Predicting mine water inrush accidents based on water level anomalies of borehole groups using long short-term memory and isolation forest

Appraisal of reservoir quality for hydrocarbon-bearing deep-water Miocene sandstones incised valley, south-east Asian offshore Indus: An application of seismic attributes and instantaneous spectral porosity quantitative reservoir simulations

“…Some of the researchers in the sub-surface characterization of diversified systems have made significant works for the development of the most sophisticated workflows such as the analysis of water level inside the drilled wells, analyzing the anomalies and ion diffusion in shale reservoirs, economic evaluation of closed-loop for the geothermal systems, spaceborne multispectral subsurface Reflectance analysis, global karst carbon sink bathymetric mapping etc. [ [29] , [74] , [75] , [76] , [81] , [82] ]. These plays can be structural, stratigraphic and/or a combination of these two regimes.…”

Preferred Ratio and Properties of Microfoam Drilling Fluid for Gas Extraction in Soft Coal Seams

“…Gas extraction ensures the safe mining of working faces and allows for the acquisition of gas resources, resulting in supplementary economic and social benefits for the mines. − High-gas mines are the primary target for gas extraction in our country, and data indicates that nearly 95% of the coal seams within these high-gas mines are soft . The characteristics of smooth coal seams, such as low strength coefficients and mechanical intensity, make them prone to accidents such as collapsing, drilling suction, roof drilling, blowouts, and stuck drilling, particularly under the weight of overlying rock strata in deeper areas. − These incidents, ranging from minor impacts on drilling efficiency, length, and extraction scope to severe cases of lost drilling directly, affects the progress of gas extraction work, restricting the safety and efficiency of the coal industry. − …”

Predictive analysis of concrete slump using a stochastic search-consolidated neural network

“…Likewise, the advent of laboratory utensils and novel modeling approaches have enabled engineers to assess the quality of construction materials [ [20] , [21] , [22] , [23] , [24] ]. However, above these advances, computational intelligence and machine learning (ML) algorithms have facilitated and enhanced the prediction of different engineering variables [ [25] , [26] , [27] , [28] ]. For instance, Ghasemi and Naser [ 29 ] tried to utilize the capability of artificial intelligence for predicting the mechanical properties (i.e., compressive strength) of 3D-printed concrete.…”