Rocío Magdalena Sánchez-Albores

Dried droplet imaging has become an established approach for analyzing complex fluid systems as evaporation patterns preserve physicochemical and structural information. However, spatial variability of these patterns limits the effectiveness of conventional texture descriptors. This work presents a region-aware deep learning algorithm for the classification of dried droplets through spatial decomposition and convolutional learning. Dried droplet images were geometrically standardized prior to patch extraction. The Hough transform supported consistent crown–core localization and patch extraction across the dataset. Each image was divided into twenty localized regions. Twelve represented peripheral patches sampled at 30° intervals. The remaining eight patches were extracted from four central regions using two complementary angular orientations (30° and 90°) per region. This process allowed dataset augmentation and evaluation of regional contributions. Patches were processed using the VGG16 convolutional neural network, following repeated patch-level and droplet-level partitioning strategies designed to prevent data leakage. The proposed algorithm was evaluated on Methotrexate (MTX) droplets prepared with 40%, 60%, and 80% water dilution levels relative to a reference solution. Results show that the proposed strategy increases classification accuracy, outperforming traditional descriptors. These findings demonstrate that spatial decomposition combined with convolutional learning constitutes an effective approach for heterogeneous evaporative pattern classification.

Water contamination by synthetic dyes such as malachite green (MG) remains a significant environmental and public health challenge due to their high toxicity, chemical stability, and resistance to biodegradation. In this study, a CaO-CuFe₂O₄ composite was synthesized through a sustainable route using eggshells and orange peel as agro-industrial waste precursors. Comprehensive structural, spectroscopic and microscopic analyses confirmed the coexistence of a predominant CaO-based phase with spinel CuFe₂O₄, together with nanometric features, satisfactory elemental dispersion and practical magnetic recoverability. Under the experimental conditions employed, the composite exhibited high adsorption performance towards MG, reaching an equilibrium capacity of 2288.4 mg g⁻¹ and 99.98% decolorization within 60 min. The kinetics were better described by the pseudo-second-order model, while the equilibrium behavior was more satisfactorily fitted by the Langmuir isotherm than by the Freundlich model. Thermodynamic analysis indicated that the adsorption process was favorable over the temperature range studied and became more pronounced at higher temperature. The results suggest that the adsorption behavior arises from the combined influence of surface chemistry, calcium-derived basic sites, ferrite-associated metal centers and interfacial accessibility, rather than from surface area alone. In addition, the material could be readily separated from aqueous solution using an external magnetic field, highlighting its practical post-treatment recoverability. Overall, this work demonstrates a viable waste valorization strategy for the development of a magnetically recoverable CaO-CuFe₂O₄ adsorbent for cationic dye removal. Beyond the specific case of MG, the study underscores the potential of agro-waste-derived hybrid oxides as application-relevant materials for water remediation.