Natural Resources Research最新文献

{"title":"Temperature Reduction Characteristics of Coal with Different Moisture Contents During Cryogenic Treatment","authors":"Siqi Zhang, Zhaofeng Wang, Xingying Ma, Lingling Qi, Shijie Li, Yanqi Chen","doi":"10.1007/s11053-024-10384-8","DOIUrl":"https://doi.org/10.1007/s11053-024-10384-8","url":null,"abstract":"<p>To investigate the effect of moisture content on coal in cryogenic treatment, based on a gas-containing coal cryogenic treatment simulation testing system and an automated mercury intrusion porosimeter, temperature changes, strains, and characteristic parameters of the pore structure of coal after cryogenic treatment were determined. In addition, a thermal–water–mechanical coupling theoretical model was established using COMSOL software to simulate the changes in temperature and volume of coal. It was observed that moisture content was correlated negatively with the rate of temperature drop of coal and correlated positively with the frost heave strain. After cryogenic treatment, the final volume of coal decreased and the pores increased. The experiment revealed that frost heave heat extended the temperature stabilization time by an average of 27%, while methane adsorption heat had almost no effect. It is recommended to control the moisture content of coal at around 5% when using cryogenic treatment for anti-outburst, while for frozen coring, the moisture content should be controlled below 3%. The research results provide significant understanding of changes caused by cryogenic treatment on coal and supply practical information for optimizing the industrial production application of cryogenic treatment on coal.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"78 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Theoretical Investigation of Coal Fracture Evolution with Hydrostatic Pressure and its Validation by CT","authors":"Changxin Zhao, Yuanping Cheng, Wei Li, Liang Wang, Zhuang Lu, Hao Wang","doi":"10.1007/s11053-024-10381-x","DOIUrl":"https://doi.org/10.1007/s11053-024-10381-x","url":null,"abstract":"<p>The stress-induced evolution of coal fractures significantly affects permeability and, consequently, gas extraction efficiency. This study introduces a novel coal fracture evolution model based on assumptions of fracture morphology and log-normal distribution of fracture aspect ratio. This model offers a theoretical framework for understanding the fracture closure process, ultimately depicting fracture evolution as a combined result of elastic compression and closure. It predicts the decay curve of fracture porosity under hydrostatic pressure loading. We conducted uniaxial compression experiments for determining the mechanical parameters of the model and in situ CT experiments with confining pressure ranging from 0 to 25 MPa for validating the model. The findings indicate the following: (1) Initially, the decline in fracture porosity with stress is predominantly due to elastic compression, followed by a rapid transition to closure. (2) Sensitivity analysis reveals that an increase in two physical quantities—the cube root of the product of the peak aspect ratio and the square of the mean aspect ratio (<i>x</i>_<i>c</i>) and the bulk modulus of the coal matrix (<i>K</i>_<i>m</i>)—results in a decrease in the rate of fracture porosity decay with stress. (3) Tectonic action has a dual effect of augmenting <i>x</i>_<i>c</i> and diminishing <i>K</i>_<i>m</i>. We define the magnification of <i>x</i>_<i>c</i> and the divisor of <i>K</i>_<i>m</i> under a common term—scaling factor. When the scaling factor of <i>x</i>_<i>c</i> is less than that of <i>K</i>_<i>m</i>, the tectonic action promotes the decay of porosity with stress. Conversely, when the scaling factor of <i>x</i>_<i>c</i> is greater than that of <i>K</i>_<i>m</i>, the effect is reversed.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"6 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141631383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CLUSTERDC: A New Density-Based Clustering Algorithm and its Application in a Geological Material Characterization Workflow","authors":"Maximilien Meyrieux, Samer Hmoud, Pim van Geffen, David Kaeter","doi":"10.1007/s11053-024-10379-5","DOIUrl":"https://doi.org/10.1007/s11053-024-10379-5","url":null,"abstract":"<p>The ore and waste materials extracted from a mineral deposit during the mining process can have significant variations in their physical and chemical characteristics. The current approaches to geological material characterization are often subjective and usually involve a significant human workload, as there is no optimized, well-defined, and robust methodology to perform this task. This paper proposes a robust, data-driven workflow for geological material characterization. The methodology involves selecting relevant features as a starting point to discriminate between material types. The workflow then employs a robust, state-of-the-art nonlinear dimension reduction (DR) algorithm when the dataset is multidimensional to obtain a two-dimensional embedding. From this two-dimensional embedding, a kernel density estimation (KDE) function is derived. Subsequently, a new clustering algorithm, named ClusterDC, is employed to generate clusters from the KDE function, accurately reflecting geological material types while achieving scalable clustering performance on large drillhole datasets. ClusterDC is a density-based clustering algorithm capable of delineating and ranking high-density zones corresponding to clusters of data samples from a two-dimensional KDE function. The algorithm reduces subjectivity by automatically determining optimal cluster numbers and minimizing reliance on hyperparameters. It also offers hierarchical and flexible clustering, allowing users to group or split clusters, optimally reassign data samples, and identify cluster core points as well as potential outliers. Two case studies were carried out to test the algorithm and demonstrate its application to geochemical drill-core assay data. The results of these case studies demonstrate that the application of ClusterDC in the presented workflow supports the characterization of geological material types based on multi-element geochemistry and thus has the potential to help mining companies optimize downstream processes and mitigate technical risks by improving their understanding of their orebodies.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"27 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141625128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Artificial Neural Network Approach for Predicting TOC and Comprehensive Pyrolysis Parameters from Well Logs and Applications to Source Rock Evaluation","authors":"Mohamed Elfatih Salaim, Huolin Ma, Xiangyun Hu, Hatim Quer","doi":"10.1007/s11053-024-10374-w","DOIUrl":"https://doi.org/10.1007/s11053-024-10374-w","url":null,"abstract":"<p>Understanding source rocks' organic content and thermal maturity is crucial in assessing their hydrocarbon potential. To address this, our study focused on developing an accurate artificial neural network (ANN) model for estimating total organic carbon (TOC) content and a complete set of pyrolysis parameters from conventional well logs. The accuracy of the ANN-based technique in estimating TOC content was found to be significantly higher (correlation coefficient of 0.95) compared to the results obtained using Passey's method (correlation coefficient of 0.44). Additionally, the ANN model provided highly accurate predictions for the pyrolysis parameters S1, S2, S3, and Tmax, with correlation coefficients of 0.85, 0.90, 0.86, and 0.93, respectively. The study focused on the Abu Gabra Formation in the Hamra field, and the ANN data analysis revealed that the source rock in this area is of fair to good quality. The assessment of kerogen type indicated a mixed kerogen type II and type III, suggesting the potentiality for oil and gas generation. The predicted parameters further confirmed that the Abu Gabra source rock is thermally mature and capable of generating indigenous hydrocarbons. The results of the ANN-based modeling were consistent with laboratory measurements, demonstrating the reliability of the predictions for comprehensive source rock evaluation using well logs.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"47 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141618251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SsL-VGMM: A Semisupervised Machine Learning Model of Multisource Data Fusion for Lithology Prediction","authors":"Pengfei Lv, Weiying Chen, Hai Li, Wangting Song","doi":"10.1007/s11053-024-10375-9","DOIUrl":"https://doi.org/10.1007/s11053-024-10375-9","url":null,"abstract":"<p>In deep mineral exploration, it is difficult to constrain the complex geological structures using a single geophysical method. To tackle the difficulty, integrated geophysical surveys and joint data interpretation are essential. Machine learning (ML) provides more accurate predictions than traditional methods, especially when dealing with complex data from multiple sources or varied statistical distributions. However, a major challenge in using ML for deep mineral exploration is the scarcity and imbalance of labeled samples, mainly due to budget constraints and the complexity of ore deposits. This issue reduces the accuracy of predictive models and introduces bias. Additionally, limited labeling can lead to difficulties in predicting previously undefined classes in training datasets. To address these challenges, we introduce a robust semisupervised ML framework that integrates diverse geophysical and geological datasets to improve model reliability with limited labeled data. Our approach uses a semisupervised ML variational Gaussian mixture model (SsL-VGMM) to handle issues related to insufficient and imbalanced data. We enhanced the model’s predictive capability for unseen data by introducing a novel penalty factor in the ‘cannot-link’ function. Moreover, we employed Bayesian optimization, focusing on the mean-mixture weight, to avoid local optima during model training. Our model demonstrated high accuracy and efficiency, with classification and prediction accuracies of 95.33% and 87.4%, respectively, in numerical and electromagnetic simulation scenarios. Its effectiveness was further validated by locating Pb–Zn–Ag deposits in Inner Mongolia, supported by actual drilling data. This paper highlights the model’s potential in complex mineral exploration and its significant practical and innovative value for deep mineral exploration.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"38 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141608162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of Different Concentrations of Weak Acid Fracturing Fluid on the Microstructure of Coal","authors":"Gan Rui, Zuo Shaojie, Si Junting, Liu Chengwei, Tian Feng, Jiang Zhizhong, Wang Changwei, Peng Shouqing, Xu Zhiyuan","doi":"10.1007/s11053-024-10380-y","DOIUrl":"https://doi.org/10.1007/s11053-024-10380-y","url":null,"abstract":"<p>As a crucial factor that influences the hydraulic fracturing effectiveness of coal seams, fracturing fluids have garnered increasing attention. Among them, acid fracturing fluids have demonstrated positive impact on the pore transformation of coal, but high-strength acid fracturing fluids can cause corrosion damage to mechanical equipment. In this study, we employed acetic acid to formulate four types of weak acid fracturing fluids with varying concentrations and conducted soaking experiments. We analyzed the changes in the physical and chemical structure of coal samples before and after treatment using Fourier-transform infrared spectroscopy and X-ray diffraction analysis. The changes in the pore structure of coal samples before and after treatment were characterized by nitrogen adsorption and scanning electron microscopy. Our findings indicate the following: (1) The effects of different concentrations of acetic acid fracturing fluid on functional groups and microcrystalline structure vary. The 5% concentration fracturing fluid had the most significant impact on the organic structure of coal samples, with decreases in the area of hydroxyl structure, aliphatic structure, and oxygen-containing structure of 2.97%, 1.37%, and 0.68%, respectively. The 6% concentration fracturing fluid had the most significant impact on crystal structure, leading to a high degree of recrystallization and a fragile crystal network structure. (2) Fracturing fluids with concentrations below 7% can increase the number of mesopores and simplify the pore structure, while concentrations above 7% can lead to an increase in micropores and a more complex pore structure. (3) After the action of fracturing fluid, carbonate minerals are dissolved, and the pores of coal samples increase. However, excessively high concentrations of acetic acid fracturing fluid can facilitate shedding of mineral particles and block some pore channels, worsening the connectivity between pores. (4) The octadecylamine acetate formed by the combination of octadecylamine and acetic acid develops as a partial film on the surface of a coal body, reducing the roughness of the fracture surface and facilitating the flow of the fracturing fluid. Our findings provide theoretical support for the preparation and selection of weak acid fracturing fluids.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"1 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141602771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolution of Broken Coal’s Permeability Characteristics under Cyclic Loading–Unloading Conditions","authors":"Liang Luo, Lei Zhang, Jianzhong Pan, Mingxue Li, Ye Tian, Chen Wang, Songzhao Li","doi":"10.1007/s11053-024-10377-7","DOIUrl":"https://doi.org/10.1007/s11053-024-10377-7","url":null,"abstract":"<p>This study conducted a cyclic loading–unloading (CLU) test on broken coal samples with three particle sizes (0–5 mm, 5–10 mm, and 10–15 mm) under four different stress path conditions. The evolution permeability characteristics of samples during repeated compaction were investigated. The dimensionless permeability and the porosity variation law were obtained under CLU conditions. The permeability loss difference (PID) index was defined, and the permeability damage was analyzed. The permeability evolution model under mining influence conditions was constructed. Results indicate that an increase in maximum loading stress (MLS) exacerbates the seepage network channel destruction of broken coal. As the MLS increases, there is a decrease in permeability recovery rate during the unloading stage and an increase in permeability loss rate during the loading stage. The first stress loading results in a rapid reduction in the porosity, while the subsequent CLU has a minor impact on porosity variation. Results of the PID analysis show positive correlation between the permeability attenuation degree and the MLS. Furthermore, both the permeability recovery rate and the permeability loss rate increase with increase in particle size, indicating that the effects of pressure relief and stress recovery have a greater influence on larger particles. Theoretical permeability values of model were verified with test results, and their high consistency proves the permeability evolution model’s feasibility. The results will help provide theoretical guidance for gas extraction in goaf.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"26 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fuzzy-AHP and GIS-Based Modeling for Food Grain Cropping Suitability in Sundarban, India","authors":"Sabir Hossain Molla, Rukhsana","doi":"10.1007/s11053-024-10373-x","DOIUrl":"https://doi.org/10.1007/s11053-024-10373-x","url":null,"abstract":"<p>Land suitability analysis is essential for informed farming decisions, revealing an area’s natural potential and limitations. The primary objective of this research is to determine the suitability of land for cultivating major food grain crops like Kharif rice, Rabi rice, and Green gram in the Sundarban region of India using geostatistics, the fuzzy-AHP (FAHP) algorithm, and GIS tools. Local experts’ insights were harnessed to ascertain the relative importance of 19 thematic layers encompassing climatic, soil, environmental, and socioeconomic factors. These were combined using the FAHP model in a GIS to produce a cropland suitability map. The soil parameters were best fitted using spherical and Gaussian semi-variogram models, which showed the best performance. Land suitability analysis revealed that highly suitable (S1) areas were most extensive for Rabi rice (21.65%), followed by those for Kharif rice (16%) and Green gram (11.8%). Moderately suitable (S2) areas dominated the landscape, with those for Kharif rice (68.70%) and Rabi rice (65.32%) exhibiting significantly larger extents than those for Green gram (44.28%). Minor limitations restricted these areas due to low organic content, salt stress, acidic pH, sandy-loamy soil texture, shallow soil depth, and poor-quality irrigation water. Marginally suitable (S3) areas for Kharif rice (14.97%), Rabi rice (12.62%), and Green gram (37.88%) were less extensive, while not suitable (N) areas were minimal (0.33–6.04%). The dependability of the FAHP procedure in suitability assessment was validated using the area under curve (AUC), which was found to be substantial for Kharif rice (81.20%), Rabi rice (83.30%), and Green gram (79.41%). The study concluded that the combined FAHP algorithm in GIS is a practical approach for assessing accurately land suitability for producing specific crops.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"18 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Hybrid Machine Learning Approach and Basin Modeling for Thermal Maturity Estimation of Source Rocks in Mandawa Basin, East Africa","authors":"Christopher N. Mkono, Chuanbo Shen, Alvin K. Mulashani, Mbega Ramadhani Ngata, Wakeel Hussain","doi":"10.1007/s11053-024-10372-y","DOIUrl":"https://doi.org/10.1007/s11053-024-10372-y","url":null,"abstract":"<p>Basin modeling and thermal maturity estimation are crucial for understanding sedimentary basin evolution and hydrocarbon potential. Assessing thermal maturity in the oil and gas industry is vital during exploration. With artificial intelligence advancements, more accurate evaluation of hydrocarbon source rocks and efficient thermal maturity estimation are possible. This study employed 1D basin modeling using PetroMod and a novel hybrid group method of data handling (GMDH) neural network optimized by a differential evolution (DE) algorithm to estimate thermal maturity (Tmax) and assess kerogen type in Triassic–Jurassic source rocks of the Mandawa Basin, Tanzania. The GMDH–DE addresses the limitations of conventional methods by offering a data-driven approach that reduces computational time, overcomes overfitting, and improves accuracy. The 1D thermal maturity basin modeling suggests that the Mbuo source rocks reached the gas–oil window in late Triassic times and began expulsion in the early Jurassic while located in an immature-to-mature zone. The GMDH–DE model effectively estimated Tmax with high coefficient of determination (<i>R</i>² = 0.9946), low root mean square error (RMSE = 0.004), and mean absolute error (MAE = 0.006) during training. When tested on unseen data, the GMDH–DE model yielded an <i>R</i>² of 0.9703, RMSE of 0.017, and MAE of 0.025. Moreover, GMDH–DE reduced the computational time by 94% during training and 87% during testing. The results demonstrated the model’s exceptional reliability compared to the benchmark methods such as artificial neural network–particle swarm optimization and principal component analysis coupled with artificial neural network. The GMDH–DE Tmax model offers a unique and independent approach for rapid real-time determination of Tmax values in organic matter, promoting efficient resource assessment in oil and gas exploration.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"36 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141452908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward Precise Long-Term Rockburst Forecasting: A Fusion of SVM and Cutting-Edge Meta-heuristic Algorithms","authors":"Danial Jahed Armaghani, Peixi Yang, Xuzhen He, Biswajeet Pradhan, Jian Zhou, Daichao Sheng","doi":"10.1007/s11053-024-10371-z","DOIUrl":"https://doi.org/10.1007/s11053-024-10371-z","url":null,"abstract":"<p>Rockburst is one of the most hazardous geological disasters in underground engineering due to its complex causes and destructive nature. To address this, there is an imperative for methodologies that can predict rockbursts quickly and effectively to mitigate preemptively the risks and damages. In this study, 259 rockburst instances were analyzed, employing six rockburst feature parameters: maximum tangential stress (<i>σ</i>_<i>θ</i>), uniaxial compressive strength of rock (<i>σ</i>_<i>c</i>), uniaxial tensile strength of rock (<i>σ</i>_<i>t</i>), stress coefficient (<i>σ</i>_<i>θ</i><i>/σ</i>_<i>t</i>), rock brittleness coefficient (<i>σ</i>_<i>c</i><i>/σ</i>_<i>t</i>), and elastic energy index (<i>Wet</i>) as inputs. By integrating three novel meta-heuristic algorithms—dingo optimization algorithm (DOA), osprey optimization algorithm (OOA), and rime-ice optimization algorithm (RIME)—with support vector machine (SVM), hybrid models for long-term rockburst trend prediction were constructed. Performance evaluations through fivefold cross-validation revealed that for the no rockbursts, DOA–SVM (Pop = 200) demonstrated superior predictive performance, achieving an accuracy of 0.9808, precision of 0.9231, recall of 1, and an F1-score of 0.96. For moderate rockbursts, OOA–SVM (Pop = 100) emerged as the most effective, registering an accuracy of 0.9808, precision of 0.9545, recall of 1, and an F1-score of 0.9767. For light and severe rockbursts, DOA–SVM, OOA–SVM, and RIME–SVM showcased comparable predictive outcomes. However, these hybrid models outperformed traditional SVM models optimized with conventional algorithms in terms of accuracy across all rockburst hazard levels. Moreover, the hybrid models underwent additional validation with a new dataset of 20 rockburst instances collected globally, confirming their robust efficacy and exceptional generalization capabilities. An ensuing analysis using local interpretable model-agnostic explanations (LIME) on the six key feature parameters revealed a significant positive correlation between <i>σ</i>_<i>θ</i> and <i>Wet</i> with the severity of rockbursts. These results not only affirm the superior optimization performance of the DOA, OOA, and RIME algorithms but also their substantial potential to enhance the predictive accuracy of machine learning models in forecasting long-term rockbursts.</p>","PeriodicalId":54284,"journal":{"name":"Natural Resources Research","volume":"44 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141425520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}