Predicción del fenómeno de la precipitación ambiental en el municipio de Aquitania

Viviana Bernal-Benítez; Juan Gómez-Malagón; Camilo Pardo-Beainy

doi:10.24054/rcta.v2i42.2649

Authors

Viviana Bernal-Benítez Universidad Santo Tomás https://orcid.org/0000-0002-8746-8583
Juan Gómez-Malagón Universidad Santo Tomás https://orcid.org/0000-0002-0040-9434
Camilo Pardo-Beainy Universidad Santo Tomás https://orcid.org/0000-0003-0012-3679

DOI:

https://doi.org/10.24054/rcta.v2i42.2649

Keywords:

Gradient Boost, Environmental Precipitation, Python, IBM Watson, Meteorology, Machine Learning

Abstract

The science of meteorology generates important predictions about the phenomena, which occur in the atmosphere every day and have a great importance in human activities such as agriculture, the sustainability of ecosystems and climate analysis. This project seeks to create a predictive system for atmospheric precipitation, which works with Machine Learning techniques using data collected from climate monitoring over Aquitania, a town in Boyacá department. To generate this classifier algorithm, the resources of IBM Watson and the tool to create the code in Python: Jupyter Notebook. The algorithm is trained using a dataset, which contains 35 years of meteorological information taken from the settlement Hoya La Manzana. The process developed begins with the refinement and cleaning of the dataset, then, the creation of the training model with 80% of the dataset to proceed with the algorithm test using the remaining 20% and finishes with the analysis of the results obtained in the predictive system implementation relying on evaluation metrics such as precision, accuracy, sensitivity of the system, which allow identifying the variations in performance of each model. An accuracy of almost 96% was achieved with the algorithm based on Decision Trees, this being a possible starting point for the construction of a high-efficiency tool that allows farmers to increase the productivity of the land, anticipating possible climatic changes, which may affect their health and the development of their crops

Downloads

Download data is not yet available.

References

Bosy, J., Rohm, W., Borkowski, A., Kroszczynski, K., & Figurski, M. (2010). Integration and verification of meteorological observations and NWP model data for the local GNSS tomography. Atmospheric Research, 96(4), 522–530. https://doi.org/10.1016/j.atmosres.2009.12.012

Chen, G., Li, S., Knibbs, L. D., Hamm, N. A. S., Cao, W., Li, T., Guo, J., Ren, H., Abramson, M. J., & Guo, Y. (2018). A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information. Science of the Total Environment, 636, 52–60. https://doi.org/10.1016/j.scitotenv.2018.04.251

Colston, J. M., Ahmed, T., Mahopo, C., Kang, G., Kosek, M., Junior, F. de S., Shrestha, P. S., Svensen, E., Turab, A., Zaitchik, B., & Network, T. M.-E. (2018). Evaluating meteorological data from weather stations, and from satellites and global models for a multi-site epidemiological study. Environmental Research, 165, 91–109.

Gonçalves, A. M., Silva, J. G., & Gomes, P. M. V. (2006). Meteorological support to forest fire prevention. In Forest Ecology and Management (Vol. 234, p. S41). https://doi.org/10.1016/j.foreco.2006.08.062

Han, H., Lee, S., Im, J., Kim, M., Lee, M. I., Ahn, M. H., & Chung, S. R. (2015). Detection of convective initiation using Meteorological Imager onboard Communication, Ocean, and Meteorological Satellite based on machine learning approaches. Remote Sensing, 7(7), 9184–9204. https://doi.org/10.3390/rs70709184

IBM’s AutoAI at work: two real-world applications | by Álvaro Corrales Cano | IBM Garage | Medium. (n.d.).

Kok, M., Smith, J. G., Wohl, C. J., Siochi, E. J., & Young, T. M. (2015). Critical considerations in the mitigation of insect residue contamination on aircraft surfaces - A review. In Progress in Aerospace Sciences (Vol. 75, pp. 1–14). https://doi.org/10.1016/j.paerosci.2015.02.001

Lu, H., Wu, Y., Li, Y., & Liu, Y. (2017). Effects of meteorological droughts on agricultural water resources in southern China. In Journal of Hydrology (Vol. 548, pp. 419–435). https://doi.org/10.1016/j.jhydrol.2017.03.021

Ma, P., Wang, S., Zhou, J., Li, T., Fan, X., Fan, J., & Wang, S. (2020). Meteorological rhythms of respiratory and circulatory diseases revealed by Harmonic Analysis. In Heliyon (Vol. 6, Issue 5). https://doi.org/10.1016/j.heliyon.2020.e04034

Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. Frontiers in Neurorobotics, 7(DEC). https://doi.org/10.3389/fnbot.2013.00021

Riabani Mercado, F., García Fernández, W., & Herrera Acebey, J. A. (2016). Sistema de inteligencia artificial para la predicción temprana de heladas meteorológicas. Acta Nova, 7(4), 483–495.

Rozenstein, O., & Karnieli, A. (2011). Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. In Applied Geography (Vol. 31, Issue 2, pp. 533–544). https://doi.org/10.1016/j.apgeog.2010.11.006

Sotelo, S., Guevara, E., Llanos-Herrera, L., Agudelo, D., Esquivel, A., Rodriguez, J., Ordoñez, L., Mesa, J., Muñoz Borja, L. A., Howland, F., Amariles, S., Rojas, A., Valencia, J. J., Segura, C. C., Grajales, F., Hernández, F., Cote, F., Saavedra, E., Ruiz, F., … Ramirez-Villegas, J. (2020). Pronosticos AClimateColombia: A system for the provision of information for climate risk reduction in Colombia. Computers and Electronics in Agriculture, 174. https://doi.org/10.1016/j.compag.2020.105486

Wardah, T., Abu Bakar, S. H., Bardossy, A., & Maznorizan, M. (2008). Use of geostationary meteorological satellite images in convective rain estimation for flash-flood forecasting. Journal of Hydrology, 356(3–4), 283–298. https://doi.org/10.1016/j.jhydrol.2008.04.015