This study presents a spatially aware machine learning model for probabilistic groundwater potential assessment using multimodal geospatial data derived from topography, hydrotopography, climate, soil, land use, Sentinel-1 SAR, and water balance variables. The model incorporates spatially consistent data partitioning, leakage-controlled model development, and probabilistic forecasting to improve the robustness and transferability of groundwater potential assessment. A total of 2402 spatial observations, including 601 groundwater-related locations and 1801 spatially filtered pseudo-absence samples, were used to evaluate eleven machine learning and deep learning models. The proposed hybrid framework achieved the best overall validation results with ROC-AUC of 0.9319, PR-AUC of 0.8363, F1-measure of 0.8226, balanced accuracy of 0.8847, and MCC of 0.7613. Independent spatial block testing further demonstrated strong generalization ability, showing ROC-AUC of 0.9535, PR-AUC of 0.9002, F1-measure of 0.7983, balanced accuracy of 0.8594, and MCC of 0.7336. Comparative experiments demonstrated that the proposed framework remains competitive with state-of-the-art machine learning and deep learning approaches while providing robust probabilistic estimates in spatially separated validation. The resulting groundwater potential maps identify areas with environmental conditions similar to known groundwater observations and provide a reliable basis for prioritizing hydrogeological studies, groundwater exploration, and regional water resources planning in data-poor settings.
The present paper addresses the problem of modeling the resilient operation of a cryptocurrency exchange (CEX) under delayed quantum attacks of the harvest-now-decrypt-later type. The proposed model diverges from extant approaches in its conceptualization of the quantum threat. Whereas extant approaches treat the quantum threat as an external shock, the proposed model conceptualizes the accumulation of cryptographically vulnerable data as an internal state variable of the system. The framework under consideration is formulated as a system of nonlinear differential equations linking the exchange’s liquidity, the intensity of post-quantum cryptography (PQC) adoption, and the volume of accumulated threat. The analytical conditions for asymptotic stability are derived. The resolution of the system enables the identification of a region of admissible defense strategies, which is interpreted in the paper as a “survival dome.” Numerical simulations demonstrate that both delayed and excessively aggressive migration strategies toward post-quantum cryptography may lead to the degradation of the exchange. The findings indicate that a balanced and adaptive transition strategy, aimed at mitigating quantum risks, can preserve liquidity while minimizing long-term losses. The findings establish a theoretical framework for the development of migration strategies for financial platforms undergoing a transition to post-quantum security standards.
This paper addresses the problem of multi-class classification of bacterial microscopic images using a rigorous experimental protocol designed to prevent information leakage and improve performance. The dataset consists of 2034 images representing 33 taxa, organized by class. Data integrity checks confirmed the absence of corrupted or unreadable files. To formalize image characteristics and ensure quality control, indirect geometric and textural features were calculated, including minimum frame size, brightness statistics (mean and standard deviation), Shannon entropy, Laplace variance, and Sobel gradient energy. Quality checks revealed a small proportion of images with extreme brightness (2.5074%), while no samples with critically low sharpness according to the selected criteria were detected. Statistical analysis of interclass differences using the Kruskal–Wallis test with multiple comparison correction demonstrated the high discriminatory power of texture features, specifically gradient energy (ε2 = 0.819987) and Laplace variance (ε2 = 0.709904). Feature correlations were consistent with their physical interpretation, revealing a strong positive relationship between sharpness and gradient energy. Principal component analysis confirmed a strong structural pattern, with the first two components explaining 75.5766% of the total variance. For a unified comparison, classical machine learning, transfer learning, and modern deep architectures were evaluated within a single protocol.