{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:59:45Z","timestamp":1793044785384,"version":"4.5.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011589","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000}}],"reference-count":54,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S023291\/1"],"award-info":[{"award-number":["EP\/S023291\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Neural Cellular Automata (NCA) are a powerful combination of machine learning and mechanistic modelling. We train NCA to learn complex dynamics from time series of images and Partial Differential Equation (PDE) trajectories. Our method is designed to identify underlying local rules that govern large scale dynamic emergent behaviours. Previous work on NCA focuses on learning rules that give stationary emergent structures. We extend NCA to capture both transient and stable structures within the same system, as well as learning rules that capture the dynamics of Turing pattern formation in nonlinear PDEs. We demonstrate that NCA can generalise very well beyond their PDE training data, we show how to constrain NCA to respect given symmetries, and we explore the effects of associated hyperparameters on model performance and stability. Being able to learn arbitrary dynamics gives NCA great potential as a data driven modelling framework, especially for modelling biological pattern formation.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011589","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T13:39:56Z","timestamp":1714138796000},"page":"e1011589","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning spatio-temporal patterns with Neural Cellular Automata"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9721-1020","authenticated-orcid":true,"given":"Alex D.","family":"Richardson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tibor","family":"Antal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8160-5068","authenticated-orcid":true,"given":"Richard A.","family":"Blythe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0797-3406","authenticated-orcid":true,"given":"Linus J.","family":"Schumacher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"issue":"3","key":"pcbi.1011589.ref001","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1080\/10919392.2020.1748977","article-title":"Emergence phenomena in self-organizing systems: a systematic literature review of concepts, researches, and future prospects","volume":"30","author":"S Kalantari","year":"2020","journal-title":"Journal of Organizational Computing and Electronic Commerce"},{"issue":"4","key":"pcbi.1011589.ref002","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/scientificamerican1070-120","article-title":"Mathematical Games","volume":"223","author":"M Gardner","year":"1970","journal-title":"Scientific American"},{"issue":"1","key":"pcbi.1011589.ref003","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1145\/349194.349202","article-title":"A Brief History of Cellular Automata","volume":"32","author":"P Sarkar","year":"2000","journal-title":"ACM Comput Surv"},{"issue":"6","key":"pcbi.1011589.ref004","first-page":"475","article-title":"A Bibliographic Review of Cellular Automaton Publications in the Last 50 Years","volume":"12","author":"Y Zhuang","year":"2017","journal-title":"Journal of Cellular Automata"},{"issue":"7649","key":"pcbi.1011589.ref005","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nature22031","article-title":"A living mesoscopic cellular automaton made of skin scales","volume":"544","author":"L Manukyan","year":"2017","journal-title":"Nature"},{"issue":"1","key":"pcbi.1011589.ref006","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-22525-1","article-title":"Reaction-diffusion in a growing 3D domain of skin scales generates a discrete cellular automaton","volume":"12","author":"A Fofonjka","year":"2021","journal-title":"Nature Communications"},{"key":"pcbi.1011589.ref007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.pbiomolbio.2018.04.007","article-title":"A threshold model for polydactyly","volume":"137","author":"A Lange","year":"2018","journal-title":"Progress in Biophysics and Molecular Biology"},{"issue":"52","key":"pcbi.1011589.ref008","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1098\/rsif.2010.0071","article-title":"Cellular automata and integrodifferential equation models for cell renewal in mosaic tissues","volume":"7","author":"JM Bloomfield","year":"2010","journal-title":"Journal of The Royal Society Interface"},{"key":"pcbi.1011589.ref009","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.semcancer.2014.03.003","article-title":"Cancer systems biology and modeling: Microscopic scale and multiscale approaches","volume":"30","author":"A Masoudi-Nejad","year":"2015","journal-title":"Seminars in Cancer Biology"},{"issue":"4","key":"pcbi.1011589.ref010","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.progress.2008.05.002","article-title":"Strategies for landscape ecology: An application using cellular automata models","volume":"70","author":"EA Silva","year":"2008","journal-title":"Progress in Planning"},{"key":"pcbi.1011589.ref011","article-title":"Growing Neural Cellular Automata","author":"A Mordvintsev","year":"2020","journal-title":"Distill"},{"issue":"7553","key":"pcbi.1011589.ref012","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pcbi.1011589.ref013","doi-asserted-by":"crossref","unstructured":"Mordvintsev A, Niklasson E. microNCA: Texture Generation with Ultra-Compact Neural Cellular Automata. 2021.","DOI":"10.1162\/isal_a_00461"},{"issue":"1","key":"pcbi.1011589.ref014","doi-asserted-by":"crossref","DOI":"10.1002\/widm.1391","article-title":"A historical perspective of explainable Artificial Intelligence","volume":"11","author":"R Confalonieri","year":"2021","journal-title":"Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery"},{"issue":"5","key":"pcbi.1011589.ref015","doi-asserted-by":"crossref","DOI":"10.1002\/widm.1424","article-title":"Explainable artificial intelligence: an analytical review","volume":"11","author":"PP Angelov","year":"2021","journal-title":"Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery"},{"issue":"641","key":"pcbi.1011589.ref016","first-page":"37","article-title":"The chemical basis of morphogenesis","volume":"237","year":"1952","journal-title":"Philosophical Transactions of the Royal Society of London Series B, Biological Sciences"},{"issue":"5118","key":"pcbi.1011589.ref017","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1126\/science.261.5118.189","article-title":"Complex Patterns in a Simple System","volume":"261","author":"JE Pearson","year":"1993","journal-title":"Science"},{"key":"pcbi.1011589.ref018","unstructured":"et al MA. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems; 2015. Available from: https:\/\/www.tensorflow.org\/."},{"key":"pcbi.1011589.ref019","doi-asserted-by":"crossref","unstructured":"Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions; 2016. Available from: https:\/\/arxiv.org\/abs\/1610.02357.","DOI":"10.1109\/CVPR.2017.195"},{"issue":"3","key":"pcbi.1011589.ref020","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.100.032402","article-title":"Cellular automata as convolutional neural networks","volume":"100","author":"W Gilpin","year":"2019","journal-title":"Physical Review E"},{"key":"pcbi.1011589.ref021","doi-asserted-by":"crossref","unstructured":"Mordvintsev A, Randazzo E, Fouts C. Growing Isotropic Neural Cellular Automata; 2022. Available from: https:\/\/arxiv.org\/abs\/2205.01681.","DOI":"10.1162\/isal_a_00552"},{"key":"pcbi.1011589.ref022","doi-asserted-by":"crossref","unstructured":"Alom MZ, Hasan M, Yakopcic C, Taha TM, Asari VK. Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation; 2018.","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"pcbi.1011589.ref023","doi-asserted-by":"crossref","first-page":"100379","DOI":"10.1016\/j.cosrev.2021.100379","article-title":"A survey on deep learning and its applications","volume":"40","author":"S Dong","year":"2021","journal-title":"Computer Science Review"},{"issue":"3-4","key":"pcbi.1011589.ref024","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/S0925-2312(97)00161-6","article-title":"Discrete time recurrent neural network architectures: A unifying review","volume":"15","author":"AC Tsoi","year":"1997","journal-title":"Neurocomputing"},{"key":"pcbi.1011589.ref025","unstructured":"Masters D, Luschi C. Revisiting Small Batch Training for Deep Neural Networks; 2018."},{"key":"pcbi.1011589.ref026","unstructured":"Brownlee J. A gentle introduction to mini-batch gradient descent and how to configure batch size; 2019. Available from: https:\/\/machinelearningmastery.com\/gentle-introduction-mini-batch-gradient-descent-configure-batch-size\/."},{"key":"pcbi.1011589.ref027","unstructured":"Hellinger distance\u2014Encyclopedia of Mathematics. Hellinger distance\u2014Encyclopedia of Mathematics;."},{"key":"pcbi.1011589.ref028","unstructured":"Bhattacharyya distance\u2014Encyclopedia of Mathematics. Bhattacharyya distance\u2014Encyclopedia of Mathematics;."},{"key":"pcbi.1011589.ref029","doi-asserted-by":"crossref","unstructured":"Villani C. In: The Wasserstein distances. Berlin, Heidelberg: Springer Berlin Heidelberg; 2009. p. 93\u2013111. Available from: https:\/\/doi.org\/10.1007\/978-3-540-71050-9_6.","DOI":"10.1007\/978-3-540-71050-9_6"},{"key":"pcbi.1011589.ref030","article-title":"Self-Organising Textures","author":"E Niklasson","year":"2021","journal-title":"Distill"},{"key":"pcbi.1011589.ref031","doi-asserted-by":"crossref","unstructured":"Heitz E, Vanhoey K, Chambon T, Belcour L. A Sliced Wasserstein Loss for Neural Texture Synthesis. 2020.","DOI":"10.1109\/CVPR46437.2021.00929"},{"key":"pcbi.1011589.ref032","article-title":"Wasserstein Generative Models for Patch-based Texture Synthesis","author":"A Houdard","year":"2020","journal-title":"CoRR"},{"key":"pcbi.1011589.ref033","unstructured":"Kaul H, Zandstra PW. GARMEN: GRN Agent-based Reaction-Diffusion Modeling Environment. 2022."},{"issue":"10","key":"pcbi.1011589.ref034","doi-asserted-by":"crossref","first-page":"e3000498","DOI":"10.1371\/journal.pbio.3000498","article-title":"Dissecting the dynamics of signaling events in the BMP, WNT, and NODAL cascade during self-organized fate patterning in human gastruloids","volume":"17","author":"S Chhabra","year":"2019","journal-title":"PLOS Biology"},{"issue":"2","key":"pcbi.1011589.ref035","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.ecolmodel.2009.09.011","article-title":"Pattern formation of a predator\u2013prey system with Ivlev-type functional response","volume":"221","author":"W Wang","year":"2010","journal-title":"Ecological Modelling"},{"issue":"2213","key":"pcbi.1011589.ref036","article-title":"Studies of Turing pattern formation in zebrafish skin","volume":"379","author":"S Kondo","year":"2021","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"key":"pcbi.1011589.ref037","unstructured":"Dozat T. Incorporating Nesterov Momentum into Adam; 2016."},{"key":"pcbi.1011589.ref038","unstructured":"Kingma DP, Ba J. Adam: A Method for Stochastic Optimization; 2014. Available from: https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"pcbi.1011589.ref039","doi-asserted-by":"crossref","unstructured":"Xie X, Zhou P, Li H, Lin Z, Yan S. Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models; 2023.","DOI":"10.1109\/TPAMI.2024.3423382"},{"key":"pcbi.1011589.ref040","unstructured":"A.3 Normalized Gradient Descent\u2014jermwatt.github.io;. https:\/\/jermwatt.github.io\/machine_learning_refined\/notes\/3_First_order_methods\/3_9_Normalized.html."},{"issue":"5","key":"pcbi.1011589.ref041","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11538-021-00870-y","article-title":"Bespoke Turing Systems","volume":"83","author":"TE Woolley","year":"2021","journal-title":"Bulletin of Mathematical Biology"},{"key":"pcbi.1011589.ref042","unstructured":"Greydanus S. Studying Growth with Neural Cellular Automata;. https:\/\/greydanus.github.io\/2022\/05\/24\/studying-growth\/."},{"key":"pcbi.1011589.ref043","unstructured":"Mainakdeb. text-2-cellular-automata: Neural cellular automata + clip;. https:\/\/github.com\/Mainakdeb\/text-2-cellular-automata."},{"key":"pcbi.1011589.ref044","unstructured":"Petersen M. Neural-Cellular-Automata-Image-Manipulation;. https:\/\/github.com\/MagnusPetersen\/Neural-Cellular-Automata-Image-Manipulation."},{"key":"pcbi.1011589.ref045","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, et al. Learning Transferable Visual Models From Natural Language Supervision; 2021."},{"issue":"7626","key":"pcbi.1011589.ref046","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"A Graves","year":"2016","journal-title":"Nature"},{"issue":"3","key":"pcbi.1011589.ref047","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/s11047-013-9370-0","article-title":"Amorphous computing: examples, mathematics and theory","volume":"12","author":"WR Stark","year":"2013","journal-title":"Natural Computing"},{"issue":"3","key":"pcbi.1011589.ref048","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1081\/CBI-100103961","article-title":"Biological timing and the clock metaphor: Oscillatory and hourglass mechanisms","volume":"18","author":"L Rensing","year":"2001","journal-title":"Chronobiology International"},{"issue":"15","key":"pcbi.1011589.ref049","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"SL Brunton","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"pcbi.1011589.ref050","doi-asserted-by":"crossref","unstructured":"Folkestad C, Pastor D, Mezic I, Mohr R, Fonoberova M, Burdick J. Extended Dynamic Mode Decomposition with Learned Koopman Eigenfunctions for Prediction and Control; 2020.","DOI":"10.23919\/ACC45564.2020.9147729"},{"key":"pcbi.1011589.ref051","doi-asserted-by":"crossref","unstructured":"Matas-Gil A, Endres RG. Unraveling biochemical spatial patterns: machine learning approaches to the inverse problem of Turing patterns. 2023;.","DOI":"10.1016\/j.isci.2024.109822"},{"key":"pcbi.1011589.ref052","unstructured":"Foret P, Kleiner A, Mobahi H, Neyshabur B. Sharpness-Aware Minimization for Efficiently Improving Generalization. 2020;."},{"key":"pcbi.1011589.ref053","unstructured":"Blalock D, Ortiz JJG, Frankle J, Guttag J. What is the State of Neural Network Pruning?; 2020."},{"key":"pcbi.1011589.ref054","doi-asserted-by":"crossref","unstructured":"Yang H, Tang M, Wen W, Yan F, Hu D, Li A, et al. Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification; 2020.","DOI":"10.1109\/CVPRW50498.2020.00347"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011589","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T23:39:19Z","timestamp":1731800359000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011589"}},"subtitle":[],"editor":[{"given":"Julio R.","family":"Banga","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":54,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011589","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]}}}