SSRF-Net: A Stagewise Scheduled Rainfall Forecasting Network With an Asymmetric Architecture

Deterministic deep learning models for precipitation nowcasting often face several limitations, including cumulative error in long-sequence predictions, over-smoothing, and a reduced ability to capture rare, high-impact rainfall due to data imbalance. To address these challenges, we propose the stag...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on geoscience and remote sensing Ročník 63; s. 1 - 18
Hlavní autori: Luo, Wenjie, Li, Chaorong, Ling, Xudong, Deng, Chuanhu, Wang, Zhuo
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Asymmetric encoder–decoder (E–D)
Asymmetry
Coders
Compression
Data models
Decoding
Deep learning
error accumulation
Floating point arithmetic
Forecasting
iterative prediction
Meteorological radar
Nowcasting
Precipitation
precipitation nowcasting
Predictions
Predictive models
Rain
Rainfall
Reliability
Smoothing
Spatiotemporal phenomena
Training
ISSN:0196-2892, 1558-0644
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Deterministic deep learning models for precipitation nowcasting often face several limitations, including cumulative error in long-sequence predictions, over-smoothing, and a reduced ability to capture rare, high-impact rainfall due to data imbalance. To address these challenges, we propose the stagewise scheduled rainfall forecasting network (SSRF-Net), a convolutional framework for continuous multistep rainfall prediction that achieves lower floating-point operations (FLOPs) than competitive baselines under a standardized evaluation. Our framework introduces a multistage, sliding-window prediction mechanism trained with teacher forcing and scheduled sampling to mitigate error accumulation and stabilize training. We design an asymmetric encoder-decoder (E-D) architecture featuring a differential selective encoder (DSE) for selective feature compression and an additive fusion decoder (AFD) that progressively reconstructs details and alleviates over-smoothing. We further introduce an intensity-weighted Gaussian KL divergence loss that aligns sequence-level Gaussian summaries (means and variances) of predictions and ground truth via a KL term, prioritizing heavy-rain events without assuming pixelwise Gaussianity. Extensive experiments on the KNMI and SEVIR datasets show that SSRF-Net outperforms strong baselines, particularly for moderate to severe precipitation; on KNMI, it yields up to 41.8% higher per-frame critical success index (CSI) at the 30-mm/h threshold, with consistent gains on SEVIR.
AbstractList Deterministic deep learning models for precipitation nowcasting often face several limitations, including cumulative error in long-sequence predictions, over-smoothing, and a reduced ability to capture rare, high-impact rainfall due to data imbalance. To address these challenges, we propose the stagewise scheduled rainfall forecasting network (SSRF-Net), a convolutional framework for continuous multistep rainfall prediction that achieves lower floating-point operations (FLOPs) than competitive baselines under a standardized evaluation. Our framework introduces a multistage, sliding-window prediction mechanism trained with teacher forcing and scheduled sampling to mitigate error accumulation and stabilize training. We design an asymmetric encoder–decoder (E–D) architecture featuring a differential selective encoder (DSE) for selective feature compression and an additive fusion decoder (AFD) that progressively reconstructs details and alleviates over-smoothing. We further introduce an intensity-weighted Gaussian KL divergence loss that aligns sequence-level Gaussian summaries (means and variances) of predictions and ground truth via a KL term, prioritizing heavy-rain events without assuming pixelwise Gaussianity. Extensive experiments on the KNMI and SEVIR datasets show that SSRF-Net outperforms strong baselines, particularly for moderate to severe precipitation; on KNMI, it yields up to 41.8% higher per-frame critical success index (CSI) at the 30-mm/h threshold, with consistent gains on SEVIR.
Author Deng, Chuanhu
Li, Chaorong
Ling, Xudong
Luo, Wenjie
Wang, Zhuo
Author_xml – sequence: 1
  givenname: Wenjie
  orcidid: 0009-0005-2620-5770
  surname: Luo
  fullname: Luo, Wenjie
  email: lwj018@stu.cqut.edu.cn
  organization: College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
– sequence: 2
  givenname: Chaorong
  orcidid: 0000-0001-8336-2661
  surname: Li
  fullname: Li, Chaorong
  email: lichaorong88@163.com
  organization: School of Computer Science and Technology (School of Artificial Intelligence), Yibin University, Yibin, China
– sequence: 3
  givenname: Xudong
  orcidid: 0009-0009-1128-8322
  surname: Ling
  fullname: Ling, Xudong
  email: clearlyzero@stu.cqut.edu.cn
  organization: College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
– sequence: 4
  givenname: Chuanhu
  surname: Deng
  fullname: Deng, Chuanhu
  email: onlyiyou@foxmail.com
  organization: College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
– sequence: 5
  givenname: Zhuo
  surname: Wang
  fullname: Wang, Zhuo
  email: 1125556251@qq.com
  organization: College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
BookMark eNpFkEFrwjAUgMNwMHX7AYMdAjvXJWmSJrsVmW4gG1jHLoOSpk-t09YlKeK_X0Vhl_cu3_cefAPUq5saELqnZEQp0U-L6TwbMcLEKJaMSpZcoT4VQkVEct5DfUK1jJjS7AYNvN8QQrmgSR99Z9l8Er1DeMYpzoJZwaHygDO7hrLdQonnpqqXZrvFk8aBNT5U9Qp3_KFxP_irCmtsapz6424HwVUWp86uqwA2tA5u0XWneri77CH6nLwsxq_R7GP6Nk5nkaUyDlFRSmFUoZjWCRVSG6r40kqhpRZFN0wRS5CcdjAIzpNCWZKwhMiiFBZKHg_R4_nu3jW_LfiQb5rW1d3LPGZSKS2FUh1Fz5R1jfcOlvneVTvjjjkl-SlifoqYnyLml4id83B2KgD45yljPJYk_gPK3G5i
CODEN IGRSD2
Cites_doi 10.1175/1520-0477(1998)079<2079:NTASR>2.0.CO;2
10.5194/gmd-13-2631-2020
10.5194/gmd-12-4185-2019
10.1126/science.adi2336
10.3390/rs17091550
10.1109/IJCNN54540.2023.10191095
10.1109/IJCNN55064.2022.9892376
10.1007/s11390-021-1103-8
10.1007/s12040-024-02508-8
10.1109/TGRS.2021.3056470
10.3390/rs16142685
10.1007/978-3-319-24574-4_28
10.1007/978-3-319-67558-9_28
10.1256/qj.04.100
10.1109/TPAMI.2016.2644615
10.3390/atmos8030048
10.1038/s41598-025-98944-7
10.14711/thesis-991013340437803412
10.1029/2024GL113699
10.1175/aies-d-23-0017.1
10.1038/s41586-023-06184-4
10.1007/978-3-319-67389-9_44
10.1038/s41586-023-06185-3
10.1109/CVPR.2019.00949
10.1109/ICCV.2017.324
10.1109/LGRS.2022.3162882
10.1029/2020MS002203
10.1109/tgrs.2024.3510693
10.1016/j.neunet.2021.08.036
10.1016/j.envsoft.2024.106001
10.1609/aaai.v38i14.29521
10.1016/j.patrec.2021.01.036
10.1109/JSTARS.2020.3040648
10.1109/CVPR.2019.00937
10.1175/BAMS-D-11-00263.1
10.1016/j.atmosres.2022.106500
10.1029/2019EA000812
10.1109/JSTARS.2025.3549678
10.1109/tgrs.2025.3528423
10.1038/s41467-022-32483-x
10.1109/TGRS.2021.3100847
10.1038/s41586-021-03854-z
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
DOI 10.1109/TGRS.2025.3621627
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Water Resources Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
ASFA: Aquatic Sciences and Fisheries Abstracts
Engineering Research Database
Aerospace Database
Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources
Civil Engineering Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) Professional
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Aerospace Database
Civil Engineering Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) Professional
Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources
Technology Research Database
ASFA: Aquatic Sciences and Fisheries Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Water Resources Abstracts
Environmental Sciences and Pollution Management
DatabaseTitleList Aerospace Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1558-0644
EndPage 18
ExternalDocumentID 10_1109_TGRS_2025_3621627
11224360
Genre orig-research
GrantInformation_xml – fundername: Yibin University Science and Technology
  grantid: 2024XJYY03; 2023YY02; 2023YY05; 2025XJZD01
  funderid: 10.13039/501100003473
– fundername: Science and Technology Department of Sichuan Province
  grantid: 2024ZYD0089
  funderid: 10.13039/501100011447
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IBMZZ
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
RXW
TAE
TN5
VH1
Y6R
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
ID FETCH-LOGICAL-c163t-bd65a8b829971569a184fc659695b969ab36e641163e5447b8c072706bd5ced43
IEDL.DBID RIE
ISSN 0196-2892
IngestDate Thu Nov 06 11:20:03 EST 2025
Sat Nov 29 06:58:52 EST 2025
Wed Nov 19 08:27:20 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c163t-bd65a8b829971569a184fc659695b969ab36e641163e5447b8c072706bd5ced43
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0009-0005-2620-5770
0000-0001-8336-2661
0009-0009-1128-8322
PQID 3268896588
PQPubID 85465
PageCount 18
ParticipantIDs crossref_primary_10_1109_TGRS_2025_3621627
proquest_journals_3268896588
ieee_primary_11224360
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev TGRS
PublicationYear 2025
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References Bengio (ref42); 1
ref15
ref14
Shi (ref12); 28
ref53
ref52
ref11
Shi (ref41)
ref10
ref54
ref17
ref16
ref19
ref18
Sønderby (ref37) 2020
ref51
ref46
ref45
ref47
Wang (ref50)
ref44
ref43
Masson-Delmotte (ref5); 2
ref8
ref7
ref9
ref4
ref3
ref6
Park (ref25)
ref40
ref35
ref34
Yan (ref48); 37
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
Turzi (ref21) 2025
ref24
ref23
ref26
ref20
ref22
ref28
Wang (ref13); 30
ref27
ref29
Kingma (ref49) 2014
Pathak (ref36) 2022
References_xml – ident: ref11
  doi: 10.1175/1520-0477(1998)079<2079:NTASR>2.0.CO;2
– ident: ref14
  doi: 10.5194/gmd-13-2631-2020
– ident: ref3
  doi: 10.5194/gmd-12-4185-2019
– ident: ref39
  doi: 10.1126/science.adi2336
– ident: ref24
  doi: 10.3390/rs17091550
– ident: ref32
  doi: 10.1109/IJCNN54540.2023.10191095
– ident: ref52
  doi: 10.1109/IJCNN55064.2022.9892376
– ident: ref7
  doi: 10.1007/s11390-021-1103-8
– ident: ref20
  doi: 10.1007/s12040-024-02508-8
– ident: ref4
  doi: 10.1109/TGRS.2021.3056470
– year: 2022
  ident: ref36
  article-title: FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators
  publication-title: arXiv:2202.11214
– ident: ref27
  doi: 10.3390/rs16142685
– ident: ref18
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref46
  doi: 10.1007/978-3-319-67558-9_28
– ident: ref9
  doi: 10.1256/qj.04.100
– ident: ref33
  doi: 10.1109/TPAMI.2016.2644615
– ident: ref10
  doi: 10.3390/atmos8030048
– ident: ref40
  doi: 10.1038/s41598-025-98944-7
– volume: 2
  start-page: 2391
  issue: 1
  volume-title: Proc. Contribution Work. Group I 6th Assessment Rep. Intergovernmental Panel Climate Change
  ident: ref5
  article-title: Climate change 2021: The physical science basis
– ident: ref23
  doi: 10.14711/thesis-991013340437803412
– ident: ref34
  doi: 10.1029/2024GL113699
– ident: ref28
  doi: 10.1175/aies-d-23-0017.1
– volume: 37
  start-page: 100007
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref48
  article-title: Fourier amplitude and correlation loss: Beyond using L2 loss for skillful precipitation nowcasting
– ident: ref2
  doi: 10.1038/s41586-023-06184-4
– start-page: 5123
  volume-title: Proc. PMLR Int. Conf. Mach. Learn.
  ident: ref50
  article-title: PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning
– year: 2014
  ident: ref49
  article-title: Adam: A method for stochastic optimization
  publication-title: arXiv:1412.6980
– ident: ref47
  doi: 10.1007/978-3-319-67389-9_44
– ident: ref35
  doi: 10.1038/s41586-023-06185-3
– ident: ref45
  doi: 10.1109/CVPR.2019.00949
– ident: ref44
  doi: 10.1109/ICCV.2017.324
– ident: ref22
  doi: 10.1109/LGRS.2022.3162882
– volume: 28
  start-page: 802
  volume-title: Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.
  ident: ref12
  article-title: Convolutional LSTM network: A machine learning approach for precipitation nowcasting
– ident: ref43
  doi: 10.1029/2020MS002203
– ident: ref26
  doi: 10.1109/tgrs.2024.3510693
– ident: ref19
  doi: 10.1016/j.neunet.2021.08.036
– ident: ref6
  doi: 10.1016/j.envsoft.2024.106001
– year: 2025
  ident: ref21
  article-title: SSA-UNet: Advanced precipitation nowcasting via channel shuffling
  publication-title: arXiv:2504.18309
– year: 2020
  ident: ref37
  article-title: MetNet: A neural weather model for precipitation forecasting
  publication-title: arXiv:2003.12140
– ident: ref53
  doi: 10.1609/aaai.v38i14.29521
– start-page: 1
  volume-title: Proc. NeurIPS
  ident: ref25
  article-title: Nowformer: A locally enhanced temporal learner for precipitation nowcasting
– volume: 1
  start-page: 1171
  volume-title: Proc. 29th Int. Conf. Neural Inf. Process. Syst.
  ident: ref42
  article-title: Scheduled sampling for sequence prediction with recurrent neural networks
– ident: ref15
  doi: 10.1016/j.patrec.2021.01.036
– ident: ref17
  doi: 10.1109/JSTARS.2020.3040648
– start-page: 5622
  volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst.
  ident: ref41
  article-title: Deep learning for precipitation nowcasting: A benchmark and a new model
– ident: ref51
  doi: 10.1109/CVPR.2019.00937
– ident: ref8
  doi: 10.1175/BAMS-D-11-00263.1
– ident: ref29
  doi: 10.1016/j.atmosres.2022.106500
– ident: ref31
  doi: 10.1029/2019EA000812
– ident: ref54
  doi: 10.1109/JSTARS.2025.3549678
– volume: 30
  start-page: 879
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref13
  article-title: PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs
– ident: ref16
  doi: 10.1109/tgrs.2025.3528423
– ident: ref38
  doi: 10.1038/s41467-022-32483-x
– ident: ref30
  doi: 10.1109/TGRS.2021.3100847
– ident: ref1
  doi: 10.1038/s41586-021-03854-z
SSID ssj0014517
Score 2.465252
Snippet Deterministic deep learning models for precipitation nowcasting often face several limitations, including cumulative error in long-sequence predictions,...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Asymmetric encoder–decoder (E–D)
Asymmetry
Coders
Compression
Data models
Decoding
Deep learning
error accumulation
Floating point arithmetic
Forecasting
iterative prediction
Meteorological radar
Nowcasting
Precipitation
precipitation nowcasting
Predictions
Predictive models
Rain
Rainfall
Reliability
Smoothing
Spatiotemporal phenomena
Training
Title SSRF-Net: A Stagewise Scheduled Rainfall Forecasting Network With an Asymmetric Architecture
URI https://ieeexplore.ieee.org/document/11224360
https://www.proquest.com/docview/3268896588
Volume 63
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-0644
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014517
  issn: 0196-2892
  databaseCode: RIE
  dateStart: 19800101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEA4qCnrwLa4vcvAkRJttmibeFnH1IIu4ih6EkiZTXVhXsV3Ff-8krbogHryUHtJS5kvnkW8ehOxzZ41Gy8VUbCQT3HGmlVGssJobDTw3NjRxvUh7PXV3py-bYvVQCwMAIfkMDv1t4PLdsx37o7Ij7mmgWGKEPp2msi7W-qYMRMKb2mjJMIpoNxQmj_TR9dlVH0PBdnKI6ppLP0FmwgiFqSq_VHGwL92lf37ZMllsHEnaqZFfIVMwWiULE-0FV8lcSO-05Rq57_evuqwH1THtUPQvH-B9UALtI2JuPARHPc1TmOGQ-lGd1pQ-GZr26hRxejuoHqkZ0U758fTkJ3BZ2pngH9bJTff0-uScNXMVmEXvq2K5k4lRuUJLlGL4pg1GeYWViZY6yfFi8liCFBwXQyJEmisboZsTydwlFpyIN8jM6HkEm4RaJ7Qp0tjTh0IK3BFxGkUgI1Ogri2gRQ6-BJ291O0zshB2RDrzqGQelaxBpUXWvWR_FjZCbZGdL2yy5g8rM3Q7lfKda9TWH49tk3n_9vq8ZIfMVK9j2CWz9q0alK97YfN8Al9AwIA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1VbRH0QKEUsdCCD5yQ3MYbx7G5rRDbIpYIdRfRA1Lk2BNYabtFTRbEv-_YSelKiEMvUQ6OEs04M_P85gPgtfDOGvJcXKdWcSm84EZbzWtnhDUoKutiE9dJXhT6_Nx87ovVYy0MIsbkMzwKt5HL95duFY7KjkWggVJFCH0rk3KYdOVaf0kDmYm-OlpxwhHDnsQUiTmenZxNCQwOsyMy2EKFGTJrbijOVfnHGEcPM96947c9god9KMlGne4fwwYu92BnrcHgHtyLCZ6ueQLfptOzMS-wfctGjCLM7_h73iCbks78aoGeBaKntosFC8M6nW1COjQruiRx9nXe_mB2yUbNn4uLMIPLsdEaA7EPX8bvZ-9OeT9ZgTuKv1peeZVZXWnyRTkBOGMJ59VOZUaZrKKLrVKFSgpajCTpvNIuoUAnUZXPHHqZPoXN5eUSnwFzXhpb52kgEKWStCfSPElQJbYma1vjAN7cCLr82TXQKCPwSEwZtFIGrZS9VgawHyR7u7AX6gAObnRT9v9YU1LgqXXoXaOf_-exV3D_dPZpUk4-FB9fwIPwpu705AA226sVHsK2-9XOm6uXcSNdA5Dzw8c
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=SSRF-Net%3A+A+Stagewise+Scheduled+Rainfall+Forecasting+Network+With+an+Asymmetric+Architecture&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Luo%2C+Wenjie&rft.au=Li%2C+Chaorong&rft.au=Ling%2C+Xudong&rft.au=Deng%2C+Chuanhu&rft.date=2025&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=63&rft.spage=1&rft.epage=18&rft_id=info:doi/10.1109%2FTGRS.2025.3621627&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2025_3621627
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon