Modelación Univariante Prophet para el Pronóstico de Precipitaciones en Estaciones Meteorológicas de Tungurahua-Ecuador

Anthony Zabala; Luis  Contreras-Vásquez; Ruth Lorena  Pérez Maldonado; Mayra  Viscaíno-Cuzco

doi:10.59169/pentaciencias.v8i2.1803

Authors

Anthony Zabala Universidad Técnica de Ambato https://orcid.org/0009-0004-6614-4186
Luis Contreras-Vásquez Universidad Técnica de Ambato https://orcid.org/0000-0002-8896-8264
Ruth Lorena Pérez Maldonado Universidad Técnica de Ambato https://orcid.org/0009-0003-2317-3529
Mayra Viscaíno-Cuzco Universidad Técnica de Ambato https://orcid.org/0000-0003-4987-7797

DOI:

https://doi.org/10.59169/pentaciencias.v8i2.1803

Keywords:

Prophet; precipitation; forecast; Andean zone

Abstract

Precipitation forecasting constitutes an essential tool for the sustainable management of water resources. This study applies the univariate Prophet model to estimate daily precipitation across 19 meteorological stations in Tungurahua Province, Ecuador, with the aim of generating reliable information to support decision-making in the infrastructure, agriculture, and environmental management sectors. Daily precipitation time series were used for model training and validation, covering data recorded between 2013 and 2024. The model was evaluated under three data partitioning schemes: 80–20%, 85–15%, and 90–10% for training and testing, respectively. In addition, both the default Prophet parameters and hyperparameter configurations obtained through grid search were considered. Model performance was assessed using the MAE and RMSE metrics, with values ranging from 1.0398 to 3.8012 mm and from 1.8956 to 6.3168 mm, respectively, indicating an adequate predictive capability relative to the average daily precipitation.Based on the results obtained, it was determined that the Prophet model improves its accuracy as the proportion of training data increases, achieving its best performance with the 85–15% and 90–10% training–validation splits when using hyperparameter configurations identified through grid search.

Downloads

Download data is not yet available.

References

Salih, S. Q., Sharafati, A., Khosravi, K., Fiza, M., Yaseen, Z. M., Inyurt, S., Bateni, S. M., Shahid, S., & Yaseen, Z. M. (2020). Integrative stochastic model standardization with genetic algorithm for rainfall pattern forecasting in tropical and semi-arid environments. Hydrological Sciences Journal, 65(7), 1145–1157. https://doi.org/10.1080/02626667.2020.1734813

Xu, L., Chen, N., Zhang, X., & Chen, Z. (2020). A data-driven multi-model ensemble for deterministic and probabilistic precipitation forecasting at seasonal scale. Climate Dynamics, 54(7–8), 3355–3374. https://doi.org/10.1007/s00382-020-05173-x

Li, Y., Niu, Z., Liu, C., & Yan, C. (2022). Credible Bayesian reliability model for structures with interval uncertain parameters. Structures, 45, 2151–2161. https://doi.org/10.1016/j.istruc.2022.09.058

Saha, A., Singh, K. N., Ray, M., & Rathod, S. (2020). A hybrid spatio-temporal modelling: An application to space-time rainfall forecasting. Theoretical and Applied Climatology, 142(3–4), 1271–1282. https://doi.org/10.1007/s00704-020-03374-2

Buhl, M., & Markolf, S. (2023). A review of emerging strategies for incorporating climate change considerations into infrastructure planning, design, and decision making. Sustainable and Resilient Infrastructure, 8(Suppl. 1), 157–169. https://doi.org/10.1080/23789689.2022.2134646

Chen, L., et al. (2025). Global increase in the occurrence and impact of multiyear droughts. Science, 387(6731), 278–284. https://doi.org/10.1126/science.ado4245

Yaseen, Z. M., Ali, M., Sharafati, A., Al-Ansari, N., & Shahid, S. (2021). Forecasting standardized precipitation index using data intelligence models: Regional investigation of Bangladesh. Scientific Reports, 11(1), Article 3435. https://doi.org/10.1038/s41598-021-82977-9

Ashok, S. P., & Pekkat, S. (2022). A systematic quantitative review on the performance of some of the recent short-term rainfall forecasting techniques. Journal of Water and Climate Change, 13(8), 3004–3029. https://doi.org/10.2166/wcc.2022.302

CRED. (2025a). Disaster year in review 2024. Centre for Research on the Epidemiology of Disasters. https://files.emdat.be/2025/05/CredCrunch78.pdf

CRED. (2025b). Hydrological disasters in South America. Centre for Research on the Epidemiology of Disasters. https://files.emdat.be/reports/2024_EMDAT_report.pdf

Abdaki, M., Al-Ozeer, A. Z. A., Alobaydy, O., & Al-Tayawi, A. N. (2023). Predicting rainfall in Nineveh Governorate in northern Iraq using machine learning time-series forecasting algorithm. Arabian Journal of Geosciences, 16(12), Article 655. https://doi.org/10.1007/s12517-023-11779-2

Saenz-Lituma, G. (2025). The agroecological transition of farms in the Ecuadorian Andes through the lens of the main agroecological structure. Land Degradation & Development, 36(2), 424–440. https://doi.org/10.1002/ldr.5368

Operador Nacional de Electricidad CENACE. (2025). Informe Anual CENACE 2024. CENACE.

Rodríguez-Gallegos, C. D., Gandhi, O., Rodríguez-Gallegos, C. A., & Alvarez-Alvarado, M. S. (2025). Co-location potential of floating PV with hydropower plants: Case study in Ecuador. Solar, 5(1), Article 3. https://doi.org/10.3390/solar5010003

Ebtehaj, I., Bonakdari, H., Zeynoddin, M., Gharabaghi, B., & Azari, A. (2020). Evaluation of preprocessing techniques for improving the accuracy of stochastic rainfall forecast models. International Journal of Environmental Science and Technology, 17(1), 505–524. https://doi.org/10.1007/s13762-019-02361-z

Khaniani, A. S., Motieyan, H., & Mohammadi, A. (2021). Rainfall forecast based on GPS PWV together with meteorological parameters using neural network models. Journal of Atmospheric and Solar-Terrestrial Physics, 214, Article 105533. https://doi.org/10.1016/j.jastp.2020.105533

Sheikh, M. R., & Coulibaly, P. (2024). Review of recent developments in hydrologic forecast merging techniques. Water, 16(2), Article 301. https://doi.org/10.3390/w16020301

Katumo, E., Katila, C., Omolo, R., & Ken, H. (2025). A drought forecasting model using the Prophet time series analysis technique. Indian Journal of Computer Science and Technology, 290–294. https://doi.org/10.59256/indjcst.20250402038

Rogers, J. K. B., Mercado, T. C. R., & Galleto, F. A., Jr. (2024). Comparison of ARIMA boost, Prophet boost, and TSLM models in forecasting Davao City weather data. Indonesian Journal of Electrical Engineering and Computer Science, 34(2), 1092–1101. https://doi.org/10.11591/ijeecs.v34.i2.pp1092-1101

Pérez-Alarcón, A., Garcia-Cortes, D., Fernández-Alvarez, J. C., & Martínez-González, Y. (2022). Improving monthly rainfall forecast in a watershed by combining neural networks and autoregressive models. Environmental Processes, 9(3), Article 53. https://doi.org/10.1007/s40710-022-00602-x

Duan, X., Ma, R., & Zhang, X. (2022). Forecasting occurrence and quantity of monthly precipitation simultaneously while accounting for complex serial correlation. International Journal of Climatology, 42(16), 9494–9509. https://doi.org/10.1002/joc.7839

Lana, X., Rodríguez-Solà, R., Martínez, M. D., Casas-Castillo, M. C., Serra, C., & Kirchner, R. (2021). Autoregressive process of monthly rainfall amounts in Catalonia (NE Spain) and improvements on predictability of length and intensity of drought episodes. International Journal of Climatology, 41(S1). https://doi.org/10.1002/joc.6915

Dahiya, P., et al. (2024). Time series study of climate variables utilising a seasonal ARIMA technique for the Indian states of Punjab and Haryana. Discover Applied Sciences, 6(12), Article 650. https://doi.org/10.1007/s42452-024-06380-5

Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37–45. https://doi.org/10.1080/00031305.2017.1380080

Hossain, M. M., Anwar, A. H. M. F., Garg, N., Prakash, M., & Bari, M. (2022). Monthly rainfall prediction at catchment level with the Facebook Prophet model using observed and CMIP5 decadal data. Hydrology, 9(6), Article 111. https://doi.org/10.3390/hydrology9060111

Bosson-Amedenu, S., Baah, E. M., Ayiah-Mensah, F., & Addor, J. A. (2025). Advanced time series modelling to address seasonal variability and extreme rainfall in Ghana. BMC Environmental Science, 2(1), Article 8. https://doi.org/10.1186/s44329-025-00024-8

Hossain, M. A., Rahman, M. M., Hasan, S. S., Mahmud, A., & Bai, L. (2025). Analysis and forecasting of meteorological drought using PROPHET and SARIMA models deploying machine learning technique for southwestern region of Bangladesh. Environmental and Sustainability Indicators, 27, Article 100761. https://doi.org/10.1016/j.indic.2025.100761

Ning, Y., Kazemi, H., & Tahmasebi, P. (2022). A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Computers & Geosciences, 164, Article 105126. https://doi.org/10.1016/j.cageo.2022.105126

Abdaki, M., Al-Ozeer, A. Z. A., Alobaydy, O., & Al-Tayawi, A. N. (2023). Predicting rainfall in Nineveh Governorate in northern Iraq using machine learning time-series forecasting algorithm. Arabian Journal of Geosciences, 16(12), Article 655. https://doi.org/10.1007/s12517-023-11779-2

Rogers, J. K. B., Mercado, T. C. R., & Galleto, F. A., Jr. (2024). Comparison of ARIMA boost, Prophet boost, and TSLM models in forecasting Davao City weather data. Indonesian Journal of Electrical Engineering and Computer Science, 34(2), 1092–1101. https://doi.org/10.11591/ijeecs.v34.i2.pp1092-1101

Li, D., et al. (2023). Prediction of rainfall time series using the hybrid DWT-SVR-Prophet model. Water, 15(10), Article 1935. https://doi.org/10.3390/w15101935

Ridwan, W. M., Sapitang, M., Aziz, A., Kushiar, K. F., Ahmed, A. N., & El-Shafie, A. (2021). Rainfall forecasting model using machine learning methods: Case study Terengganu, Malaysia. Ain Shams Engineering Journal, 12(2), 1651–1663. https://doi.org/10.1016/j.asej.2020.09.011

Unnikrishnan, P., & Jothiprakash, V. (2020). Hybrid SSA-ARIMA-ANN model for forecasting daily rainfall. Water Resources Management, 34(11), 3609–3623. https://doi.org/10.1007/s11269-020-02638-w

Suárez-Aguilar, Z. E., Sepúlveda-Delgado, O., Patarroyo-Mesa, M., & Canaria-Camargo, L. C. (2020). Mathematical model to estimate curves of intensity, duration and frequency of extreme rains in Tunja, Colombia. Informacion Tecnologica, 31(1), 193–206. https://doi.org/10.4067/S0718-07642020000100193

Kwarteng, S., & Andreevich, P. (2024). Comparative analysis of ARIMA, SARIMA and Prophet model in forecasting. Research & Development, 5(4), 110–120. https://doi.org/10.11648/j.rd.20240504.13

NASA POWER Project. (2025). NASA prediction of worldwide energy resources (POWER) project. NASA. https://power.larc.nasa.gov/data-access-viewer/

Pulzara Mora, C. A., & Losada Losada, J. D. (2023). Análisis de series temporales en estaciones meteorológicas para la predicción de la precipitación en la ciudad de Manizales, Colombia. Revista de Climatología, 23, 58–70. https://doi.org/10.59427/rcli/2023/v23.58-70

Chipindu, L., Mupangwa, W., Nyagumbo, I., & Zaman-Allah, M. (2023). Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes. Geoscience Data Journal. https://doi.org/10.1002/gdj3.228

Basak, A., Rahman, A. T. M. S., Das, J., Hosono, T., & Kisi, O. (2022). Drought forecasting using the Prophet model in a semi-arid climate region of western India. Hydrological Sciences Journal, 67(9), 1397–1417. https://doi.org/10.1080/02626667.2022.2082876

Ning, Y., Kazemi, H., & Tahmasebi, P. (2022). A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Computers & Geosciences, 164, Article 105126. https://doi.org/10.1016/j.cageo.2022.105126

Taylor, S. J., & Letham, B. (2017). Forecasting at scale (PeerJ Preprints 3190v2). PeerJ. https://doi.org/10.7287/peerj.preprints.3190v2

Sulasikin, A., Nugraha, Y., Kanggrawan, J. I., & Suherman, A. L. (2021). Monthly rainfall prediction using the Facebook Prophet model for flood mitigation in Central Jakarta. In Proceedings of the 8th International Conference on ICT for Smart Society (ICISS 2021). IEEE. https://doi.org/10.1109/ICISS53185.2021.9532507

Armando, J., et al. (n.d.). Estimation of average monthly rainfall with multiple linear regression and artificial neural networks in a semi-arid basin. [Unpublished manuscript].

Hossain, M. M., Anwar, A. H. M. F., Garg, N., Prakash, M., & Bari, M. (2022). Monthly rainfall prediction at catchment level with the Facebook Prophet model using observed and CMIP5 decadal data. Hydrology, 9(6), Article 111. https://doi.org/10.3390/hydrology906011