eprintid: 28590 rev_number: 8 eprint_status: archive userid: 2 dir: disk0/00/02/85/90 datestamp: 2026-07-06 23:30:11 lastmod: 2026-07-06 23:30:12 status_changed: 2026-07-06 23:30:11 type: article metadata_visibility: show creators_name: Shandilya, Gunjan creators_name: Gupta, Sheifali creators_name: Saudagar, Abdul Khader Jilani creators_name: Ikram, Sunnia creators_name: Rehman, Ateeq Ur creators_name: De la Torre Díez, Isabel creators_name: Mohamed, Heba G. creators_name: Pali-Casanova, Ramón creators_name: Kuc Castilla, Ángel Gabriel creators_name: Kaur, Upinder creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: ramon.pali@unini.edu.mx creators_id: angel.kuc@uneatlantico.es creators_id: title: Enhanced weather classification using xception with SENet and attention mechanisms ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: unincol_produccion_cientifica divisions: uninipr_produccion_cientifica divisions: unic_produccion_cientifica divisions: uniromana_produccion_cientifica full_text_status: public keywords: attention mechanisms, cloudy, deep learning (DL), image classification, rain, squeeze and excitation (SE), sunrise, sunshine abstract: Introduction: Weather classification plays a crucial role in applications such as environmental monitoring, disaster management, and smart city infrastructure. Accurate and efficient classification of weather conditions from images remains a challenging task due to variations in illumination, texture, and atmospheric conditions.Methods: This study proposes an efficient deep learning framework for multi-class weather classification by integrating the Xception architecture with Squeeze-and-Excitation (SE) blocks and a spatial attention mechanism. Transfer learning with pre-trained ImageNet weights was employed, and a comparative analysis was conducted using EfficientNet-B3, ResNet152V2, and Xception architectures. The proposed enhanced Xception model incorporates channel-wise recalibration and spatial feature refinement to improve representational capability. The model was trained and evaluated on the Multi-Class Weather Dataset (MWD), which consists of 1,125 images categorized into four classes: sunshine, cloudy, rain, and sunrise. To ensure robustness and generalization, 5-fold cross-validation, statistical significance testing, calibration analysis, and robustness evaluation under image perturbations were performed.Results: The proposed model achieved a classification accuracy of 99.06% on the test set. Additionally, it attained a macro precision of 98.3%, macro recall of 97.7%, and macro F1-score of 98.0%. The model demonstrated strong generalization capability and robustness under varying perturbation conditions, with only moderate computational overhead.Discussion: The integration of SE blocks and spatial attention significantly enhances feature representation by emphasizing informative channels and spatial regions. Compared to baseline architectures, the proposed framework shows superior performance in terms of accuracy and robustness. These results indicate that the model is well-suited for real-world weather classification applications, particularly in intelligent environmental monitoring systems. date: 2026-05 publication: Frontiers in Environmental Science volume: 14 id_number: doi:10.3389/fenvs.2026.1797545 refereed: TRUE issn: 2296-665X official_url: http://doi.org/10.3389/fenvs.2026.1797545 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Fundación Universitaria Internacional de Colombia > Investigación > Artículos y libros Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Universidad de La Romana > Investigación > Producción Científica Abierto Inglés Introduction: Weather classification plays a crucial role in applications such as environmental monitoring, disaster management, and smart city infrastructure. Accurate and efficient classification of weather conditions from images remains a challenging task due to variations in illumination, texture, and atmospheric conditions.Methods: This study proposes an efficient deep learning framework for multi-class weather classification by integrating the Xception architecture with Squeeze-and-Excitation (SE) blocks and a spatial attention mechanism. Transfer learning with pre-trained ImageNet weights was employed, and a comparative analysis was conducted using EfficientNet-B3, ResNet152V2, and Xception architectures. The proposed enhanced Xception model incorporates channel-wise recalibration and spatial feature refinement to improve representational capability. The model was trained and evaluated on the Multi-Class Weather Dataset (MWD), which consists of 1,125 images categorized into four classes: sunshine, cloudy, rain, and sunrise. To ensure robustness and generalization, 5-fold cross-validation, statistical significance testing, calibration analysis, and robustness evaluation under image perturbations were performed.Results: The proposed model achieved a classification accuracy of 99.06% on the test set. Additionally, it attained a macro precision of 98.3%, macro recall of 97.7%, and macro F1-score of 98.0%. The model demonstrated strong generalization capability and robustness under varying perturbation conditions, with only moderate computational overhead.Discussion: The integration of SE blocks and spatial attention significantly enhances feature representation by emphasizing informative channels and spatial regions. Compared to baseline architectures, the proposed framework shows superior performance in terms of accuracy and robustness. These results indicate that the model is well-suited for real-world weather classification applications, particularly in intelligent environmental monitoring systems. metadata Shandilya, Gunjan; Gupta, Sheifali; Saudagar, Abdul Khader Jilani; Ikram, Sunnia; Rehman, Ateeq Ur; De la Torre Díez, Isabel; Mohamed, Heba G.; Pali-Casanova, Ramón; Kuc Castilla, Ángel Gabriel y Kaur, Upinder mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, ramon.pali@unini.edu.mx, angel.kuc@uneatlantico.es, SIN ESPECIFICAR (2026) Enhanced weather classification using xception with SENet and attention mechanisms. Frontiers in Environmental Science, 14. ISSN 2296-665X document_url: http://repositorio.unincol.edu.co/id/eprint/28590/1/fenvs-14-1797545.pdf