Drilling and blasting are essential operations within the mining industry, playing a critical role in material fragmentation. Despite advancements in various blasting technologies, the process remains a dominant contributor to overall mining costs. Achieving cost efficiency requires the precise configuration of blast design parameters, including explosive charge quantity, to attain desired outcomes in fragmentation, ground vibrations, fly rock, and air over-pressure. This study introduces a novel artificial intelligence (AI)-driven model, XGBoost-PSO-T, which combines eXtreme Gradient Boosting (XGBoost) with Particle Swarm Optimization (PSO) through the integration of the Tri-Weight technique. The PSO-Tri-Weight method optimizes the hyperparameters of the XGBoost model, enhancing its predictive capabilities. The model's performance was evaluated using root mean square error (RMSE) and coefficient of determination (R²), with the results demonstrating that the XGBoost-PSO-T system outperforms the standard XGBoost approach, achieving an RMSE of 0.657 and an R² of 0.922. These findings suggest that the XGBoost-PSO-T model is a valuable tool for predicting fragmentation outcomes and optimizing blast designs in surface mining operations. The implementation of this system is recommended to improve blasting efficiency and reduce operational costs.

According to data from the National Disaster Management Agency (BNPB), 629 landslides occurred in 2022, resulting in 318 fatalities, 459 displaced individuals, and extensive damage to 892 buildings and public facilities. To mitigate the impacts of such events, an early warning system for landslides based on Long Range Wide Area Network (LoRaWAN) was developed, enabling more effective monitoring and response in high-risk areas. This system integrates LoRaWAN technology with a suite of sensors, including a soil moisture sensor to track moisture levels, a Global Position System (GPS) sensor to provide location data, and an accelerometer to detect tilt and acceleration changes. Sensor data were transmitted to a gateway and monitored in real time via the Blynk application. Furthermore, the relationship between Spreading Factor (SF) values, transmission distance, Time on Air (ToA), and Packet Delivery Ratio (PDR) was examined to optimize system performance. The results indicate that SF 12 provides the most reliable performance in the context of early landslide detection. Data transmission in both emergency and scheduled modes was successfully achieved, with seamless integration of the gateway and Blynk platform. This research presents a robust framework for improving disaster mitigation efforts through early detection and monitoring systems.

The utilization of oil-based drilling fluids is a significant technical approach for drilling in ultra-deep, unconventional, and other complex hydrocarbon reservoirs. However, these fluids present notable disadvantages, including high preparation costs and environmental pollution. There is an urgent need to develop an eco-friendly, high-performance water-based drilling fluid system suitable for complex geological conditions to support the exploration and development of oil and gas under deep, challenging, and unconventional conditions. Addressing the current issue where polymer filtrate reducers cannot simultaneously achieve temperature resistance, salt resistance, and environmental performance, a novel organic/inorganic composite micro-nano filtrate reducer (MNFR) was developed using inverse emulsion polymerization. The MNFR has a D₅₀ particle size of 1.313μm, withstands temperatures up to 200℃, resists saturated NaCl brine, and exhibits an EC₅₀ biotoxicity value of 86700 mg/L. Furthermore, a high-temperature-resistant (up to 200℃) eco-friendly high-performance drilling fluid system (HBHP) was constructed, demonstrating excellent rheological and filtration properties, with a high temperature and high pressure (HTHP) filtration volume of only 7.6mL and an EC₅₀ biotoxicity value of 54300mg/L. It also shows outstanding plugging, anti-collapse, and hydration inhibition properties. The HBHP system has been applied in three wells in the Shengli oilfield, with no complex situations related to wellbore stability occurring during field operations, thus providing technical support for the green development of complex hydrocarbon reservoirs such as deep, ultra-deep, offshore deepwater, and unconventional formations.

The utilization of remote sensing (RS) techniques plays a crucial role in the efficient planning and monitoring of afforestation projects within constrained timeframes. This study evaluates the progress of the Billion Trees Afforestation Project (BTAP) in Dera Ismail Khan (DIK), Khyber Pakhtunkhwa, Pakistan, using RS technology. Geographical positioning systems were employed to delineate the boundaries of the plantation areas, and two temporal Sentinel-2 images from 2016 (the commencement of the plantation) and 2018 were analyzed to calculate the normalized difference vegetation index (NDVI). The results revealed that the survival rate of plantations varied between 37.39% and 85.15%, while the area of unstocked regions ranged from 14.84% to 62.60%. Overall, in 2016, the survival rate was determined to be 61.28%, with 38.72% of the area remaining unstocked. The NDVI values in 2016 ranged from -1 to -0.43, whereas in 2018, they spanned from -0.43 to 0.80, indicating significant progress in plantation growth and a substantial reduction in unstocked areas. The RS-based assessment proved to be highly effective, suggesting its adoption for the rapid detection and evaluation of plantation efforts. It is recommended to use high-resolution satellite images and drone technology to enhance accuracy further. Additionally, measures such as the establishment of closures, pit sowing, appropriate site and species selection, and effective soil and water conservation techniques are essential to maximizing the survival rate of plantations.

Rainfall is crucial for agricultural practices, and climate change has significantly altered rainfall patterns. Understanding the dynamic nature of rainfall in the context of climate change through Machine Learning (ML) and Deep Learning (DL) algorithms is essential for ensuring food security. ML techniques provide tools for processing large-scale data to extract meaningful insights. This study aims to compare the performance of a ML algorithm, Random Forest (RF), with a DL algorithm, Long Short-Term Memory (LSTM), in predicting rainfall in six state capitals in Southwest Nigeria: Osogbo, Ikeja, Ibadan, Akure, Ado-Ekiti, and Abeokuta. The dataset for this study was sourced from the HelioClim website archive, which offers high-quality solar radiation and meteorological data derived from satellite measurements. This archive is known for its accuracy and reliability, providing extensive and consistent historical datasets for various applications. The monthly rainfall data spanning from January 1, 1980, to December 31, 2022, were used, with 80% allocated for training and 20% for validation. As the data are time series, each model was constructed using a look-back period of five months, meaning the past five months' rainfall data served as input features. The performance of these algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The results indicated that the RF algorithm yielded the lowest MSE, RMSE, and MAE across all selected cities in Southwest Nigeria. This study demonstrated the superiority of RF regression over LSTM in predicting rainfall in these regions, providing a valuable tool for agricultural planning and climate adaptation strategies.

The Jaintiapur-Jaflong region, strategically positioned between the subsiding Surma Basin to the south and the uplifting Shillong Massif to the north, presents a unique geological setting. This study employed geological clinometers and other field methods to ascertain the geological characteristics of the area. The regional strike was determined to be N66˚W, with a dip direction of S24˚W and a dip angle of 42.25˚. Through extensive field investigations, including geological mapping, stratigraphic logging, rock sampling, fossil analysis, and structural analysis, complemented by Global Positioning System (GPS), photography, remote sensing, and Geographic Information System (GIS) technologies, seven lithostratigraphic units were identified. These include the variegated color sandstone, mottled clay, yellowish to reddish-grey sandstone, sandy shale with intercalated silty shale, pinkish sandstone, bluish to blackish-grey shale, and limestone units, corresponding sequentially to Dupi Tila, Girujan Clay, Tipam Sandstone, Surma Group, Jenum Shale Fm, Kopili Shale, and Sylhet Limestone Fm, respectively. Five critical geological contact boundaries were delineated, with notable boundaries identified at the Dupigaon-Sari River Section, the Lalakhal-Tetulghat Section, the Nayagang-Gourishankar Section, and between the Barail and Jaintia groups at the Tamabil-Jaflong Highway Road Cut Section. These findings elucidate the geological contacts and stratigraphic units, providing significant implications for paleoenvironmental reconstruction, resource potential assessment, and stratigraphic correlation, thus enhancing the understanding of regional geological history and laying a foundation for future research endeavors.

Over a thirty-year period (1990-2020), the spatiotemporal changes in riverbank erosion and accretion along the Jamuna River in Shariakandi Upazila, Bogura District, Bangladesh, were investigated using Landsat satellite imagery processed through ArcGIS 10.8 and Erdas Imagine 2015. The analysis delineated significant alterations in the riverbank, quantifying a decrease in the river area from 108 km² to 79.99 km², with a net erosion of 50.02 km² and an accretion of 78.03 km². Among the nine unions affected, Karnibari, Kazla, and Chaulabari were most impacted, with erosion accounting for 14.79%, 25.98%, and 28.42% of the total, respectively. This study established a direct correlation between riverbank erosion and increased vulnerability for local populations, characterized by loss of homesteads and agricultural lands, displacement, income reduction, and a cycle of poverty. Environmental repercussions included deteriorated water quality and an increased prevalence of diseases. The effectiveness of various local adaptation strategies, such as financial reliance on external sources, migration, and occupational shifts, was also assessed, revealing a spectrum of success and underscoring the necessity for more sustainable, holistic approaches. This research emphasizes the imperative for integrated riverbank management strategies that concurrently address the geological and socio-economic ramifications of riverbank erosion.

A geoelectrical imaging survey, employing resistivity and induced polarization (IP) methodologies, was executed on Dala Hill, Kano, Nigeria, positioned between latitudes 12.008611°N and 12.009722°N, and longitudes 8.505833°E and 8.507222°E. The objective was to assess and compare findings with prior ground magnetic studies to delineate subsurface geological structures. The survey utilized an ABEM Terrameter SAS 1000 for data acquisition along three distinct profiles encompassing the hill and adjacent areas, with electrode separations fixed at 10 meters. Data processing was conducted using RES2DINV software, revealing resistivity profiles that identified three stratified layers with resistivity values ranging from 300Ωm to 6798Ωm for the first layer, 128Ωm to 744Ωm for the second, and 4Ωm to 127Ωm for the third. IP profiles identified zones of varying chargeability, from -3.44 msec to 19.6 msec. Analysis indicated a consistent positive correlation between zones of high resistivity and low chargeability. For instance, a zone along Profile 1 demonstrated high resistivity values (2142Ωm - 6798Ωm) between 60m and 190m, coinciding with a low chargeability zone (0.506 msec to 2.43 msec) observed from 20m to 100m along the profile, equating to depths of 10m to 39.6m. Similar correlations were observed in the subsequent profiles, with significant intersections between high resistivity and low chargeability zones. These areas were interpreted as being rich in iron ore minerals, predominantly magnetite, based on the comparative analysis with standard values of rocks and minerals. The presence of magnetite, known for its high iron content and magnetic properties, underscores the area's potential for steel production. Moreover, the identification of a dyke within the study area corroborates findings from earlier magnetic studies, further validating the geophysical methodology's effectiveness in revealing the shallow subsurface structural settings. This alignment not only substantiates the layered configurations deduced from magnetic studies but also highlights the geoelectrical survey's capability in providing a comprehensive understanding of subsurface geology.

In mines characterized by high gas concentrations, the process of extracting natural resources frequently precipitates coal and gas outbursts, positioning borehole gas extraction as a pivotal preventative strategy. Investigations aimed at identifying an optimal borehole diameter for gas extraction were undertaken within the Puxi Mine, entailing the drilling of boreholes across a spectrum of diameters and subsequent comparative analysis of the resultant data. This study meticulously evaluated the influence of seven distinct borehole diameters on gas concentration and pure flow rate, per unit length of coal hole and per unit of applied negative pressure. It was discerned that boreholes with larger diameters significantly enhance gas extraction efficacy. Specifically, boreholes of 113mm and 94mm diameters were noted for their exceptional performance, delivering pure flow rates of gas at 0.0215 m³/min and 0.0428 m³/min, respectively. Through a detailed examination of borehole diameters that presented considerable advantages, notably 113mm, 105mm, and 94mm, it was ascertained that the 94mm borehole diameter achieved the highest utilization efficiency, registering a gas pure flow rate of 1.62×10^-4 m³/min per unit diameter. Consequently, this diameter was identified as the most advantageous for gas extraction purposes. The insights garnered from this investigation are instrumental for the selection of borehole diameters tailored to gas extraction in coal seams of varying thicknesses, and they significantly contribute to the formulation of rationalized gas extraction methodologies.

In response to the prevalent high water cut challenge in horizontal wells of the Bohai A Oilfield, this study introduces an innovative approach for pinpointing water production points in horizontal wells. The methodology leverages a comprehensive evaluation that integrates techniques such as curve identification, dynamic analysis, numerical simulation, and seepage model calculations. In conjunction, a novel hydraulic control-based balanced oil production process has been developed. This process utilizes a specialized water plugging string to effectively seal water production points in horizontal wells. Additionally, a hydraulic control system for horizontal well oil production has been implemented, facilitating staged extraction and thus achieving balance in oil production. Field application, particularly in Well X1, demonstrates a marked improvement post-implementation: the comprehensive water cut in Well X1 decreased from an initial 98.1% to 87.3%, and the production pressure differential escalated from 0.55 MPa to 2.01 MPa. This substantial enhancement in reservoir utilization indicates a notable reduction in water cut within the crude oil. The application of this balanced production technology in horizontal wells has led to a decrease in water cut and liquid production, significantly alleviating surface processing pressures. Consequently, there has been an improvement in well productivity and the overall development effectiveness of the oilfield. These findings suggest that the balanced oil production technique offers a promising solution for enhancing oil recovery in horizontal wells, particularly in fields grappling with high water cuts.

Meteorological parameter modeling is imperative for predicting future atmospheric conditions. This study focuses on the Sub-Saharan region of West Africa, a region characterized by its climatic diversity and unique weather patterns, making it an ideal subject for meteorological research. The objective was to model meteorological parameters using trigonometric and polynomial functions, assessing their predictive accuracy in selected West African stations. The parameters considered include air temperature, air pressure, wind speed, rainfall, and relative humidity, with data sourced from the HelioClim satellite archive, spanning 1980 to 2022. The data, recorded in comma-separated value (CSV) format, were analyzed using descriptive statistics, specifically mean and standard deviation. Each meteorological parameter underwent modeling through both polynomial and trigonometric functions. The comparative effectiveness of these models was evaluated using the adjusted coefficient of determination and Root Mean Square Error (RMSE). The preference for the adjusted coefficient of determination over the standard coefficient of determination (R²) was due to its ability to account for biases arising from variances in the number of parameters in both model types. The results indicated that both trigonometric and polynomial models are robust in their predictive capabilities, demonstrating their utility in accurate parameter estimation and future weather prediction. These findings suggest that such models are valuable tools in climate studies, enhancing understanding and awareness of weather conditions in the Sub-Saharan West African region.