The week's pick
Random Articles
Reseach Article
Hybrid Machine Learning Approach for Weather Pattern Recognition and Anomaly Detection using Self-Organizing Maps and K-Nearest Neighbours
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 80 |
| Year of Publication: 2026 |
| Authors: Olamide T. Bello, Adebola K. Ojo |
10.5120/ijca2026926368
|
Olamide T. Bello, Adebola K. Ojo . Hybrid Machine Learning Approach for Weather Pattern Recognition and Anomaly Detection using Self-Organizing Maps and K-Nearest Neighbours. International Journal of Computer Applications. 187, 80 ( Feb 2026), 15-22. DOI=10.5120/ijca2026926368
Abstract
Accurate identification of weather patterns and timely detection of anomalies are critical for effective meteorological forecasting, especially in regions where predictive systems remain underdeveloped. In much of sub-Saharan Africa, the use of hybrid machine learning methods for long-term weather analysis is still limited. This study investigates the combination of Self-Organizing Maps (SOM) and K-Nearest Neighbours (KNN) to improve weather pattern recognition and anomaly detection. Focusing on meteorological data from Oyo State, Nigeria, spanning 2013 to 2023, the research utilizes SOM to project multidimensional weather variables onto a two-dimensional topological grid, facilitating clustering of similar conditions. KNN is subsequently applied to these clusters to flag outliers that represent potential anomalies. The dataset, obtained from regional meteorological stations, was complete and did not require data imputation. Model performance was assessed using the Silhouette Score and the Davies-Bouldin Index, both of which indicated satisfactory cluster cohesion and separation. The findings show that the integrated SOM-KNN approach reliably identifies recurring weather trends and isolates unusual events, highlighting its value in climate monitoring and anomaly detection. The study demonstrates the applicability of hybrid machine learning techniques in enhancing environmental data analysis in data-limited settings. It offers a practical framework for supporting early warning systems and developing region-specific climate adaptation strategies.
References
- A. H. Pratomo, Budi Santosa, S. P. Tahalea, E. T. Paripurno, J. D. Peasetyo, Herlina Jayadianti, M. F. Pitayandanu. (2022, May). Rainfall Prediction Using Artificial Neural Network with Historical Weather Data as Supporting Parameters. Jurnal Informatika (JIFO), 16(2), 63–73. doi: http://journal.uad.ac.id/index.php/JIFO/article/view/25422
- T. Brown. (2018). Statistical Models for Climate Analysis. Climate Press.
- Y. Wang & L. Zhang. (2022). Adaptive Anomaly Detection in Climate Data. Journal of Climate, 35(4), 123–145.
- Kohonen, T. (2001). Self-Organizing Maps (3rd ed.). Berlin, Heidelberg: Springer. doi:https://doi.org/10.1007/978-3-642-56927-2
- Yin, H. (2008). The self-organizing maps: Background, theories, extensions and applications. In J. &. Fulcher (Ed.), Computational intelligence: A compendium (Vol. 115, pp. 3–25). Berlin, Heidelberg: Springer. doi:https://doi.org/10.1007/978-3-540-78293-3_1
- Johnson, M. (2022). SOMs for precipitation classification. Geoscientific Model Development, 15, 1–15. doi:10.5194/gmd-15-1-2022
- Chandola, V.; Banerjee, A.; Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 14(3), 1–58. doi:10.1145/1541880.1541882
- Huang, A., & Chang, F.-J. (2021). Using a self-organizing map to explore local weather features for smart urban agriculture in Northern Taiwan. Water, 13(23), 3457. doi:https://doi.org/10.3390/w13233457
- Chen, L., Han, B., Wang, X., Zhao, J., Yang, W., & Yang, Z. (2023). KNN-based anomaly detection in weather data. Journal of Climate Informatics, 12(3), 45–60.
- Garcia, R. (2020). Machine learning for atmospheric science. AI in Meteorology, 8(2), 112–130.
- Oyeniyi, O., & Adebola, K. (2024). Weather forecasting using deep learning and seasonal autoregressive integrated moving average model. IOSR Journal of Computer Engineering (IOSR-JCE)(2, Ser. 3), 33–38.
- Himanshu, G., Singh, S., & Neha, R. (2024). Comprehensive Analysis of Weather Forecasting Techniques. International Journal of Innovative Research in Engineering & Multidisciplinary Physical Sciences, 12(5). doi:https://doi.org/10.37082/ijirmps.v12.i5.231092
- Prasanta, R. J., Bhanu, S. K., & Nithin, C. (2015, October–November). Weather forecasting using artificial neural networks and data mining techniques. International Journal of Innovative Technology and Research, 3(6), 2534–2539.
- Ihab, H., Mohammed, A., & Walid, S. (2018, May 15). Short-term forecasting of weather conditions in Palestine using artificial neural networks. Journal of Theoretical and Applied Information Technology, 96(9).
- Ihab, H., Mohammed, A., & Walid, S. (2018, May 15). Short-term forecasting of weather conditions in Palestine using artificial neural networks. Journal of Theoretical and Applied Information Technology, 96(9).
- Mulyani, H., Setiawan, R. A., & Fathi, H. (2023). Optimization of K Value in Clustering Using Silhouette Score (Case Study: Mall Customers Data). Journal of Information Technology and Its Utilization, 6(2), 45–50. doi:https://doi.org/10.56873/jitu.6.2.5243
- Batta, V. (2024). Machine Learning. International Journal of Advanced Research in Science, Communication and Technology, 583–591. doi:https://doi.org/10.48175/ijarsct-17677
- Kumar, N. (2024). Review Paper on Machine Learning Algorithms. Indian Scientific Journal of Research in Engineering and Management, 8(5), 1–5. doi:https://doi.org/10.55041/ijsrem34900
- Bose, S., Halder, S., & Mazumdar, A. (2024). Exploring groundwater quality dynamics: A holistic study of Kolkata and its peri-urban surroundings. Sustainable Water Resources Management, 10(6). doi:https://doi.org/10.1007/s40899-024-01168-2
Index Terms
Keywords