{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:48:12Z","timestamp":1791809292977,"version":"4.3.4"},"reference-count":61,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2026AFC1190"],"award-info":[{"award-number":["2026AFC1190"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3804502"],"award-info":[{"award-number":["2023YFC3804502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Microscopic deformation stage recognition from molecular dynamics (MD) trajectories is crucial for understanding the evolution of material damage; however, traditional empirical analysis and black-box single deep-learning models lack both high-throughput spatiotemporal modeling and transparent physical interpretability. This work develops a multiscale interpretable deep-learning framework to automatically classify elastic, plastic, and fracture stages from uniaxial tensile MD trajectories and physically decode model decision logic. First, a 3D atomic trajectory is converted to 2D gray-scale image sequences; a CNN-LSTM hybrid architecture is built to jointly extract spatial atomic textures and long-time deformation dynamics, reaching 98.8% test accuracy and far surpassing spatial-only CNN baselines in both supervised classification and unsupervised clustering. More importantly, a hierarchical multiscale interpretability toolkit, including multilayer feature heatmaps, smoothed gradient saliency maps, gradient-weighted class activation maps, and regularized SHAP attribution, is integrated to quantify positive\/negative feature contributions and localize model focus regions. The visualized attention zones perfectly match core physical fields (von Mises strain, atomic displacement, and nonaffine deformation), resolving the explainability gap of conventional MD data mining pipelines. This work establishes a generalizable, trustworthy AI paradigm that connects data-driven prediction to intrinsic microscale mechanical mechanisms for computational material research.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01426","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T07:01:57Z","timestamp":1789974117000},"page":"12326-12345","source":"Crossref","is-referenced-by-count":0,"title":["Multiscale Interpretable\nDeep-Learning Framework for\nthe Identification and Visualization of Deformation Stages in Molecular\nDynamics Trajectory"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3984-5468","authenticated-orcid":true,"given":"Zhengwu","family":"Long","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]},{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]},{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6576-8200","authenticated-orcid":true,"given":"Lingyun","family":"You","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]},{"name":"Huazhong University of Science and Technology , , ,","place":["Wuhan, China, 430074"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"2026101208075315100_cit1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2024.100600","article-title":"Review of machine learning\napplications for defect detection in composite materials","volume":"18","author":"Daghigh","year":"2024","journal-title":"Mach. Learn. Appl."},{"key":"2026101208075315100_cit2","doi-asserted-by":"publisher","DOI":"10.1002\/inf2.12275","article-title":"Next-generation\nmachine vision systems incorporating two-dimensional materials: Progress\nand perspectives","volume":"4","author":"Wu","year":"2022","journal-title":"InfoMat"},{"key":"2026101208075315100_cit3","doi-asserted-by":"publisher","first-page":"2797","DOI":"10.1080\/10589759.2024.2404497","article-title":"A review of machine\nvision technology for defect detection in curved\nceramic materials","volume":"40","author":"Dong","year":"2025","journal-title":"Nondestruct. Test. Eval."},{"key":"2026101208075315100_cit4","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41586-020-2038-x","article-title":"Ultrafast machine vision with 2D\nmaterial neural network image sensors","volume":"579","author":"Mennel","year":"2020","journal-title":"Nature"},{"key":"2026101208075315100_cit5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2025.166262","article-title":"Epoxy steel slag asphalt\nmixture: Achieving breakthrough in pavement performance and efficient\nwaste resource utilization","volume":"520","author":"Sun","year":"2025","journal-title":"Chem. Eng. J."},{"key":"2026101208075315100_cit6","doi-asserted-by":"publisher","DOI":"10.1002\/app.70532","article-title":"Multi-Physical Properties\nof Epoxy Asphalt Under Component Variations: A Molecular Dynamics\nSimulation and Experimental Study","volume":"143","author":"Sun","year":"2026","journal-title":"J. Appl.\nPolym. Sci."},{"key":"2026101208075315100_cit7","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1021\/acsmaterialslett.2c00911","article-title":"Photoelectric Memristor-Based\nMachine Vision for Artificial Intelligence Applications","volume":"5","author":"Yang","year":"2023","journal-title":"ACS Mater. Lett."},{"key":"2026101208075315100_cit8","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1038\/s41578-024-00750-6","article-title":"Biomimetic optoelectronics with nanomaterials\nfor artificial vision","volume":"10","author":"Long","year":"2025","journal-title":"Nat. Rev. Mater."},{"key":"2026101208075315100_cit9","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100134","article-title":"Deep learning\nin computer vision: A critical review of emerging techniques and application\nscenarios","volume":"6","author":"Chai","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"2026101208075315100_cit10","doi-asserted-by":"publisher","first-page":"139489","DOI":"10.1109\/ACCESS.2021.3118541","article-title":"Video Processing Using\nDeep Learning Techniques: A Systematic Literature Review","volume":"9","author":"Sharma","year":"2021","journal-title":"IEEE Access"},{"key":"2026101208075315100_cit11","doi-asserted-by":"publisher","first-page":"5929","DOI":"10.1007\/s10462-020-09838-1","article-title":"A review on\nthe long short-term memory model","volume":"53","author":"Van Houdt","year":"2020","journal-title":"Artif. Intell.\nRev."},{"key":"2026101208075315100_cit12","doi-asserted-by":"crossref","unstructured":"Dhongde, V. S.; Sharma, C. In  Anomaly Detection\nin Video Surveillance using Deep Learning Techniques: A Review, 2025 5th International Conference on Expert Clouds and Applications\n(ICOECA); IEEE, 2025; pp 751\u2013757.","DOI":"10.1109\/ICOECA66273.2025.00134"},{"key":"2026101208075315100_cit13","doi-asserted-by":"publisher","first-page":"26597","DOI":"10.1007\/s11042-019-07788-7","article-title":"A Hybrid CNN-LSTM Model\nfor Improving Accuracy of Movie Reviews Sentiment Analysis","volume":"78","author":"Rehman","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"2026101208075315100_cit14","doi-asserted-by":"publisher","first-page":"9396","DOI":"10.1109\/TPAMI.2021.3126387","article-title":"Low-Light Image and Video Enhancement Using Deep Learning:\nA Survey","volume":"44","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026101208075315100_cit15","doi-asserted-by":"publisher","first-page":"164811","DOI":"10.1109\/ACCESS.2024.3491868","article-title":"Video Surveillance\nAnomaly Detection:\nA Review on Deep Learning Benchmarks","volume":"12","author":"Duja","year":"2024","journal-title":"IEEE Access"},{"key":"2026101208075315100_cit16","doi-asserted-by":"publisher","DOI":"10.1080\/10298436.2026.2633307","article-title":"Mechanistic\ninsights into restoring\nseverely aged asphalt using sustainable rejuvenators from molecular\nto macroscopic scales","volume":"27","author":"Long","year":"2026","journal-title":"Int. J. Pavement Eng."},{"key":"2026101208075315100_cit17","doi-asserted-by":"publisher","DOI":"10.1016\/j.carbon.2026.121449","article-title":"In situ nanomechanical\nvisualization reveals nanocracks in aged asphalt during stress relaxation","volume":"253","author":"Long","year":"2026","journal-title":"Carbon"},{"key":"2026101208075315100_cit18","doi-asserted-by":"publisher","DOI":"10.1016\/j.corsci.2026.113794","article-title":"Molecular\ndynamics of salt solution\nmigration and damage on rough aggregate surfaces","volume":"265","author":"Wang","year":"2026","journal-title":"Corros. Sci."},{"key":"2026101208075315100_cit19","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.1007\/s11831-025-10257-0","article-title":"Recent Trends and Progress\nin Molecular Dynamics Simulations of 2D\nMaterials for Tribological Applications: An Extensive Review","volume":"32","author":"Kumar","year":"2025","journal-title":"Arch. Comput. Method Eng."},{"key":"2026101208075315100_cit20","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1038\/nsb0902-646","article-title":"Molecular dynamics\nsimulations of biomolecules","volume":"9","author":"Karplus","year":"2002","journal-title":"Nat. Struct. Biol."},{"key":"2026101208075315100_cit21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ceja.2025.100731","article-title":"Applications\nof molecular dynamics\nin nanomaterial design and characterization - A review","volume":"22","author":"Islam","year":"2025","journal-title":"Chem. Eng. J. Adv."},{"key":"2026101208075315100_cit22","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning\nfor molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"2026101208075315100_cit23","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","article-title":"Inverse molecular\ndesign using machine learning: Generative\nmodels for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science"},{"key":"2026101208075315100_cit24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18959-8","article-title":"Learning molecular\ndynamics with\nsimple language model built upon long short-term memory neural network","volume":"11","author":"Tsai","year":"2020","journal-title":"Nat. Commun."},{"key":"2026101208075315100_cit25","doi-asserted-by":"publisher","first-page":"9722","DOI":"10.1021\/acs.chemrev.0c01195","article-title":"Unsupervised Learning\nMethods for Molecular Simulation Data","volume":"121","author":"Glielmo","year":"2021","journal-title":"Chem.\nRev."},{"key":"2026101208075315100_cit26","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","article-title":"Machine Learning Force Fields","volume":"121","author":"Unke","year":"2021","journal-title":"Chem. Rev."},{"key":"2026101208075315100_cit27","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2026.103452","article-title":"Fusing generative AI and ML-FFs for inverse design and high-fidelity\ndynamic simulation of fused-ring aromatic hydrocarbons","volume":"7","author":"Long","year":"2026","journal-title":"Cell Rep. Phys. Sci."},{"key":"2026101208075315100_cit28","doi-asserted-by":"publisher","first-page":"2177","DOI":"10.1021\/acs.jcim.5c03194","article-title":"Reactive Neural Network Potential\nDeveloped for Asphalt Aging Systems\nThrough Active Learning and Enhanced Sampling","volume":"66","author":"Long","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208075315100_cit29","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1021\/acs.jctc.0c01343","article-title":"TorchMD: A\nDeep Learning Framework for Molecular Simulations","volume":"17","author":"Doerr","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"2026101208075315100_cit30","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1021\/acs.jctc.3c00975","article-title":"Analyzing\nMolecular Dynamics Trajectories Thermodynamically through Artificial\nIntelligence","volume":"20","author":"Liu","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101208075315100_cit31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-022-00773-z","article-title":"Accurate and\nefficient molecular dynamics based on machine learning\nand non von Neumann architecture","volume":"8","author":"Mo","year":"2022","journal-title":"Npj Comput.\nMater."},{"key":"2026101208075315100_cit32","doi-asserted-by":"publisher","first-page":"5375","DOI":"10.1021\/acs.jpcb.4c08824","article-title":"Using Machine\nLearning to Analyze Molecular Dynamics Simulations of Biomolecules","volume":"129","author":"Brownless","year":"2025","journal-title":"J. Phys. Chem. B"},{"key":"2026101208075315100_cit33","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2024.113403","article-title":"Combining\nmachine learning\nand molecular dynamics to predict strength-toughness and energy dissipation\nmechanisms of hybrid double-crosslinked CNT networks","volume":"246","author":"Wu","year":"2025","journal-title":"Comput. Mater. Sci."},{"key":"2026101208075315100_cit34","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202405379","article-title":"Machine Learning\nMolecular Dynamics Shows Anomalous Entropic Effect on Catalysis through\nSurface Pre-melting of Nanoclusters","volume":"63","author":"Gong","year":"2024","journal-title":"Angew.\nChem., Int. Ed."},{"key":"2026101208075315100_cit35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csite.2025.106684","article-title":"A hybrid molecular\ndynamics\u2013machine learning framework for boiling point estimation\nin aromatic fluids","volume":"73","author":"Shateri","year":"2025","journal-title":"Case Stud. Therm. Eng."},{"key":"2026101208075315100_cit36","doi-asserted-by":"publisher","DOI":"10.1088\/2752-5724\/ac681d","article-title":"Deep potentials\nfor materials science","volume":"1","author":"Wen","year":"2022","journal-title":"Mater. Futures"},{"key":"2026101208075315100_cit37","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201902765","article-title":"Machine Learning\nInteratomic Potentials\nas Emerging Tools for Materials Science","volume":"31","author":"Deringer","year":"2019","journal-title":"Adv.\nMater."},{"key":"2026101208075315100_cit38","doi-asserted-by":"publisher","first-page":"4790","DOI":"10.1039\/D5CS00104H","article-title":"The evolution\nof machine learning\npotentials for molecules, reactions and materials","volume":"54","author":"Xia","year":"2025","journal-title":"Chem. Soc. Rev."},{"key":"2026101208075315100_cit39","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1038\/s41563-020-0777-6","article-title":"Machine-learned\npotentials for next-generation matter simulations","volume":"20","author":"Friederich","year":"2021","journal-title":"Nat. Mater."},{"key":"2026101208075315100_cit40","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1021\/acs.nanolett.9b04090","article-title":"Machine Learning\nin Nanoscience: Big Data at Small Scales","volume":"20","author":"Brown","year":"2020","journal-title":"Nano\nLett."},{"key":"2026101208075315100_cit41","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00884-7","article-title":"Explainable machine learning in materials\nscience","volume":"8","author":"Zhong","year":"2022","journal-title":"Npj Comput. Mater."},{"key":"2026101208075315100_cit42","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1080\/07350015.2019.1624293","article-title":"Causal Interpretations\nof Black-Box Models","volume":"39","author":"Zhao","year":"2021","journal-title":"J. Bus. Econ. Stat."},{"key":"2026101208075315100_cit43","doi-asserted-by":"publisher","first-page":"3416","DOI":"10.1109\/TPAMI.2020.2982882","article-title":"Interpretable\nCNNs for Object Classification","volume":"43","author":"Zhang","year":"2021","journal-title":"IEEE Trans.\nPattern Anal. Mach. Intell."},{"key":"2026101208075315100_cit44","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1021\/accountsmr.1c00244","article-title":"Interpretable and\nExplainable Machine Learning for Materials Science and Chemistry","volume":"3","author":"Oviedo","year":"2022","journal-title":"Acc. Mater. Res."},{"key":"2026101208075315100_cit45","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abm7185","article-title":"Machine learning of material properties:\nPredictive\nand interpretable multilinear models","volume":"8","author":"Allen","year":"2022","journal-title":"Sci. Adv."},{"key":"2026101208075315100_cit46","unstructured":"Lundberg, S. M.; Lee, S. In  A Unified Approach\nto Interpreting Model Predictions, Proceedings of the 31st\nInternational Conference on Neural Information Processing Systems; NeurIPS: Long Beach, California,\nUSA, 2017; pp 4768\u20134777."},{"key":"2026101208075315100_cit47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108171","article-title":"LAMMPS\n- a flexible simulation tool for particle-based materials modeling\nat the atomic, meso, and continuum scales","volume":"271","author":"Thompson","year":"2022","journal-title":"Comput.\nPhys. Commun."},{"key":"2026101208075315100_cit48","doi-asserted-by":"publisher","first-page":"7338","DOI":"10.1021\/jp980939v","article-title":"COMPASS: An\nab Initio Force-Field Optimized for Condensed-Phase ApplicationsOverview\nwith Details on Alkane and Benzene Compounds","volume":"102","author":"Sun","year":"1998","journal-title":"J. Phys. Chem. B"},{"key":"2026101208075315100_cit49","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1063\/1.447334","article-title":"A unified\nformulation of the constant temperature molecular dynamics methods","volume":"81","author":"Nose\u0301","year":"1984","journal-title":"J. Chem. Phys."},{"key":"2026101208075315100_cit50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.31.1695","article-title":"Canonical\ndynamics: Equilibrium phase-space distributions","volume":"31","author":"Hoover","year":"1985","journal-title":"Phys. Rev. A"},{"key":"2026101208075315100_cit51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1995.1039","article-title":"Fast Parallel\nAlgorithms for Short-Range Molecular Dynamics","volume":"117","author":"Plimpton","year":"1995","journal-title":"J. Comput. Phys."},{"key":"2026101208075315100_cit52","doi-asserted-by":"publisher","first-page":"6478","DOI":"10.1021\/acs.jcim.6c00479","article-title":"Constrained Low-Dimensional Parametrization of Coarse-Grained Force\nFields for Structural and Thermodynamic Consistency","volume":"66","author":"Xie","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208075315100_cit53","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1016\/j.jcis.2022.08.014","article-title":"Nanomechanical-atomistic\ninsights on interface interactions in asphalt\nmixtures with various chloride ion erosion statuses","volume":"628","author":"Long","year":"2022","journal-title":"J. Colloid. Interface. Sci."},{"key":"2026101208075315100_cit54","doi-asserted-by":"publisher","first-page":"17433","DOI":"10.1039\/D5CP01370D","article-title":"New chemical average\nmodel for molecular simulations of the asphalt\nsystem","volume":"27","author":"Long","year":"2025","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026101208075315100_cit55","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.msea.2015.11.100","article-title":"Molecular dynamics\nsimulation study of deformation mechanisms in\n3C\u2013SiC during nanometric cutting at elevated temperatures","volume":"654","author":"Chavoshi","year":"2016","journal-title":"Mater. Sci. Eng. A"},{"key":"2026101208075315100_cit56","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2026.122263","article-title":"Atomistic insights\ninto the enhancement of dynamic yield and fracture responses by chemical\nshort-range order in CoCrNi multi-principal element alloy under quasi-isentropic\nloading","volume":"312","author":"Xie","year":"2026","journal-title":"Acta Mater."},{"key":"2026101208075315100_cit57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnoncrysol.2025.123483","article-title":"Revealing\nstructural evolution during stress relaxation in metallic glass by\nnanoindentation and molecular dynamic simulation","volume":"656","author":"Liu","year":"2025","journal-title":"J. Non-Cryst. Solids"},{"key":"2026101208075315100_cit58","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A Review of Recurrent Neural Networks:\nLSTM Cells and Network Architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural\nComput."},{"key":"2026101208075315100_cit59","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. In  Grad-CAM: Visual Explanations\nfrom Deep\nNetworks via Gradient-Based Localization, 2017 IEEE International\nConference on Computer Vision (ICCV); IEEE, 2017.","DOI":"10.1109\/ICCV.2017.74"},{"key":"2026101208075315100_cit60","doi-asserted-by":"publisher","first-page":"5875","DOI":"10.1109\/TIP.2021.3089943","article-title":"LayerCAM:\nExploring Hierarchical Class Activation Maps for Localization","volume":"30","author":"Jiang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"2026101208075315100_cit61","doi-asserted-by":"crossref","unstructured":"Ribeiro\n            ; ; Tulio, M.; Singh, S.; Guestrin, C. In  \u201cWhy Should I Trust You?\u201d, Proceedings\nof the 22nd ACM SIGKDD international conference on knowledge discovery\nand data mining; ACM, 2016.","DOI":"10.1145\/2939672.2939778"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01426","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12326\/68569753\/acs.jcim.6c01426.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12326\/68569753\/acs.jcim.6c01426.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:14:06Z","timestamp":1791807246000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/19\/12326\/5433640\/Multiscale-Interpretable-Deep-Learning-Framework"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":61,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,21]]},"published-print":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01426","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}