Automatic lithology identification in meteorite impact craters using machine learning algorithms.

Identifying lithologies in meteorite impact craters is an important task to unlock processes that have shaped the evolution of planetary bodies. Traditional methods for lithology identification rely on time-consuming manual analysis, which is costly and limits the efficiency of rapid decision-making. This paper utilizes different machine learning algorithms namely Random Forest, Decision Tree, K Nearest Neighbors, and Logistic Regression with Grid Search to classify rock lithologies using data from the Bosumtwi impact crater in Ghana. A repeated stratified k-fold cross-validation method is applied to Grid Search to select the best combination of hyperparameters. The findings demonstrate that the Random Forest algorithm achieves the most promising results in classifying lithologies in the meteorite impact crater with an accuracy score of 86.89%, a recall score of 84.88%, a precision score of 87.21%, and an F1 score of 85.48%. The findings also suggest that more high-quality data has the potential to further increase the accuracy scores of the machine learning algorithm. In conclusion, this study demonstrates the significant potential of machine learning techniques to revolutionize lithology identification in meteorite impact craters, thus paving the way for their influential role in future space exploration endeavors.

Seismic activities in Ghana: A systematic review.

Seismic activities pose significant challenges to societies globally. Therefore, it is crucial to understand their occurrence, patterns, and impacts. By studying seismic activities, including earthquakes, researchers can investigate their occurrence, distribution, and characteristics which can provide effective management and risk reduction strategies. The southern part of Ghana is prone to earthquakes and this study aims to shed more light into the nature of seismic events in the area and country at large. A systematic review was conducted using the PRISMA technique across three electronic databases (SCOPUS, Dimensions and Google Scholar) to identify relevant studies published between 2000 and 2023. Extraction of data and quality assessment were performed in order to ensure reliability and validity of included studies. Results identified only 17 papers from published records to meet the inclusion criteria. Despite the grave threat earthquakes pose to vital infrastructure and human life in Ghana, research in this area remains remarkably deficient. Our findings underscore the urgent need for further study given the catastrophic potential of seismic disasters in the region. Moreover, upon scrutinizing the methodologies deployed in extant literature concerning seismic activity in Ghana, a recurring constraint that emerged was the scarce availability of data. In essence, this study offers an indispensable panorama of earthquake research in Ghana, bridging the existing knowledge chasm on seismic phenomena in the region. The insights gleaned from this review promise to fortify our comprehension of Ghana's seismic activities, thereby bolstering the country's capabilities for more effective preparedness and response strategies.

Prediction of compressional sonic log in the western (Tano) sedimentary basin of Ghana, West Africa using supervised machine learning algorithms.

Sonic logs are essential for determining important reservoir properties such as porosity, permeability, lithology, and elastic properties, among others, and yet may be missing in some well logging suites due to high acquisition costs, borehole washout, tool damage, poor tool calibration, or faulty logging instruments. This study aims at predicting the compressional sonic log from commonly acquired logs (gamma ray, resistivity, density, and neutron-porosity) in the Tano basin of Ghana using Support Vector Machines (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) Machine Learning (ML) algorithms and comparing the performances of the algorithms. The algorithms were trained with 70% of the data from two wells and tested using the remaining 30% of the data from the wells after cross-validation. Subsequently, they were applied to the data from a third well to predict the sonic log in the well. The performances of the algorithms were assessed with five statistical tools: coefficient of determination (R2), adjusted R2, Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). All three algorithms successfully predicted the compressional sonic log (DT). XGBoost demonstrated the highest prediction accuracy, with R2 of 0.9068 and the least errors. RF exhibited the next highest accuracy, with R2 being 0.85478, while SVM had R2 of 0.66591. Therefore, the ensemble algorithms (XGBoost and RF) proved to be more accurate than the non-ensemble algorithm (SVM) in this study. The outcome of the study will accelerate and enhance the understanding of oil and gas fields with few or no compressional sonic logs. To the best of the authors' knowledge, this is the first study to have predicted the compressional sonic log from well data (logs) in a Ghanaian sedimentary basin using machine learning algorithms, and only a few such studies have been conducted in the whole West African sub-region.

A meteorological dataset of the West African monsoon during the 2016 DACCIWA campaign.

As part of the Dynamics-Aerosol-Chemistry-Cloud Interactions in West Africa (DACCIWA) project, extensive in-situ measurements of the southern West African atmospheric boundary layer (ABL) have been performed at three supersites Kumasi (Ghana), Savè (Benin) and Ile-Ife (Nigeria) during the 2016 monsoon period (June and July). The measurements were designed to provide data for advancing our understanding of the relevant processes governing the formation, persistence and dissolution of nocturnal low-level stratus clouds and their influence on the daytime ABL in southern West Africa. An extensive low-level cloud deck often forms during the night and persists long into the following day strongly influencing the ABL diurnal cycle. Although the clouds are of a high significance for the regional climate, the dearth of observations in this region has hindered process understanding. Here, an overview of the measurements ranging from near-surface observations, cloud characteristics, aerosol and precipitation to the dynamics and thermodynamics in the ABL and above, and data processing is given. So-far achieved scientific findings, based on the dataset analyses, are briefly overviewed.

Characterization of complex fluvio-deltaic deposits in Northeast China using multi-modal machine learning fusion.

Due to the lack of petroleum resources, stratigraphic reservoirs have become an important source of future discoveries. We describe a methodology for predicting reservoir sands from complex reservoir seismic data. Data analysis involves a bio-integrated framework called multi-modal machine learning fusion (MMMLF) based on neural networks. First, acoustic-related seismic attributes from post-stack seismic data were used to characterize the reservoirs. They enhanced the understanding of the structure and spatial distribution of petrophysical properties of lithostratigraphic reservoirs. The attributes were then classified as varied modal inputs into a central fusion engine for prediction. We applied the method to a dataset from Northeast China. Using seismic attributes and rock physics relationships as input data, MMMLF was performed to predict the spatial distribution of lithology in the Upper Guantao substrata. Despite the large scattering in the acoustic-related data properties, the proposed MMMLF methodology predicted the distribution of lithological properties through the gamma ray logs. Moreover, complex stratigraphic traps such as braided fluvial sandstones in the fluvio-deltaic deposits were delineated. These findings can have significant implications for future exploration and production in Northeast China and similar petroleum provinces around the world.

Probabilistic seismic hazard assessment of southern part of Ghana.

This paper presents a seismic hazard map for the southern part of Ghana prepared using the probabilistic approach, and seismic hazard assessment results for six cities. The seismic hazard map was prepared for 10% probability of exceedance for peak ground acceleration in 50 years. The input parameters used for the computations of hazard were obtained using data from a catalogue that was compiled and homogenised to moment magnitude (Mw). The catalogue covered a period of over a century (1615-2009). The hazard assessment is based on the Poisson model for earthquake occurrence, and hence, dependent events were identified and removed from the catalogue. The following attenuation relations were adopted and used in this study-Allen (for south and eastern Australia), Silva et al. (for Central and eastern North America), Campbell and Bozorgnia (for worldwide active-shallow-crust regions) and Chiou and Youngs (for worldwide active-shallow-crust regions). Logic-tree formalism was used to account for possible uncertainties associated with the attenuation relationships. OpenQuake software package was used for the hazard calculation. The highest level of seismic hazard is found in the Accra and Tema seismic zones, with estimated peak ground acceleration close to 0.2 g. The level of the seismic hazard in the southern part of Ghana diminishes with distance away from the Accra/Tema region to a value of 0.05 g at a distance of about 140 km.