{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T12:40:46Z","timestamp":1790772046042,"version":"4.1.0"},"reference-count":26,"publisher":"The Royal Society","issue":"194","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":1078,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":1078,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":1078,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/royalsociety.org\/journals\/ethics-policies\/data-sharing-mining\/"}],"funder":[{"name":"Internal Grant - Swiss Federal Institute for Forest, Snow and Landscape Research","award":["202011N2099"],"award-info":[{"award-number":["202011N2099"]}]},{"name":"Internal Grant - Swiss Federal Institute for Forest, Snow and Landscape Research","award":["202011N2099"],"award-info":[{"award-number":["202011N2099"]}]}],"content-domain":{"domain":["royalsocietypublishing.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Like many scientists, ecologists depend heavily on continuous uninterrupted data in order to understand better the object of their study. Although this might be straightforward to achieve under controlled laboratory conditions, the situation is easily complicated under field conditions where sensors and data transmission are affected by harsh weather, living organisms, changes in atmospheric conditions etc. This often results in parts of the data being corrupted or missing altogether. We propose the use of the most recent machine-learning techniques to reverse such data losses in multi-channel time series. In particular, we focus on tree stem growth data obtained from the TreeNet project, which monitors the changes in stem radius and environmental conditions of a few hundred trees across Switzerland. In the first part of the study, we test the performance of five architectures based on encoders and recurrent and convolutional neural networks, and we show that a deep neural network combining long short-term memory with one-dimensional convolutional layers performs the best. In the second part, we adopt this model to reconstruct the original TreeNet dataset, which we then use in a separate classification problem to show the effect of the proposed gap-filling procedure.<\/jats:p>","DOI":"10.1098\/rsif.2022.0349","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T03:06:14Z","timestamp":1663729574000},"update-policy":"https:\/\/doi.org\/10.1098\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Reconstructing radial stem size changes of trees with machine learning"],"prefix":"10.1098","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0694-1621","authenticated-orcid":true,"given":"Mirko","family":"Lukovi\u0107","sequence":"first","affiliation":[{"name":"Laboratory for Cellulose & Wood Materials, Group WoodTec, 8600 D\u00fcbendorf, Switzerland 1","department":["Empa, Swiss Federal Laboratories for Materials Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9438-0582","authenticated-orcid":false,"given":"Roman","family":"Zweifel","sequence":"additional","affiliation":[{"name":"8903 Birmensdorf, Switzerland 2","department":["WSL, Swiss Federal Institute for Forest, Snow and Landscape Research"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Thiry","sequence":"additional","affiliation":[{"name":"Department of Computer Science, 8092 Z\u00fcrich, Switzerland 3","department":["ETH Zurich"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, 8092 Z\u00fcrich, Switzerland 3","department":["ETH Zurich"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6900-0370","authenticated-orcid":false,"given":"Mark","family":"Schubert","sequence":"additional","affiliation":[{"name":"Laboratory for Cellulose & Wood Materials, Group WoodTec, 8600 D\u00fcbendorf, Switzerland 1","department":["Empa, Swiss Federal Laboratories for Materials Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2022,9,21]]},"reference":[{"key":"2026010520250753700_RSIF20220349C1","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1111\/nph.13995","article-title":"Are trees able to grow in periods of stem shrinkage?","volume":"211","author":"Zweifel","year":"2016","journal-title":"New Phytol."},{"key":"2026010520250753700_RSIF20220349C2","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1111\/nph.16582","article-title":"Determinants of legacy effects in pine trees \u2013 implications from an irrigation-stop experiment","volume":"227","author":"Zweifel","year":"2020","journal-title":"New Phytol."},{"key":"2026010520250753700_RSIF20220349C3","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1111\/nph.17552","article-title":"Why trees grow at night","volume":"231","author":"Zweifel","year":"2021","journal-title":"New Phytol."},{"key":"2026010520250753700_RSIF20220349C4","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1111\/ele.13933","article-title":"Number of growth days and not length of the growth period determines radial stem growth of temperate trees","volume":"25","author":"Etzold","year":"2022","journal-title":"Ecol. Lett."},{"key":"2026010520250753700_RSIF20220349C5","doi-asserted-by":"crossref","first-page":"765","DOI":"10.3390\/f12060765","article-title":"Processing and extraction of seasonal tree physiological parameters from stem radius time series","volume":"12","author":"Kn\u00fcsel","year":"2021","journal-title":"Forests"},{"key":"2026010520250753700_RSIF20220349C6","unstructured":"TreeNet. 2022https:\/\/treenet.info\/."},{"key":"2026010520250753700_RSIF20220349C7","doi-asserted-by":"crossref","first-page":"162","DOI":"10.3389\/ffgc.2021.776905","article-title":"TreeNet\u2013the biological drought and growth indicator network","volume":"4","author":"Zweifel","year":"2021","journal-title":"Front. Forests Global Change"},{"key":"2026010520250753700_RSIF20220349C8","doi-asserted-by":"crossref","first-page":"6085","DOI":"10.1038\/s41598-018-24271-9","article-title":"Recurrent neural networks for multivariate time series with missing values","volume":"8","author":"Che","year":"2018","journal-title":"Sci. Rep."},{"key":"2026010520250753700_RSIF20220349C9","unstructured":"Natkon; 2022. https:\/\/natkon.ch\/."},{"key":"2026010520250753700_RSIF20220349C10","unstructured":"Point Dendrometer ZN11-T-WP. L\u00fceholz, Switzerland; 2014. See http:\/\/natkon.ch\/wp-content\/uploads\/2017\/12\/DatasheetCollection_2017.pdf."},{"key":"2026010520250753700_RSIF20220349C11","doi-asserted-by":"crossref","first-page":"102028","DOI":"10.1016\/j.displa.2021.102028","article-title":"Image inpainting based on deep learning: a review","volume":"69","author":"Qin","year":"2021","journal-title":"Displays"},{"key":"2026010520250753700_RSIF20220349C12","doi-asserted-by":"crossref","unstructured":"Liu\n              G\n            , RedaFA, ShihKJ, WangTC, TaoA, CatanzaroB. 2018Image inpainting for irregular holes using partial convolutions. In Computer Vision \u2013 ECCV 2018 (eds V Ferrari, M Hebert, C Sminchisescu, Y Weiss), pp. 89\u2013105. Cham, Switzerland: Springer International Publishing.","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"2026010520250753700_RSIF20220349C13","volume-title":"Conservation and care of museum collections","author":"Newman","year":"2011","edition":"1st edn, p. 29"},{"key":"2026010520250753700_RSIF20220349C14","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learning Res."},{"key":"2026010520250753700_RSIF20220349C15","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2026010520250753700_RSIF20220349C16","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"2026010520250753700_RSIF20220349C17","doi-asserted-by":"crossref","unstructured":"Cho\n              K\n            , Van Merri\u00ebnboerB, GulcehreC, BahdanauD, BougaresF, SchwenkH, BengioY. 2014Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proc. of the 2014 Conf. on Empirical Methods in Natural Language Processing (EMNLP 2014), Doha, Qatar, 26\u201328 October, pp. 1724\u20131734.","DOI":"10.3115\/v1\/D14-1179"},{"key":"2026010520250753700_RSIF20220349C18","unstructured":"Baldi\n              P\n            \n          . 2012Autoencoders, unsupervised learning, and deep architectures. In Proc. of ICML Workshop on Unsupervised and Transfer Learning, Bellevue, WA, 2 July (ed. N Lawrence), vol. 27, pp. 37\u201349. Washington, DC: Machine Learning Press."},{"key":"2026010520250753700_RSIF20220349C19","unstructured":"Abadi\n              M\n            , et al.\n          2015\n          TensorFlow: large-scale machine learning on heterogeneous systems. Software available from https:\/\/www.tensorflow.org\/."},{"key":"2026010520250753700_RSIF20220349C20","doi-asserted-by":"crossref","unstructured":"He\n              K\n            , ZhangX, RenS, SunJ. 2016Deep residual learning for image recognition. In 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 27\u201330 June, pp. 770\u2013778. (doi:10.1109\/CVPR.2016.90)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026010520250753700_RSIF20220349C21","unstructured":"TensorFlow R; 2022. https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/keras\/applications\/resnet."},{"key":"2026010520250753700_RSIF20220349C22","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: a review","volume":"33","author":"Ismail Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"2026010520250753700_RSIF20220349C23","unstructured":"Fawaz\n              I\n            \n          . 2022Deep Learning for Time Series Classification. https:\/\/github.com\/hfawaz\/dl-4-tsc."},{"key":"2026010520250753700_RSIF20220349C24","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2026010520250753700_RSIF20220349C25","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"2026010520250753700_RSIF20220349C26","unstructured":"Richard\n              A\n            , FineL, RozensteinO, TannyJ, GeistM, PradalierC. 2021Filling gaps in micro-meteorological data. In Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track (eds Y Dong, G Ifrim, D Mladeni\u0107, C Saunders, S Van Hoecke), pp. 101\u2013117. Cham: Springer International Publishing."}],"container-title":["Journal of the Royal Society Interface"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsif.2022.0349","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/full-xml\/10.1098\/rsif.2022.0349","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2022.0349\/475709\/rsif.2022.0349.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2022.0349\/475709\/rsif.2022.0349.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T01:25:16Z","timestamp":1767662716000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article\/19\/194\/20220349\/65002\/Reconstructing-radial-stem-size-changes-of-trees"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":26,"journal-issue":{"issue":"194","published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1098\/rsif.2022.0349","relation":{},"ISSN":["1742-5662"],"issn-type":[{"value":"1742-5662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"assertion":[{"value":"2022-05-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-31","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"20220349"}}