Detecting the formation of explosive methane–air mixtures in a longwall face is still a challenging task. Even though atmospheric monitoring systems and computational fluid dynamics modeling are utilized to inspect methane concentrations, they are not sufficient as a warning system in critical regions, such as near cutting drums, in real-time. The long short-term memory algorithm has been established to predict and manage explosive gas zones in longwall mining operations before explosions happen. This paper introduces a novel methodology with an artificial intelligence algorithm, namely, modified long short-term memory, to detect the formation of explosive methane–air mixtures in the longwall face and identify possible explosive gas accumulations prior to them becoming hazards. The algorithm was trained and tested based on CFD model outputs for six locations of the shearer for similar locations and operational conditions of the cutting machine. Results show that the algorithm can predict explosive gas zones in 3D with overall accuracies ranging from 87.9% to 92.4% for different settings; output predictions took two minutes after measurement data were fed into the algorithm. It was found that faster and more prominent coverage of accurate real-time explosive gas accumulation predictions are possible using the proposed algorithm compared to computational fluid dynamics and atmospheric monitoring systems.

<!-- *** Custom HTML *** --> The aim of this study is to investigate the potential of the Sentinel-2 satellite for land use and land cover (LULC) mapping. The commonly known supervised classification algorithms, support vector machines (SVMs), random forest (RF), and maximum likelihood (ML) classification are adopted for investigation along with a proposed hierarchical classification model based on a coordination of information on the environment land cover system. The main classes for land cover and mapping in the proposed hierarchical classification are selected as water, vegetation, built-up, and bare land in the first level, which is followed by inland water, marine water, forest/meadow, vegetated agricultural land, barren land, and nonvegetated agricultural land in the second level. The study areas for the experiments are selected as the two biggest cities of Turkey, namely Ankara and Izmir, providing a sufficient number of classes for comparison purposes. During the utilized hierarchical methodology, water and vegetation are first extracted using the normalized difference water and vegetation indices. This is followed by the selection of training pixels from the remaining classes to perform and compare different supervised learning algorithms for the first- and second-level classification in terms of accuracy rates. The experimental results first reveal that while the SVMs have close accuracy performances to those with RF, they are significantly superior to the ML classification, with an average of 8% accuracy rates for LULC mapping. Second, the hierarchical classification also gives higher performances with respect to the nonhierarchical classification, with the provided gains between 4% and 10% for class-based accuracies. The overall accuracy rates of the proposed hierarchical methodology are 85% and 84% for the first-level classes and 83% and 72% for the second-level classes, respectively, for Izmir and Ankara.

Atmospheric monitoring systems are critical in underground coal mine ventilation where methane explosion hazards can develop. The number and location of sensors are important for ventilation monitoring. Atmospheric monitoring system sensors should be installed near the most critical locations like the shearer cutting drum and along the longwall face. Sensors can provide information for a limited area, and their readings may have delays caused by sensor response time, gas diffusion rate, and temperature. Computational fluid dynamics modeling can provide relatively accurate predictions regarding the location of possible explosive gas concentrations. However, it requires significant computational resources and time, which is not conducive to real-time decision-making. This paper evaluates artificial intelligence systems for predicting near-real-time explosion hazards. The prediction performance of 10 time series algorithms is compared by using seven datasets and assessed by classification accuracy. Accurate real-time/near-real-time methane predictions are possible with two algorithms: HIVE-COTE and RISE. Initial results demonstrate that near-real-time decision-making for explosive hazard warning systems is accurate and robust, and artificial intelligence modeling of explosion hazards enhances mine safety.

First responders in underground mines face a myriad of challenges when searching for personnel in a disaster scenario. Possibly, the most acute challenge is the complete lack of visibility owing to a combination of dust, smoke, and pitch-black conditions. Moreover, the complex environment compounds the difficulty of navigating and searching the area as well as identifying hazardous conditions until in close proximity. Enhanced perception and localization technologies that enable rapid and safe disaster response could mitigate the mine rescue team’s risk and reduce response times. We developed a proof of concept perception enhancement tool for mine rescue personnel in pitch-black conditions by leveraging LiDAR, thermal camera, and data fusion to reconstruct a 3D representation of the space in real-time. This enhancement is visualized on HoloLens, allowing the responders real-time situational awareness of personnel, walls, obstacles, or fires in otherwise opaque environments. The technology is a first step towards faster, safer, and more effective disaster response for mine rescue operations, including detection of unexpected hazards before they become imminent threats.