{"id":2024,"date":"2025-11-25T15:31:25","date_gmt":"2025-11-25T07:31:25","guid":{"rendered":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/?p=2024"},"modified":"2025-11-25T15:33:42","modified_gmt":"2025-11-25T07:33:42","slug":"advancing-rock-mass-classification-using-machine-learning-approach","status":"publish","type":"post","link":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/?p=2024","title":{"rendered":"Advancing Rock Mass Classification Using Machine Learning Approach"},"content":{"rendered":"\n<p>Abstract<br>The rock mass rating (RMR) system is a widely used tool for assessing rock quality and recommending support, relying on six parameters: rock quality designation, uniaxial compressive strength, groundwater conditions, discontinuity spac-ing, condition, and orientation. The conventional RMR classification system necessitates the presence of all parameters. This study introduces a machine learning (ML) approach utilizing the random forest (RF) algorithm to predict rock mass classification with a reduced set of easily accessible parameters. A synthetic database of RMR parameters was generated to train the RF model, with Bayesian optimization applied to refine key settings such as learning rate, ensemble cycles, and maximum splits. The ML model was validated for accuracy and reliability through several performance metrics. Predictions of the proposed ML model using data from 41 real-world field cases demonstrate a high accuracy of 100%. With the advantages of the artificial intelligence (AI), the proposed ML model maintained over 90% accuracy even when key parameters such as discontinuity length, separation, or infilling were unavailable. This AI-powered approach offers a significant improvement over traditional methods, providing superior accuracy, adaptability, and reliability for rock quality assessment and support recommendations.<br>Keywords Rock mass classification \u00b7 Rock mass rating \u00b7 Random forest \u00b7 Rock quality designation \u00b7 Machine learning<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>Bulletin of Engineering Geology and the Environment (2025) 84:612 <\/p>\n\n\n\n<p>https:\/\/doi.org\/10.1007\/s10064-025-04585-5<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u4e00\u3001\u7814\u7a76\u80cc\u666f\u8207\u52d5\u6a5f<\/h2>\n\n\n\n<p>\u50b3\u7d71\u7684 <strong>RMR\uff08Rock Mass Rating\uff09\u5ca9\u9ad4\u5206\u985e\u7cfb\u7d71<\/strong>\u9700\u516d\u5927\u53c3\u6578\uff0c\u5e38\u4ef0\u8cf4\u5927\u91cf\u73fe\u5730\u8abf\u67e5\uff0c\u8017\u6642\u3001\u6602\u8cb4\u4e14\u90e8\u5206\u53c3\u6578\u4e3b\u89c0\u6027\u9ad8\u3002<br>\u672c\u7814\u7a76\u5e0c\u671b\u900f\u904e <strong>\u6a5f\u5668\u5b78\u7fd2\uff08ML\uff09\u2014 \u96a8\u6a5f\u68ee\u6797\uff08RF\uff09<\/strong> \u5efa\u7acb\u4e00\u5957\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u53ef\u7528<strong>\u8f03\u5c11\u4e14\u5bb9\u6613\u53d6\u5f97\u7684\u53c3\u6578<\/strong><\/li>\n\n\n\n<li>\u4ecd\u80fd<strong>\u6e96\u78ba\u9810\u6e2c\u5ca9\u9ad4\u54c1\u8cea\uff08RMR\uff09<\/strong><\/li>\n\n\n\n<li>\u4e26\u80fd\u8655\u7406<strong>\u7f3a\u5c11\u90e8\u5206\u53c3\u6578<\/strong>\u7684\u60c5\u6cc1<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u4e8c\u3001\u65b9\u6cd5\u8a2d\u8a08<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">1. \u5efa\u69cb\u300c\u5408\u6210\u8cc7\u6599\u5eab\u300d<\/h3>\n\n\n\n<p>\u56e0\u771f\u5be6\u5b8c\u6574\u7684 12 \u9805 RMR \u53c3\u6578\u4e0d\u6613\u6536\u96c6\uff0c\u672c\u7814\u7a76\u4f9d\u64da\u6587\u737b\u7bc4\u570d\uff0c<strong>\u7cfb\u7d71\u6027\u751f\u6210 932,400 \u7d44\u8cc7\u6599<\/strong>\uff0c\u6db5\u84cb\u4ee5\u4e0b 12 \u53c3\u6578\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>UCS\u3001RQD\u3001\u7bc0\u7406\u9593\u8ddd\u3001\u7bc0\u7406\u9577\u5ea6\u3001\u958b\u53e3\u3001\u7c97\u7cd9\u5ea6\u3001\u5145\u586b\u3001\u98a8\u5316\u3001\u5730\u4e0b\u6c34\u3001\u7bc0\u7406\u8d70\u5411-\u50be\u89d2\u5f71\u97ff\u3001\u5de5\u7a0b\u985e\u578b\u3001\u50be\u89d2<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">2. \u96a8\u6a5f\u68ee\u6797\u6a21\u578b\u5efa\u7acb<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u4f7f\u7528 12 \u9805\u53c3\u6578\u4f5c\u70ba\u8f38\u5165\uff0c\u7e3d RMR \u4f5c\u70ba\u8f38\u51fa<\/li>\n\n\n\n<li>\u4f7f\u7528 <strong>Bayesian optimization\uff08\u8c9d\u6c0f\u6700\u4f73\u5316\uff09<\/strong> \u5fae\u8abf\u4e09\u500b\u95dc\u9375\u8d85\u53c3\u6578\uff1a\n<ul class=\"wp-block-list\">\n<li>Ensemble \u6578\u91cf\uff08\u6700\u4f73\u70ba 477\uff09<\/li>\n\n\n\n<li>Learning rate\uff08\u6700\u4f73\u70ba 0.37\uff09<\/li>\n\n\n\n<li>Maximum splits\uff08\u6700\u4f73\u70ba 120\uff09<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">3. \u6a21\u578b\u9a57\u8b49<\/h3>\n\n\n\n<p>\u6a21\u578b\u5728\u8a13\u7df4\u8207\u6e2c\u8a66\u4e0a\u5747\u8868\u73fe\u51fa\u6975\u9ad8\u7cbe\u5ea6\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>R\u00b2 = 0.99<\/strong><\/li>\n\n\n\n<li><strong>RMSE = 1.12\u00d710\u207b\u00b2<\/strong><\/li>\n\n\n\n<li><strong>WMAPE = 1.42\u00d710\u207b\u00b2<\/strong><\/li>\n\n\n\n<li><strong>NS = 0.99<\/strong><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u4e09\u3001\u91cd\u8981\u53c3\u6578\u5206\u6790<\/h2>\n\n\n\n<p>\u6a21\u578b\u5229\u7528 Out-of-Bag\uff08OOB\uff09\u5206\u6790\u5f97\u51fa\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u6700\u91cd\u8981\u7684\u5169\u9805\u53c3\u6578\uff1aRQD\uff08\u53c3\u65782\uff09\u8207\u5730\u4e0b\u6c34\u689d\u4ef6\uff08\u53c3\u65789\uff09<\/strong>\n<ul class=\"wp-block-list\">\n<li>RQD \u91cd\u8981\u6027\uff1a50.24<\/li>\n\n\n\n<li>\u5730\u4e0b\u6c34\u689d\u4ef6\u91cd\u8981\u6027\uff1a39.06<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n<p>\u8868\u793a\u9019\u5169\u8005\u5c0d RMR \u8a55\u5206\u7684\u5f71\u97ff\u6700\u95dc\u9375\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u56db\u3001\u7f3a\u53c3\u6578\u7684\u6a21\u578b\u8868\u73fe<\/h2>\n\n\n\n<p>\u4f5c\u8005\u69cb\u5efa 13 \u7a2e\u6a21\u578b\uff0c\u6bcf\u6b21\u79fb\u9664\u5176\u4e2d\u4e00\u500b\u53c3\u6578\u4ee5\u6e2c\u8a66\u5f71\u97ff\uff1a<\/p>\n\n\n\n<p><strong>\u7d50\u679c\u4eae\u9ede\uff1a<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u6a21\u578b1\uff08\u5168\u90e8\u53c3\u6578\uff09\u6e96\u78ba\u7387\uff1a100%<\/strong><\/li>\n\n\n\n<li><strong>\u6a21\u578b5\uff08\u7121\u7bc0\u7406\u9577\u5ea6\uff09\u4ecd\u9054 100%<\/strong><\/li>\n\n\n\n<li><strong>\u6a21\u578b6\u30017\u30018\uff08\u7f3a\u958b\u53e3\/\u7c97\u7cd9\u5ea6\/\u5145\u586b\uff09\u4ecd\u9054 90%\u2191<\/strong><\/li>\n\n\n\n<li><strong>\u6a21\u578b9\uff08\u7f3a\u98a8\u5316\uff09\u4ecd\u6709 87.8%<\/strong><\/li>\n<\/ul>\n\n\n\n<p>\u2192 \u8868\u793a RF \u6a21\u578b\u5373\u4f7f\u7f3a\u5c11\u90e8\u5206\u53c3\u6578\u4ecd\u80fd\u7dad\u6301\u9ad8\u6e96\u78ba\u5ea6\uff0c\u6975\u5177\u5de5\u7a0b\u61c9\u7528\u5f48\u6027\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u4e94\u3001\u5be6\u969b\u6848\u4f8b\u9a57\u8b49<\/h2>\n\n\n\n<p>\u8cc7\u6599\u4f86\u81ea\u7f8e\u570b\u3001\u6fb3\u6d32\u3001\u5e0c\u81d8\u3001\u7fa9\u5927\u5229\u3001\u5370\u5ea6\u3001\u4e2d\u570b\u3001\u4f0a\u6717\u7b49 41 \u7b46\u6a23\u672c\u3002<\/p>\n\n\n\n<p>\u6a21\u578b1 \u8207 \u6a21\u578b5 \u5b8c\u5168\u9810\u6e2c\u6b63\u78ba\uff0841\/41\uff09\u3002<br>\u6a21\u578b6\u20139 \u4e5f\u4fdd\u6301 87.8\u201392.7% \u7684\u6e96\u78ba\u7387\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u516d\u3001\u7814\u7a76\u7d50\u8ad6<\/h2>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>RF + Bayesian optimization<\/strong> \u53ef\u5927\u5e45\u63d0\u5347 RMR \u9810\u6e2c\u6548\u80fd\u3002<\/li>\n\n\n\n<li>\u5373\u4f7f **\u7f3a\u4e4f\u90e8\u5206\u7bc0\u7406\u53c3\u6578\uff08\u5982\u9577\u5ea6\u3001\u7c97\u7cd9\u3001\u958b\u53e3\uff09**\u4ecd\u53ef\u7dad\u6301\u9ad8\u6e96\u78ba\u5ea6\u3002<\/li>\n\n\n\n<li><strong>RQD \u8207\u5730\u4e0b\u6c34\u689d\u4ef6\u662f\u6700\u5177\u5f71\u97ff\u529b\u7684\u53c3\u6578\u3002<\/strong><\/li>\n\n\n\n<li>\u63d0\u4f9b\u4e00\u7a2e\u7701\u6642\u3001\u5177\u5be6\u52d9\u50f9\u503c\u7684 AI \u8f14\u52a9\u5ca9\u9ad4\u8a55\u4f30\u65b9\u6cd5\u3002<\/li>\n\n\n\n<li>\u672a\u4f86\u5efa\u8b70\u52a0\u5165 <strong>\u4e0d\u78ba\u5b9a\u6027\u5206\u6790<\/strong> \u8207\u91dd\u5c0d<strong>\u5be6\u969b\u566a\u97f3\u8cc7\u6599<\/strong>\u7684\u5f37\u5316\u8a13\u7df4\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>AbstractThe rock mass rating (RMR) system is a widely u [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2025,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14],"tags":[],"class_list":["post-2024","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-article"],"_links":{"self":[{"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/2024","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2024"}],"version-history":[{"count":2,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/2024\/revisions"}],"predecessor-version":[{"id":2027,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/2024\/revisions\/2027"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/2025"}],"wp:attachment":[{"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2024"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2024"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gsclab.ntou.edu.tw\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2024"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}