With the rapid advancement of artificial neural network (ANN) algorithms, many researchers have applied these methods to mine gas prediction and achieved numerous research achievements. It is of great significance to study methods that can accurately predict the gas content for the prevention of gas disasters in mining areas. In order to enhance the accuracy, stability, and generalization capability of the gas content prediction model, the GASA-KELM prediction model was established using the GASA algorithm to improve the KELM initial parameter assignment method, and the prediction model based on BPNN and SVM was established under the same conditions. The experimental results show that the GASA-BPNN model failed to achieve the desired outcome within 800 iterations. On the other hand, the GASA-SVM and GASA-KELM models accomplished the goal in significantly fewer iterations, taking only 673 and 487 iterations, respectively. Moreover, the overall average relative errors of the cross-validated gas content predictions were 15.74%, 13.85%, and 9.87% for the three models, respectively. Furthermore, the total average variance of the test set was 3.99, 2.76, and 2.05 for the GASA-BPNN, GASA-SVM, and GASA-KELM models, respectively. As a result, compared with other ANN models, the GASA-KELM model demonstrates higher accuracy, stronger prediction stability, and generalization ability in the practical application. This novel model provides a basis for accurately predicting gas content and proposing effective regional gas management measures.

Hidden disaster-causing factors (HDCFs) in coal mines can be identified via the rerefinement and classification of disaster-causing factors (DCFs) in coal mines. The study of the disaster-causing mechanism of accidents from the perspective of HDCFs in coal mines could be helpful to analyze the accident occurrence process from a new perspective, and new ideas for accident prevention and control could then be proposed. To clarify the disaster-causing mechanism of HDCFs of major and extraordinarily serious gas explosion accidents (MESGEAs) in coal mine goafs, 32 MESGEAs in coal mine goafs in China from 2000 to 2021 were adopted as a data source. By redefining the definition, connotation and characteristics of HDCFs in coal mines, 10 HDCFs were identified. Consequently, an improved decision-making trial and evaluation laboratory (DEMATEL)-interpretive structural model (ISM)-matrix of cross impact multiplications applied to classification (MICMAC) model was used to comprehensively analyze HDCFs in 3 aspects, including the centrality and cause degrees, hierarchical structure, and driving and dependence powers, from a completely objective perspective. The results demonstrated that (1) the considered MESGEAs in coal mine goafs were caused by DCFs in the management aspect by affecting the DCFs in the 3 aspects of human factors, equipment and environment, as well as under the combined effect of DCFs internal interaction contained in itself. (2) There were 2 types of disaster-causing mechanisms of HDCFs of MESGEAs in coal mine goafs: (a) the indirect disaster-causing by HDCFs in the management aspect and (b) the random coupling disaster-causing by HDCFs in human factors, equipment and environment 3 aspects.

The porosity distribution law of overlying strata in the goaf has an important guiding role in distinguishing hidden disaster-causing factors in the goaf, such as the gas enrichment area and spontaneous combustion area. Existing research is concentrated on the overlying strata in the goaf of a single working face (GSWF), and the porosity distribution law of overlying strata in the goaf of an adjacent working face (GAWF) must be different from that in the GSWF. By selecting Longshan Coal Mine as an engineering background and applying theoretical analysis, numerical simulation and formula-fitting methods, the porosity distribution law of overlying strata in the GAWF was obtained for different section coal pillar types. The results demonstrate that (1) according to the supporting effect of different sections of coal pillar widths on overlying strata, the GAWF can be divided into three types: goaf of an adjacent working face with small-section coal pillar width type (GFST), goaf of an adjacent working face with moderate-section coal pillar width type (GFMT), and goaf of an adjacent working face with large-section coal pillar width type (GFLT). (2) In the goaf of a working face, the offset distance from the maximum porosity value area of each overlying rock stratum to the middle of the rock stratum is positively correlated with the distance between the overlying strata and the coal seam floor. In the area affected by the section coal pillar (ASCP), the porosity of each overlying rock stratum increases with an increase in the section coal pillar width, but is still smaller than its own initial porosity, and its increase rate continuously decreases. (3) From the coal seam floor upward, the porosity spatial form distribution of overlying strata in the GFST and GFMT is described as follows: partial “dustpan” shape–unilateral “concave-convex peak” combined shape. The porosity spatial form distribution of overlying strata in the GFLT is described as follows: “dustpan” shape–“concave-convex peak” combined shape-“Λ” shape.

In high-risk mining environments, the emotional state of individuals can play a critical role in shaping decision-making during emergencies. To investigate this phenomenon, we adopted an event-related potential (ERP) approach within a within-subject experimental framework. Participants were first exposed to a series of emotionally evocative cues designed to elicit distinct affective states, immediately followed by decision-making tasks that simulate coal mine emergency scenarios. Behavioral indices—such as reaction speed and task engagement—were recorded concurrently with ERP signals, with a specific focus on components including N1, P2, N2, P300, and LPP. Our analysis revealed that both the valence and intensity of emotional cues substantially modulated the decision-making process, as reflected by significant variations in response times and ERP measures. These findings offer fresh insights into the neural mechanisms through which emotional factors influence critical decisions in crisis situations, highlighting implications for the development of enhanced safety strategies in coal mining operations.