{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:31:05Z","timestamp":1772119865858,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"data61"},{"DOI":"10.13039\/501100001773","name":"University of New South Wales","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001773","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>New roads are being constructed all the time. However, the capabilities of previous deep forecasting models to generalize to new roads not seen in the training data (unseen roads) are rarely explored. In this paper, we introduce a novel setup called a spatio-temporal split to evaluate the models\u2019 capabilities to generalize to unseen roads. In this setup, the models are trained on data from a sample of roads, but tested on roads not seen in the training data. Moreover, we also present a novel framework called Spatial Contrastive Pre-Training (SCPT) where we introduce a spatial encoder module to extract latent features from unseen roads during inference time. This spatial encoder is pre-trained using contrastive learning. During inference, the spatial encoder only requires two days of traffic data on the new roads and does not require any re-training. We also show that the output from the spatial encoder can be used effectively to infer latent node embeddings on unseen roads during inference time. The SCPT framework also incorporates a new layer, named the spatially gated addition layer, to effectively combine the latent features from the output of the spatial encoder to existing backbones. Additionally, since there is limited data on the unseen roads, we argue that it is better to decouple traffic signals to trivial-to-capture periodic signals and difficult-to-capture Markovian signals, and for the spatial encoder to only learn the Markovian signals. Finally, we empirically evaluated SCPT using the ST split setup on four real-world datasets. The results showed that adding SCPT to a backbone consistently improves forecasting performance on unseen roads. More importantly, the improvements are greater when forecasting further into the future. The codes are available on GitHub:<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/cruiseresearchgroup\/forecasting-on-new-roads\">https:\/\/github.com\/cruiseresearchgroup\/forecasting-on-new-roads<\/jats:ext-link>.<\/jats:p>","DOI":"10.1007\/s10618-023-00982-0","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T14:03:37Z","timestamp":1695823417000},"page":"913-937","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Traffic forecasting on new roads using spatial contrastive pre-training\u00a0(SCPT)"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0459-354X","authenticated-orcid":false,"given":"Arian","family":"Prabowo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Flora D.","family":"Salim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,27]]},"reference":[{"key":"982_CR1","unstructured":"Ahmed MS, Cook AR (1979) Analysis of Freeway Traffic Time-series Data by Using Box-Jenkins Techniques vol. 722. Transportation Research Record"},{"issue":"1","key":"982_CR2","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/T-C.1974.223784","volume":"100","author":"N Ahmed","year":"1974","unstructured":"Ahmed N, Natarajan T, Rao KR (1974) Discrete cosine transform. IEEE Trans Comput 100(1):90\u201393","journal-title":"IEEE Trans Comput"},{"key":"982_CR3","unstructured":"Baevski A, Hsu W-N, Xu Q, Babu A, Gu J, Auli M (2022) Data2vec: a general framework for self-supervised learning in speech, vision and language. arXiv preprint arXiv:2202.03555"},{"key":"982_CR4","unstructured":"Bai L, Yao L, Li C, Wang X, Wang C (2020) Adaptive graph convolutional recurrent network for traffic forecasting. In: NeurIPS"},{"key":"982_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. NeurIPS 33:1877\u20131901","journal-title":"NeurIPS"},{"key":"982_CR6","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.trc.2011.12.006","volume":"22","author":"C Chen","year":"2012","unstructured":"Chen C, Wang Y, Li L, Hu J, Zhang Z (2012) The retrieval of intra-day trend and its influence on traffic prediction. Transp Res Part C Emerg Technol 22:103\u2013118","journal-title":"Transp Res Part C Emerg Technol"},{"key":"982_CR7","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR"},{"key":"982_CR8","unstructured":"Chen M, Radford A, Child R, Wu J, Jun H, Luan D, Sutskever I (2020) Generative pretraining from pixels. In: ICML, pp. 1691\u20131703. PMLR"},{"key":"982_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102671","volume":"117","author":"Z Cui","year":"2020","unstructured":"Cui Z, Lin L, Pu Z, Wang Y (2020) Graph markov network for traffic forecasting with missing data. Transp Res Part C Emerg Technol 117:102671","journal-title":"Transp Res Part C Emerg Technol"},{"key":"982_CR10","first-page":"3844","volume":"29","author":"M Defferrard","year":"2016","unstructured":"Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. NeurIPS 29:3844\u20133852","journal-title":"NeurIPS"},{"key":"982_CR11","doi-asserted-by":"crossref","unstructured":"Fu R, Zhang Z, Li L (2016) Using lstm and gru neural network methods for traffic flow prediction. In: YAC, pp 324\u2013328. IEEE","DOI":"10.1109\/YAC.2016.7804912"},{"issue":"3","key":"982_CR12","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1061\/(ASCE)0733-947X(1995)121:3(249)","volume":"121","author":"MM Hamed","year":"1995","unstructured":"Hamed MM, Al-Masaeid HR, Said ZMB (1995) Short-term prediction of traffic volume in urban arterials. J Transp Eng 121(3):249\u2013254","journal-title":"J Transp Eng"},{"issue":"4","key":"982_CR13","first-page":"1700","volume":"14","author":"Y-S Jeong","year":"2013","unstructured":"Jeong Y-S, Byon Y-J, Castro-Neto MM, Easa SM (2013) Supervised weighting-online learning algorithm for short-term traffic flow prediction. TITS 14(4):1700\u20131707","journal-title":"TITS"},{"key":"982_CR14","doi-asserted-by":"crossref","unstructured":"Jiang R, Yin D, Wang Z, Wang Y, Deng J, Liu H, Cai Z, Deng J, Song X, Shibasaki R (2021) Dl-traff: survey and benchmark of deep learning models for urban traffic prediction. CIKM","DOI":"10.1145\/3459637.3482000"},{"issue":"1","key":"982_CR15","doi-asserted-by":"publisher","first-page":"74","DOI":"10.3141\/1857-09","volume":"1857","author":"Y Kamarianakis","year":"2003","unstructured":"Kamarianakis Y, Prastacos P (2003) Forecasting traffic flow conditions in an urban network: comparison of multivariate and univariate approaches. Transp Res Record 1857(1):74\u201384","journal-title":"Transp Res Record"},{"issue":"1","key":"982_CR16","doi-asserted-by":"publisher","first-page":"179","DOI":"10.3141\/1678-22","volume":"1678","author":"S Lee","year":"1999","unstructured":"Lee S, Fambro DB (1999) Application of subset autoregressive integrated moving average model for short-term freeway traffic volume forecasting. Transp Res Record 1678(1):179\u2013188","journal-title":"Transp Res Record"},{"key":"982_CR17","unstructured":"Liang X, Wu L, Li J, Wang Y, Meng Q, Qin T, Chen W, Zhang M, Liu T-Y (2021) R-drop: regularized dropout for neural networks. In: NeurIPS"},{"key":"982_CR18","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maji S, Koniusz P (2018) Second-order democratic aggregation. In: ECCV","DOI":"10.1007\/978-3-030-01219-9_38"},{"issue":"2","key":"982_CR19","first-page":"871","volume":"14","author":"M Lippi","year":"2013","unstructured":"Lippi M, Bertini M, Frasconi P (2013) Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning. TITS 14(2):871\u2013882","journal-title":"TITS"},{"key":"982_CR20","doi-asserted-by":"crossref","unstructured":"Liu X, Liang Y, Huang C, Zheng Y, Hooi B, Zimmermann R (2022) When do contrastive learning signals help spatio-temporal graph forecasting? In: SIGSPATIAL","DOI":"10.1145\/3557915.3560939"},{"key":"982_CR21","unstructured":"Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: ICLR"},{"key":"982_CR22","doi-asserted-by":"crossref","unstructured":"Li R, Zhong T, Jiang X, Trajcevski G, Wu J, Zhou F (2022) Mining spatio-temporal relations via self-paced graph contrastive learning. In: SIGKDD, pp. 936\u2013944","DOI":"10.1145\/3534678.3539422"},{"issue":"2","key":"982_CR23","first-page":"865","volume":"16","author":"Y Lv","year":"2014","unstructured":"Lv Y, Duan Y, Kang W, Li Z, Wang F-Y (2014) Traffic flow prediction with big data: a deep learning approach. T-ITS 16(2):865\u2013873","journal-title":"T-ITS"},{"issue":"9","key":"982_CR24","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1177\/0361198120930010","volume":"2674","author":"T Mallick","year":"2020","unstructured":"Mallick T, Balaprakash P, Rask E, Macfarlane J (2020) Graph-partitioning-based diffusion convolutional recurrent neural network for large-scale traffic forecasting. Transp Res Record 2674(9):473\u2013488","journal-title":"Transp Res Record"},{"key":"982_CR25","doi-asserted-by":"crossref","unstructured":"Manibardo EL, La\u00f1a I, Del\u00a0Ser J (2021) Deep learning for road traffic forecasting: Does it make a difference? T-ITS","DOI":"10.1109\/TITS.2021.3083957"},{"key":"982_CR26","unstructured":"Oord A.v.d, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"982_CR27","unstructured":"Prabowo A (2022) Spatiotemporal deep learning. PhD thesis, RMIT University"},{"key":"982_CR28","doi-asserted-by":"crossref","unstructured":"Prabowo A, Chen K, Xue H, Sethuvenkatraman S, Salim FD (2023) Continually learning out-of-distribution spatiotemporal data for robust energy forecasting. In: ECML PKDD. Springer","DOI":"10.1007\/978-3-031-43430-3_1"},{"key":"982_CR29","doi-asserted-by":"crossref","unstructured":"Prabowo A, Koniusz P, Shao W, Salim F (2019) Coltrane: convolutional trajectory network for deep map inference. BuildSys, p 10. Association for Computing Machinery, New York, USA","DOI":"10.1145\/3360322.3360853"},{"key":"982_CR30","doi-asserted-by":"crossref","unstructured":"Prabowo A, Shao W, Xue H, Koniusz P, Salim FD (2023) Because every sensor is unique, so is every pair: Handling dynamicity in traffic forecasting. In: IoTDI, pp 93\u2013104. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3576842.3582362"},{"key":"982_CR31","unstructured":"Prabowo A, Xue H, Shao W, Koniusz P, Salim FD (2023) Message Passing Neural Networks for Traffic Forecasting"},{"key":"982_CR32","doi-asserted-by":"crossref","unstructured":"Roth A, Liebig T (2022) Forecasting unobserved node states with spatio-temporal graph neural networks. In: Data Mining Workshops ICDMW\u201922","DOI":"10.1109\/ICDMW58026.2022.00101"},{"key":"982_CR33","unstructured":"Shang, C., Chen, J., Bi, J (2021) Discrete graph structure learning for forecasting multiple time series. In: ICLR"},{"key":"982_CR34","unstructured":"Shao H (2020) Deep learning approaches for traffic prediction. PhD thesis, Nanyang Technological University, Nanyang"},{"key":"982_CR35","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.neucom.2021.04.136","volume":"472","author":"W Shao","year":"2022","unstructured":"Shao W, Prabowo A, Zhao S, Koniusz P, Salim FD (2022) Predicting flight delay with spatio-temporal trajectory convolutional network and airport situational awareness map. Neurocomputing 472:280\u2013293","journal-title":"Neurocomputing"},{"issue":"11","key":"982_CR36","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.14778\/3551793.3551827","volume":"15","author":"Z Shao","year":"2022","unstructured":"Shao Z, Zhang Z, Wei W, Wang F, Xu Y, Cao X, Jensen CS (2022) Decoupled dynamic spatial-temporal graph neural network for traffic forecasting. Proc VLDB Endow 15(11):2733\u20132746","journal-title":"Proc VLDB Endow"},{"key":"982_CR37","doi-asserted-by":"crossref","unstructured":"Shao W, Prabowo A, Zhao S, Tan S, Koniusz P, Chan J, Hei X, Feest B, Salim FD (2019) Flight delay prediction using airport situational awareness map. SIGSPATIAL \u201919, pp 432\u2013435. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3347146.3359079"},{"key":"982_CR38","unstructured":"Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Guyon I, von Luxburg U, Bengio S, Wallach HM, Fergus R, Vishwanathan SVN, Garnett R (eds) NeurIPS, pp 4077\u20134087"},{"key":"982_CR39","first-page":"2","volume":"125","author":"A Van Den Oord","year":"2016","unstructured":"Van Den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior AW, Kavukcuoglu K (2016) Wavenet: A generative model for raw audio. SSW 125:2","journal-title":"SSW"},{"key":"982_CR40","unstructured":"van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) WaveNet: A Generative Model for Raw Audio. In: Proc. 9th ISCA workshop on speech synthesis workshop (SSW 9), p 125"},{"issue":"5","key":"982_CR41","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0968-090X(97)82903-8","volume":"4","author":"M Van Der Voort","year":"1996","unstructured":"Van Der Voort M, Dougherty M, Watson S (1996) Combining kohonen maps with arima time series models to forecast traffic flow. Transp Res Part C Emerg Technol 4(5):307\u2013318","journal-title":"Transp Res Part C Emerg Technol"},{"key":"982_CR42","unstructured":"Wang T, Isola P (2020) Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: ICML"},{"key":"982_CR43","doi-asserted-by":"crossref","unstructured":"Wang L, Koniusz P (2022) Uncertainty-dtw for time series and sequences. In: ECCV, pp 176\u2013195. Springer","DOI":"10.1007\/978-3-031-19803-8_11"},{"key":"982_CR44","doi-asserted-by":"crossref","unstructured":"Wang L, Koniusz P (2022)Temporal-viewpoint transportation plan for skeletal few-shot action recognition. In: ACCV","DOI":"10.1007\/978-3-031-26316-3_19"},{"key":"982_CR45","unstructured":"Wang L, Liu J, Koniusz P (2021) 3D skeleton-based few-shot action recognition with JEANIE is not so na\u00efve. arXiv preprint arXiv: 2112.12668"},{"issue":"1","key":"982_CR46","doi-asserted-by":"publisher","first-page":"194","DOI":"10.3141\/1776-25","volume":"1776","author":"BM Williams","year":"2001","unstructured":"Williams BM (2001) Multivariate vehicular traffic flow prediction: evaluation of arimax modeling. Transp Res Record 1776(1):194\u2013200","journal-title":"Transp Res Record"},{"issue":"6","key":"982_CR47","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1061\/(ASCE)0733-947X(2003)129:6(664)","volume":"129","author":"BM Williams","year":"2003","unstructured":"Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal arima process: theoretical basis and empirical results. J Transp Eng 129(6):664\u2013672","journal-title":"J Transp Eng"},{"key":"982_CR48","doi-asserted-by":"crossref","unstructured":"Wu Z, Pan S, Long G, Jiang J, Chang X, Zhang C (2020) Connecting the dots: multivariate time series forecasting with graph neural networks. In: SIGKDD","DOI":"10.1145\/3394486.3403118"},{"key":"982_CR49","doi-asserted-by":"crossref","unstructured":"Wu Z, Pan S, Long G, Jiang J, Zhang C (2019) Graph wavenet for deep spatial-temporal graph modeling. IJCAI","DOI":"10.24963\/ijcai.2019\/264"},{"key":"982_CR50","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? In: ICLR"},{"key":"982_CR51","doi-asserted-by":"crossref","unstructured":"Yue Z, Wang Y, Duan J, Yang T, Huang C, Tong Y, Xu B (2022) Ts2vec: towards universal representation of time series","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"982_CR52","doi-asserted-by":"crossref","unstructured":"Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: IJCAI","DOI":"10.24963\/ijcai.2018\/505"},{"key":"982_CR53","doi-asserted-by":"crossref","unstructured":"Zhang S, Luo D, Wang L, Koniusz P (2020) Few-shot object detection by second-order pooling. In: ACCV","DOI":"10.1007\/978-3-030-69538-5_23"},{"key":"982_CR54","doi-asserted-by":"crossref","unstructured":"Zhang S, Murray N, Wang L, Koniusz P (2022) Time-rEversed diffusion tensor transformer: a new TENET of few-shot object detection. In: ECCV. Springer","DOI":"10.1007\/978-3-031-20044-1_18"},{"key":"982_CR55","doi-asserted-by":"crossref","unstructured":"Zhang S, Wang L, Murray N, Koniusz P (2022) Kernelized few-shot object detection with efficient integral aggregation. In: CVPR","DOI":"10.1109\/CVPR52688.2022.01861"},{"key":"982_CR56","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhu H, Song Z, Koniusz P, King I (2022) Costa: covariance-preserving feature augmentation for graph contrastive learning. In: SIGKDD","DOI":"10.1145\/3534678.3539425"},{"key":"982_CR57","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhu H, Song Z, Koniusz P, King I (2023) Spectral feature augmentation for graph contrastive learning and beyond. In: AAAI","DOI":"10.1609\/aaai.v37i9.26336"},{"key":"982_CR58","unstructured":"Zhu H, Koniusz P (2021) Simple spectral graph convolution. In: ICLR"},{"key":"982_CR59","unstructured":"Zhu H, Koniusz P (2022) Generalized laplacian eigenmaps. NeurIPS"},{"key":"982_CR60","doi-asserted-by":"crossref","unstructured":"Zhu H, Koniusz P (2023) Transductive few-shot learning with prototype-based label propagation by iterative graph refinement. CVPR","DOI":"10.1109\/CVPR52729.2023.02298"},{"key":"982_CR61","doi-asserted-by":"crossref","unstructured":"Zhu H, Koniusz, P (2022) EASE: Unsupervised discriminant subspace learning for transductive few-shot learning. CVPR","DOI":"10.1109\/CVPR52688.2022.00887"},{"key":"982_CR62","unstructured":"Zhu H, Sun K, Koniusz P (2021) Contrastive laplacian eigenmaps. NeurIPS"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00982-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-023-00982-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00982-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:42:45Z","timestamp":1730191365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-023-00982-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,27]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["982"],"URL":"https:\/\/doi.org\/10.1007\/s10618-023-00982-0","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,27]]},"assertion":[{"value":"29 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that this research was supported by the Data61\/CSIRO PhD scholarship, RMIT Research Stipend Scholarship (RRSS), and the Australian Government RTP Scholarship. We would like to also acknowledge the support of the Investigative Analytics team (Data61\/CSIRO) and Cisco\u2019s National Industry Innovation Network (NIIN) Research Chair Program. The research utilized computing resources and services provided by Gadi, supercomputer of the National Computational Infrastructure (NCI) supported by the Australian Government, and Bracewell, supercomputer of the Commonwealth Scientific and Industrial Research Organisation (CSIRO).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}