{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T18:28:05Z","timestamp":1786991285794,"version":"build-2736575974"},"reference-count":41,"publisher":"AIP Publishing","issue":"7","funder":[{"name":"National Science Foundation of Xiamen","award":["3502Z202674013"],"award-info":[{"award-number":["3502Z202674013"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12275228"],"award-info":[{"award-number":["12275228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["124B2108"],"award-info":[{"award-number":["124B2108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,21]]},"abstract":"<jats:p>Diffusion Ordered NMR Spectroscopy (DOSY) is a powerful technique for studying mixtures by probing the diffusion behavior of mixed compounds and enabling their identification and separation in mixture samples. The performance of DOSY generally relies on the adopted reconstruction algorithm to determine diffusion coefficients from diffusion-dependent signal decays, thus producing a 2D spectrum that resolves components by chemical shift and molecular diffusion. Although deep-learning provides an effective approach to DOSY reconstruction, existing deep-learning-based reconstruction methods generally face the limitation of inadequate feature extraction, which may lead to reconstruction artifacts in some scenarios. Here, we propose STELT (Spatiotemporal Extraction Laplace Transform), a lightweight deep-learning framework based on spatiotemporal feature extraction. STELT uses a dual-branch architecture that combines a temporal convolution module to capture dynamic patterns in decay signals with a self-attention module to extract spatial features along the chemical-shift dimension. Experimental results demonstrate the proposed method achieves superior reconstruction accuracy and noise suppression with significantly reduced computational overhead, thereby offering a practical and efficient solution for high-quality DOSY analysis.<\/jats:p>","DOI":"10.1063\/5.0346251","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T17:53:56Z","timestamp":1786989236000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["STELT: A spatiotemporal deep learning framework for diffusion-ordered NMR spectroscopy reconstruction with artifact suppression"],"prefix":"10.1063","volume":"165","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9907-5533","authenticated-orcid":false,"given":"Jingmin","family":"Lin","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Application Technology Research Center of Artificial Intelligence, Xiamen City University 1 , Xiamen, Fujian 361008,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1695-9895","authenticated-orcid":false,"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, State Key Laboratory of Physical Chemistry of Solid Surfaces, Xiamen University 2 , Xiamen, Fujian 361005,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1689-0137","authenticated-orcid":false,"given":"Guolan","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Application Technology Research Center of Artificial Intelligence, Xiamen City University 1 , Xiamen, Fujian 361008,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3401-2354","authenticated-orcid":false,"given":"Hai","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Application Technology Research Center of Artificial Intelligence, Xiamen City University 1 , Xiamen, Fujian 361008,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0606-1165","authenticated-orcid":false,"given":"Yuqing","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, State Key Laboratory of Physical Chemistry of Solid Surfaces, Xiamen University 2 , Xiamen, Fujian 361005,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"issue":"12","key":"2026081713535135400_c1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/ac00163a001","article-title":"Nuclear magnetic resonance spectroscopy","volume":"60","year":"1988","journal-title":"Anal. Chem."},{"issue":"8","key":"2026081713535135400_c2","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1021\/ja00034a071","article-title":"Diffusion-ordered two-dimensional nuclear magnetic resonance spectroscopy","volume":"114","year":"1992","journal-title":"J.\u00a0Am. Chem. Soc."},{"issue":"1-2","key":"2026081713535135400_c3","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/s0003-2670(03)00752-9","article-title":"Assessment of techniques for DOSY NMR data processing","volume":"490","year":"2003","journal-title":"Anal. Chim. Acta"},{"issue":"8","key":"2026081713535135400_c4","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.talanta.2012.04.046","article-title":"Screening \u03b1-glucosidase inhibitors from mulberry extracts via DOSY and relaxation-edited NNR","volume":"97","year":"2012","journal-title":"Talanta"},{"issue":"22","key":"2026081713535135400_c5","doi-asserted-by":"publisher","first-page":"13256","DOI":"10.1021\/acs.est.7b03322","article-title":"Diffusion-ordered nuclear magnetic resonance spectroscopy (DOSY-NMR): A novel tool for identification of phosphorus compounds in soil extracts","volume":"51","year":"2017","journal-title":"Environ. Sci. Technol."},{"issue":"1","key":"2026081713535135400_c6","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1042\/etls20170139","article-title":"Protein dynamics revealed by NMR relaxation methods","volume":"2","year":"2018","journal-title":"Emerging Top. Life Sci."},{"issue":"2","key":"2026081713535135400_c7","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.mrl.2021.100007","article-title":"NMR signal separation of ionic liquids by poly (sodium-p-styrenesulfonate)-assisted chromatographic NMR spectroscopy","volume":"1","year":"2021","journal-title":"Magn. Reson. Lett."},{"issue":"2","key":"2026081713535135400_c8","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.mrl.2021.100021","article-title":"Utilizing 3D DOSY NMR in the characterization of organic compounds in coal chemical wastewater","volume":"2","year":"2022","journal-title":"Magn. Reson. Lett."},{"issue":"1","key":"2026081713535135400_c9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41664-023-00293-9","article-title":"Accurate quantification of pure thiacloprid with mass balance and quantitative H-NMR","volume":"8","year":"2024","journal-title":"J.\u00a0Anal. Test."},{"key":"2026081713535135400_c10","doi-asserted-by":"publisher","first-page":"110707","DOI":"10.1016\/j.microc.2024.110707","article-title":"Metabolomics analysis using matrix-assisted diffusion-ordered spectroscopy (DOSY) and its application in acrylamide-induced cardiovascular toxicity","volume":"201","year":"2024","journal-title":"Microchem. J."},{"issue":"1","key":"2026081713535135400_c11","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.jmr.2010.02.010","article-title":"Understanding NMR T2 spectral uncertainty","volume":"204","year":"2010","journal-title":"J.\u00a0Magn. Reson."},{"issue":"42","key":"2026081713535135400_c12","doi-asserted-by":"publisher","first-page":"10331","DOI":"10.1021\/ja962172v","article-title":"Generalized rank annihilation method applied to a single multicomponent pulsed gradient spin echo NMR data set","volume":"118","year":"1996","journal-title":"J.\u00a0Am. Chem. Soc."},{"issue":"2","key":"2026081713535135400_c13","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/s0169-7439(97)00028-2","article-title":"Direct exponential curve resolution algorithm (DECRA): A novel application of the generalized rank annihilation method for a single spectral mixture data set with exponentially decaying contribution profiles","volume":"37","year":"1997","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"2","key":"2026081713535135400_c14","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/S0169-7439(98)00172-5","article-title":"Resolving nuclear magnetic resonance data of complex mixtures by three-way methods: Examples of chemical solutions and the human brain","volume":"46","year":"1999","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"4","key":"2026081713535135400_c15","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1002\/cmr.10026","article-title":"Using pulsed gradient spin echo NMR for chemical mixture analysis: How to obtain optimum results","volume":"14","year":"2002","journal-title":"Concepts Magn. Reson."},{"issue":"12","key":"2026081713535135400_c16","doi-asserted-by":"publisher","first-page":"4380","DOI":"10.1063\/1.1147539","article-title":"Global least-squares analysis of large, correlated spectral data sets and application to chemical kinetics and time-resolved fluorescence","volume":"67","year":"1996","journal-title":"Rev. Sci. Instrum."},{"issue":"20","key":"2026081713535135400_c17","doi-asserted-by":"publisher","first-page":"8180","DOI":"10.1021\/jp9535607","article-title":"Global least-squares analysis of large, correlated spectral data sets: Application to component-resolved FT-PGSE NMR spectroscopy","volume":"100","year":"1996","journal-title":"J.\u00a0Phys. Chem."},{"issue":"6","key":"2026081713535135400_c18","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1021\/jp963298h","article-title":"FT-PGSE NMR study of mixed micellization of an anionic and a sugar-based nonionic surfactant","volume":"101","year":"1997","journal-title":"J.\u00a0Phys. Chem. B"},{"issue":"10","key":"2026081713535135400_c19","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1021\/ja00063a053","article-title":"Resolution of discrete and continuous molecular size distributions by means of diffusion-ordered 2D NMR spectroscopy","volume":"115","year":"1993","journal-title":"J.\u00a0Am. Chem. Soc."},{"issue":"3","key":"2026081713535135400_c20","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/0010-4655(82)90173-4","article-title":"A constrained regularization method for inverting data represented by linear algebraic or integral equations","volume":"27","year":"1982","journal-title":"Comput. Phys. Commun."},{"issue":"10","key":"2026081713535135400_c21","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1021\/ac9800715","article-title":"Maximum entropy processing of DOSY NMR spectra","volume":"70","year":"1998","journal-title":"Anal. Chem."},{"issue":"3","key":"2026081713535135400_c22","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1021\/ac3032004","article-title":"Iterative thresholding algorithm for multiexponential decay applied to PGSE NMR data","volume":"85","year":"2013","journal-title":"Anal. Chem."},{"issue":"10","key":"2026081713535135400_c23","doi-asserted-by":"publisher","first-page":"3777","DOI":"10.1021\/ac7025833","article-title":"Speedy component resolution: An improved tool for processing diffusion-ordered spectroscopy data","volume":"80","year":"2008","journal-title":"Anal. Chem."},{"key":"2026081713535135400_c24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmr.2017.03.004","article-title":"Reconstructing diffusion ordered NMR spectroscopy by simultaneous inversion of Laplace transform","volume":"278","year":"2017","journal-title":"J.\u00a0Magn. Reson."},{"issue":"1","key":"2026081713535135400_c25","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1021\/acs.analchem.9b03865","article-title":"High-resolution reconstruction for diffusion-ordered NMR spectroscopy","volume":"92","year":"2019","journal-title":"Anal. Chem."},{"key":"2026081713535135400_c26","doi-asserted-by":"publisher","first-page":"101556","DOI":"10.1016\/j.pnmrs.2024.101556","article-title":"Deep learning and its applications in nuclear magnetic resonance spectroscopy","volume":"146-147","year":"2025","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"key":"2026081713535135400_c27","doi-asserted-by":"publisher","first-page":"101575","DOI":"10.1016\/j.pnmrs.2025.101575","article-title":"Machine learning in NMR spectroscopy","volume":"148-149","year":"2025","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"issue":"39","key":"2026081713535135400_c28","doi-asserted-by":"publisher","first-page":"eadw8122","DOI":"10.1126\/sciadv.adw8122","article-title":"Scalable deep learning reconstruction for accelerated multidimensional nuclear magnetic resonance spectroscopy of proteins","volume":"11","year":"2025","journal-title":"Sci. Adv."},{"issue":"2","key":"2026081713535135400_c29","doi-asserted-by":"publisher","first-page":"100017","DOI":"10.3866\/pku.whxb202310045","article-title":"Noise reduction of nuclear magnetic resonance spectroscopy using lightweight deep neural network","volume":"41","year":"2025","journal-title":"Acta Phys.-Chim. Sin."},{"issue":"31","key":"2026081713535135400_c30","doi-asserted-by":"publisher","first-page":"11596","DOI":"10.1021\/acs.analchem.3c00537","article-title":"High-quality reconstruction for Laplace NMR based on deep learning","volume":"95","year":"2023","journal-title":"Anal. Chem."},{"key":"2026081713535135400_c31","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026081713535135400_c32","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","year":"2024","journal-title":"The Twelfth International Conference on Learning Representations (ICLR)"},{"key":"2026081713535135400_c33","unstructured":"S.\n            Bai\n          , J. Z.Kolter, and V.Koltun, \u201cAn empirical evaluation of generic convolutional and recurrent networks for sequence modeling,\u201d arXiv:1803.01271 (2018)."},{"key":"2026081713535135400_c34","doi-asserted-by":"publisher","first-page":"106252","DOI":"10.1016\/j.infrared.2025.106252","article-title":"ATFusion: An alternate cross-attention transformer network for infrared and visible image fusion","volume":"152","year":"2026","journal-title":"Infrared Phys. Technol."},{"issue":"50","key":"2026081713535135400_c35","doi-asserted-by":"publisher","first-page":"15579","DOI":"10.1002\/anie.201609676","article-title":"Ultrahigh-resolution diffusion-ordered spectroscopy","volume":"55","year":"2016","journal-title":"Angew. Chem., Int. Ed."},{"issue":"3","key":"2026081713535135400_c36","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1021\/acs.jpclett.0c03549","article-title":"Diffusion analysis on complex mixtures under adverse magnetic field conditions by spatially-selective pure shift-based DOSY","volume":"12","year":"2021","journal-title":"J.\u00a0Phys. Chem. Lett."},{"issue":"3","key":"2026081713535135400_c37","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.pnsc.2025.02.014","article-title":"Leveraging deep learning for accurate and automated interpretation of molecular IR and Raman spectra","volume":"35","year":"2025","journal-title":"Prog. Nat. Sci.: Mater. Int."},{"key":"2026081713535135400_c38","doi-asserted-by":"publisher","first-page":"119034","DOI":"10.1016\/j.measurement.2025.119034","article-title":"Correction of particle size effect interference in NIRS-XRF coal analysis using imaging techniques","volume":"257","year":"2025","journal-title":"Measurement"},{"issue":"2","key":"2026081713535135400_c39","doi-asserted-by":"publisher","first-page":"843","DOI":"10.5194\/mr-2-843-2021","article-title":"NUScon: A community-driven platform for quantitative evaluation of nonuniform sampling in NMR","volume":"2","year":"2021","journal-title":"Magn. Reson."},{"issue":"21","key":"2026081713535135400_c40","doi-asserted-by":"publisher","first-page":"5085","DOI":"10.1021\/acs.jpclett.1c01022","article-title":"High-resolution reconstruction for multidimensional Laplace NMR","volume":"12","year":"2021","journal-title":"J.\u00a0Phys. Chem. Lett."},{"issue":"6","key":"2026081713535135400_c41","doi-asserted-by":"publisher","first-page":"2699","DOI":"10.1021\/acs.analchem.1c03883","article-title":"Neural network method for diffusion-ordered NMR spectroscopy","volume":"94","year":"2022","journal-title":"Anal. Chem."}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0346251\/21108151\/074108_1_5.0346251.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0346251\/21108151\/074108_1_5.0346251.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T17:53:58Z","timestamp":1786989238000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/165\/7\/074108\/3401241\/STELT-A-spatiotemporal-deep-learning-framework-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":41,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,8,21]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0346251","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"value":"0021-9606","type":"print"},{"value":"1089-7690","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8,21]]},"published":{"date-parts":[[2026,8,17]]},"article-number":"074108"}}