{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:46:10Z","timestamp":1791996370898,"version":"4.4.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T00:00:00Z","timestamp":1791849600000},"content-version":"vor","delay-in-days":92,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate and efficient coal classification is essential for optimizing energy production, improving resource utilization, and ensuring environmental compliance in industrial applications. Traditional methods that rely on visual inspection and laboratory analysis are often slow, subjective, and difficult to scale. In response to these challenges, this research proposes a custom task adaptive lightweight convolutional neural network that integrates Separable Convolutional Blocks, Inverted Residual Blocks, and Squeeze and Excitation mechanisms to achieve high classification performance with low computational overhead. The model is trained and evaluated on the large scale DsCGF dataset, which comprises over 270,000 images of coal, gangue, foreign objects, and unknown materials collected under real world production and non-production conditions from multiple mining regions. The experimental results show that the proposed model achieves classification accuracies of 93.73% on Anhui Guobei production dataset, 99.97% on the Anhui Guobei non-production dataset, 99.26% on the Inner Mongolia Erlintu production dataset, and 90.50% on the challenging Shanxi Wangjialing production dataset, while using only 1.72\u00a0million parameters and achieving an average inference time of 0.023\u00a0s per image. Compared with well-established transfer learning models such as MobileNetV2, DenseNet201, and Xception, the proposed architecture consistently demonstrates superior or comparable performance across accuracy, precision, recall, and F1 score metrics with significantly reduced computational complexity. To enhance interpretability and provide visual insights into model predictions, explainable artificial intelligence techniques including Grad-CAM, Grad-CAM++, and Score-CAM are employed to visualize class discriminative regions. The proposed framework provides a practical, interpretable, and resource efficient solution for coal classification and contributes meaningfully to the advancement of intelligent mining systems.<\/jats:p>","DOI":"10.1038\/s41598-026-61406-9","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:08:17Z","timestamp":1783919297000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A lightweight explainable deep learning framework for coal classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Avijit","family":"Paul","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farjahan Akter","family":"Boby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yamina","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fariha","family":"Haque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeasin","family":"Arafat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Asif","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7300-506X","authenticated-orcid":false,"given":"Mominul","family":"Ahsan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanaa A.","family":"Abdallah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"61406_CR1","doi-asserted-by":"crossref","unstructured":"Yin, J., Liu, R., Yin, W., Jia, S. & Zhang, L. Deit and image deep learning-driven correction of particle size effect: A novel approach to improving NIRS-XRF coal quality analysis accuracy. Sensors, 25 (2025). ,3,928.","DOI":"10.3390\/s25030928"},{"key":"61406_CR2","doi-asserted-by":"crossref","unstructured":"Maxwell, K., Rajabi, M. & Esterle, J. Automated classification of metamorphosed coal from geophysical log data using supervised machine learning techniques. International J. Coal Geology, 214,103284, (2019).","DOI":"10.1016\/j.coal.2019.103284"},{"issue":"1","key":"61406_CR3","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1071\/AJ18091","volume":"59","author":"R Zhong","year":"2019","unstructured":"Zhong, R., Johnson, R., Chen, Z. & Chand, N. Coal identification using neural networks with real-time coalbed methane drilling data. APPEA J. 59 (1), 319\u2013327 (2019).","journal-title":"APPEA J."},{"issue":"7","key":"61406_CR4","doi-asserted-by":"publisher","first-page":"4192","DOI":"10.1109\/TGRS.2018.2890040","volume":"57","author":"BT Le","year":"2019","unstructured":"Le, B. T. et al. Coal quality exploration technology based on an incremental multilayer extreme learning machine and remote sensing images. IEEE Trans. Geosci. Remote Sens. 57(7), 4192\u20134201 (2019).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"61406_CR5","doi-asserted-by":"crossref","unstructured":"Shi, P., Zhang, J., Li, B., Yan, H. & Xia, Y. Mechanical property weakening mechanisms and ensemble assessment during coalbed carbon sequestration. Fuel, 395,135197, (2025).","DOI":"10.1016\/j.fuel.2025.135197"},{"key":"61406_CR6","doi-asserted-by":"crossref","unstructured":"Wang, C., Liu, Y., Li, Y., Liu, X. & Wang, Q. Classification of coal bursting liability of some Chinese coals using machine learning methods. Scientific Reports, 14,1,14030, (2024).","DOI":"10.1038\/s41598-024-61801-0"},{"key":"61406_CR7","doi-asserted-by":"publisher","first-page":"1675","DOI":"10.1007\/s11053-019-09536-y","volume":"29,3","author":"S Karimpouli","year":"2020","unstructured":"Karimpouli, S., Tahmasebi, P. & Saenger, E. H. Coal Cleat\/Fracture Segmentation Using Convolutional Neural Networks: Karimpouli, Tahmasebi, and Saenger. Nat. Resour. Res. 29,3, 1675\u20131685 (2020).","journal-title":"Nat. Resour. Res."},{"key":"61406_CR8","doi-asserted-by":"crossref","unstructured":"Yang, X. et al. Coal burst spatio-temporal prediction method based on bidirectional long short-term memory network. International J. Coal Sci. & Technology, 12,1,11, (2025).","DOI":"10.1007\/s40789-025-00759-4"},{"key":"61406_CR9","doi-asserted-by":"crossref","unstructured":"Gao, R. et al. Automatic coal and gangue segmentation using u-net based fully convolutional networks. Energies, 13 (2020). ,4,829.","DOI":"10.3390\/en13040829"},{"key":"61406_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2024.100388","volume":"17","author":"K Zhang","year":"2024","unstructured":"Zhang, K. et al. STATNet: One-stage coal-gangue detector based on deep learning algorithm for real industrial application. Energy AI 17, 100388 (2024).","journal-title":"Energy AI"},{"key":"61406_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, Z., Liu, X., Wang, L. & Xia, X. Deep learning-based image classification for online multi-coal and multi-class sorting. Computers & Geosciences, 157,104922, (2021).","DOI":"10.1016\/j.cageo.2021.104922"},{"key":"61406_CR12","doi-asserted-by":"crossref","unstructured":"Song, Q. et al. A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition. Scientific Reports, 15 (2025). ,1,101.","DOI":"10.1038\/s41598-024-83604-z"},{"key":"61406_CR13","doi-asserted-by":"publisher","first-page":"107126","DOI":"10.1016\/j.mineng.2021.107126","volume":"171","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Zhang, Z., Liu, X., Wang, L. & Xia, X. Performance evaluation of a deep learning based wet coal image classification. Miner. Eng. 171, 107126 (2021).","journal-title":"Miner. Eng."},{"key":"61406_CR14","doi-asserted-by":"crossref","unstructured":"Ye, Y., Dong, L., Zhou, C. & Dai, W. Advancing coal and gangue classification: A novel approach using 3D-CT data and deep learning. Measurement, 250,117118, (2025).","DOI":"10.1016\/j.measurement.2025.117118"},{"issue":"1","key":"61406_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-67323-z","volume":"14","author":"K Zhang","year":"2024","unstructured":"Zhang, K. et al. Design and application of coal gangue sorting system based on deep learning. Sci. Rep. 14(1), 16508 (2024).","journal-title":"Sci. Rep."},{"key":"61406_CR16","doi-asserted-by":"publisher","first-page":"77599","DOI":"10.1109\/ACCESS.2021.3081442","volume":"9","author":"Q Liu","year":"2021","unstructured":"Liu, Q., Li, J., Li, Y. & Gao, M. Recognition methods for coal and coal gangue based on deep learning. IEEE Access 9, 77599\u201377610 (2021).","journal-title":"IEEE Access"},{"key":"61406_CR17","doi-asserted-by":"crossref","unstructured":"Hu, T., Zhuang, D. & Qiu, J. An EfficientNetv2-based method for coal conveyor belt foreign object detection. Frontiers Energy Research, 12,1444877, (2025).","DOI":"10.3389\/fenrg.2024.1444877"},{"key":"61406_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2024.106342","volume":"157","author":"S Xu","year":"2025","unstructured":"Xu, S. et al. Neural texture synthesis and style transfer of coal-rock images in coal mine heading faces using very deep convolutional networks. Tunn. Undergr. Space Technol. 157, 106342 (2025).","journal-title":"Tunn. Undergr. Space Technol."},{"issue":"4","key":"61406_CR19","doi-asserted-by":"publisher","DOI":"10.3390\/app14041606","volume":"14","author":"D Wang","year":"2024","unstructured":"Wang, D. et al. Application of semi-supervised learning model to coal sample classification. Appl. Sci. 14(4), 1606 (2024).","journal-title":"Appl. Sci."},{"key":"61406_CR20","doi-asserted-by":"crossref","unstructured":"He, L., Zhou, Y., Liu, G. & Ma, J. An intelligent measurement framework for multi-type rock detection and classification in geological images. Measurement, 120304, (2026).","DOI":"10.1016\/j.measurement.2026.120304"},{"key":"61406_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2025.117674","volume":"253","author":"L-h He","year":"2025","unstructured":"He, L.-h, Zhou, Y.-z, Liu, L., Zhang, Y.-q & Ma, J.-h. Research on the directional bounding box algorithm of YOLO11 in tailings pond identification. Measurement 253, 117674 (2025).","journal-title":"Measurement"},{"key":"61406_CR22","doi-asserted-by":"crossref","unstructured":"He, L., Zhou, Y., Liu, L., Cao, W. & Ma, J. Research on object detection and recognition in remote sensing images based on YOLOv11. Scientific Reports, 15 (2025). ,1,14032.","DOI":"10.1038\/s41598-025-96314-x"},{"key":"61406_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.113651","volume":"167","author":"J Ma","year":"2026","unstructured":"Ma, J., Zhou, Y., Su, L., Yang, H. & He, L. A domain-specific language model for engineering-scale geological reasoning and mineral exploration in the Qin-Hang belt. Eng. Appl. Artif. Intell. 167, 113651 (2026).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"61406_CR24","doi-asserted-by":"publisher","first-page":"80794","DOI":"10.1109\/ACCESS.2023.3300243","volume":"11","author":"S Chuanmeng","year":"2023","unstructured":"Chuanmeng, S., Xinyu, L., Jiaxin, C., Zhibo, W. & Yong, L. Coal-rock image recognition method for complex and harsh environment in coal mine using deep learning models. IEEE Access 11, 80794\u201380805 (2023).","journal-title":"IEEE Access"},{"key":"61406_CR25","doi-asserted-by":"crossref","unstructured":"Sui, Y., Zhang, L., Sun, Z., Yi, W. & Wang, M. Research on coal and rock recognition in coal mining based on artificial neural network models. Applied Sciences, 14,2,864, (2024).","DOI":"10.3390\/app14020864"},{"key":"61406_CR26","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1038\/s41597-025-04719-0","volume":"12","author":"Z Lv","year":"2025","unstructured":"Lv, Z. et al. A large-scale open image dataset for deep learning-enabled intelligent sorting and analyzing of raw coal. Sci. Data. 12, 1403 (2025).","journal-title":"Sci. Data"},{"key":"61406_CR27","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P. & Balasubramanian, V. N. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks.839\u2013847 .","DOI":"10.1109\/WACV.2018.00097"},{"key":"61406_CR28","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization.618\u2013626 .","DOI":"10.1109\/ICCV.2017.74"},{"issue":"2","key":"61406_CR29","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336\u2013359 (2020).","journal-title":"Int. J. Comput. Vis."},{"key":"61406_CR30","unstructured":"Mundhenk, T. N., Chen, B. Y. & Friedland, G. Efficient saliency maps for explainable AI, arXiv preprint arXiv:.11293, 2019., 2019. (1911)."},{"key":"61406_CR31","unstructured":"Omeiza, D., Speakman, S., Cintas, C. & Weldermariam, K. Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models, arXiv preprint arXiv:.01224, 2019., 2019. (1908)."},{"key":"61406_CR32","unstructured":"Wang, H. et al. Score-CAM: Score-weighted visual explanations for convolutional neural networks.24\u201325."},{"key":"61406_CR33","doi-asserted-by":"publisher","first-page":"13711","DOI":"10.1109\/ACCESS.2025.3528341","volume":"13","author":"SA Birahim","year":"2025","unstructured":"Birahim, S. A. et al. Intrusion detection for wireless sensor network using particle swarm optimization based explainable ensemble machine learning approach. IEEE Access. 13, 13711\u201313730 (2025).","journal-title":"IEEE Access."},{"key":"61406_CR34","doi-asserted-by":"publisher","DOI":"10.62177\/jaet.v2i4.958","author":"W Chai","year":"2025","unstructured":"Chai, W. et al. Image classification in coal production using deep neural networks: A comprehensive benchmarking study. Journal of Advances in Engineering and Technology https:\/\/doi.org\/10.62177\/jaet.v2i4.958 (2025).","journal-title":"Journal of Advances in Engineering and Technology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61406-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61406-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61406-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:02:11Z","timestamp":1791993731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61406-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["61406"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-61406-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"13 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"32001"}}