Authors : Tayo P. Ogundunmade; Opeyemi Adewale Okunoye

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/3p7b4xby

Scribd : https://tinyurl.com/4mmz35fk

DOI : https://doi.org/10.38124/ijisrt/26mar796

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The data includes information from ten years, from 2014 up to 2023. Weather data is recorded monthly from the meteorological station at the Forestry Research Institute in Nigeria. Important data recorded includes temperature in Celsius, humidity, wind speed in km/h, and relative humidity. This data is recorded in seven columns and 120 rows. It includes temperature, humidity, wind speed, and relative humidity. Three models are applied in solving this problem. These models are time-aware long short-term memory networks, gated recurrent units, and the Transformer. These models have been improved with an attention-based approach to interpretability, inspired by RETAIN. The GRU model can forecast data up to six months into the future. This data shows an inverse correlation with temperature and relative humidity. Relative humidity goes down to 72% ± 5, indicating pre-rainy conditions. This occurs while temperatures peak at 31°C ± 0.8 in Month 4. In Month 6, temperatures drop to 28.2°C ± 0.5, and relative humidity rises to 85% ± 3, indicating that rain is on the way. Wind speeds decrease to 9.8-10.5 km/h in Months 3 and 4, when temperatures are at their peak and relative humidity is at its lowest. The weather forecasting model has shown how GRU, Time Aware, and even the Transformer can be applied in solving weather problems in Nigeria.

Keywords : Weather Prediction, Long Short-Term Memory (LSTM) Networks, Gated Recurrent Units (GRUs), Transformer Models, Deep Learning.

References :

1. Adefisan, E. A., & Abatan, A. A. (2022). Evaluating short-term rainfall prediction models over West Africa using satellite and ground observations. African Journal of Environmental Science and Technology, 16(4), 143–154. https://doi.org/10.5897/AJEST2021.3041
2. Ali, S., Malik, A., & Khan, A. (2021). Machine learning-based approaches for weather forecasting: A review. IEEE Access, 9, 61271–61294. https://doi.org/10.1109/ACCESS.2021.3074164
3. Mohammed, I. A., Abba, S. I., & Elkiran, G. (2020). Application of hybrid data-intelligent models for forecasting meteorological drought in semi-arid regions. Environmental Science and Pollution Research, 27(17), 21150–21167. https://doi.org/10.1007/s11356-020-08614-z
4. LeCun, Y., Bengio, Y., & Hinton,G.(2015). Deep learning. Nature, 521(7553), 436–444 https://doi.org/10.1038/nature14539
5. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
6. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. https://arxiv.org/abs/1412.3555
7. Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28, 802–810. https://papers.nips.cc/paper/2015
8. Rasp, S., Pritchard, M. S., & Gentine, P. (2018). Deep learning to represent subgrid processes in climate models. Proceedings of the National Academy of Sciences, 115(39), 9684–9689. https://doi.org/10.1073/pnas.1810286115
9. Ogutu, B., Atzberger, C., & Mungai, K. (2021). Satellite-based rainfall prediction in East Africa using machine learning techniques. Remote Sensing, 13(8), 1550. https://doi.org/10.3390/rs13081550
10. Fashae, O. A., & Ajayi, G. O. (2023). Deep learning models for short-term temperature prediction in tropical West Africa. Heliyon, 9(3), e14522. https://doi.org/10.1016/j.heliyon.2023.e14522
11. Eze, E. O., Nwokoye, C. H., & Okoro, C. (2020). A hybrid machine learning approach for rainfall prediction in Lagos, Nigeria. International Journal of Computer Applications. 176(30), 1–8 https://doi.org/10.5120/ijca2020920410
12. Olowe, O. A., Balogun, I. A., & Adefisan, E. A. (2023). Deep learning applications in urban microclimate modeling: Insights from Ibadan, Nigeria. Atmospheric Research, 292, 10659 https://doi.org/10.1016/j.atmosres.2023.106591
13. Balogun, I. A., Olanrewaju, R. M., & Adefisan, E. A. (2021). Urban heat island characteristics in major Nigerian cities. Theoretical and Applied Climatology, 143(1), 523–538. https://doi.org/10.1007/s00704-020-03424-3
14. Adelekan, I. O. (2016). Urban climate adaptation in Africa: A case study of Lagos, Nigeria. Current Opinion in Environmental Sustainability, 19, 45–53. https://doi.org/10.1016/j.cosust.2015.12.002
15. Ogunjo, S. T., & Akinbobola, A. (2021). Rainfall prediction using convolutional neural networks: A case study of southwestern Nigeria. Journal of African Earth Sciences, 182, 104251. https://doi.org/10.1016/j.jafrearsci.2021.104251
16. Aremu, O. T., & Oladimeji, K. A. (2022). Application of LSTM neural networks for short-term weather forecasting in Northern Nigeria. Nigerian Journal of Technological Development, 19(2), 90–98. https://doi.org/10.4314/njtd.v19i2.4
17. Leinonen, J., Nerini, D., & Berne, A. (2020). Stochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network. IEEE Transactions on Geoscience and Remote Sensing, 58(5), 3487–3500. https://doi.org/10.1109/TGRS.2019.2956613
18. Mahmud, A., Shuvo, M. A., & Rahman, S. (2021). A hybrid CNN-LSTM model for tropical cyclone track prediction in the Bay of Bengal. Springer Nature Applied Sciences, 3(5), 512. https://doi.org/10.1007/s42452-021-04521-9
19. Okafor, C. J., Adebayo, Y. R., & Omotosho, J. B. (2023). Artificial intelligence-driven meteorological forecasting for sustainable development in Nigeria. Environmental Challenges, 12, 100835. https://doi.org/10.1016/j.envc.2023.100835
20. Pathak, J., Subramanian, S., Harrington, P., & Schneider, T. (2022). FourCastNet: Global high-resolution weather forecasting using adaptive Fourier neural operators. arXiv preprint arXiv:2202.11214. https://arxiv.org/abs/2202.11214
21. Lam, R., et al. (2023). GraphCast: Learning skillful medium-range global weather forecasting. Science, 382(6677), 1211–1217. https://doi.org/10.1126/science.adi2336
22. Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat. (2019). Deep learning and process understanding for data-driven Earth system science. Nature, 566(7743), 195–204. https://doi.org/10.1038/s41586-019-0912-1
23. Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., & Ganguly, A. R. (2018). Generating high-resolution climate change projections through single image super-resolution: An adversarial learning approach. Remote Sensing of Environment, 233, 111406. https://doi.org/10.1016/j.rse.2019.111406
24. Kadow, C., Hall, D. M., & Ulbrich, U. (2020). Artificial intelligence reconstructs missing climate information. Nature Geoscience, 13(6), 408–413. https://doi.org/10.1038/s41561-020-0582-5
25. Adedayo Adepoju A., Tayo P. Ogundunmade and Kayode B. Adebayo (2017). Regression Methods in the presence of heteroscdesticity and outliers, Academia Journal of Scientific Research 5(2): 776-783.
26. Ogundunmade TP, Abidoye M, Olunfunbi OM. Modelling Residential Housing Rent Price Using Machine Learning Models. Mod Econ Manag, 2023; 2: 14.
27. Afolabi O. Adedamola; Tayo P. Ogundunmade (2025). Predictive Modelling of Crime Data using Machine Learning Models: A Case Study of Oyo State, Nigeria. International Journal of Innovative Science and Research Technology, 10(4), 1669-1677. https://doi.org/10.38124/ijisrt/25apr851.
28. Tayo P. Ogundunmade; Olayinka B. Ayeni (2025). Stock Price Prediction of Major Technology Companies Using Machine Learning. International Journal of Innovative Science and Research Technology (IJISRT) 2573-2586, Volume 10, Issue 10, October 2025. https://doi.org/10.38124/ijisrt/25oct1245.
29. Ogundunmade TP, Ganiyu KA, Yahaya OT. Assessment of profitability and inventory management in the Nigerian power generation asset companies. Financial Statistical Journal. 2025; 8(1): 11398. https://doi.org/10.24294/fsj1139
30. Ogundunmade TP, Assessment of Inventory Management for Profitability in the Energy Sector: A Case Study of Nigerian Power Distribution Asset Companies. Mod Econ Manag, 2025; 4: 4. DOI: 10.53964/mem.2025004.