016.06.023","article-title":"Marine Spatial Planning advancing the Ecosystem-Based Approach to coastal zone management: A review","volume":"72","author":"Metternicht","year":"2016","journal-title":"Mar. Policy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1007\/s10236-011-0393-8","article-title":"Numerical modelling of organic waste dispersion from fjord located fish farms","volume":"61","author":"Ali","year":"2011","journal-title":"Ocean Dyn."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.marenvres.2015.11.006","article-title":"How can we quantify impacts of contaminants in marine ecosystems? The ICON project","volume":"24","author":"Hylland","year":"2017","journal-title":"Mar. Environ. Res."},{"key":"ref_5","first-page":"1","article-title":"Global Warming of 1.5 \u2218C an IPCC Special Report on the Impacts of Global Warming of 1.5 \u2218C above Pre-Industrial Levels and Related Global Greenhouse Gas Emission Pathways, in the Context of Strengthening the Global Response to the Threat of Climate Change","volume":"1","author":"First","year":"2019","journal-title":"Sustain. Dev. Efforts Eradicate Poverty"},{"key":"ref_6","unstructured":"Agency, I.E. (2018). Global Energy & CO2 Status Report, IEA. Technical Report."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3935","DOI":"10.1007\/s12665-013-2883-0","article-title":"Impacts of the use of the geological subsurface for energy storage: An investigation concept","volume":"70","author":"Bauer","year":"2013","journal-title":"Environ. Earth Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.ijggc.2014.10.004","article-title":"Marine baseline and monitoring strategies for carbon dioxide capture and storage (CCS)","volume":"38","author":"Blackford","year":"2015","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.ijggc.2015.05.032","article-title":"Developments since 2005 in understanding potential environmental impacts of {CO2} leakage from geological storage","volume":"40","author":"Jones","year":"2015","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1142\/S0219622006002258","article-title":"10 challenging problems in data mining research","volume":"5","author":"Yang","year":"2006","journal-title":"Int. J. Inf. Technol. Decis. Mak."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/2379776.2379788","article-title":"Time-series data mining","volume":"45","author":"Esling","year":"2012","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1007\/s10618-016-0483-9","article-title":"The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances","volume":"31","author":"Bagnall","year":"2017","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_13","unstructured":"Berndt, D.J., and Clifford, J. (1994). Using Dynamic Time Warping to Find Patterns in Time Series, KDD Workshop."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ratanamahatana, C.A., and Keogh, E. (2005, January 21\u201323). Three myths about dynamic time warping data mining. Proceedings of the 2005 SIAM International Conference on Data Mining, SIAM, Newport Beach, CA, USA.","DOI":"10.1137\/1.9781611972757.50"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s00357-013-9135-6","article-title":"A run length transformation for discriminating between auto regressive time series","volume":"31","author":"Bagnall","year":"2014","journal-title":"J. Classif."},{"key":"ref_16","unstructured":"Smyth, P. (2020, June 01). Clustering Sequences with Hidden Markov Models. Available online: http:\/\/papers.nips.cc\/paper\/1217-clustering-sequences-with-hidden-markov-models.pdf."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/34.735807","article-title":"Bayesian classification with Gaussian processes","volume":"20","author":"Williams","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1111\/1467-9868.00297","article-title":"Functional linear discriminant analysis for irregularly sampled curves","volume":"63","author":"James","year":"2001","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1198\/00401700152404273","article-title":"A functional data\u2014Analytic approach to signal discrimination","volume":"43","author":"Hall","year":"2001","journal-title":"Technometrics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2522","DOI":"10.1109\/TKDE.2015.2416723","article-title":"Time-series classification with COTE: The collective of transformation-based ensembles","volume":"27","author":"Bagnall","year":"2015","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lines, J., Taylor, S., and Bagnall, A. (2018). Time Series Classification with HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles. ACM Trans. Knowl. Discov. Data, 12.","DOI":"10.1145\/3182382"},{"key":"ref_22","first-page":"1","article-title":"Deep learning for time series classification: A review","volume":"33","author":"Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Liu, Q., Chen, E., Ge, Y., and Zhao, J.L. (2014, January 16\u201318). Time series classification using multi-channels deep convolutional neural networks. Proceedings of the International Conference on Web-Age Information Management, Macau, China.","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yan, W., and Oates, T. (2017, January 14\u201319). Time series classification from scratch with deep neural networks: A strong baseline. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0925-2312(01)00706-8","article-title":"Recurrent neural networks for time series classification","volume":"50","author":"Stagge","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","article-title":"A Practical Bayesian Framework for Backpropagation Networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3607","DOI":"10.1016\/j.egypro.2017.03.1492","article-title":"Using Bayes Theorem to Quantify and Reduce Uncertainties when Monitoring Varying Marine Environments for Indications of a Leak","volume":"114","author":"Alendal","year":"2017","journal-title":"Energy Procedia"},{"key":"ref_28","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_29","unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., and Wierstra, D. (2015). Weight uncertainty in neural networks. arXiv."},{"key":"ref_30","unstructured":"Shridhar, K., Laumann, F., and Liwicki, M. (2019). A comprehensive guide to bayesian convolutional neural network with variational inference. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"17816","DOI":"10.1038\/s41598-017-17876-z","article-title":"Leveraging uncertainty information from deep neural networks for disease detection","volume":"7","author":"Leibig","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"22812","DOI":"10.1109\/ACCESS.2020.2970023","article-title":"Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks","volume":"8","author":"Abideen","year":"2020","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kendall, A., and Cipolla, R. (2016, January 16\u201321). Modelling uncertainty in deep learning for camera relocalization. Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden.","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Malde, K., Handegard, N.O., Eikvil, L., and Salberg, A.B. (2019). Machine intelligence and the data-driven future of marine science. ICES J. Mar. Sci.","DOI":"10.1093\/icesjms\/fsz057"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1016\/j.apr.2016.12.014","article-title":"Recursive neural network model for analysis and forecast of PM10 and PM2.5","volume":"8","author":"Biancofiore","year":"2017","journal-title":"Atmos. Pollut. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1080\/10962247.2018.1459956","article-title":"Forecasting air quality time series using deep learning","volume":"68","author":"Freeman","year":"2018","journal-title":"J. Air Waste Manag. Assoc."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Denison, D.D., Hansen, M.H., Holmes, C.C., Mallick, B., and Yu, B. (2003). Environmental Monitoring Using a Time Series of Satellite Images and Other Spatial Data Sets. Nonlinear Estimation and Classification, Springer.","DOI":"10.1007\/978-0-387-21579-2"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1080\/07038992.2014.987376","article-title":"Forest Monitoring Using Landsat Time Series Data: A Review","volume":"40","author":"Banskota","year":"2014","journal-title":"Can. J. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ijggc.2017.06.020","article-title":"Monitoring of offshore geological carbon storage integrity: Implications of natural variability in the marine system and the assessment of anomaly detection criteria","volume":"64","author":"Blackford","year":"2017","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.jmarsys.2006.01.018","article-title":"Modelling the hydrodynamics and ecosystem of the North-West European continental shelf for operational oceanography","volume":"65","author":"Siddorn","year":"2007","journal-title":"J. Mar. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1029\/1999JC000290","article-title":"Two-phase, near-field modeling of purposefully released CO2 in the ocean","volume":"106","author":"Alendal","year":"2001","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Dewar, M., Sellami, N., and Chen, B. (2014). Dynamics of rising CO2 bubble plumes in the QICS field experiment. Int. J. Greenh. Gas Control.","DOI":"10.1016\/j.ijggc.2014.11.003"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1002\/2015JC011198","article-title":"Simulating spatial and temporal varying CO2 signals from sources at the seafloor to help designing risk-based monitoring programs","volume":"121","author":"Ali","year":"2016","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"102949","DOI":"10.1016\/j.ijggc.2019.102949","article-title":"Impact and detectability of hypothetical CCS offshore seep scenarios as an aid to storage assurance and risk assessment","volume":"95","author":"Blackford","year":"2020","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1016\/j.marpetgeo.2015.07.030","article-title":"Quantification of methane emissions at abandoned gas wells in the Central North Sea","volume":"68","author":"Karstens","year":"2015","journal-title":"Mar. Pet. Geol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_47","unstructured":"Chen, C. (2012). An Unstructured-Grid, Finite-Volume Community Ocean Model: FVCOM User Manual, Sea Grant College Program, Massachusetts Institute of Technology."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.5194\/gmd-9-1293-2016","article-title":"ERSEM 15.06: A generic model for marine biogeochemistry and the ecosystem dynamics of the lower trophic levels","volume":"9","author":"Clark","year":"2016","journal-title":"Geosci. Model Dev."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"109278","DOI":"10.1016\/j.jcp.2020.109278","article-title":"Using deep learning to extend the range of air pollution monitoring and forecasting","volume":"408","author":"Monteil","year":"2020","journal-title":"J. Comput. Phys."},{"key":"ref_50","first-page":"1","article-title":"Deep neural networks motivated by partial differential equations","volume":"62","author":"Ruthotto","year":"2019","journal-title":"J. Math. Imaging Vis."},{"key":"ref_51","unstructured":"Gal, Y. (2016). Uncertainty in Deep Learning. [Ph.D. Thesis, University of Cambridge]."},{"key":"ref_52","unstructured":"Gal, Y., and Ghahramani, Z. (2015). Bayesian convolutional neural networks with Bernoulli approximate variational inference. arXiv."},{"key":"ref_53","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_54","first-page":"1","article-title":"An introduction to the bootstrap","volume":"57","author":"Tibshirani","year":"1993","journal-title":"Monogr. Stat. Appl. Probab."},{"key":"ref_55","unstructured":"Berger, J.O. (2013). Statistical Decision Theory and Bayesian Analysis, Springer Science & Business Media."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Cazenave, P., Blackford, J., and Artioli, Y. (2018, January 21\u201326). Regional Modelling to Inform the Design of Sub-Sea CO2 Storage Monitoring Networks. Proceedings of the 14th Greenhouse Gas Control Technologies Conference Melbourne, Melbourne, Australia.","DOI":"10.2139\/ssrn.3366246"},{"key":"ref_57","unstructured":"Riebesell, U., Fabry, V.J., Hansson, L., and Gattuso, J.P. (2011). Guide to Best Practices for Ocean Acidification Research and Data Reporting."},{"key":"ref_58","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.artint.2014.02.004","article-title":"The dropout learning algorithm","volume":"210","author":"Baldi","year":"2014","journal-title":"Artif. Intell."},{"key":"ref_60","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.ijggc.2015.03.013","article-title":"Layout of CCS monitoring infrastructure with highest probability of detecting a footprint of a CO2 leak in a varying marine environment","volume":"37","author":"Hvidevold","year":"2015","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.ijggc.2015.05.010","article-title":"Coastal monitoring strategy for geochemical detection of fugitive CO2 seeps from the seabed","volume":"39","author":"Greenwood","year":"2015","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.envsoft.2016.06.006","article-title":"Survey strategies to quantify and optimize detecting probability of a CO2 seep in a varying marine environment","volume":"83","author":"Hvidevold","year":"2016","journal-title":"Environ. Model. Softw."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"5458","DOI":"10.1002\/2016JC012655","article-title":"Cost efficient environmental survey paths for detecting continuous tracer discharges","volume":"122","author":"Alendal","year":"2017","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"102951","DOI":"10.1016\/j.ijggc.2019.102951","article-title":"Optimal sensors placement for detecting CO2 discharges from unknown locations on the seafloor","volume":"95","author":"Oleynik","year":"2020","journal-title":"Int. J. Greenh. Gas Control"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1002\/lno.10037","article-title":"The effect of submarine CO2 vents on seawater: Implications for detection of subsea Carbon sequestration leakage","volume":"60","author":"Botnen","year":"2015","journal-title":"Limnol. Oceanogr."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/MCI.2011.940751","article-title":"Anomaly detection in environmental monitoring networks [application notes]","volume":"6","author":"Bezdek","year":"2011","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"161","DOI":"10.3153\/AR19014","article-title":"Machine learning applications in oceanography","volume":"2","author":"Ahmad","year":"2019","journal-title":"Aquat. Res."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/6\/145\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:40:40Z","timestamp":1760175640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/6\/145"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,19]]},"references-count":68,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["a13060145"],"URL":"https:\/\/doi.org\/10.3390\/a13060145","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,19]]}}}