{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T12:43:17Z","timestamp":1784292197248,"version":"3.55.0"},"reference-count":69,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":166,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["KQTD20170810150821146"],"award-info":[{"award-number":["KQTD20170810150821146"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Air pollution is a significant public concern worldwide, and accurate data\u2010driven air pollution prediction is crucial for developing alerting systems and making urban decisions. As more and more cities establish their monitoring networks, there is a pressing need for coldstart model training with limited data accumulation in new cities. However, traditional spatial\u2010temporal modeling and transfer learning schemes have been challenged under this scenario because of insufficient usage of available source data and suboptimal transferring strategy. To address these issues, we propose a meta\u2010learning\u2010based spatial\u2010temporal adaptation solution for coldstart air pollution prediction. Our approach is a model\u2010agnostic framework that enables a given backbone predictor with adaption ability across different space and time locations. Specifically, it learns a factorization of the available source data distribution and recognizes the target city as one of its components, greatly reducing the data accumulation requirement and providing coldstart capability. Furthermore, we design a novel bidirectional meta\u2010learner that can simultaneously leverage task embeddings learned from data and features constructed based on prior knowledge. We conduct comprehensive experiments on both synthetic and real\u2010world air pollution datasets of four distinct pollutants. The results demonstrate that our proposed method achieves a 5.2% lower 24\u2010hour prediction mean absolute error (MAE) than pretraining and fine\u2010tuning solutions when facing a new city with only 200\u2009hours of data, which empirically verifies the effectiveness of our approach as a coldstart training solution.<\/jats:p>","DOI":"10.1155\/2023\/3734557","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T01:35:14Z","timestamp":1686965714000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Meta\u2010Learning\u2010Based Spatial\u2010Temporal Adaption for Coldstart Air Pollution Prediction"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5646-2875","authenticated-orcid":false,"given":"Zhiyuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3250-3919","authenticated-orcid":false,"given":"Guodong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4394-2685","authenticated-orcid":false,"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"e_1_2_9_1_2","volume-title":"Ambient Air Pollution: A Global Assessment of Exposure and burden of Disease","author":"Organisation W. H.","year":"2016"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2021.129072"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"LuoZ. HuangJ. HuK. LiX. andZhangP. Accuair: winning solution to air quality prediction for kdd cup 2018 Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining June 2019 Anchorage AK USA 1842\u20131850.","DOI":"10.1145\/3292500.3330787"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosenv.2022.119347"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"e_1_2_9_7_2","article-title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","volume":"45","author":"Wang J.","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.135771"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105622"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"ZhangY. LvQ. GaoD. ShenS. DickR. P. HanniganM. andLiuQ. Multi-group encoder-decoder networks to fuse heterogeneous data for next-day air quality prediction Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19} July 2019 Macao China 4341\u20134347.","DOI":"10.24963\/ijcai.2019\/603"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"YaoH. LiuY. WeiY. TangX. andLiZ. Learning from multiple cities: a meta-learning approach for spatial-temporal prediction Proceedings of the The World Wide Web Conference August 2019 New York NY USA 2181\u20132191.","DOI":"10.1145\/3308558.3313577"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474837"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"DuY. WangJ. FengW. PanS. QinT. XuR. andWangC. Adarnn: adaptive learning and forecasting of time series Proceedings of the 30th ACM International Conference on Information & Knowledge Management November 2021 Queensland Australia 402\u2013411.","DOI":"10.1145\/3459637.3482315"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"HowardJ.andRuderS. Universal language model fine-tuning for text classification 2018 https:\/\/arxiv.org\/abs\/1801.06146.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"HospedalesT. M. AntoniouA. MicaelliP. andStorkeyA. J. Meta-learning in neural networks: a survey \u201d ieee transactions on pattern analysis and machine intelligence 2021 https:\/\/arxiv.org\/abs\/2004.05439.","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"e_1_2_9_17_2","unstructured":"GarneloM. RosenbaumD. MaddisonC. RamalhoT. SaxtonD. ShanahanM. TehY. W. RezendeD. andEslamiS. A. Conditional neural processes Proceedings of the International Conference on Machine Learning June 2018 Baltimore MA USA PMLR 1704\u20131713."},{"key":"e_1_2_9_18_2","unstructured":"FinnC. AbbeelP. andLevineS. PrecupD.andTehY. W. Model-agnostic meta-learning for fast adaptation of deep networks Proceedings of the 34th International Conference On Machine Learning Ser. Proceedings of Machine Learning Research August 2017 Baltimore MA USA 1126\u20131135."},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-1434-8_2"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"WuZ. WangY. andZhangL. Msstn: multi-scale spatial temporal network for air pollution prediction Proceedings of the IEEE International Conference on Big Data (Big Data) June 2019 Los Angeles CA USA.","DOI":"10.1109\/BigData47090.2019.9005574"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"ZhengY. YiX. LiM. LiR. ShanZ. ChangE. andLiT. Forecasting fine-grained air quality based on big data Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining December 2015 Singapore 2267\u20132276.","DOI":"10.1145\/2783258.2788573"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"ZhaoP.andZettsuK. Mastgn: multi-attention spatio-temporal graph networks for air pollution prediction Proceedings of the 2020 IEEE International Conference on Big Data (Big Data) July 2020 Manhattan New York USA 1442\u20131448.","DOI":"10.1109\/BigData50022.2020.9378156"},{"key":"e_1_2_9_23_2","volume-title":"Journal of Time Series Analysis","author":"Wilson G. T.","year":"2016"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2018.08.032"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.12.017"},{"key":"e_1_2_9_26_2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever I.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_27_2","unstructured":"TiwariA. GuptaR. andChandraR. Delhi Air Quality Prediction Using Lstm Deep Learning Models with a Focus on Covid-19 Lockdown 2021 https:\/\/arxiv.org\/abs\/2102.10551."},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"LiangY. KeS. ZhangJ. YiX. andZhengY. Geoman: multi-level attention networks for geo-sensory time series prediction Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence June 2018 Stockholm Sweden 3428\u20133434.","DOI":"10.24963\/ijcai.2018\/476"},{"key":"e_1_2_9_29_2","unstructured":"GehringJ. AuliM. GrangierD. YaratsD. andDauphinY. N. Convolutional sequence to sequence learning Proceedings of the International Conference on Machine Learning June 2017 Baltimore MA USA 1243\u20131252."},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apr.2021.101144"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"YiX. ZhangJ. WangZ. LiT. andZhengY. Deep distributed fusion network for air quality prediction Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining August 2018 New York NY USA 965\u2013973.","DOI":"10.1145\/3219819.3219822"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"ZhangJ. ZhengY. andQiD. Deep spatio-temporal residual networks for citywide crowd flows prediction Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence August 2018 San Francisco CA USA.","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"e_1_2_9_34_2","unstructured":"All\u00e9onA. JauvionG. QuennehenB. andLissmyrD. Plumenet: Large-Scale Air Quality Forecasting Using a Convolutional Lstm Network 2020 https:\/\/arxiv.org\/abs\/2006.09204."},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.2008.2005605"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"ToutouhJ. Conditional generative adversarial networks to model urban outdoor air pollution Proceedings of the Ibero-American Congress of Smart Cities May 2020 Berlin Germany 90\u2013105.","DOI":"10.1007\/978-3-030-69136-3_7"},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"LinY. MagoN. GaoY. LiY. ChiangY.-Y. ShahabiC. andAmbiteJ. L. Exploiting spatiotemporal patterns for accurate air quality forecasting using deep learning Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems November 2018 Seattle WA USA 359\u2013368.","DOI":"10.1145\/3274895.3274907"},{"key":"e_1_2_9_38_2","unstructured":"XuJ. ChenL. LvM. ZhanC. ChenS. andChangJ. Highair: a hierarchical graph neural network-based air quality forecasting method 2021 https:\/\/arxiv.org\/abs\/2101.04264."},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"YuC. MaX. RenJ. ZhaoH. andYiS. Spatio-temporal graph transformer networks for pedestrian trajectory prediction Proceedings of the European Conference on Computer Vision May 2020 Berlin Germany 507\u2013523.","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"e_1_2_9_40_2","doi-asserted-by":"crossref","unstructured":"ArangoS. P. HeinrichF. MadhusudhananK. andSchmidt-ThiemeL. Multimodal meta-learning for time series regression Proceedings of the International Workshop on Advanced Analytics and Learning on Temporal Data August 2021 Berlin Germany 123\u2013138.","DOI":"10.1007\/978-3-030-91445-5_8"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2021.1996537"},{"key":"e_1_2_9_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhazmat.2020.124753"},{"key":"e_1_2_9_43_2","doi-asserted-by":"crossref","unstructured":"WuZ. MaC. ShiX. WuL. ZhangD. TangY. andStojmenovicM. Brnn-gan: generative adversarial networks with bi-directional recurrent neural networks for multivariate time series imputation Proceedings of the 2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS) December 2021 Beijing China 217\u2013224.","DOI":"10.1109\/ICPADS53394.2021.00033"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2022.108896"},{"key":"e_1_2_9_45_2","first-page":"120","article-title":"Learning to learn: introduction and overview","volume":"78","author":"Thrun S.","year":"1998","journal-title":"Learning to Learn"},{"key":"e_1_2_9_46_2","unstructured":"FinnC. RajeswaranA. KakadeS. andLevineS. Online meta-learning Proceedings of the International Conference on Machine Learning September 2019 Baltimore MA USA 1920\u20131930."},{"key":"e_1_2_9_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"e_1_2_9_48_2","unstructured":"SchwarzJ. R.andTehY. W. Meta-learning sparse compression networks 2022 https:\/\/arxiv.org\/abs\/2205.08957."},{"key":"e_1_2_9_49_2","unstructured":"SantoroA. BartunovS. BotvinickM. WierstraD. andLillicrapT. Meta-learning with memory-augmented neural networks Proceedings of the International Conference on Machine Learning May 2016 Baltimore MA USA 1842\u20131850."},{"key":"e_1_2_9_50_2","unstructured":"KimH. MnihA. SchwarzJ. GarneloM. EslamiA. RosenbaumD. VinyalsO. andTehY. W. Attentive neural processes 2019 https:\/\/arxiv.org\/abs\/1901.05761."},{"key":"e_1_2_9_51_2","unstructured":"KaoC. H. ChiuW.-C. andChenP.-Y. Maml is a noisy contrastive learner in classification Proceedings of the International Conference on Learning Representations August 2021 Addis Ababa Ethiopia."},{"key":"e_1_2_9_52_2","unstructured":"SnellJ. SwerskyK. andZemelR. S. Prototypical networks for few-shot learning 2017 https:\/\/arxiv.org\/abs\/1703.05175."},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"LeeK. MajiS. RavichandranA. andSoattoS. Meta-learning with differentiable convex optimization Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 10657\u201310665.","DOI":"10.1109\/CVPR.2019.01091"},{"key":"e_1_2_9_54_2","unstructured":"NicholA. AchiamJ. andSchulmanJ. On first-order meta-learning algorithms 2018 https:\/\/arxiv.org\/abs\/1803.02999."},{"key":"e_1_2_9_55_2","unstructured":"RusuA. A. RaoD. SygnowskiJ. VinyalsO. PascanuR. OsinderoS. andHadsellR. Meta-learning with latent embedding optimization 2018 https:\/\/arxiv.org\/abs\/1807.05960."},{"key":"e_1_2_9_56_2","unstructured":"XuJ. TonJ.-F. KimH. KosiorekA. andTehY. W. Metafun: meta-learning with iterative functional updates Proceedings of the International Conference on Machine Learning November 2020 Beijing China."},{"key":"e_1_2_9_57_2","unstructured":"DeleuT. KanaaD. FengL. KergG. BengioY. LajoieG. andBaconP.-L. Continuous-time meta-learning with forward mode differentiation 2022 https:\/\/arxiv.org\/abs\/2203.01443."},{"key":"e_1_2_9_58_2","unstructured":"EdwardsH.andStorkeyA. Towards a neural statistician 2016 https:\/\/arxiv.org\/abs\/1606.02185."},{"key":"e_1_2_9_59_2","unstructured":"GrantE. FinnC. LevineS. DarrellT. andGriffithsT. Recasting gradient-based meta-learning as hierarchical bayes 2018 https:\/\/arxiv.org\/abs\/1801.08930."},{"key":"e_1_2_9_60_2","unstructured":"FinnC. XuK. andLevineS. Probabilistic model-agnostic meta-learning Proceedings of the 32nd International Conference On Neural Information Processing Systems June 2018 Red Hook NY USA 9537\u20139548."},{"key":"e_1_2_9_61_2","unstructured":"RaviS.andBeatsonA. Amortized bayesian meta-learning Proceedings of the International Conference on Learning Representations May 2018 Addis Ababa Ethiopia."},{"key":"e_1_2_9_62_2","unstructured":"YoonJ. KimT. DiaO. KimS. BengioY. andAhnS. Bayesian model-agnostic meta-learning Proceedings of the 32nd International Conference on Neural Information Processing Systems December 2018 Red Hook NY USA 7343\u20137353."},{"key":"e_1_2_9_63_2","article-title":"Spatio-temporal meta learning for urban traffic prediction","volume":"34","author":"Pan Z.","year":"2020","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_9_64_2","unstructured":"ZaheerM. KotturS. RavanbakhshS. PoczosB. SalakhutdinovR. andSmolaA. Deep sets 2017 https:\/\/arxiv.org\/abs\/1703.06114."},{"key":"e_1_2_9_65_2","doi-asserted-by":"crossref","unstructured":"ZhangX. LiY. ZhouX. MangoubiO. ZhangZ. FilardiV. andLuoJ. Dac-ml: domain adaptable continuous meta-learning for urban dynamics prediction Proceedings of the 2021 IEEE International Conference on Data Mining (ICDM) June 2021 Shanghai China 906\u2013915.","DOI":"10.1109\/ICDM51629.2021.00102"},{"key":"e_1_2_9_66_2","unstructured":"LeeJ. LeeY. KimJ. KosiorekA. ChoiS. andTehY. W. Set transformer: a framework for attention-based permutation-invariant neural networks Proceedings of the International Conference on Machine Learning June 2019 Long Beach CA USA 3744\u20133753."},{"key":"e_1_2_9_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(94)00114-6"},{"key":"e_1_2_9_68_2","doi-asserted-by":"crossref","unstructured":"GaoN. ZiescheH. VienN. A. VolppM. andNeumannG. What matters for meta-learning vision regression tasks? Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition November 2022 Washington DC USA 14776\u201314786.","DOI":"10.1109\/CVPR52688.2022.01436"},{"key":"e_1_2_9_69_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3734557.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3734557.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/3734557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:42:28Z","timestamp":1735623748000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/3734557"}},"subtitle":[],"editor":[{"given":"Alexander","family":"Ho\u0161ovsk\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":69,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/3734557"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3734557","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-10-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3734557"}}