Mining Environment Research Articles

Image Enhancement Method in Underground Coal Mines Based on an Improved Particle Swarm Optimization Algorithm

Due to the poor lighting conditions and the presence of a large amount of suspended dust in coal mines, obtained video has problems with uneven lighting and low differentiation of facial features. In order to address these problems, an improved image enhancement method is proposed. Firstly, the characteristics of underground coal mine images are analyzed, and median filtering is selected for noise removal. Then, the gamma function and fractional order operator are introduced, and an image enhancement algorithm based on particle swarm optimization is proposed. Finally, several experiments are conducted, and the results show that the proposed improved algorithm outperforms classical image enhancement algorithms, such as MSR, CLAHE and HF. Compared with the original image, the evaluation metrics of the enhanced Yale face images, including average local standard deviation, average gradient, information entropy and contrast, are improved by 113.1%, 63.8%, 22.8% and 24.1%, respectively. Moreover, the proposed algorithm achieves a superior enhancement effect in the simulated coal mine environment.

Continuous Monitoring of the Mining Activities, Restoration Vegetation Status and Solar Farm Growth in Coal Mine Region Using Remote Sensing Data

Abstract Land reclamation of previously mined regions has been incorporated in the mining process as awareness of environmental protection has grown. In this study, we used the open-pit coal mine Oslomej in R. N. Macedonia to demonstrate the activities related to the monitoring process of the study area. We combined the Google Earth Engine (GEE) computing platform with the Landsat time-series data, Normalized Difference Vegetation Index (NDVI), Random Forest (RF) algorithm, and the LandTrendr algorithm to monitor the mining impacts, land reclamation, and the solar farm growth of the coalfield region between 1984 and 2021. The data from the sequential Landsat archive that was used to construct the spatiotemporal variability of the NDVI over the Oslomej mine site (1984-2021) and the pixel-based trajectories from the LandTrendr algorithm were used to achieve accurate measurements and analysis of vegetation disturbances. The different land use/land cover (LULC) classes herbaceous, water, mine, bare land, and solar farm in the Oslomej coalfield area were identified, and the effects of LULC changes on the mining environment were discussed. The RF classification algorithm was capable of separating these LULC classes with accuracies exceeding 90 %. We also validated our results using random sample points, field knowledge, imagery, and Google Earth. Our methodology, which is based on GEE, effectively captured information on mining, reclamation, and solar farm change, providing annual data (maps and change attributes) that can help local planners, policymakers, and environmentalists to better understand environmental influences connected to the ongoing conversion of the mining areas.

Assessment of the efficiency methods and means of mine degasation projects of methane coal deposits

Purpose. The formation of a methodological approach to the evaluation of the effectiveness of gas release management methods in the development of methane coal seams and the design of mine degassing systems. Research methodology. Qualitative and quantitative indicators of the influence of the mine environment on the economic parameters of the methods of degassing of methane coal seams and the establishment of the efficiency of the existing degassing systems were considered.Analysis and synthesis of operational indicators of extracting, removal and utilization of mine methane used in the coal industry and the results of studies of the effectiveness of mine degassing systems, allowing to highlight the main economic effects characterizing the degassing of coal mines. Findings. According to the results of the assessment of modern trends in determining the economic efficiency of degassing of highly loaded beds, it was established that fundamentally new approaches are being implemented in foreign practice for the selection of innovative means of degassing of coal mines due to which it is possible to achieve an economic effect and reduce the costs of degassing. It was also established that electricity savings during the operation of degassing plants can be obtained by increasing the tightness of the vacuum gas pipelines of the degassing network. Originality .A theoretically grounded methodology for determining the technical and economic indicators of degassing of methane coal seams due to the modernization of existing mine degassing systems.The methodology for calculating the economic efficiency of degassing systems has been developed, taking into account the side effect of increasing the tightness of the vacuum gas pipelines of the degassing network. Practical meaning. The methodology for evaluating the technical and economic indicators of the existing degassing systems has been developed. The practical application of the results of the study is to improve the methodology for determining the economic effect of degassing of methane coal mines of Ukraine.

Calculation of the strength of cast and packaged concrete protective walls

Purpose. The substantiation of the compliance of the selected cement-mineral mixture with the mining and geological conditions of the working location when calculating the parameters of cast or packaged walls, considering the intensity of concrete hardening over time, the compliance of the set strength of concrete with the expected load. Method. To substantiate the compliance of the physical and mechanical properties of the pressure mixture on the means of protection of the production from the side of the fake roof of the coal seam, the values of the limit strength of concrete for uniaxial compression, obtained according to standard tests in laboratory conditions, are used. At the same time, concrete samples are subjected to uniaxial compression, the surfaces of which must be smooth and parallel, which does not correspond to the mine conditions for the construction and operation of cast and packaged protective walls. Quick-hardening liquid mixtures are used in the construction technologies of cast and packaged security walls. For some time, necessary for the hardening of concrete, they are not able to perceive the pressure from the rocks forged by longwall. Therefore, the criterion for evaluating the stability of cast or packaged walls is the correspondence of the rate of growth of the strength limit of the wall to uniaxial compression with the load from the forged roof of the coal seam at the moment of timeτ. Results.The importance of the impact on the strength limit of the concrete wall of each of the factors that create the risk of its destruction has been established. At the same time, the ranges of change of these factors are considered. The largest influence (up to 33%) is exerted by the coal seam capacity factor km. The scientific novelty of the work consists in the integration of the influence coefficients of the factors that create the risk of destruction of the concrete protective wall: its structure; relief of forged and crushed rocks pressing on the wall; chemical aggressiveness of mine water, which is used to dissolve the mixture; the temperature of the mine environment and the power of the coal seam to obtain a formula for calculating the growth of wall strength over time. The practical significance of the work lies in the improvement of the method of calculating the strength of concrete protective walls over time by considering the factors that form the mine conditions of their construction and operation.

The use of copper isotopes for understanding metal transfer mechanisms within the continuum mine-river-dam (Huelva Region, Spain).

Mining areas and in particular those containing massive sulfides have left a heavy environmental legacy with soils and hydrographic networks highly contaminated with metals and metalloids as for example in the Iberian Pyrite Belt (Huelva, Spain). Here, we present new data on copper (Cu) isotopic composition of waters and solids collected along a continuum Mine (Tharsis)-River (Meca)-Lake (Sancho) in the Iberian Pyrite Belt. Our results show that the isotopic signature of pit lakes is spatially variable, but remains stable over the seasons; this signature seems to be controlled by water-rock interaction processes. The data obtained on the Meca River imply a number of attenuation processes such as decrease in the metal concentration by precipitation of secondary minerals. This is accompanied by preferential retention of the heavy isotope (65Cu) with a possibility of living organisms (e.g., algae) participation. The terminal Sancho lake demonstrated constant isotopic signature over the entire depth of the water column despite sizable variations in Cu concentrations, which can be tentatively explained by a superposition of counter-interacting biotic and abiotic processes of Cu fractionation. Overall, the understanding of the isotopic variations along the hydrological continuum is useful for a better understanding of metal element transfer within mining environments and surrounding surface waters.

Coal and gangue classification in actual environment of mines based on deep learning

Existing deep learning technologies used to classify coal and gangue are mostly carried out in laboratory environment, which cannot meet the needs of actual coal mining process. To apply in actual environment, we propose an image window pixel information interaction method that synergizes the strengths of Convolutional Neural Networks (CNN) and Swin Transformer. Specifically, we propose a coal and gangue classification framework which combines traditional convolutional neural networks for feature extraction of coal and gangue, while optimizing the model using Batch Normalization (BN) layers and freezing fully connected layer (FFCL) weights. We evaluate our method using real data gathered from coal mines and compare results to some existing methods, demonstrating that our method can classify coal and gangue with high accuracy in actual environment, achieving approximately 95% in precision, recall, accuracy, and F1 Score. Our method paves the way for accurately classifying coal and gangue in actual environment of mines.

Coal-source acid mine drainage reduced the soil multidrug-dominated antibiotic resistome but increased the heavy metal(loid) resistome and energy production-related metabolism

A recent global scale study found that mining-impacted environments have multi-antibiotic resistance gene (ARG)-dominated resistomes with an abundance similar to urban sewage but much higher than freshwater sediment. These findings raised concern that mining may increase the risk of ARG environmental proliferation. The current study assessed how typical multimetal(loid)-enriched coal-source acid mine drainage (AMD) contamination affects soil resistomes by comparing with background soils unaffected by AMD. Both contaminated and background soils have multidrug-dominated antibiotic resistomes attributed to the acidic environment. AMD-contaminated soils had a lower relative abundance of ARGs (47.45 ± 23.34 ×/Gb) than background soils (85.47 ± 19.71 ×/Gb) but held high-level heavy metal(loid) resistance genes (MRGs, 133.29 ± 29.36 ×/Gb) and transposase- and insertion sequence-dominated mobile genetic elements (MGEs, 188.51 ± 21.81 ×/Gb), which was 56.26 % and 412.12 % higher than background soils, respectively.Procrustes analysis showed that the microbial community and MGEs exerted more influence on driving heavy metal(loid) resistome variation than antibiotic resistome. The microbial community increased energy production-related metabolism to fulfill the increasing energy needs required by acid and heavy metal(loid) resistance. Horizontal gene transfer (HGT) events primarily exchanged energy- and information-related genes to adapt to the harsh AMD environment. These findings provide new insight into the risk of ARG proliferation in mining environments.

Contamination characteristics of polycyclic aromatic compounds from coal sources in typical coal mining areas in Huaibei area, China

The Huaibei area is rich in coal resources and serves as the main energy production base in East China. However, serious environmental consequences are associated with coal mining and utilization. With increasing reports on distribution and risks by polycyclic aromatic compounds (PACs), the potential pollution of coal sources must be addressed. Here, the PAC concentrations in the topsoil, coal, and coal gangue of a typical coal mining area in Huaibei were evaluated. The mean ΣPACs in topsoil, coal, and coal gangue were 1528.3, 274,815.8, and 10,908.3 μg·kg−1, respectively. Alkyl polycyclic aromatic hydrocarbons (aPAHs) were identified as primary contributors to PACs, and the concentrations of oxygenated PAHs (oPAHs) were significantly higher in coal and coal gangue than in topsoil. PAC pollution was mainly concentrated in the coal mine area and near the coal gangue landfill road. Not only sixteen high priority pollutant PAHs (16PAHs), but PAH derivatives also contributed to the organic pollution from coal sources. Principal components analysis, multiple linear regression, characteristic ratios, and positive matrix factor analysis were used to trace PAC sources. The characteristic ratios for organic pollution from coal and gangue particles involving 16PAHs, aPAHs, and oPAHs were proposed. Further, the high–ring 16PAH ratio was also found suitable for coal mining areas. The Monte–Carlo risk assessment showed that coal particles were highly carcinogenic, and despite the low carcinogenicity of coal gangue and topsoil, they might also serve as potential carcinogens. This study aimed to disseminate knowledge on PACs from coal and coal gangue, provide a useful background for efficient resource utilization of coal gangue, and a reference for tracing PAC sources in coal mine environment media.

Assessment of the multilevel correlations of the pollution indicators and lithological vulnerabilities in a passive limestone mining and cement producing environment.

This study presents the assessment of the air, soil, and water quality within the residential communities around two passive limestone mining/cement factories. The associations between the pollutants were tested across the media, within each medium, between the layers, and between two groups of the communities. The mean values for the PM1.0, PM2.5, and PM10 were 65.8 µgm-3, 50.1, and 73.7, respectively, in the air; for the Mn, Fe, Cu, Zn, Cr, K-40, U-238, and Th-232 were 0.433g/kg, 8.950, 0.005, 0.054, 0.104, 161.57Bq. kg-1, 61.10, and 15.85, respectively, in the topsoil; 0.365g/kg, 8.259, 0.004, 0.029, 0.057, 71.84Bq. kg-1, 16.37, 4.66, respectively, in the subsoil; and for the Mn, Fe, and Zn were 0.190, 1.499, and 0.256mg/l, respectively, in the water. The PM10, Fe, and K-40 were the most abundant pollutants. The Co and Mn, Zn and Cu, Fe and Cu, the absorbed dose rate (ADR) and K-40, and ADR and U-238 correlated significantly. Though the Ibese group was more polluted than the Ewekoro group, the generally low levels of the pollutions were confirmatory of the earlier suspicions of the mining/production activities. The 2nd lithological layer at 0.5 to 1.9m depths or the 3rd lithological layer at 1.1 to 7.69m depths for the Ibese group and the 1st layer at the surface or the 2nd layer at 0.5m depth for the Ewekoro group are protective layers for the groundwater that must not be exploited, given the three classes of groundwater vulnerability indices observed in the area.

Dynamic Response Analysis of a Reinforced Concrete Structure in Underground Coal Mine Environment with Various Strata Conditions

Dynamic Response Analysis of a Reinforced Concrete Structure in Underground Coal Mine Environment with Various Strata Conditions

A Novel Mine-Specific Eco-Environment Index (MSEEI) for Mine Ecological Environment Monitoring Using Landsat Imagery

The excessive exploitation of mineral resources will lead to environmental pollution, resource depletion, environmental disaster, and other problems. The contradiction between the environment and development, and the management of the ecological environment in mining areas are urgent p-problems to be solved. An ecological environment assessment is an important part of the ecological environment in a mining area. The accurate evaluation of the ecological environment is the premise behind environmental governance in a mining area. However, current ecological assessment indicators were not developed specifically for mine environment monitoring and, thus, cannot provide an effective and comprehensive assessment of the mineral environment. To this end, in order to improve the environmental monitoring performance in mining areas, a novel Mine-Specific Eco-Environment Index (MSEEI) was proposed, integrating factors from five main aspects associated with minerals, including temperature, vegetation, soil moisture, atmospheric environment, and mining scale. Meanwhile, a widely concerned mine—Luanchuan mine—was used as the case area to test the performance of our MSEEI. The results showed a significant correlation between RSEI and MSEEI (p < 0.01). The mean correlation achieved between RSEI and MSEEI was 0.91, which was much higher than the correlations between RSEI and enhanced vegetation index (EVI), soil moisture monitoring index (SMMI), normalized difference built-up and soil index (NDBSI), PM2.5 concentration (DI), and heat (LST). In addition, based on our long-term MSEEI results of Luanchuan mine from 1997 to 2021, the ecological status of Luanchuan mine showed a trend of first declining and then rising. Specifically, the MSEEI first declined from 0.85 to 0.77 between 1997 and 2012, and then rebounded to about 0.8 in recent years. The MSEEI exhibited a good applicability in the ecological assessment of mining areas. Our MSEEI can provide useful guidance for mine environment monitoring. MSEEI can directly reflect the ecological damage after mining, provide scientific guidance for the exploitation and utilization of mineral resources, and promote the protection and sustainable development of Earth’s resources and mine ecological environments.

Tribological properties of PEEK composites reinforced by MoS2 modified carbon fiber and nano SiO2

An anti-wear filler of molybdenum disulfide (MoS2) coated chopped carbon fiber (SCF) was synthesized by hydrothermal method and blended with nano-SiO2 to enhance the tribological properties of PEEK composites materials. The results show that the SCF-MoS2 has stronger adhesion with the PEEK matrix, which is more conducive to the internal stress transfer of PEEK composites. Compared with pure PEEK, the elastic modulus and tensile strength of PEEK/SiO2/SCF-MoS2 composites are increased by 62.04% and 26.49% respectively. The friction coefficient and wear rate of PEEK/SiO2/SCF-MoS2 composites are reduced by 31.43% and 79.18% respectively. In addition, it also shows good tribological properties in the simulation coal mine environment.

Research on Invalid Detection Data Model of Mine Catalytic Sensors Based on Machine Learning

In order to solve the problem of nonlinear failure data output by the catalytic combustible sensor (later referred as a sensor) when working in the mine environment, this article proposes a backpropagation (BP) neural network nonlinear data filtering model based on the Levenberg–Marquardt (L-M) algorithm. The experimental analysis shows that this model has obvious advantages in training speed and error performance compared with the BP neural network model established by a quasi-Newton algorithm and adaptive linear regression (lr) momentum gradient descent algorithm. In terms of generalization ability, this model has better generalization ability than the radial basis function (RBF) feedforward neural network model with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering. Based on the above advantages, the model can effectively filter the sensor failure output data, eliminate the hidden danger of safety production caused by the failure output data, and improve the level of safety production in coal mines.

Review of machine learning application in mine blasting

Mine blasting has adopted machine learning (ML) into its practices with the aims of performance optimization, better decision-making process, and work safety. This study is aimed at reviewing the status of ML method applications to mine blasting issues. One of the most important observations of this research highlights the developed ML methods such as hybrids/ensembles, outperforming the other methods at 61% of the sample of case studies. The first section provides a background on the application of ML methods in mining. Two sections of the review provide the trends in the application of ML methods and the utilization of input parameters in surface and underground blasting problems. The appraisal reveals an increase of hybrid/ensemble or highly developed ML methods for the top four blast issues on the surface (72%) and underground (45%). The sample of studies reviewed indicated through graphical/statistical means a continuing increase in hybrids/ensembles’ use mirrored by high research output for the top four surface blast issues. This is contrasted by a low rate of research in underground blasting, under the encountered operational conditions applied. Regarding the input parameters, controllable parameters (blast design and geometry) were recognized to be steadily used in surface blasting for the top four surface blast issues, along with less involvement from the uncontrollable parameters (geological and geotechnical parameters). On the contrary, underground blasting has a slight involvement of the uncontrollable parameters more than the controllable parameters, in the top four blast issues. In the final section of this paper, the review offers a discussion of the current state of research under the encountered limits and where the efforts should be focused concerning ML methods applied, input parameters involved, and the challenges faced. Such high levels of performances are in demand in a highly complex mining environment. Persistent research, and development of mining employees’ technological skills alongside an increased awareness among mining industry of the benefits of highly developed ML techniques, is greatly needed at this stage. This would establish the role of highly developed ML methods in improving both the blasting process and the overall decision-making and mining management.

Degradation Mechanism of Coal Gangue Concrete Suffering from Sulfate Attack in the Mine Environment.

Recycling coal gangue as aggregate to produce concrete in situ is the most effective way to solve the problem of deposited coal gangue in mines. Nevertheless, the mine environment underground is rich in sulfate ions, posing a threat to the durability of coal gangue concrete (CGC). Hence, the degradation process of sulfate-attacked CGC is investigated. A series of tests is performed to evaluate its variation law of mass, dynamic elastic modulus, compressive strength and sulfate ion distribution. Meanwhile, the microstructure and phases of sulfate-attacked CGC are identified by scanning electron microscopy, X-ray diffraction and thermogravimetric analysis. The results indicate that the residual compressive strength ratio of CGC is higher than that of normal concrete after a 240 d sulfate attack, implying a superior sulfate resistance for CGC. Additionally, the higher the sulfate concentration, the more severe the degradation. Except for the secondary hydration of CGC itself, the diffused sulfate ions also react with Ca(OH)2, forming gypsum and ettringite; this plays a positive role in filling the pores at the early stage, whereas, at the later stage, the generated micro-cracks are detrimental to the performance of CGC. In particular, the proposed sulfate corrosion model elucidates the degradation mechanism of CGC exposed to a sulfate-rich environment.

Reliable prediction of geotechnical risks in open pit mining

The currently required minimization of geotechnical risks in open pit mineral mining includes timely prediction of slope failure probabilities and their impacts on personnel, environment, equipment, infrastructure and production efficiency of mines. The main tool to predict stability of pitwall slopes in modern geomechanics of rocks is the numerical modeling greatly dependent on the reliability of the source data. The risk prediction reliability is in focus of this study. It is preferable to use the notion &ldquo;failure probability&rdquo; as the criterion of pitwall stability as the uncertainty of parameters has already been determined quantitatively in this case. With the notion &ldquo;stability factor&rdquo; used as the stability criterion, it is required to add the calculated stability factor with the degree of variability of the initial parameters, with an emphasis on the reliability of geotechnical data. The reliability of the pitwall stability estimation largely depends on the geotechnical data reliability. The projects at the stage of a mineral field development should have the confidence level of data not lower than 80 %. The point rating system is presented for the estimate of the geotechnical data reliability. The procedure has been tested at some deposits at different project stages, and has proved to be handy, simple and objective. Using the described assessment system of the data reliability, the actual &ldquo;standard&rdquo; values of the stability factor are obtained for some open pit mines in operation and under design.

Error State Extended Kalman Filter Localization for Underground Mining Environments

The article addresses the issue of mobile robotic platform positioning in GNSS-denied environments in real-time. The proposed system relies on fusing data from an Inertial Measurement Unit (IMU), magnetometer, and encoders. To get symmetrical error gauss distribution for the measurement model and achieve better performance, the Error-state Extended Kalman Filter (ES EKF) is chosen. There are two stages of vector state determination: vector state propagation based on accelerometer and gyroscope data and correction by measurements from additional sensors. The error state vector is composed of the velocities along the x and y axes generated by combining encoder data and the orientation of the magnetometer around the axis z. The orientation angle is obtained from the magnetometer directly. The key feature of the algorithm is the IMU measurements’ isolation from additional sensor data, with its further summation in the correction step. Validation is performed by a simulation in the ROS (Robot Operating System) and the Gazebo environment on the grounds of the developed mathematical model. Trajectories for the ES EKF, Extended Kalman Filter (EKF), and Unscented Kalman Filter (UKF) algorithms are obtained. Absolute position errors for all trajectories are calculated with an EVO package. It is shown that using the simplified version of IMU’s error equations allows for the achievement of comparable position errors for the proposed algorithm, EKF and UKF.

Rare earth element recovery in hard-rock acid mine drainage and mine waste: A case study in Idaho Springs, Colorado

While the geochemistry of hard-rock generated acid mine drainage (AMD) and waste rock has been extensively studied for environmental and toxicological impacts, their critical metal contents have only recently begun to be characterized. We investigated rare earth element (REE) geochemistry in AMD and waste rock in the Idaho Springs gold district, Colorado. Specifically, we found that two AMD inputs to the Argo Tunnel Wastewater Treatment Plant (ATWTP) contain high dissolved REE concentrations (0.7 and 1.3 mg*L−1), and that REEs could be concentrated using a two-stage pH adjustment. The first stage precipitated iron and removed thorium by adsorption, while the second stage precipitated aluminum, which removed REEs by adsorption. Solids generated were 2670 and 2800 mg*kg−1 for each of the REE-bearing AMD sources, and at 90% REE recovery, the ATWTP could produce nearly 1000 kg of REEs each year with an economically favorable MREE enrichment. REE leaching in waste rock was also investigated, but results indicate that it is unlikely to be a significant source of REEs. More work is needed to characterize both the critical metal content (including other metals besides REEs) and economic feasibility of extraction for mine waste and AMD in hard-rock mining environments.

Hydrochemical Characterization and Assessment of Groundwater Quality in the Mining Environment of Afema Township (South-East of Côte d’Ivoire)

Afema Township, located in the department of Aboisso, was mined from 1992 to 1998. At the end of the exploitation, the sites did not undergo any real rehabilitation work. In order to determine the impact of these mining activities on the physicochemical characteristics and quality of groundwater, this study was undertaken. The results of the water analyses collected in the mining area were processed using Piper's triangular diagram and Principal Component Analysis (PCA). The methodological approach consisted, first of all, in determining the hydro-facies of the waters studied, then in dividing them into different groups on the basis of their hydro-chemical similarity and in identifying the factors likely to explain both the origin of the parameters studied and their correlation. Finally, the overall quality of these waters was estimated from the calculation of the quality index. The results showed that the waters studied were divided into two main families: chloride-calcium-magnesium waters and bicarbonate-calcium-magnesium waters. They were on the whole weakly mineralized, with an average electrical conductivity of 195.76 μS.cm-1. This mineralization was controlled by two essential phenomena, the residence time of water in the aquifers and surface infiltration and leaching from unsaturated ground. The physico-chemical quality of the groundwater studied complied with the standards of potability recommended by the WHO. However, the results also showed high levels of cadmium (0.052 mg.L-1) and lead (0.058 mg.L-1); this explained the overall poor quality of these waters according to the water quality index. Thus, the studied waters presented a real risk for human consumption. The consumption of these waters by local communities exposes them to health risks.

Predicting mechanical development of mine functional mortar: experiment and thermodynamic analysis

Shotcrete mortar is an imperative material for tunnel surface supporting. The mine environment with different temperature affects the mechanical development of mortar, resulting in a difficult to predict its compressive strength development at high temperature. In this investigation, the compressive strength, hydration heat, mineral evolution, pore content of mortar samples at 20 and 60 °C, containing partial steel slag powder, were comprehensively compared by experiment and simulation in order to provide a reliable approach for underground materials compressive strength prediction. Results show that the compressive strength development of the samples cured at 20 and 60 °C, is consisted with the corresponding cumulative hydration heat, and the correlation coefficient is higher than 0.96. The hydrates and heat of the samples are significantly affected by the cement type, mineral admixture, and temperature. Indeed, increasing temperature significantly accelerates the minerals’ hydration and heat release. Combining the composition, pore and single mineral hydration heat simulation, the mortar compressive strength development of the mortar in deep mine can be predicted by a thermodynamic model.