Optimizing Time Series Models for Forecasting Environmental Variables: A Rainfall Case Study
Abstract
1. Introduction
2. Literature Review
3. Materials and Methods
3.1. Simple Moving Average (SMA)
3.2. Weighted Moving Average (WMA)
3.3. Exponential Smoothing (ES)
3.4. Holt–Winters Multiplicative and Additive Methods
- (Level): Smoothed value at period t or average of the series at time t.
- (Trend): Estimated trend at period t.
- (Seasonality): Estimated seasonality at period t.
3.5. Forecasting Accuracy Metrics and Optimization Approach
3.6. Data Description and Modeling Pipeline
4. Results
5. Discussion
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
IDEAM | Institute of Hydrology, Meteorology and Environmental Studies |
SMA | Simple Moving Average |
WMA | Weighted Moving Average |
ES | Exponential Smoothing |
MSE | Mean Squared Error |
MAE | Mean Absolute Error |
Smoothed value at period t or average of the series at time t | |
Estimated trend at period t | |
Estimated seasonality at period t | |
α | Smoothing constant for the level component |
β | Smoothing constant for the trend component |
γ | Smoothing constant for the seasonal component |
L | Number of periods in a seasonal cycle |
p | Number of periods to forecast into the future |
θ | Smoothing parameter |
Weighting coefficients | |
Forecasted value for period t + 1 | |
Actual observed value of the variable in period t | |
k + 1 | Number of periods considered in the series |
References
- Adame Romero, A. Contaminación Ambiental Y Calentamiento Global; Editorial Trillas: Mexico City, México, 2010. [Google Scholar]
- Cuéllar, J.L.N.; Rivadeneira, B.A.C.; Solarte, D.M.M.; Gómez, C.C.C.; Rosero, R.E.Á. Caracterización del impacto fisicoquímico y microbiológico causado por vertimientos en el Río Suaza en el suroeste de Colombia. Investig. E Innov. Ing. 2025, 13, 147–180. [Google Scholar] [CrossRef]
- Cardinale, B.J.; Duffy, J.E.; Gonzalez, A.; Hooper, D.U.; Perrings, C.; Venail, P.; Narwani, A.; Mace, G.M.; Tilman, D.; Wardle, D.A.; et al. Biodiversity Loss and Its Impact on Humanity. Nature 2012, 486, 59–67. [Google Scholar] [CrossRef]
- Polley, H.W.; Briske, D.D.; Morgan, J.A.; Wolter, K.; Bailey, D.W.; Brown, J.R. Climate change and North American rangelands: Trends, projections, and implications. Rangel. Ecol. Manag. 2013, 66, 493–511. [Google Scholar] [CrossRef]
- Juvinao, D.D.L.; Guerrero, J.M.A.; Moreno, J.A.B. Planificación ambiental como estrategia de sostenibilidad en una empresa minera de yeso. Investig. E Innov. Ing. 2024, 12, 118–136. [Google Scholar] [CrossRef]
- Abbass, K.; Qasim, M.Z.; Song, H.; Murshed, M.; Mahmood, H.; Younis, I. A Review of the Global Climate Change Impacts, Adaptation, and Sustainable Mitigation Measures. Environ. Sci. Pollut. Res. 2022, 29, 42539–42559. [Google Scholar] [CrossRef]
- VijayaVenkataRaman, S.; Iniyan, S.; Goic, R. A Review of Climate Change, Mitigation and Adaptation. Renew. Sustain. Energy Rev. 2012, 16, 878–897. [Google Scholar] [CrossRef]
- Mawdsley, J.R.; O’Malley, R.; Ojima, D.S. A Review of Climate-Change Adaptation Strategies for Wildlife Management and Biodiversity Conservation. Conserv. Biol. 2009, 23, 1080–1089. [Google Scholar] [CrossRef] [PubMed]
- Dore, M.H. Climate change and changes in global precipitation patterns: What do we know? Environ. Int. 2005, 31, 1167–1181. [Google Scholar] [CrossRef] [PubMed]
- Vrac, M.; Loukos, H.; Noël, T.; Defrance, D. Should We Use Quantile-Mapping-Based Methods in a Climate Change Context? A “Perfect Model” Experiment. Climate 2025, 13, 137. [Google Scholar] [CrossRef]
- Asadieh, B.; Krakauer, N.Y. Global Trends in Extreme Precipitation: Climate Models versus Observations. Hydrol. Earth Syst. Sci. 2015, 19, 877–891. [Google Scholar] [CrossRef]
- Oyarzun, D.A.; Andrés, G.D. el papel de las variables ambientales en la nueva geografía económica. Investig. Reg. 2004, 4, 145–175. Available online: https://www.redalyc.org/pdf/289/28900408.pdf (accessed on 13 June 2025).
- de Sherbinin, A.; Carr, D.; Cassels, S.; Jiang, L. Population and Environment. Annu. Rev. Environ. Resour. 2007, 32, 345–373. [Google Scholar] [CrossRef] [PubMed]
- Yang, Y.; Sun, F.; Hu, C.; Gao, J.; Wang, W.; Chen, Q.; Ye, J. Emissions of Biogenic Volatile Organic Compounds from Plants: Impacts of Air Pollutants and Environmental Variables. Curr. Pollut. Rep. 2025, 11, 10. [Google Scholar] [CrossRef]
- Charalampopoulos, I.; Droulia, F. Climate Evolution of Agricultural and Natural Areas of Southeastern Europe According to Pinna, Johansson and Kerner Climate Indices. Climate 2025, 13, 121. [Google Scholar] [CrossRef]
- Ali, S.; Basit, A.; Umair, M.; Makanda, T.A.; Shaik, M.R.; Ibrahim, M.; Ni, J. The role of climate change and its sensitivity on long-term standardized precipitation evapotranspiration index, vegetation and drought changing trends over East Asia. Plants 2024, 13, 399. [Google Scholar] [CrossRef]
- Chokkavarapu, N.; Mandla, V.R. Comparative study of GCMs, RCMs, downscaling and hydrological models: A review toward future climate change impact estimation. SN Appl. Sci. 2019, 1, 1698. [Google Scholar] [CrossRef]
- Zhang, R.; Awang, N. A novel ST-iTransformer model for spatio-temporal ambient air pollution forecasting. J. Big Data 2025, 12, 101. [Google Scholar] [CrossRef]
- Salcedo-Bosch, A.; Zong, L.; Yang, Y.; Cohen, J.B.; Lolli, S. Forecasting particulate matter concentration in Shanghai using a small-scale long-term dataset. Environ. Sci. Eur. 2025, 37, 47. [Google Scholar] [CrossRef]
- Rad, A.K.; Nematollahi, M.J.; Pak, A.; Mahmoudi, M. Predictive modeling of air quality in the Tehran megacity via deep learning techniques. Sci. Rep. 2025, 15, 1367. [Google Scholar] [CrossRef]
- Maraun, D.; Wetterhall, F.; Ireson, A.M.; Chandler, R.E.; Kendon, E.J.; Widmann, M.; Brienen, S.; Rust, H.W.; Sauter, T.; Themeßl, M.; et al. Precipitation downscaling under climate change: Recent developments to bridge the gap between dynamical models and the end user. Rev. Geophys. 2010, 48, RG3003. [Google Scholar] [CrossRef]
- Camacho, A.; Ariosa, L. Diccionario de Términos Ambientales, Publicaciones Acuario; Centro Félix Varela: La Habana, Cuba, 2000. [Google Scholar]
- Universidad del Norte. Arroyos: Desarrollo, Riesgo Y Sostenibilidad. Available online: https://www.uninorte.edu.co/web/dip/arroyos-en-barranquilla (accessed on 2 July 2025).
- Garrido, J.V.G. Análisis de Impacto Por La Canalización del Arroyo la Felicidad-Barranquilla Desde la Percepción Local. Master’s Thesis, Universidad de la Costa, Barranquilla, Colombia, 23 August 2022. Available online: https://hdl.handle.net/11323/9598 (accessed on 15 June 2025).
- Castro, C.C. Incidencia de la problemática de los arroyos en los sectores productivos en Barranquilla. Gest. Compet. Innov. 2016, 1, 128–144. [Google Scholar]
- Arévalo Carmona, M.I. Variables Para Medir la Vulnerabilidad Físico-Espacial a Inundaciones en Asentamientos Informales: Caso de Estudio Arroyo La Esmeralda en el Distrito de Barranquilla-Colombia; Universidad del Atlántico: Barranquilla, Colombia, 2018; Available online: https://hdl.handle.net/20.500.12834/1111 (accessed on 4 July 2025).
- Plaza Capital. Barranquilla Bajo la Lluvia: Cambios Y Desafíos en la Ciudad. Available online: https://www.plazacapital.co/conexiones/7285-barranquilla-bajo-la-lluvia-cambios-y-desafios-en-la-ciudad (accessed on 31 July 2025).
- Alcaldía de Barranquilla. Distrito Atiende Emergencias Por Torrencial Aguacero en Barranquilla Y Área Metropolitana. Available online: https://www.barranquilla.gov.co/mi-barranquilla/distrito-atiende-emergencias-por-torrencial-aguacero-en-barranquilla-y-area-metropolitana (accessed on 31 July 2025).
- El Tiempo. Fuertes Lluvias en Barranquilla Provocan Emergencias Por Desbordamiento de Arroyos e Inundaciones. Available online: https://www.eltiempo.com/colombia/barranquilla/fuertes-lluvias-en-barranquilla-provocan-emergencias-por-desbordamiento-de-arroyos-e-inundaciones-3454265 (accessed on 31 July 2025).
- Pulido-Rojano, A.; Gutiérrez-Peralta, E.; Castro-Espinosa, K.; Hernández-Moreno, F.; Alcalá-Vila, N.; Barrios-Santiago, B. Análisis de la precipitación en la ciudad de Barranquilla-Colombia mediante métodos de pronóstico. In Proceedings of the Décima Quinta Conferencia Iberoamericana de Complejidad, Informática Y Cibernética (CICIC 2025), Orlando, FL, USA, 25–28 March 2025. [Google Scholar]
- Carrasquilla-Batista, A.; Chacón-Rodríguez, A.; Núñez-Montero, K.; Gómez-Espinoza, O.; Valverde, J.; Guerrero-Barrantes, M. Regresión lineal simple y múltiple: Aplicación en la predicción de variables naturales relacionadas con el crecimiento microalgal, Tecnol. Marcha 2016, 29, 33–45. [Google Scholar] [CrossRef]
- Mora, C.P.; Losada, J.L. Análisis de series temporales en estaciones meteorológicas para la predicción de la precipitación en la ciudad de Manizales, Colombia. Rev. Climatol. 2023, 23, 58–70. [Google Scholar] [CrossRef]
- Mangukiya, N.K.; Sharma, A. Deep Learning-Based Approach for Enhancing Streamflow Prediction in Watersheds with Aggregated and Intermittent Observations. Water Resour. Res. 2025, 61, e2024WR037331. [Google Scholar] [CrossRef]
- Asperti, A.; Merizzi, F.; Paparella, A.; Pedrazzi, G.; Angelinelli, M.; Colamonaco, S. Precipitation nowcasting with generative diffusion models. Appl. Intell. 2025, 55, 187. [Google Scholar] [CrossRef]
- Igwebuike, N.; Ajayi, M.; Okolie, C.; Kanyerere, T.; Halihan, T. Application of machine learning and deep learning for predicting groundwater levels in the West Coast Aquifer System, South Africa. Earth Sci. Inform. 2025, 18, 6. [Google Scholar] [CrossRef]
- Bai, X.; Zhang, L.; Feng, Y.; Yan, H.; Mi, Q. Multivariate temperature prediction model based on CNN-BiLSTM and RandomForest. J. Supercomput. 2025, 81, 162. [Google Scholar] [CrossRef]
- García Díaz, J.C. Predicción en el Dominio del Tiempo: Análisis de Series Temporales Para Ingenieros; Editorial Universitat Politècnica de València: Valencia, España, 2016. [Google Scholar]
- Valencia, M.; Ramírez, S.; Tabares, J.; Velásquez, C. Métodos de Pronósticos-Clásicos Y Bayesianos Con Aplicaciones; Universidad Nacional de Colombia: Medellín, Colombia, 2014; Available online: https://repositorio.unal.edu.co/handle/unal/21604 (accessed on 20 June 2025).
- Chinlli, C.M. Modelización de Series Temporales Modelos Clásicos Y SARIMA; Universidad de Granada: Granada, España, 2021. [Google Scholar]
- Pulido-Rojano, A.D.J.; Sanchez-Sanchez, P.; Melamed-Varela, E. Nuevas Tendencias en Investigación de Operaciones Y Ciencias Administrativas: Un Enfoque Desde Estudios Iberoamericanos; Ediciones Universidad Simón Bolívar: Barranquilla, Colombia, 2018. [Google Scholar]
- Mahajan, S.; Chen, L.-J.; Tsai, T.-C. Short-Term PM2.5 Forecasting Using Exponential Smoothing Method: A Comparative Analysis. Sensors 2018, 18, 3223. [Google Scholar] [CrossRef]
- Junthopas, W.; Wongoutong, C. Setting the Initial Value for Single Exponential Smoothing and the Value of the Smoothing Constant for Forecasting Using Solver in Microsoft Excel. Appl. Sci. 2023, 13, 4328. [Google Scholar] [CrossRef]
- Trull, O.; García-Díaz, J.C.; Troncoso, A. Initialization Methods for Multiple Seasonal Holt–Winters Forecasting Models. Mathematics 2020, 8, 268. [Google Scholar] [CrossRef]
- Kalekar, P. Time series forecasting using Holt–Winters exponential smoothing. Kanwal Rekhi Sch. Inf. Technol. 2004, 4329008, 1–13. [Google Scholar]
- Makridakis, S.; Wheelwright, S.C.; Hyndman, R.J. Forecasting: Methods and Applications; John Willey and Sons, Inc.: Chichester, UK, 1998. [Google Scholar]
SMA Model | Holt–Winters Multiplicative Model | ||
---|---|---|---|
3 | MAE = 87.74, MSE = 13,908.29, = 104.17 mm | 4 | Optimal values for MAE minimization = 4.45 × 10−6, = 0.1183, = 0.0116 |
4 | MAE = 93.49, MSE = 14,129.13, = 78.13 mm | MAE* = 79.11, MSE = 12,901.06, = 58.64 mm | |
5 | MAE = 96.12, MSE = 14,429.65, = 62.50 mm | 4 | Optimal values for MSE minimization = 0.04591, = 0.00777, = 0.00603 |
6 | MAE = 99.21, MSE = 14,542.07, = 52.20 mm | MAE = 86.20, MSE* = 11,557.56, = 101.10 mm | |
WMA model | 5 | Optimal values for MAE minimization = 0.9232, = 1 × 10−7, = 1 × 10−7 | |
3 | Optimal values for MAE minimization = 0.93, = 0.07, = 0.00 | MAE* = 75.33, MSE = 12,968.22, = 22.04 mm | |
MAE* = 76.44, MSE = 13,207.28, = 21.90 mm | 5 | Optimal values for MSE minimization = 0.05958, = 0.003628, = 1 × 10−7 | |
3 | Optimal values for MSE minimization = 0.685, = 0.143, = 0.172 | MAE = 86.65, MSE* = 11,600.84, = 108.01 mm | |
MAE = 77.51, MSE* = 12,312.44, = 47.23 mm | 6 | Optimal values for MAE minimization = 0.0007, = 0.01461, = 0.02327 | |
4 | Optimal values for MAE minimization = 0.907, = 0.071, = 0.016, = 0.006 | MAE* = 76.68, MSE = 12,542.91, = 22.49 mm | |
MAE* = 76.99, MSE = 13,107.32, = 22.40 mm | 6 | Optimal values for MSE minimization = 0.161118, = 1 × 10−7, = 0.08227 | |
4 | Optimal values for MSE minimization = 0.65, = 0.11, = 0.02, = 0.22 | MAE = 80.10, MSE* = 9647.07, = 34.86 mm | |
MAE = 81.06, MSE* = 11,845.28, = 33.57 mm | Holt–Winters additive model | ||
5 | Optimal values for MAE minimization = 0.913, = 0.072, = 0.00, = 0.00, = 0.015 | 4 | Optimal values for MAE minimization = 0.003163, = 0.002364, = 0.023723 |
MAE* = 77.50, MSE = 13,238.17, = 22.16 mm | MAE* = 79.72, MSE = 13455.09, = 64.91 mm | ||
5 | Optimal values for MSE minimization = 0.628, = 0.112, = 0.005, = 0.142, = 0113 | 4 | Optimal values for MSE minimization = 0.054176, = 0.00333, = 0.033139 |
MAE = 81.29, MSE* = 11,790.73, = 32.61 mm | MAE = 85.70, MSE* = 11,391.63, = 103.05 mm | ||
6 | Optimal values for MAE minimization = 0.793, = 0.072, = 0.011, = 0.00, = 0.00, = 0.124 | 5 | Optimal values for MAE minimization = 0.000618, = 0.26748, = 1 × 10−7 |
MAE* = 77.11, MSE = 12,235.30, = 22.30 mm | MAE* = 80.39, MSE = 13,874.74, = 96.04 mm | ||
6 | Optimal values for MSE minimization = 0.612, = 0.09, = 0.004, = 0.127, = 0.01, = 0.157 | 5 | Optimal values for MSE minimization = 0.05838, = 0.003793, = 1 × 10−7 |
MAE = 81.05, MSE* = 11,602.88, = 26.44 mm | MAE = 86.64, MSE* = 11,595.23, = 108.21 mm | ||
Optimal value | ES model | 6 | Optimal values for MAE minimization = 1 × 10-07, = 0.004155, = 0.058804 |
= 0.92 | MAE* = 76.44, MSE = 13,158.93, = 22.04 mm | MAE* = 77.82, MSE = 12764.91, = 26.58 mm | |
= 0.07 | MAE = 87.56, MSE* = 11,779.45, = 103.17 mm | 6 | Optimal values for MSE minimization = 0.06650, = 4.17 × 10−5, = 0.080602 |
MAE = 83.53, MSE* = 10,704.47, = 51.84 mm |
SMA Model | |||||
3 | MSE = 12,485, = 8.60 mm | ||||
4 | MSE = 12,784, = 6.45 mm | ||||
5 | MSE = 13,188 = 5.16 mm | ||||
WMA model | |||||
= 0.5 | = 0.3 | = 0.2 | |||
3 | MSE = 11,322, = 10.62 mm | ||||
= 0.65 | = 0.20 | = 0.15 | |||
3 | MSE = 10,878, = 12.97 mm | ||||
= 0.45 | = 0.25 | = 0.20 | = 0.10 | ||
4 | MSE = 11,281, = 9.71 mm | ||||
= 0.50 | = 0.30 | = 0.10 | = 0.10 | ||
4 | MSE = 11,016, = 9.86 mm | ||||
= 0.40 | = 0.25 | = 0.20 | = 0.10 | = 0.05 | |
5 | MSE = 11,473, = 8.80 mm | ||||
= 0.45 | = 0.25 | = 0.15 | = 0.10 | = 0.05 | |
5 | MSE = 11,137, = 9.33 mm | ||||
θ | ES model | ||||
0.5 | MSE* = 10,487, = 13.82 mm |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pulido-Rojano, A.D.; Sablón-Cossío, N.; Iglesias-Ortega, J.; Ruiz-Berdugo, S.; Torres-Cervantes, S.; Durant-Daza, J. Optimizing Time Series Models for Forecasting Environmental Variables: A Rainfall Case Study. Water 2025, 17, 2863. https://doi.org/10.3390/w17192863
Pulido-Rojano AD, Sablón-Cossío N, Iglesias-Ortega J, Ruiz-Berdugo S, Torres-Cervantes S, Durant-Daza J. Optimizing Time Series Models for Forecasting Environmental Variables: A Rainfall Case Study. Water. 2025; 17(19):2863. https://doi.org/10.3390/w17192863
Chicago/Turabian StylePulido-Rojano, Alexander D., Neyfe Sablón-Cossío, Jhoan Iglesias-Ortega, Sheila Ruiz-Berdugo, Silvia Torres-Cervantes, and Josueth Durant-Daza. 2025. "Optimizing Time Series Models for Forecasting Environmental Variables: A Rainfall Case Study" Water 17, no. 19: 2863. https://doi.org/10.3390/w17192863
APA StylePulido-Rojano, A. D., Sablón-Cossío, N., Iglesias-Ortega, J., Ruiz-Berdugo, S., Torres-Cervantes, S., & Durant-Daza, J. (2025). Optimizing Time Series Models for Forecasting Environmental Variables: A Rainfall Case Study. Water, 17(19), 2863. https://doi.org/10.3390/w17192863