This study introduces the Spatio-Temporal Attention Enhanced Encoder-Decoder Damage Prediction Network (STAE-EDDPNet), an innovative deep learning model designed to enhance the predictive capabilities of coal-rock damage infrared temperature fields, which is crucial for the safe production in rock engineering and mining engineering. STAE-EDDPNet integrates a spatio-temporal attention mechanism, significantly improving the capture of complex nonlinear spatio-temporal information in rock infrared radiation. Compared with baseline models such as 3DCNN, ConvLSTM, and EDDPNet, STAE-EDDPNet demonstrated superior performance in both single-step and multi-step forecasting tasks. Test set results show that its predictive accuracy is 25.56% higher than 3DCNN, 5.69% higher than ConvLSTM, and 0.19% higher than EDDPNet. The study also found that the characteristics of brittle failure rock data significantly affect model training and predictive performance, providing a direction for future data collection and experimental design improvements. The introduction of STAE-EDDPNet not only promotes the application of infrared monitoring technology in the field of safety monitoring but also provides valuable reference for rock damage early warning.

@en

The recent research aims to investigate the petrophysical and hydrogeological parameters of the Nubian aquifer system (NAS) in Northern Khartoum State, Sudan, using integrated geophysical methods, including surface electrical resistivity and geophysical well-logging. The Nubian aquifer is a transboundary regional aquifer that covers vast areas in Sudan, Egypt, Libya and Chad. The well-logs, including self-potential (SP), natural gamma ray (GR), and long normal resistivity (RS), are integrated with Vertical Electrical Sounding (VES) measurements to delineate the hydrostratigraphical units. As a result, two aquifers are detected. An upper aquifer comprises coarse sand with an average thickness of 50 m and a lower aquifer of sandstone with more than 200 m thickness. For a thorough evaluation of the aquifers, in the first stage, the petrophysical and hydrogeological parameters, including formation factor, total and effective porosity, shale volume, hydraulic conductivity, and transmissivity, are measured solely from geophysical well-logs. In the second step, the results of geophysical well logs are combined with VES and pumping test data to detect the spatial variation of the measured parameters over the study area. As a result, the hydraulic conductivity of the Nubian aquifers ranged from 1.9 to 7.8 m/day, while the transmissivity varied between 120 and 733 m2/day. These results indicated that the potentiality of the Nubian formation is high; however, in some regions, due to the sediment heterogeneity, the aquifers have intermediate to high potential. According to the obtained results, it can be concluded that the Nubian Aquifer in Khartoum state is ideal for groundwater development. This research discovered that geophysical approaches can be used to characterize moderately heterogeneous groundwater systems by comparing the Nubian aquifer with similar aquifer systems that have similar hydrogeological settings. This study emphasized the application of universal principles in extrapolating hydraulic parameters in hydrogeophysical surveys. This approach aims to reduce the costs and efforts associated with traditional hydrogeological approaches.@en

This study combined gravity data from the Earth Gravitational Model (EGM2008) with other data to better understand the spatial variations of the sedimentary cover and the structural trends that affect groundwater flow in the Nubian Sandstone Aquifer System. Our findings were verified and evidenced by geological, geochronological, geochemical data, and earthquake records: 1) The Uweinat-Aswan basement uplift, which runs east-west, partially isolates the Dakhla subbasin from the shallower northern Sudan subbasin, and thereby impeding the south-to-north groundwater flow from northern Sudan platform to the Dakhla subbasin; 2) A thickening of the sedimentary cover in the NE-SW direction from the southern Kufra through the northern Kufra to the Dakhla subbasin; 3) The sedimentary cover was found to increase from less than 500 m in the south (Northern Sudan and Uweinat region) to more than 6 km in the north (Mediterranean coast); 4) A number of structural trends (NE-SW, N-S, E-W, and NW-SE) affecting the region; 5) A large Pelusium megashear system that runs northeast to southwest makes it easier for groundwater to flow from the Kufra subbasin to the Dakhla subbasin; 6) Along the paths that groundwater takes, like from Siwa to Qattara and from northwest Farafra to north Bahariya, and along structures that run in the same direction as the flow, a progressive increase in 36Cl groundwater ages were observed; 7) It is a better way to learn about the hydrogeological context of large aquifers and figure out how to best manage these underground water sources.@en

The numerous hydrothermal alteration zones and subsurface structures affecting the mineralized deposits of the Dungash region were identified using aeromagnetic data. The Center of Exploration Targeting (CET) approach and several filters, such as reduction-to-pole, Tilt derivative, First Vertical Derivative, Horizontal gradient map, Downward continuation, analytical signal methods, regional, and residual separation, were used to analyze the aeromagnetic data. The research region is impacted by several structural trends running in the N-S, E-W, NW-SE, and NE-SW directions, and these trends are strongly related to the gold mineralization and surrounding hydrothermal alteration zones. In the NW-SE direction, four alteration zones have been identified. The research region's northern and eastern regions have shallower basement relief, with depths of only approximately 100 m, and those depths show that the area is rootless. Conversely, the basement relief and surface depths are lower in the study region's western and southern regions. The routes taken by the ascending hydrothermal fluids can be seen as aeromagnetic lineaments at the hydrothermal alteration zones. Mineralization appears to be linked to structural lineaments, as evidenced by airborne magnetic data. For gold prospecting, the aeromagnetic technique seems to be the most effective and efficient geophysical method because gold is typically found in severely deformed shear zones and faults.

@en

Agriculture is considered one of the primary elements for socioeconomic stability in most parts of Sudan. Consequently, the irrigation water should be properly managed to achieve sustainable crop yield and soil fertility. This research aims to predict the irrigation indices of sodium adsorption ratio (SAR), sodium percentage (Na%), permeability index (PI), and potential salinity (PS) using innovative machine learning (ML) techniques, including K-nearest neighbor (KNN), random forest (RF), support vector regression (SVR), and Gaussian process regression (GPR). Thirty-seven groundwater samples are collected and analyzed for twelve physiochemical parameters (TDS, pH, EC, TH, Ca+2, Mg+2, Na+, HCO3−, Cl, SO4−2, and NO3−) to assess the hydrochemical characteristics of groundwater and its suitability for irrigation purposes. The primary investigation indicated that the samples are dominated by Ca-Mg-HCO3 and Na-HCO3 water types resulted from groundwater recharge and ion exchange reactions. The observed irrigation indices of SAR, Na%, PI, and PS showed average values of 7, 42.5%, 64.7%, and 0.5, respectively. The ML modeling is based on the ion’s concentration as input and the observed values of the indices as output. The data is divided into two sets for training (70%) and validation (30%), and the models are validated using a 10-fold cross-validation technique. The models are tested with three statistical criteria, including mean square error (MSE), root means square error (RMSE), and correlation coefficient (R2). The SVR algorithm showed the best performance in predicting the irrigation indices, with the lowest RMSE value of 1.45 for SAR. The RMSE values for the other indices, Na%, PI, and PS, were 6.70, 7.10, and 0.55, respectively. The models were applied to digital predictive data in the Nile River area of Khartoum state, and the uncertainty of the maps was estimated by running the models 10 times iteratively. The standard deviation maps were generated to assess the model’s sensitivity to the data, and the uncertainty of the model can be used to identify areas where a denser sampling is needed to improve the accuracy of the irrigation indices estimates.@en

Because of climate change and human activity, North and Central Africa are experiencing a significant water shortage. Recent advancements in earth observation technologies have made widespread groundwater monitoring possible. To examine spatial and temporal mass fluctuations caused by groundwater variations in Chad, gravity solutions from the Gravity Recovery and Climate Experiment (GRACE), climatic model outputs, and precipitation data are integrated. The results are as follows: (1) The investigated region experienced average annual precipitation (AAP) rates of 351.6, 336.22, and 377.8 mm yr−1, throughout the overall investigation period (04/2002–12/2021), Period I (04/2002–12/2011), and Period II (01/2012–12/2021), respectively. (2) Using the three gravity solutions, the average Terrestrial Water Storage Variations (ΔTWS) values are estimated to be +0.26 ± 0.04, +0.006 ± 0.10, and +0.64 ± 0.12 cm yr−1, for the overall study period, periods I, and II, respectively. (3) Throughout the full period, periods I, and II, the groundwater storage fluctuations (ΔGWS) are calculated to be +0.25 ± 0.04, +0.0001 ± 0.099, and +0.62 ± 0.12 cm yr−1, respectively after removing the soil moisture (ΔSMS) and Lake Chad water level trend values. (4) The country receives an average natural recharge rate of +0.32 ± 0.04, +0.068 ± 0.099, and +0.69 ± 0.12 cm yr−1, throughout the whole period, Periods I, and II, respectively. (5) The southern mountainous regions of Erdi, Ennedi, Tibesti, and Darfur are receiving higher rainfall rates that may recharge the northern part of Chad through the stream networks; in addition to the Lake Chad and the higher rainfall over southern Chad might help recharge the central and southern parts of the country. (6) A preferred groundwater flow path from the Kufra (Chad and Libya) to the Dakhla basin (Egypt) appears to be the Pelusium mega shear system, which trends north-east. The findings suggest that GRACE is useful for monitoring changes in groundwater storage and recharge rates across large areas. Our observation-based methodology provides a unique understanding of monthly ground-water patterns at the state level, which is essential for successful interstate resource allocation, future development, and policy initiatives, as well as having broad scientific implications for arid and semiarid countries.@en

The present work used the electrical resistivity approach to conduct a three-dimensional modeling and initial volume estimation of the limestone layer in the Mintom region located in southern Cameroon. In order to achieve the objectives of the study, a total of 21 electrical soundings spaced 250 m were first collected in the field using the Schlumberger array. These soundings were conducted along three profiles oriented in an east–west direction, spaced 500 m. Additionally, a geological survey was conducted to identify and emphasize the presence of limestone formations within the designated study region. The interpretation of the sounding data was conducted based on the analysis of the sounding curves. The interpretation outcomes, specifically resistivity and thickness, were compared with the geological field data, resulting in the development of lithostratigraphic logs for each sounding. The geological sections were constructed using the logs of the designated profile. The lithological logs were utilized to establish a lithological interface model and calculate the volume of the limestone layer at 260 ± 13 × 106 m3, utilizing the inverse distance method built into RockWorks software. A resistivity value is assigned to each geological layer in a sounding curve, allowing for the development of a resistivity variation model specific to the limestone layer. The proposed model facilitates the categorization of limestone layers based on their resistivity variations, thus serving as a fundamental reference for prospective exploratory activities within the designated study region. Our integrated approach provides a replicable model for a better understanding of the limestone reserve and effective management of this valuable resource.@en