{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T16:43:48Z","timestamp":1778431428606,"version":"3.51.4"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Research and Development Program of China State Railway Group Co., Ltd.","award":["K2022G015"],"award-info":[{"award-number":["K2022G015"]}]},{"name":"Science and Technology Research and Development Program of China State Railway Group Co., Ltd.","award":["2022YJ305"],"award-info":[{"award-number":["2022YJ305"]}]},{"name":"Fund Project of China Academy of Railway Sciences Corporation Limited","award":["K2022G015"],"award-info":[{"award-number":["K2022G015"]}]},{"name":"Fund Project of China Academy of Railway Sciences Corporation Limited","award":["2022YJ305"],"award-info":[{"award-number":["2022YJ305"]}]},{"name":"Delft University of Technology","award":["K2022G015"],"award-info":[{"award-number":["K2022G015"]}]},{"name":"Delft University of Technology","award":["2022YJ305"],"award-info":[{"award-number":["2022YJ305"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Vehicle-mounted ground-penetrating radar (GPR) has been used to non-destructively inspect and evaluate railway subgrade conditions. However, existing GPR data processing and interpretation methods mostly rely on time-consuming manual interpretation, and limited studies have applied machine learning methods. GPR data are complex, high-dimensional, and redundant, in particular with non-negligible noises, for which traditional machine learning methods are not effective when applied to GPR data processing and interpretation. To solve this problem, deep learning is more suitable to process large amounts of training data, as well as to perform better data interpretation. In this study, we proposed a novel deep learning method to process GPR data, the CRNN network, which combines convolutional neural networks (CNN) and recurrent neural networks (RNN). The CNN processes raw GPR waveform data from signal channels, and the RNN processes features from multiple channels. The results show that the CRNN network achieves a higher precision at 83.4%, with a recall of 77.3%. Compared to the traditional machine learning method, the CRNN is 5.2 times faster and has a smaller size of 2.6 MB (traditional machine learning method: 104.0 MB). Our research output has demonstrated that the developed deep learning method improves the efficiency and accuracy of railway subgrade condition evaluation.<\/jats:p>","DOI":"10.3390\/s23125383","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T02:02:15Z","timestamp":1686103335000},"page":"5383","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Combined CNN and RNN Neural Networks for GPR Detection of Railway Subgrade Diseases"],"prefix":"10.3390","volume":"23","author":[{"given":"Huan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China"},{"name":"Railway Engineering Research Institute, China Academy of Railway Sciences Co., Ltd., Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shilei","family":"Wang","sequence":"additional","affiliation":[{"name":"Infrastructure Inspection Research Institute, China Academy of Railway Sciences Co., Ltd., Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9655-2229","authenticated-orcid":false,"given":"Guoqing","family":"Jing","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziye","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Geophysics, China Earthquake Administration, Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Railway Engineering Research Institute, China Academy of Railway Sciences Co., Ltd., Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4339-1833","authenticated-orcid":false,"given":"Yunlong","family":"Guo","sequence":"additional","affiliation":[{"name":"Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, G., Jing, G., Feng, Q., Liu, H., and Guo, Y. (2022). State-of-the-Art Review of Ground Penetrating Radar (GPR) Applications for Railway Ballast Inspection. Sensors, 22.","DOI":"10.3390\/s22072450"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Fontul, S., Paix\u00e3o, A., Solla, M., and Pajewski, L. (2018). Railway Track Condition Assessment at Network Level by Frequency Domain Analysis of GPR Data. Remote Sens., 10.","DOI":"10.3390\/rs10040559"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/JSTARS.2015.2487970","article-title":"Permafrost Subgrade Condition Assessment Using Extrapolation by Deterministic Deconvolution on Multifrequency GPR Data Acquired Along the Qinghai-Tibet Railway","volume":"9","author":"Xiao","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bano, M., Tsend-Ayush, N., Schlupp, A., and Munkhuu, U. (2021). Ground-Penetrating Radar Imaging of Near-Surface Deformation along the Songino Active Fault in the Vicinity of Ulaanbaatar, Mongolia. Appl. Sci., 11.","DOI":"10.3390\/app11178242"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Solla, M., P\u00e9rez-Gracia, V., and Fontul, S. (2021). A Review of GPR Application on Transport Infrastructures: Troubleshooting and Best Practices. Remote Sens., 13.","DOI":"10.3390\/rs13040672"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1177\/1475921719838081","article-title":"Deep learning-based automated underground cavity detection using three-dimensional ground penetrating radar","volume":"19","author":"Kang","year":"2020","journal-title":"Struct. Health Monit."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Manataki, M., Vafidis, A., and Sarris, A. (2021). GPR Data Interpretation Approaches in Archaeological Prospection. Appl. Sci., 11.","DOI":"10.3390\/app11167531"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Francke, J. (2010, January 21\u201325). Applications of GPR in mineral resource evaluations. Proceedings of the XIII Internarional Conference on Ground Penetrating Radar, Lecce, Italy.","DOI":"10.1109\/ICGPR.2010.5550188"},{"key":"ref_9","unstructured":"Valles, J., Chapa, T., Matesanz, J., and Gonz\u00e1lez, M.A.M. (2017, January 20\u201323). Combined application of Multi-Channel 3D GPR and Photogrammetry from UAVs for the study of Archaeological sites. Proceedings of the 3th Technoheritage 2017 International Congress, C\u00e1diz, Spain."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.ndteint.2017.04.002","article-title":"A review of Ground Penetrating Radar application in civil engineering: A 30-year journey from Locating and Testing to Imaging and Diagnosis","volume":"96","author":"Lai","year":"2018","journal-title":"NDT E Int."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, S., Lu, Q., Li, H., and Wang, Y. (2020). Estimation of Moisture Content in Railway Subgrade by Ground Penetrating Radar. Remote Sens., 12.","DOI":"10.3390\/rs12182912"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Shao, W., Bouzerdoum, A., Phung, S.L., Su, L., Indraratna, B., and Rujikiatkamjorn, C. (2010, January 21\u201325). Automatic classification of GPR signals. Proceedings of the XIII Internarional Conference on Ground Penetrating Radar, Lecce, Italy.","DOI":"10.1109\/ICGPR.2010.5550187"},{"key":"ref_13","unstructured":"Du, C., Zhang, Q., and Liu, J. (2017, January 10\u201312). Intelligent identification of railway roadbed defects by vector machines. Proceedings of the 2017 Conference of China Civil Engineering Society, Guangzhou, China. (In Chinese)."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6030","DOI":"10.1038\/s41598-023-33278-w","article-title":"Identification of railway subgrade defects based on ground penetrating radar","volume":"13","author":"Hou","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2352006","DOI":"10.1142\/S0218001423520067","article-title":"A Deep CRNN-Based Sentiment Analysis System with Hybrid BERT Embedding","volume":"37","author":"Alyoubi","year":"2023","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lee, K., Lee, S., and Kim, H.Y. (2023). Deep Learning-Based Defect Detection Framework for Ultra High Resolution Images of Tunnels. Sustainability, 15.","DOI":"10.3390\/su15021292"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"628","DOI":"10.26599\/TST.2022.9010023","article-title":"SUNet++: A Deep Network with Channel Attention for Small-Scale Object Segmentation on 3D Medical Images","volume":"28","author":"Zhang","year":"2023","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108077","DOI":"10.1016\/j.measurement.2020.108077","article-title":"Autonomous pavement distress detection using ground penetrating radar and region-based deep learning","volume":"164","author":"Gao","year":"2020","journal-title":"Measurement"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Del Rincon, J.M., and Miller, P. (2016, January 27\u201330). Recurrent Convolutional Network for Video-Based Person Re-identification. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1111\/mice.12406","article-title":"Convolutional Neural Network for Asphalt Pavement Surface Texture Analysis: Convolutional neural network","volume":"33","author":"Tong","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_21","unstructured":"Bishop, S.S., and Isaacs, J.C. (2015). Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, SPIE Defense + Security."},{"key":"ref_22","first-page":"99","article-title":"Intelligent identification method for railway roadbed slurry and mud infestation based on Cas-cade R-CNN","volume":"29","author":"Xu","year":"2019","journal-title":"Railw. Eng."},{"key":"ref_23","first-page":"272","article-title":"Intelligent detection method for railway roadbed defects","volume":"57","author":"Ma","year":"2021","journal-title":"Comput. Eng. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"120371","DOI":"10.1016\/j.conbuildmat.2020.120371","article-title":"Advances of deep learning applications in ground-penetrating radar: A survey","volume":"258","author":"Tong","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xu, Y., Kong, Q., Huang, Q., Wang, W., and Plumbley, M.D. (2017, January 14\u201319). Convolutional gated recurrent neural network incorporating spatial features for audio tagging. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104402","DOI":"10.1016\/j.tust.2022.104402","article-title":"Building simplified uncertainty models of object depth measurement by ground penetrating radar","volume":"123","author":"Xie","year":"2022","journal-title":"Tunn. Undergr. Space Technol."},{"key":"ref_27","unstructured":"Read, D., Meddah, A., Li, D., and Mui, W. (2017). Volpe Center, Ground Penetrating Radar Technology Evaluation on the High Tonnage Loop: Phase 1: DOT\/FRA\/ORD-17\/18."},{"key":"ref_28","unstructured":"Brown, M., and Li, D. (2017). Ground Penetrating Radar Technology Evaluation and Implementation: Phase 2: DOT\/FRA\/ORD-17\/19."},{"key":"ref_29","unstructured":"Basye, C., Wilk, S., and Gao, Y. (2020). Ground Penetrating Radar (GPR) Technology Evaluation and Implementation: DOT\/FRA\/ORD-20\/18."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104608","DOI":"10.1016\/j.jappgeo.2022.104608","article-title":"GPR method for continuous monitoring of compaction during the construction of railways subgrade","volume":"199","author":"Shapovalov","year":"2022","journal-title":"J. Appl. Geophys."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, F., Yang, F., Yan, R., Qiao, X., Xing, H., and Li, Y. (2022). Study on Significance Enhancement Algorithm of Abnormal Features of Urban Road Ground Penetrating Radar Images. Remote Sens., 14.","DOI":"10.3390\/rs14071546"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bianchini Ciampoli, L., Tosti, F., Economou, N., and Benedetto, F. (2019). Signal Processing of GPR Data for Road Surveys. Geosciences, 9.","DOI":"10.3390\/geosciences9020096"},{"key":"ref_33","unstructured":"Lombardi, F., Griffiths, H., and Lualdi, M. (2016, January 5\u20137). The Influence of Spatial Sampling in GPR Surveys for the Detection of Landmines and IEDs. Proceedings of the 2016 European Radar Conference (EuRAD), London, UK."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.sigpro.2016.05.016","article-title":"An overview of ground-penetrating radar signal processing techniques for road inspections","volume":"132","author":"Benedetto","year":"2017","journal-title":"Signal Process."},{"key":"ref_35","unstructured":"Jol, H.M. (2009). Ground Penetrating Radar: Theory and Application, Elsevier."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.jappgeo.2015.06.006","article-title":"Application of the Ground Penetrating Radar ARMA power spectrum estimation method to detect moisture content and compactness values in sandy loam","volume":"120","author":"Cui","year":"2015","journal-title":"J. Appl. Geophys."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1111\/mice.12409","article-title":"Automated Pixel-Level Pavement Crack Detection on 3D Asphalt Surfaces with a Recurrent Neural Network: Automated pixel-level pavement crack detection on 3D asphalt surfaces using CrackNet-R","volume":"34","author":"Zhang","year":"2019","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Mauch, L., and Yang, B. (2015, January 14\u201316). A new approach for supervised power disaggregation by using a deep recurrent LSTM network. Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, USA.","DOI":"10.1109\/GlobalSIP.2015.7418157"},{"key":"ref_40","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, Chia, Italy."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_42","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., and Bengio, Y. (2014, January 25). On the Properties of Neural Machine Translation: Encoder\u2013Decoder Approaches. Proceedings of the SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar.","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref_44","unstructured":"Pascanu, R., Mikolov, T., and Bengio, Y. (2013). On the difficulty of training Recurrent Neural Networks. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Hou, F., Rui, X., Fan, X., and Zhang, H. (2022). Review of GPR Activities in Civil Infrastructures: Data Analysis and Applications. Remote Sens., 14.","DOI":"10.3390\/rs14235972"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5383\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:49:30Z","timestamp":1760125770000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,6]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23125383"],"URL":"https:\/\/doi.org\/10.3390\/s23125383","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,6]]}}}