Muhammad Risha

Muhammad Risha


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2025
Verified
Preprint
Open access
MRMuhammad Risha
Muhammad Risha
PLPaul Liu
Paul Liu
The dynamic nature of coastal zones is characterized by continuous change in shoreline position due to natural and anthropogenic processes. These changes present challenges for coastal management and conservation efforts. Traditionally, shoreline change analysis relied mainly on empirical observations and numerical models which was limited in dealing with complex, multi-dimensional interactions along our coasts. Recent decades have witnessed an integration of machine learning (ML) techniques into coastal studies to predict shoreline changes. This review aims to provide a general overview of the development of shoreline modeling and the evolution of ML applications in the field. The review synthesizes findings from 18 research papers, tracing the development of shoreline prediction methodologies from early empirical models to modern ML-based frameworks. The analysis highlights a shift from deterministic approaches to data-driven models that leverage multiple ML techniques for improved predictions. By comparing different modeling approaches over time, this study evaluates the effectiveness of ML in capturing shoreline dynamics and enhancing predictive capabilities. The review shows that new methods can significantly enhance shoreline modeling, offering improved predictive power and new insights into coastal dynamics. The findings suggest future research directions in the context of climate change and increasing human interventions.

19 February 2025
Verified
Preprint
Open access
MRMuhammad Risha
Muhammad Risha
The characterization of pore-throat structures in tight sandstones is crucial for understanding fluid flow in hydrocarbon reservoirs and groundwater systems. Both thin-section and Mercury Intrusion Capillary Pressure (MICP) offer insights rock petrophysical parameters. However, thin-section analysis is limited by its 2D nature and subjective interpretation, while MICP provides 3D pore-throat distributions, it lacks direct visualization of pore morphology. This study evaluates AI-assisted thin-section image analysis for pore-throat characterization by comparing its results to MICP-derived measurements. A machine learning-based workflow was developed using color thresholding, K-Means clustering, and medial axis transformation to segment pore structures in thin-section images. Throat width, porosity, and permeability were quantitatively assessed against MICP to determine the accuracy and reliability of the technique. The analysis of 26 sandstone samples outlined differences between the two methods. Thinsection analysis showed porosity values from 1.37% to 53.37%, with average pore-throat sizes between 5.63 µm and 30.09 µm, while permeability estimates ranged from 0.01 mD to 344.35 mD. Correlation analysis showed moderate agreement for throat size (r=0.62) and permeability (r=0.61), but weaker for porosity (r=0.32), highlighting the differences in how each method captures pore connectivity. Results demonstrate that the AI-assisted segmentation provides a scalable and reproducible approach but is constrained by thin-section imaging resolution. While MICP remains reliable for permeability evaluation, its comparison with AI-driven image analysis helps assess the reliability of the method. Future research should refine segmentation algorithms, incorporate pretrained data to validate AIderived pore-throat attributes for improved reservoir quality assessment and predictive modeling.

28 April 2025 in Qeios Preprints
Verified
Preprint
Open access
PDF file
MRMuhammad Risha
Muhammad Risha
PLPaul Liu
Paul Liu
The dynamic nature of coastal zones is characterized by continuous change in shoreline position due to natural and anthropogenic processes. These changes present challenges for coastal management and conservation efforts. Traditionally, shoreline change analysis relied mainly on empirical observations and numerical models which was limited in dealing with complex, multi-dimensional interactions along our coasts. Recent decades have witnessed an integration of machine learning (ML) techniques into coastal studies to predict shoreline changes. This review aims to provide a general overview of the development of shoreline modeling and the evolution of ML applications in the field. The review synthesizes findings from 18 research papers, tracing the development of shoreline prediction methodologies from early empirical models to modern ML-based frameworks. The analysis highlights a shift from deterministic approaches to data-driven models that leverage multiple ML techniques for improved predictions. By comparing different modeling approaches over time, this study evaluates the effectiveness of ML in capturing shoreline dynamics and enhancing predictive capabilities. The review shows that new methods can significantly enhance shoreline modeling, offering improved predictive power and new insights into coastal dynamics. The findings suggest future research directions in the context of climate change and increasing human interventions.

4 June 2025 in Qeios Preprints
Verified
Preprint
Open access
PDF file
MRMuhammad Risha
Muhammad Risha
MEMohamed Elsaadany
Mohamed Elsaadany
PLPaul Liu
Paul Liu
Predicting microporosity and permeability in clastic reservoirs is a challenge in reservoir quality assessment, especially in formations where direct measurements are difficult or expensive. These reservoir properties are fundamental in determining a reservoir's capacity for fluid storage and transmission, yet conventional methods for evaluating them, such as Mercury Injection Capillary Pressure (MICP) and Scanning Electron Microscopy (SEM), are resource-intensive. The aim of this study is to develop a cost-effective machine learning model to predict complex reservoir properties using readily available field data and basic laboratory analyses. A Random Forest classifier was employed, utilizing key geological parameters such as porosity, grain size distribution, and spectral gamma-ray (SGR) measurements. An uncertainty analysis was applied to account for natural variability, expanding the dataset, and enhancing the model's robustness. The model achieved a high level of accuracy in predicting microporosity (93%) and permeability levels (88%) using cross-validation and independent holdout evaluation. By using easily obtainable data, this model reduces the reliance on expensive laboratory methods, making it a valuable tool for early-stage exploration, especially in remote or offshore environments. By incorporating uncertainty, the model reflects geological variability more realistically and improves confidence in predictions, particularly when decisions must be made with limited or noisy input data. The integration of machine learning with uncertainty analysis provides a reliable and cost-effective approach for evaluating key reservoir properties in siliciclastic formations. This model offers a practical solution to improve reservoir quality assessments, enhancing decision-making in exploration planning and risk reduction, especially where direct measurements are limited enabling more informed decision-making and optimizing exploration efforts.

9 October 2025 in Earth
Verified
Journal Article
Open access
PDF file
MRMuhammad Risha
Muhammad Risha
J. Paul LiuJ. Paul Liu
J. Paul Liu
The Nile, Indus, and Yellow River deltas are historically significant and have experienced extensive shoreline changes over the past 50 years, yet the roles of human interventions and natural events remain unclear. In this study, the Net Shoreline Movement and End Point Rate (EPR) were calculated to quantify the erosion and accretion of the shoreline, respectively. Subsequently, linear trend analysis was employed to identify potential directional shifts in shoreline behavior. These measures are combined with segment-scale cumulative area and the EPR trend to reveal where erosion or accretion intensifies, weakens, or reverses through time. Results show distinct, system-specific trajectories, the Nile lost ~27 km2 from 1972 to1997 as a result of the dam construction and sediment reduction, and lost only ~3 km2 more from 1997 to 2022, with local stabilization. The Indus switched from intermittent gains before 1990s to sustained loss after that, totaling ~300 km2 of cumulative land loss mainly due to upstream dam constructions and storm events. The Yellow River gained ~500 km2 from 1973 to 1996 then lost ~200 km2 after main-channel relocation and reduced sediment supply despite active-mouth management. These outcomes indicate that deltas are very vulnerable to system wide human activities and natural events. Combined, satellite-derived metrics can help prioritize locations, guide feasible interventions, establish annual monitoring and trigger action. A major caveat of this study is that yearly shoreline rates and 5–10-yearaverages can mask short-lived or very local shifts. Targeted field surveys and finer-scale modeling (hydrodynamics, subsidence monitoring, bathymetry) are therefore needed to refine the design and inform better policy choices.

22 February 2024 in Atmosphere
Verified
Journal Article
Open access
PDF file
YZYunfeng Zhang
Yunfeng Zhang
KWkuifeng wang
kuifeng wang
JSJianchao Song
Jianchao Song
J. Paul LiuJ. Paul Liu
J. Paul Liu
CXChuanbo Xia
Chuanbo Xia
LWLin Wang
Lin Wang
Loess deposits are widely distributed across the globe and provide detailed records of climatic changes since the Quaternary period. Their geochemical element characteristics are important indicators of paleoenvironmental evolution and provenance. Therefore, four typical loess sections from four different islands of the Miaodao Islands were selected for systematically geochemical analysis of major and trace elements. The geochemical data of major and trace elements are very similar, indicating that the loess of all islands on the Miaodao have a common provenance. The geochemical test results show that t SiO2, Al2O3, Fe2O3 and CaO are the major chemical components of loess, with an average total content of 85–90%. The average Eu/Eu*, ΣLREE/ΣHREE, LaN/YbN, GdN/YbN values of the Miaodao Islands loess range from 0.65 to 0.69, 7.84 to 8.31, 8.02 to 9.99, 1.40 to 1.76. These data are similar to and different from those of the Chinese Loess Plateau, indicating the diversity of Miaodao Islands Loess provenance. The CIA (Chemical Index of Alteration) (50–65) and Na/K results suggest that the loess here had experienced incipient chemical weathering. The A-CN-K (Al2O3-CaO* + Na2O-K2O) diagram indicates that the weathering trend of the loess sections is consistent with that of continental weathering. The local loess data points are close and parallel to the A-CN line, suggesting that the loess dust material on the Miaodao Islands originated from the extensive upper continental crust, and was highly mixed in the process of wind transport and deposition. The relationships of Log[(CaO + Na2O)/K2O] versus Log(SiO2/Al2O3), Na2O/Al2O3 versus K2O/Al2O3, LaN/YbN versus Eu/Eu*, Sc-Th-La and Zr-Sc-Th plots of major and trace elements reveal that the loess sources for the Miaodao Islands are similar to those of the Loess Plateau, which were derived from alluvial fan deposits flanking the Qilian Shan in China, the Gobi Altay and Hangayn Mountains in Mongolia. However, the loess of the Miaodao Islands is coarser in average grain size and contains abundant marine fossils, with gravel layers, indicating it is allochthous and near-source, which suggests it mainly originated from the adjacent exposed sea floor sediments of the Bohai Sea during glacial periods. Finally, we conclude that the loess of the Miaodao Islands is the result of a gradual accumulation process, in which the relative amount of distant-source material decreased and the near-source material increased in response to changes in sea level and paleoclimate. Our findings support that the loess of the Miaodao Islands was formed by mixing material from distant and proximal sources.