Sistema de pronóstico meteorológico marítimo de alta resolución utilizando IA y datos de fuentes abiertas
| dc.audience | Todo Público | |
| dc.contributor.author | Ruiz Guzman, Laura Alejandra | |
| dc.contributor.author | Torres, Alberto | |
| dc.coverage.spatial | Cali de Lat: 03 24 00 N degrees minutes Lat: 3.4000 decimal degrees Long: 076 30 00 W degrees minutes Long: -76.5000 decimal degrees. | |
| dc.date.accessioned | 2026-03-06T15:31:48Z | |
| dc.date.available | 2026-03-06T15:31:48Z | |
| dc.date.issued | 2025-06-27 | |
| dc.description.abstract | Este trabajo aborda la necesidad crítica de la Armada de Colombia de contar con pronósticos meteorológicos marítimos precisos y oportunos. Presenta el desarrollo de un sistema de pronóstico de alta resolución para las aguas del Pacífico y el Atlántico colombianos, basado en técnicas de aprendizaje profundo. La metodología se centró en la recopilación y el procesamiento de datos históricos del reanálisis ERA5 para una región estratégicamente importante, con el fin de capturar fenómenos climáticos clave como el ENSO. Se desarrolló un modelo predictivo para pronosticar un "panel" de variables operativas, incluyendo la altura de las olas, el viento y la temperatura. El rendimiento del modelo se evalúa con métricas estándar como la pérdida, el MAE y el RMSE. Como resultado final, se propone un modelo integrado en un contenedor Docker y expuesto mediante una API RESTful para uso operativo, lo que proporciona a la Armada una herramienta robusta y específica para sus áreas de operación. | spa |
| dc.description.abstract | This work addresses the critical need of the Colombian Navy to have accurate and timely maritime weather forecasts. It presents the development of a high-resolution forecasting system for Colombian Pacific and Atlantic waters, based on Deep Learning techniques. The methodology focused on the collection and processing of historical data from the ERA5 reanalysis for a strategically important region, to capture key climate phenomena such as ENSO. A predictive model was developed to forecast a "dashboard" of operational variables, including wave height, wind, and temperature. The model's performance is evaluated against standard metrics such as Loss, MAE, and RMSE. As a final deliverable, a model integrated into a Docker container and exposed via a RESTful API for operational use is proposed, providing the Navy with a robust and specific tool for its areas of operation. | eng |
| dc.description.degreelevel | Magíster | |
| dc.description.degreename | Trabajo de grado para optar al título de Magister en Ciencia de Datos | |
| dc.description.tableofcontents | I. Introducción -- II. Materiales y Métodos -- Tabla 1 Modelos Referentes en la Industria -- Tabla 4 Variables Efecto -- V. Conclusiones -- Reconocimiento -- Referencias | spa |
| dc.format.extent | 15 páginas | |
| dc.format.medium | Digital | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.OLIB | https://biblioteca2.icesi.edu.co/cgi-olib/?oid=366457 | |
| dc.identifier.instname | instname:Universidad Icesi | |
| dc.identifier.reponame | reponame:Biblioteca Digital | |
| dc.identifier.repourl | repourl:https://repository.icesi.edu.co/ | |
| dc.identifier.uri | https://hdl.handle.net/10906/130583 | |
| dc.language.iso | spa | |
| dc.publisher | Universidad Icesi | |
| dc.publisher.faculty | Barberi de Ingeniería, Diseño y Ciencias Aplicadas | |
| dc.publisher.place | Santiago de Cali | |
| dc.publisher.program | Maestría en Ciencia de Datos | |
| dc.relation.references | NOAA Fisheries. (2024, January). Targeted Climate Research Can Benefit Marine Resource Management in the Northeast United States. [Online]. Available: https://www.fisheries.noaa.gov/feature-story/targeted-climate-research-can-benefit-marine-resource-management-northeast-united. | spa |
| dc.relation.references | A. Allen, et al., "End-to-end datadriven weather prediction," Nature, Mar. 2025. | spa |
| dc.relation.references | A. Denvil-Sommer. (2024, December). Advancing Mesoscale Process Representation in Ocean Models with Machine Learning. Weather and Climate @ Reading [Online]. Available: https://blogs.reading.ac.uk/weather-and-climate-at-reading/2024/advancing-mesoscale-process-representation-in-ocean-models-with-machine-learning/ | spa |
| dc.relation.references | Armada de la República de Colombia, Informe de Gestión 2024. 2024. [Online]. Available: https://www.armada.mil.co/sites/default/files/varios/Informe%20de%20Gestion%20ARC%202024.pdf | spa |
| dc.relation.references | G. Bonino, G. Galimberti, S. Masina, R. McAdam, and E. Clementi, "Machine learning methods to predict sea surface temperature and marine heatwave occurrence: a case study of the Mediterranean Sea," Ocean Sci., vol. 20, pp. 417 – 432, Mar. 2024. | spa |
| dc.relation.references | Z. Ouyang, Y. Gao, X. Zhang, X. Wu, and D. Zhang, "Significant Wave Height Forecasting Based on EMD-TimesNet Networks," J. Mar. Sci. Eng., vol. 12, p. 536, Mar. 2024. | spa |
| dc.relation.references | J. Zhang, et al., "Improving wave height prediction accuracy with deep learning," Ocean Modelling, vol. 188, p. 102312, Apr. 2024. | spa |
| dc.relation.references | J. P. Mishra, S. Sharda, S. Vyas, R. Parashar, and Y. Sharma, "Machine Learning-Based Approach for Predicting Ocean Surface Temperature," Research Square, [Preprint], Jul. 2024. Available: https://doi.org/10.21203/rs.3.rs-4501938/v1 | spa |
| dc.relation.references | F. C. Minuzzi and L. Farina, "A deep learning approach to predict significant wave height using long short-term memory," Ocean Modelling, p. 102151, Dec. 2022. | spa |
| dc.relation.references | C. Bodnar, et al., "A Foundation Model for the Earth System," arXiv preprint arXiv:2405.13063, 2024. | spa |
| dc.relation.references | R. Lam. (2023, November). GraphCast: AI model for faster and more accurate global weather forecasting. Google DeepMind [Online]. Available: https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/ | spa |
| dc.relation.references | K. Bi, L. Xie, H. Zhang, X. Chen, X. Gu, and Q. Tian, "Accurate medium-range global weather forecasting with 3D neural networks," Nature, vol. 619, pp. 533 – 538, Jul. 2023. | spa |
| dc.relation.references | J. Pathak, et al., "FourCastNet: A Global Data-Driven High-Resolution Weather Model Using Adaptive Fourier Neural Operators," arXiv preprint arXiv:2202.11214, Feb. 2022. | spa |
| dc.relation.references | I. Hoyos, G. Poveda, et al., "The hydroclimatology of Colombia: A synthesis of the authors' contributions," in The Geology of Colombia. Servicio Geológico Colombiano, 2011, pp. 531 - 561. | spa |
| dc.relation.references | G. Poveda and O. J. Mesa, "On the existence of the Chocó jet in the pacific coast of Colombia," Estudios Geográficos, vol. 61 , no. 238, pp. 177 - 188, 2000. | spa |
| dc.relation.references | T. A. Smith, et al., "Ocean-wave coupled modeling in COAMPS - TC: A study of Hurricane Ivan (2004)," Ocean Modelling, vol. 69, pp. 181 - 194, 2013. | spa |
| dc.relation.references | J. Marshall and R. A. Plumb, Atmosphere, Ocean, and Climate Dynamics: An Introductory Text. Burlington, MA: Elsevier Academic Press, 2008. | spa |
| dc.relation.references | A. R. J. M. Lloyd, Seakeeping: Ship Behaviour in Rough Weather. Chichester: Ellis Horwood, 1989. | spa |
| dc.relation.references | Department of the Navy, U.S. Marine Corps, and U.S. Coast Guard, The Commander’s Handbook on the Law of Naval Operations. Mar. 2022. [Online]. Available: https://usnwc.edu/Portals/2/documents/stockton/nwcs-review/2022_Commanders_Handbook_Naval_Operations.pdf | spa |
| dc.relation.references | Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., & Tian, Q. (2023). Accurate medium-range global weather forecasting with 3D neural networks. Nature, 619, 533 - 538. | spa |
| dc.rights | EL AUTOR, expresa que la obra objeto de la presente autorización es original y la elaboró sin quebrantar ni suplantar los derechos de autor de terceros, y de tal forma, la obra es de su exclusiva autoría y tiene la titularidad sobre éste. PARÁGRAFO: en caso de queja o acción por parte de un tercero referente a los derechos de autor sobre el artículo, folleto o libro en cuestión, EL AUTOR, asumirá la responsabilidad total, y saldrá en defensa de los derechos aquí autorizados; para todos los efectos, la Universidad Icesi actúa como un tercero de buena fe. Esta autorización, permite a la Universidad Icesi, de forma indefinida, para que en los términos establecidos en la Ley 23 de 1982, la Ley 44 de 1993, leyes y jurisprudencia vigente al respecto, haga publicación de este con fines educativos. | spa |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | |
| dc.rights.coar | http://purl.org/coar/access_right/c_abf2 | |
| dc.rights.license | Attribution-NonCommercial-NoDerivatives 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject.proposal | Aprendizaje Profundo | spa |
| dc.subject.proposal | ENSO | spa |
| dc.subject.proposal | Pronóstico Meteorológico | spa |
| dc.subject.proposal | Seguridad Marítima | spa |
| dc.subject.proposal | Series de Tiempo | spa |
| dc.subject.proposal | Deep Learning | eng |
| dc.subject.proposal | ENSO | eng |
| dc.subject.proposal | Weather Forecasting | eng |
| dc.subject.proposal | Maritime Security | eng |
| dc.subject.proposal | Time Series | eng |
| dc.subject.proposal | Tesis de Maestría en Ciencia de Datos | spa |
| dc.title | Sistema de pronóstico meteorológico marítimo de alta resolución utilizando IA y datos de fuentes abiertas | spa |
| dc.type | master thesis | |
| dc.type.coar | http://purl.org/coar/resource_type/c_ba08 | |
| dc.type.coarversion | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |
| dc.type.driver | info:eu-repo/semantics/masterThesis | |
| dc.type.local | Tesis de maestría | |
| dc.type.version | info:eu-repo/semantics/publishedVersion |
