Optimizing rainfall prediction in coastal and inland areas: a comparative analysis of forecasting models in eThekwini district, South Africa

Abstract

While floods and droughts are natural occurrences in the earth’s hydrological cycle, their escalating frequency and intensity have become a major concern for governments throughout the globe. Developing nations, such as South Africa, are weary of these extreme weather events because they understand they lack the necessary resources and infrastructure to deal with them. The eThekwini Municipality serves as a prime example of how vulnerable developing nations' regions are to the devastating effects of floods and droughts, as multiple floods have devastated the area, resulting in fatalities, damaging public infrastructure, and demolishing houses. The scale of the damage from the floods reveals that significant gaps exist in disaster preparedness in the eThekwini Region. Rainfall forecasting is a vital tool that has been underutilised that can be used preemptively to manage or mitigate flooding and enhance water resource management in the region. Machine learning models in particular are very useful in rainfall forecasting; hence, the goal of this study was to evaluate the most efficient models for forecasting precipitation in the eThekwini northern and central regions, which are coastal and inland areas, respectively. Rainfall data spanning 32 years was obtained from meteorological stations in both regions, and the SARIMA, ARIMA, and ETS machine learning models were used for rainfall forecasting and evaluated based on their ability to capture seasonal patterns, handle non-stationarity, and provide accurate predictions. Model performance was analysed, and comparisons were made using the root mean squared error (RMSE), mean absolute error (MAE), and mean absolute scaled error (MASE) as evaluation metrics. The study's findings indicate that the most effective models for both the northern and central regions were SARIMA (0,0,0) (2,0,0) [12] and SARIMA (1,0,0) (1,0,0) [12]. These findings provide valuable insights for meteorologists, hydrologists, and policymakers involved in regional climate modelling and water resource management.

Keywords: {'name': 'Rainfall Prediction, ARIMA, SARIMA, ETS, Climate Modelling'}

Authors & affiliations

Ntokozo Xaba
Affiliation not supplied

Ajay Kumar Mishra
Affiliation not supplied

Deposited references

Supplied references, not a list of publications citing this article.

DOI: 10.1080/19475705.2024.2347414

DOI: 10.1007/s00704-018-2693-0

Aborass, D., Hassan, H. A., Sahalash, I., & Al-Rimmawi, H. (2022). Application of ARIMA models in forecasting average monthly rainfall in Birzeit, Palestine. International Journal of Water Resources and Arid Environments, 11(1), 62-80.

Agricultural Research Council. (2023). Climate dataset for South Africa by the Agricultural Research Council. Agricultural Research Council, South Africa.

DOI: 10.33793/acperpro.04.02.24

DOI: 10.3390/atmos14010088

DOI: 10.1109/ICICT50816.2021.9358615

DOI: 10.1007/s11269-018-1903-y

DOI: 10.1038/nature14956

DOI: 10.1109/ICAIA57370.2023.10169493

Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). John Wiley & Sons.

DOI: 10.1007/s42452-021-04667-5

Brown, T., & Lee, H. (2021). The influence of coastal proximity on climate stability. Journal of Coastal Climatology, 45(3), 289–302.

Brown, T., Lee, H., & Martinez, R. (2019). Inland versus coastal rainfall patterns and SARIMA model adaptations. Journal of Environmental and Climate Studies, 41(4), 203–214.

DOI: 10.54302/mausam.v74i4.805

DOI: 10.9734/ijecc/2023/v13i123740

Davis, C. L., & Vincent, K. (2017). Climate risk and vulnerability: A handbook for Southern Africa (2nd ed.). CSIR.

Davis, R. (2017). South Africa—Storm leaves 8 dead, record rain in Durban. FloodList. Retrieved from http://floodlist.com/africa/kwazulu-natal-durban-flood-october2017

De-Greef, K. (2019). South Africa floods leave at least 60 dead. The New York Times. Retrieved from https://www.nytimes.com/2019/04/24/world/africa/durban-floods.html

DOI: 10.9734/AIR/2016/24175

eThekwini Municipality. (2022). Employment in Durban increased by 2% in the first quarter of 2022. eThekwini Municipality, South Africa. Retrieved from https://www.durban.gov.za/news/Employment%2Bin%2BDurban%2Bincreased%2Bby%2B2%25%2Bin%2Bthe%2Bfirst%2Bquarter%2Bof%2B2022

DOI: 10.1175/1520-0442(2000)013<0297:IVOCRE>2.0.CO;2

DOI: 10.3390/atmos8040067

DOI: 10.54386/jam.v25i4.2250

DOI: 10.1007/978-981-33-6912-2_5

DOI: 10.4018/IJEIS.2019040103

DOI: 10.1016/j.eswa.2023.121160

DOI: 10.1016/j.ress.2023.109453

Hoegh-Guldberg, O., Jacob, D., Bindi, M., Brown, S., Camilloni, I., Diedhiou, A., Djalante, R., Ebi, K., Engelbrecht, F., Guiot, J., Hijioka, S., Mehrotra, A., Payne, S. I., Seneviratne, A., Thomas, R., Warren, & Zhou, G. (2018). Impacts of 1.5°C global warming on natural and human systems. In Global Warming of 1.5°C. IPCC Secretariat.

Holt, C. C. (1957). Forecasting seasonals and trends by exponentially weighted averages (O.N.R. Memorandum No. 52). Carnegie Institute of Technology, Pittsburgh, USA.

DOI: 10.1016/B978-0-12-814820-4.00003-1

Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice. O Texts. Available at: https://robjhyndman.com/uwafiles/fpp-notes.pdf

Jafarian-Namin, S., Shishebori, D., & Goli, A. (2023). Analyzing and predicting the monthly temperature of Tehran using ARIMA model, artificial neural network, and its improved variant. Journal of Applied Research on Industrial Engineering, 11(1), 76–93. https://www.journal-aprie.com/article_167429_bbd2e798c9c4a5ec4e981703899fd52a.pdf

DOI: 10.1088/1757-899X/352/1/012055

Johnson, R., & Walker, P. (2020). Humidity and rainfall distribution in coastal versus inland areas. Climate Dynamics, 33(2), 101–114.

Johnson, R., Walker, P., & Patel, S. (2019). Oceanic influence on rainfall seasonality in coastal regions. Coastal Climate Dynamics, 29(6), 187–201.

DOI: 10.17159/wsa/2022.v48.i4.3991

DOI: 10.4314/wsa.v44i2.15

DOI: 10.1038/s41467-020-16757-w

DOI: 10.4314/wsa.v43i2.12

DOI: 10.1007/s10661-023-12270-x

DOI: 10.1016/j.aej.2023.09.060

DOI: 10.1038/s41467-023-38203-3

DOI: 10.1590/sajs.2014/20130353

DOI: 10.4491/eer.2016.075

Markovska, M., Buchkovska, A., & Taskovski, D. (2016). Comparative study of ARIMA and Holt-Winters statistical models for prediction of energy consumption. In Proceedings of Abstracts of XIII International Conference ETAI16 (pp. 30–31), Republic of Macedonia.

DOI: 10.3390/w15010050

DOI: 10.3390/data7080117

DOI: 10.52339/tjet.v41i2.786

DOI: 10.11591/ijeecs.v34.i2.pp1092-1101

DOI: 10.3390/ECWS-7-14243

Scholes, R., & Engelbrecht, F. (2021). Climate impacts in Southern Africa during the 21st century. Global Change Institute, University of the Witwatersrand.

Sharma, P. K., Dwivedi, S., Ali, L., & Arora, R. K. (2018). Forecasting maize production in India using ARIMA model. Agro Economist - An International Journal, 5(1), 1-7. https://doi.org/10.30954/2394-8159.01.2018.1

Smith, J., & Johnson, L. (2021). Seasonality and climate moderation in coastal areas. International Journal of Meteorological Research, 47(3), 121-137.

Smith, L., & Jones, M. (2020). Oceanic moisture influence on coastal rainfall stability. Journal of Marine Climate, 50(1), 85-97.

Somvanshi, V. K., Pandey, O. P., Agrawal, P. K., Kalanker, N. V., Prakash, M. R., & Chand, R. (2006). Modelling and prediction of rainfall using artificial neural network and ARIMA techniques. Journal of the Indian Geophysical Union, 10(2), 141-151.

Statistics South Africa. (2020). How unequal is South Africa. https://www.statssa.gov.za/?p=12930

DOI: 10.24425/jwld.2022.140785

Thompson, K., & Green, A. (2020). Comparative analysis of SARIMA models in coastal versus inland rainfall patterns. Meteorological Insights, 30(5), 317-327.

Tihi, N., & Popov, S. (2023). Selection of the best ARIMA models for urban drought prediction. Fresenius Environmental Bulletin, 32(6), 2564-2572.

DOI: 10.1016/j.scitotenv.2020.140596

DOI: 10.3390/w11102055

United States Climate Prediction Center. (2020). El Niño and La Niña ocean temperature patterns. https://www.cpc.ncep.noaa.gov/products/analysis_monitoring/ensocycle/ensocycle.shtml

DOI: 10.5194/nhess-21-1011-2021

DOI: 10.5539/mas.v12n11p181

DOI: 10.22214/ijraset.2021.35032

Williams, A., & Thompson, K. (2019). Orographic lifting and its impact on coastal rainfall consistency. Applied Geography, 22(6), 159-172.

Williams, D. (2020). Oceanic proximity and its effect on predicting seasonal patterns using SARIMA models. Journal of Climate Prediction, 33(2), 220-234.

DOI: 10.1287/mnsc.6.3.324

DOI: 10.36096/ijbes.v6i3.515

Yusof, F., & Kane, I. L. (2012). Modelling monthly rainfall time series using ETS state space and SARIMA models. International Journal of Current Research, 4(9), 195-200.

DOI: 10.1088/1742-6596/2294/1/012029

DOI: 10.1088/1742-6596/1631/1/012141

DOI: 10.1002/hyp.14424

DOI: 10.2166/nh.2018.023

DOI: 10.1002/wcc.295