Journal article · 2026 · Open access

Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models

Gbenga Ogunsanwo, Ismail Ogunshina, Olumuyiwa Bamidele Alaba, Ayoade Owoade, Godwin Odulaja

Pharaonic Journal of Science, 2(2), 48–62 · Published 30 May 2026 · DOI 10.71428/pjs.2026.0206

Open PDFView at the publisherCite this paper

In brief

“Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models” is a 2026 journal article by Gbenga Ogunsanwo and 4 co-authors, published in Pharaonic Journal of Science. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at Pharaonic Journal of Science.

Citations
0
References
15
Authors
5

Abstract

Rainfall prediction is critical for agricultural planning, water resource management, and disaster preparedness, particularly in regions vulnerable to climate variability. Traditional forecasting techniques often struggle to capture the non‑linear and complex dynamics of meteorological data. This study developed machine learning models to improve rainfall prediction using historical data obtained from the Nigerian Meteorological Agency, which includes climatic variables such as temperature, wind speed, humidity, and prior rainfall. After preprocessing and normalization, the dataset was divided into training (80%) and testing (20%) subsets. Four algorithms, such as Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Deep Neural Network (DNN), were implemented and evaluated using regression metrics such as R², Mean Squared Error, and Mean Absolute Error. The results show that RF and XGBoost achieved moderate accuracy, with R² values below 0.87. SVR performed better, reducing error significantly (MAE = 0.6839, MSE = 13.8717, R² = 0.893). The DNN model outperformed all others, achieving very low error (MAE = 0.2334, MSE = 0.1956) and near‑perfect accuracy (R² = 0.9985). These findings demonstrate the superior capacity of deep learning approaches to model complex rainfall patterns compared to traditional ensemble and regression methods, while SVR remains a reliable alternative. The study recommends that stakeholders in meteorology and agriculture adopt advanced machine learning models for improved decision‑making. Future research should incorporate high‑resolution satellite data and ground station records for hybrid modeling and employ techniques such as SHAP and LIME.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ogunsanwo, G., Ogunshina, I., Alaba, O. B., Owoade, A., & Odulaja, G. (2026). Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models. Pharaonic Journal of Science, 2(2), 48–62. https://doi.org/10.71428/pjs.2026.0206

MLA 9

Ogunsanwo, Gbenga, et al. “Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models.” Pharaonic Journal of Science, vol. 2, no. 2, 2026, pp. 48–62. https://doi.org/10.71428/pjs.2026.0206.

Chicago

Ogunsanwo, Gbenga, Ismail Ogunshina, Olumuyiwa Bamidele Alaba, Ayoade Owoade, and Godwin Odulaja. 2026. “Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models.” Pharaonic Journal of Science 2 (2): 48–62. https://doi.org/10.71428/pjs.2026.0206.

Harvard

Ogunsanwo, G. et al. (2026) ‘Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models’, Pharaonic Journal of Science, 2(2), pp. 48–62. doi:10.71428/pjs.2026.0206.

IEEE

G. Ogunsanwo, I. Ogunshina, O. B. Alaba, A. Owoade, and G. Odulaja, “Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models,” Pharaonic Journal of Science, vol. 2, no. 2, pp. 48–62, 2026, doi: 10.71428/pjs.2026.0206.

BibTeX

@article{ogunsanwo2026machine,
  title     = {{Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models}},
  author    = {Ogunsanwo, Gbenga and Ogunshina, Ismail and Alaba, Olumuyiwa Bamidele and Owoade, Ayoade and Odulaja, Godwin},
  journal   = {Pharaonic Journal of Science},
  year      = {2026},
  volume    = {2},
  number    = {2},
  pages     = {48--62},
  doi       = {10.71428/pjs.2026.0206},
  url       = {https://doi.org/10.71428/pjs.2026.0206}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI

  • precipitation forecasting
  • support vector regression
  • XGBoost
  • random forest
  • deep neural network
  • ensemble regression
  • meteorological parameters
  • climate variability

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Ogunsanwo, G., Ogunshina, I., Alaba, O. B., Owoade, A., & Odulaja, G. (2026). Machine Learning Approaches to Rainfall Forecasting in Nigeria: A Comparative Study of RF, SVR, XGBoost, and DNN Models. Pharaonic Journal of Science, 2(2), 48–62. https://doi.org/10.71428/pjs.2026.0206

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Pharaonic Journal of Science: sign in and open the PDF from this page.

Who wrote this paper?

Gbenga Ogunsanwo, Ismail Ogunshina, Olumuyiwa Bamidele Alaba, Ayoade Owoade, Godwin Odulaja.

What is the DOI of this paper?

10.71428/pjs.2026.0206, permanently at https://doi.org/10.71428/pjs.2026.0206. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.