This study is based on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and aims to explore early detection and disease progression in Alzheimer's disease (AD). We employ innovative data preprocessing strategies, including the use of the random forest algorithm to fill missing data and the handling of outliers and invalid data, thereby fully mining and utilizing these limited data resources. Through Spearman correlation coefficient analysis, we identify some features strongly correlated with AD diagnosis. We build and test three machine learning models using these features: random forest, XGBoost, and support vector machine (SVM). Among them, the XGBoost model performs the best in terms of diagnostic performance, achieving an accuracy of 91%. Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.

This study is based on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and aims to explore early detection and disease progression in Alzheimer's disease (AD). We employ innovative data preprocessing strategies, including the use of the random forest algorithm to fill missing data and the handling of outliers and invalid data, thereby fully mining and utilizing these limited data resources. Through Spearman correlation coefficient analysis, we identify some features strongly correlated with AD diagnosis. We build and test three machine learning models using these features: random forest, XGBoost, and support vector machine (SVM). Among them, the XGBoost model performs the best in terms of diagnostic performance, achieving an accuracy of 91%. Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.

Surfactants play a crucial role in enhanced oil recovery by reducing interfacial tension (IFT) and promoting emulsification. However, for low-permeability reservoirs after water flooding, it remains unclear which ability is more crucial for improving recovery. To address this question, this study compared the oil displacement effects of three surfactants with different IFTs and emulsifying properties using a series of core displacement experiments. The results show that the strongly emulsifying surfactant S1# achieved an incremental oil displacement efficiency of 9.94%, which is higher than that of the ultra-low-IFT surfactant S3# (8.63%), while the composite surfactant S2# (strong emulsification + ultra-low-IFT) achieved the highest incremental oil displacement efficiency of 11.79%, representing an improvement of 3.16% compared with S3#. The three surfactants have the same effect on improving oil recovery and oil displacement efficiency in heterogeneous rock cores. Strong emulsification promotes abundant in situ emulsions, increases injection pressure (up to 0.85 MPa compared with 0.41 MPa for ultra-low-IFT flooding), and expands the swept volume, indicating that emulsification-driven sweep improvement dominates over capillary-force reduction under the investigated conditions. Furthermore, a composite displacement strategy combining emulsification-driven plugging and ultra-low-IFT oil washing achieved a 12.37% recovery improvement while maintaining relatively low injection pressure (~0.48 MPa). However, the effectiveness of this mechanism is strongly dependent on reservoir heterogeneity. When the permeability contrast increased from 5.4 to 17.3, incremental recovery decreased by up to 7.03%, demonstrating that strong heterogeneity significantly limits the effectiveness of emulsification-driven sweep expansion. This work advances the understanding of surfactant flooding mechanisms and provides guidance for designing and deploying surfactants in water-flooded low-permeability reservoirs.

The accumulation of residual hydrolyzed polyacrylamide (HPAM) gel or molecular-based solutions in reservoirs after polymer flooding poses dual challenges: irreversible formation damage and long-term environmental risk issues. However, existing research mainly focuses on treating polymers in surface-produced water, neglecting both in situ decomposition of residual polymer gel or molecular-based solutions in reservoirs and the degradation of HPAM gels under high temperatures from in situ combustion (ISC). This work investigates the thermochemical behavior of HPAM gel during ISC and its dual-function role in enhanced oil recovery (EOR) and reservoir remediation. It was demonstrated that the residual gel and/or molecular-based solutions undergo efficient degradation, serving as an in situ fuel that significantly reduces the activation energy for crude oil oxidation by up to 58.4% in the low-temperature stage and 75.2% in the high-temperature stage. Factors influencing the gel’s degradation and the combustion process, including its molecular weight, ionic type, and crude oil viscosity, were systematically evaluated. Optimal conditions achieved over 90% gel degradation. Combustion tube experiments validated the dual benefits of this approach: an incremental oil recovery of 68.6% and an average HPAM gel removal efficiency of 64.8%. This work presents a novel strategy for utilizing retained gels in situ to simultaneously enhance oil recovery and mitigate gel-induced formation damage, offering significant insights for the management of mature gel-treated reservoirs.

Knowledge of the migration characteristics of polymer systems in pore throats is essential for the effective application of polymers as a profile-control oil-displacement agent for enhanced oil recovery. In this study, the effect of concentration on the viscosity and hydrodynamic radius of polymer systems was investigated using a rheometer and a dynamic light scattering instrument. Furthermore, pore-throat models, homogeneous cores, and multi-measuring-point sand-packed models were constructed to investigate pore-scale migration patterns and the effect of the throat–polymer ratio (defined as the ratio of throat size to polymer hydrodynamic radius) on the migration properties of polymers in porous media. The results showed that the transport of polymer systems in porous media is primarily related to the throat–polymer ratio. When this ratio is sufficiently small (i.e., no more than 18.94), the migration pattern of the polymer systems in the pore-throat model does not exhibit the characteristics of polymer solution flow, but rather, of discontinuous-dispersion retention, plugging-breakthrough migration, and stable-plugging retention. Upon increasing the injection rate, the polymer systems also exhibit the migration characteristics of discontinuous dispersion at a larger throat–polymer ratio. Moreover, polymer system migration resistance and improved sweep efficiency in porous media are influenced by not only the viscosity of polymer systems, but also the throat–polymer ratio. The smaller the throat–polymer ratio, the stronger the retention and plugging ability of the polymer systems. The outcomes of this study are significant for the design of polymer flooding operations in oilfields.