A novel spatial–temporal generative autoencoder for wind speed uncertainty forecasting
Wind speed interval prediction is one of the most long-standing challenges because of the high uncertainty and the complex spatial–temporal correlation between wind turbines. In this paper, based on variational Bayesian inference, we propose a novel spatial–temporal generative autoencoder (STGAE) mo...
Saved in:
| Published in: | Energy (Oxford) Vol. 282; p. 128946 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
01.11.2023
|
| Subjects: | |
| ISSN: | 0360-5442 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Wind speed interval prediction is one of the most long-standing challenges because of the high uncertainty and the complex spatial–temporal correlation between wind turbines. In this paper, based on variational Bayesian inference, we propose a novel spatial–temporal generative autoencoder (STGAE) model to capture the continuous probability distribution of each wind turbine on an arbitrary graph structure. In the encoding process, a parameterization strategy is used to expand the hypothesis space of the adjacency matrix rather than being limited by the distance between nodes. The multiple graph convolution layers with kernels approximated by Chebyshev polynomials adjust the collecting scope of spatial information. The bi-directional dependency is modeled by the multi-head attention to tap correlations of different time horizons effectively. The interval prediction at each node is yielded based on the probability densities of generated samples produced by the decoder. Using publicly available wind data from the Global Energy Forecasting Competition 2014, numerical experiments are conducted to compare the prediction reliability and accuracy between the proposed model and the recent state-of-the-art models. The forecasting results suggest that the proposed model significantly improves performance, especially the strong generalization ability makes it practical under different weather conditions. |
|---|---|
| AbstractList | Wind speed interval prediction is one of the most long-standing challenges because of the high uncertainty and the complex spatial–temporal correlation between wind turbines. In this paper, based on variational Bayesian inference, we propose a novel spatial–temporal generative autoencoder (STGAE) model to capture the continuous probability distribution of each wind turbine on an arbitrary graph structure. In the encoding process, a parameterization strategy is used to expand the hypothesis space of the adjacency matrix rather than being limited by the distance between nodes. The multiple graph convolution layers with kernels approximated by Chebyshev polynomials adjust the collecting scope of spatial information. The bi-directional dependency is modeled by the multi-head attention to tap correlations of different time horizons effectively. The interval prediction at each node is yielded based on the probability densities of generated samples produced by the decoder. Using publicly available wind data from the Global Energy Forecasting Competition 2014, numerical experiments are conducted to compare the prediction reliability and accuracy between the proposed model and the recent state-of-the-art models. The forecasting results suggest that the proposed model significantly improves performance, especially the strong generalization ability makes it practical under different weather conditions. |
| ArticleNumber | 128946 |
| Author | Shi, Huifeng Ma, Long Huang, Ling |
| Author_xml | – sequence: 1 givenname: Long surname: Ma fullname: Ma, Long – sequence: 2 givenname: Ling surname: Huang fullname: Huang, Ling – sequence: 3 givenname: Huifeng surname: Shi fullname: Shi, Huifeng |
| BookMark | eNp9kL1OwzAUhT0UibbwBgwZWRL8Fydhqyr-pEosILFZrnNdpUrtYDtF3XgH3pAnIVGYGJiudM_5zvAt0Mw6CwhdEZwRTMTNPgMLfnfKKKYsI7SsuJihOWYCpznn9BwtQthjjPOyqubobZVYd4Q2CZ2KjWq_P78iHDrnVZvsxqXhe4RE9dGB1a4Gnxjnk4_G1gMCUCe91eCjamw8jRFoFWJjdxfozKg2wOXvXaLX-7uX9WO6eX54Wq82qWasimluaFUVqmC4LKhmoI0wnKqCC0MoMF1xU6ha5QBYYF5vmWIlLUWxFUYMsWFLdD3tdt699xCiPDRBQ9sqC64PkpGckUpQmg9VPlW1dyF4MLLzzUH5kyRYjvLkXk7y5ChPTvIG7PYPpps4aHE2etW0_8M_s9p_UA |
| CitedBy_id | crossref_primary_10_1007_s42835_025_02353_9 crossref_primary_10_1109_TSTE_2025_3543420 crossref_primary_10_1016_j_segan_2024_101591 crossref_primary_10_1016_j_energy_2024_131590 crossref_primary_10_1016_j_jweia_2024_105875 |
| Cites_doi | 10.1016/j.energy.2022.124095 10.1109/TPWRS.2013.2287871 10.1016/j.renene.2010.06.049 10.1016/j.ijforecast.2015.11.007 10.1016/j.energy.2021.122012 10.1016/j.energy.2023.127852 10.1109/TPAMI.2021.3116668 10.1016/j.renene.2022.09.036 10.1016/j.renene.2020.10.132 10.1016/j.apenergy.2019.04.047 10.1109/TSTE.2019.2926147 10.1016/j.rser.2008.02.002 10.1109/TSTE.2018.2844102 10.1016/j.enconman.2018.07.052 10.1109/TII.2020.2973413 10.1016/j.apenergy.2016.08.108 10.3390/en15082881 10.1016/j.enconman.2016.08.086 10.1109/TPWRS.2021.3105101 10.1016/j.epsr.2020.106865 10.1109/TNN.2010.2096824 10.1016/j.epsr.2011.08.009 10.1016/j.renene.2022.04.055 10.1016/j.neucom.2020.10.093 10.1016/j.apenergy.2019.114259 10.3390/en13226125 10.1016/j.enconman.2019.112077 10.1016/j.ijforecast.2016.02.001 10.3390/electronics11020206 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.energy.2023.128946 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Environmental Sciences |
| ExternalDocumentID | 10_1016_j_energy_2023_128946 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1RT 1~. 1~5 29G 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ 9DU 9JN AABNK AAEDT AAEDW AAHBH AAHCO AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AARJD AATTM AAXKI AAXUO AAYWO AAYXX ABDPE ABFNM ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFS ACIWK ACLOT ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADXHL AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFRAH AFTJW AGHFR AGQPQ AGUBO AGYEJ AHHHB AHIDL AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG AVWKF AXJTR AZFZN BELTK BKOJK BLXMC CITATION CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HVGLF HZ~ IHE J1W JARJE KOM LY6 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RNS ROL RPZ SAC SDF SDG SES SEW SPC SPCBC SSR SSZ T5K TN5 WUQ XPP ZMT ~02 ~G- ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c339t-5f2997a730872c3ecf6f42a746f12e3c94f7ada5ee0604db3a382867b6f6e3cf3 |
| ISICitedReferencesCount | 6 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001071022400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0360-5442 |
| IngestDate | Sun Nov 09 11:04:55 EST 2025 Sat Nov 29 07:18:42 EST 2025 Tue Nov 18 22:12:47 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c339t-5f2997a730872c3ecf6f42a746f12e3c94f7ada5ee0604db3a382867b6f6e3cf3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 3153196225 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_3153196225 crossref_primary_10_1016_j_energy_2023_128946 crossref_citationtrail_10_1016_j_energy_2023_128946 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-11-00 20231101 |
| PublicationDateYYYYMMDD | 2023-11-01 |
| PublicationDate_xml | – month: 11 year: 2023 text: 2023-11-00 |
| PublicationDecade | 2020 |
| PublicationTitle | Energy (Oxford) |
| PublicationYear | 2023 |
| References | Zhang (10.1016/j.energy.2023.128946_b16) 2019; 247 Khodayar (10.1016/j.energy.2023.128946_b3) 2019; 10 Saeed (10.1016/j.energy.2023.128946_b19) 2022; 238 Zhang (10.1016/j.energy.2023.128946_b7) 2016; 126 Harrou (10.1016/j.energy.2023.128946_b6) 2019; 201 Khosravi (10.1016/j.energy.2023.128946_b12) 2011; 22 Khodayar (10.1016/j.energy.2023.128946_b32) 2019; 10 Li (10.1016/j.energy.2023.128946_b5) 2011; 36 Oliveira Santos (10.1016/j.energy.2023.128946_b29) 2023; 278 Deng (10.1016/j.energy.2023.128946_b24) 2021; 163 Pan (10.1016/j.energy.2023.128946_b27) 2022; 253 Qin (10.1016/j.energy.2023.128946_b8) 2011; 81 Zhang (10.1016/j.energy.2023.128946_b9) 2020; 13 Shang (10.1016/j.energy.2023.128946_b33) 2022; 15 Bergstra (10.1016/j.energy.2023.128946_b35) 2012; 13 Khodayar (10.1016/j.energy.2023.128946_b2) 2017; PP Tang (10.1016/j.energy.2023.128946_b20) 2020; 16 Gan (10.1016/j.energy.2023.128946_b18) 2021; 191 Salazar (10.1016/j.energy.2023.128946_b22) 2022; 10 Lei (10.1016/j.energy.2023.128946_b1) 2009; 13 Hong (10.1016/j.energy.2023.128946_b25) 2016; 32 Mangalova (10.1016/j.energy.2023.128946_b10) 2016; 32 Mhaskar (10.1016/j.energy.2023.128946_b14) 2016 Liu (10.1016/j.energy.2023.128946_b30) 2020; 260 Khan (10.1016/j.energy.2023.128946_b31) 2022; 11 Li (10.1016/j.energy.2023.128946_b17) 2020; 11 He (10.1016/j.energy.2023.128946_b13) 2021; 430 Hu (10.1016/j.energy.2023.128946_b4) 2018; 173 Huang (10.1016/j.energy.2023.128946_b26) 2022; 192 Zheng (10.1016/j.energy.2023.128946_b23) 2022; 37 Wu (10.1016/j.energy.2023.128946_b28) 2022; 199 Doersch (10.1016/j.energy.2023.128946_b34) 2016 Bond-Taylor (10.1016/j.energy.2023.128946_b21) 2022; 44 Wang (10.1016/j.energy.2023.128946_b15) 2016; 182 Wan (10.1016/j.energy.2023.128946_b11) 2014; 29 |
| References_xml | – volume: 253 year: 2022 ident: 10.1016/j.energy.2023.128946_b27 article-title: Short-term wind speed forecasting based on spatial-temporal graph transformer networks publication-title: Energy doi: 10.1016/j.energy.2022.124095 – volume: 29 start-page: 1033 issue: 3 year: 2014 ident: 10.1016/j.energy.2023.128946_b11 article-title: Probabilistic forecasting of wind power generation using extreme learning machine publication-title: IEEE Trans Power Syst doi: 10.1109/TPWRS.2013.2287871 – volume: 13 start-page: 281 issue: 1 year: 2012 ident: 10.1016/j.energy.2023.128946_b35 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – volume: 36 start-page: 352 issue: 1 year: 2011 ident: 10.1016/j.energy.2023.128946_b5 article-title: Bayesian adaptive combination of short-term wind speed forecasts from neural network models publication-title: Renew Energy doi: 10.1016/j.renene.2010.06.049 – volume: 32 start-page: 1067 issue: 3 year: 2016 ident: 10.1016/j.energy.2023.128946_b10 article-title: K-nearest neighbors for GEFCom2014 probabilistic wind power forecasting publication-title: Int J Forecast doi: 10.1016/j.ijforecast.2015.11.007 – volume: 238 year: 2022 ident: 10.1016/j.energy.2023.128946_b19 article-title: A simple approach for short-term wind speed interval prediction based on independently recurrent neural networks and error probability distribution publication-title: Energy doi: 10.1016/j.energy.2021.122012 – volume: 278 year: 2023 ident: 10.1016/j.energy.2023.128946_b29 article-title: Spatiotemporal analysis of bidimensional wind speed forecasting: Development and thorough assessment of LSTM and ensemble graph neural networks on the Dutch database publication-title: Energy doi: 10.1016/j.energy.2023.127852 – volume: 44 start-page: 7327 issue: 11 year: 2022 ident: 10.1016/j.energy.2023.128946_b21 article-title: Deep generative modelling: A comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2021.3116668 – volume: 199 start-page: 977 year: 2022 ident: 10.1016/j.energy.2023.128946_b28 article-title: Promoting wind energy for sustainable development by precise wind speed prediction based on graph neural networks publication-title: Renew Energy doi: 10.1016/j.renene.2022.09.036 – volume: 163 start-page: 1951 year: 2021 ident: 10.1016/j.energy.2023.128946_b24 article-title: A new wind speed scenario generation method based on spatiotemporal dependency structure publication-title: Renew Energy doi: 10.1016/j.renene.2020.10.132 – volume: 247 start-page: 270 year: 2019 ident: 10.1016/j.energy.2023.128946_b16 article-title: Wind speed prediction method using shared weight long short-term memory network and Gaussian process regression publication-title: Appl Energy doi: 10.1016/j.apenergy.2019.04.047 – volume: 11 start-page: 1370 issue: 3 year: 2020 ident: 10.1016/j.energy.2023.128946_b17 article-title: Short-term wind speed interval prediction based on ensemble GRU model publication-title: IEEE Trans Sustain Energy doi: 10.1109/TSTE.2019.2926147 – volume: PP start-page: 1 issue: 99 year: 2017 ident: 10.1016/j.energy.2023.128946_b2 article-title: Rough deep neural architecture for short-term wind speed forecasting publication-title: IEEE Trans Ind Inf – year: 2016 ident: 10.1016/j.energy.2023.128946_b14 – volume: 10 start-page: 1855 issue: 6 year: 2022 ident: 10.1016/j.energy.2023.128946_b22 article-title: Deep generative model for probabilistic wind speed and wind power estimation at a wind farm publication-title: Wiley Online Library – volume: 13 start-page: 915 issue: 4 year: 2009 ident: 10.1016/j.energy.2023.128946_b1 article-title: A review on the forecasting of wind speed and generated power publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2008.02.002 – volume: 10 start-page: 670 issue: 2 year: 2019 ident: 10.1016/j.energy.2023.128946_b3 article-title: Spatio-temporal graph deep neural network for short-term wind speed forecasting publication-title: IEEE Trans Sustain Energy doi: 10.1109/TSTE.2018.2844102 – volume: 173 start-page: 197 year: 2018 ident: 10.1016/j.energy.2023.128946_b4 article-title: Research and application of a hybrid model based on Meta learning strategy for wind power deterministic and probabilistic forecasting publication-title: Energy Convers Manage doi: 10.1016/j.enconman.2018.07.052 – volume: 16 start-page: 6806 issue: 11 year: 2020 ident: 10.1016/j.energy.2023.128946_b20 article-title: A novel wind speed interval prediction based on error prediction method publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2020.2973413 – volume: 182 start-page: 80 year: 2016 ident: 10.1016/j.energy.2023.128946_b15 article-title: Deep belief network based deterministic and probabilistic wind speed forecasting approach publication-title: Appl Energy doi: 10.1016/j.apenergy.2016.08.108 – volume: 15 issue: 8 year: 2022 ident: 10.1016/j.energy.2023.128946_b33 article-title: Wind speed forecasting using attention-based causal convolutional network and wind energy conversion publication-title: Energies doi: 10.3390/en15082881 – volume: 126 start-page: 1084 year: 2016 ident: 10.1016/j.energy.2023.128946_b7 article-title: A Gaussian process regression based hybrid approach for short-term wind speed prediction publication-title: Energy Convers Manage doi: 10.1016/j.enconman.2016.08.086 – volume: 37 start-page: 1386 issue: 2 year: 2022 ident: 10.1016/j.energy.2023.128946_b23 article-title: Generative probabilistic wind speed forecasting: A variational recurrent autoencoder based method publication-title: IEEE Trans Power Syst doi: 10.1109/TPWRS.2021.3105101 – volume: 191 year: 2021 ident: 10.1016/j.energy.2023.128946_b18 article-title: Temporal convolutional networks interval prediction model for wind speed forecasting publication-title: Electr Power Syst Res doi: 10.1016/j.epsr.2020.106865 – volume: 22 start-page: 337 issue: 3 year: 2011 ident: 10.1016/j.energy.2023.128946_b12 article-title: Lower upper bound estimation method for construction of neural network-based prediction intervals publication-title: IEEE Trans Neural Netw doi: 10.1109/TNN.2010.2096824 – year: 2016 ident: 10.1016/j.energy.2023.128946_b34 – volume: 81 start-page: 2139 issue: 12 year: 2011 ident: 10.1016/j.energy.2023.128946_b8 article-title: Estimating wind speed probability distribution using kernel density method publication-title: Electr Power Syst Res doi: 10.1016/j.epsr.2011.08.009 – volume: 192 start-page: 526 year: 2022 ident: 10.1016/j.energy.2023.128946_b26 article-title: Spatio-temporal wind speed prediction based on Clayton Copula function with deep learning fusion publication-title: Renew Energy doi: 10.1016/j.renene.2022.04.055 – volume: 430 start-page: 121 year: 2021 ident: 10.1016/j.energy.2023.128946_b13 article-title: Uncertainty analysis of wind power probability density forecasting based on cubic spline interpolation and support vector quantile regression publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.10.093 – volume: 260 year: 2020 ident: 10.1016/j.energy.2023.128946_b30 article-title: Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model publication-title: Appl Energy doi: 10.1016/j.apenergy.2019.114259 – volume: 13 issue: 22 year: 2020 ident: 10.1016/j.energy.2023.128946_b9 article-title: Probability density forecasting of wind speed based on quantile regression and kernel density estimation publication-title: Energies doi: 10.3390/en13226125 – volume: 201 year: 2019 ident: 10.1016/j.energy.2023.128946_b6 article-title: Wind power prediction using bootstrap aggregating trees approach to enabling sustainable wind power integration in a smart grid publication-title: Energy Convers Manage doi: 10.1016/j.enconman.2019.112077 – volume: 32 start-page: 896 issue: 3 year: 2016 ident: 10.1016/j.energy.2023.128946_b25 article-title: Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond publication-title: Int J Forecast doi: 10.1016/j.ijforecast.2016.02.001 – volume: 11 issue: 2 year: 2022 ident: 10.1016/j.energy.2023.128946_b31 article-title: Power forecasting of regional wind farms via variational auto-encoder and deep hybrid transfer learning publication-title: Electronics doi: 10.3390/electronics11020206 – volume: 10 start-page: 670 issue: 2 year: 2019 ident: 10.1016/j.energy.2023.128946_b32 article-title: Spatio-temporal graph deep neural network for short-term wind speed forecasting publication-title: IEEE Trans Sustain Energy doi: 10.1109/TSTE.2018.2844102 |
| SSID | ssj0005899 |
| Score | 2.4528303 |
| Snippet | Wind speed interval prediction is one of the most long-standing challenges because of the high uncertainty and the complex spatial–temporal correlation between... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Enrichment Source Index Database |
| StartPage | 128946 |
| SubjectTerms | Bayesian theory energy prediction probability distribution spatial data uncertainty wind speed wind turbines |
| Title | A novel spatial–temporal generative autoencoder for wind speed uncertainty forecasting |
| URI | https://www.proquest.com/docview/3153196225 |
| Volume | 282 |
| WOSCitedRecordID | wos001071022400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0360-5442 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0005899 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nj9MwELWgiwQXBAsrdvmQkbhVqVrbieNjhYoALSskFqm3yElt0VWVVJt06ZH_sP-QX8KM7SQtKwF74BJVruNandcZZ_rmDSFvcqZyLix4v4nUkYAQHalUj6NcqFSxXKU2980m5NlZOp-rz6GEoHbtBGRZptutWv9XU8MYGBtLZ29h7m5RGIDXYHS4gtnh-k-Gnw7L6sqshjVypfWqZTPwIEK1wqbJJuh9601ToZIlCkog3_D7EtPoa4hoQ4h3ni3gKZ2m0HXThrk2k-_rBlGwdOs58l1W4ZM7k55W4QaHm5CZPl32g1---abZm6U1YTRkIBgPpXi9o-LJOIqF2POqzPcUCn4RoqDyqcYbLttnDy5Gxu15hB8w6qfvK2T_Frk6PmFLVbvI_CoZrpL5Ve6SAyZjlQ7IwfTDbP6xJwClrrtot_u2sNKx_27uZv_gsh-33WHk_BF5GJ4i6NRb_zG5Y8pDcr8tMq8PydGsL2CEicGD10_IfEodPGiAx88f1y0waA8MugMMCqalCAzqgEF3gEF3gPGUfH03O3_7PgrdNaKCc9VEsYWTiNQSJSFZwU1hEyuYliKxE2Z4oeAXrBc6Ngb1lRY51xwlB2Se2ATetvyIDMqqNM8INbkcL5BTkMDTtVDYwNqImMnCTLAQWh4T3n51WRGk57EDyir7k-GOSdTdtfbSK3-Z_7q1SgY-Ev_40qWpNnXGJy7SQOg6ueWaz8mDHvEvyKC53JiX5F5x1Szry1cBUb8AXROL2A |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+novel+spatial%E2%80%93temporal+generative+autoencoder+for+wind+speed+uncertainty+forecasting&rft.jtitle=Energy+%28Oxford%29&rft.au=Ma%2C+Long&rft.au=Huang%2C+Ling&rft.au=Shi%2C+Huifeng&rft.date=2023-11-01&rft.issn=0360-5442&rft.volume=282&rft.spage=128946&rft_id=info:doi/10.1016%2Fj.energy.2023.128946&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_energy_2023_128946 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-5442&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-5442&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-5442&client=summon |