ANALYSIS AND PREDICTION OF WEATHER CONDITIONS BASED ON MACHINE LEARNING WITH INTEGRATION OF WEB TECHNOLOGIES

DOI: 10.31673/2786-8362.2025.023547

Abstract

The article highlights the
relevance of applying machine learning methods to weather prediction and analyzes modern AutoML
approaches that simplify model selection and hyperparameter tuning. An integrated software solution is
proposed, ensuring a complete data workflow: from dataset import and basic exploratory analysis to model
construction and the generation of forecasts based on fundamental methods with fixed hyperparameters.
The system architecture is composed of a client interface and an application logic server implemented on
the MERN stack, as well as a separate machine learning module developed with Python libraries. The
developed tool emphasizes transparency and ease of use, allowing non-expert users to perform experiments
with minimal technical effort. Logistic regression, gradient boosting, and multilayer perceptron models are
used to predict values in localized climate datasets. The developed application can be used as a tool for
rapid hypothesis verification, educational and demonstration purposes, and for obtaining forecasts with
acceptable accuracy on localized weather datasets. Future development of the system may focus on
integrating time-series forecasting models such as ARIMA and SARIMA to account for seasonal and
autocorrelated characteristics of climatic processes.
Keywords: machine learning, AutoML, weather prediction, web application, MERN, Scikit-learn

References
1. Machine Learning Methods for Weather Forecasting: A Survey / H. Zhang та ін. Atmosphere.
2025. Т. 16, № 1. С. 82. URL: https://doi.org/10.3390/atmos16010082.
2. Probabilistic weather forecasting with machine learning / I. Price та ін. Nature. 2024.
URL: https://doi.org/10.1038/s41586-024-08252-9.
3. Feurer M., Eggensperger K., Falkner S., Lindauer M., Hutter F. Auto-sklearn 2.0: Hands-free
automl via meta-learning // Journal of Machine Learning Research. – 2022. – Vol. 23, № 261. – С.
1–61.
4. Erickson N., Mueller J., Shirkov A., Zhang H., Larroy P., Li M., Smola A. Autogluon-tabular:
Robust and accurate automl for structured data // arXiv preprint arXiv:2003.06505. – 2020. – URL:
https://arxiv.org/abs/2003.06505.
5. AMLB: Frameworks. AMLB An AutoML Benchmark.
URL: https://openml.github.io/automlbenchmark/frameworks.html (дата звернення: 07.11.2025).
6. What is Exploratory Data Analysis? – GeeksforGeeks. – URL:
https://www.geeksforgeeks.org/data-analysis/what-is-exploratory-data-analysis.
7. Advanced EDA – GeeksforGeeks. – URL: https://www.geeksforgeeks.org/datascience/advanced-eda.
8. Geron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts,
Tools, and Techniques to Build Intelligent Systems. – 2nd ed. – Sebastopol (CA) : O’Reilly Media,
Inc., 2019. – 851 с.
9. Raschka S., Liu Y., Mirjalili V. Machine Learning with PyTorch and Scikit-Learn. –
Birmingham : Packt Publishing Ltd., 2022. – 771 с.
10. Supervised Machine Learning – GeeksforGeeks. – URL:
https://www.geeksforgeeks.org/machine-learning/supervised-machine-learning.
11. Logistic Regression in Machine Learning – GeeksforGeeks. – URL:
https://www.geeksforgeeks.org/machine-learning/understanding-logistic-regression.
12. Gradient Boosting in ML – GeeksforGeeks. – URL:
https://www.geeksforgeeks.org/machine-learning/ml-gradient-boosting.
13. Multi-layer Perceptron: a Supervised Neural Network Model using Sklearn –
GeeksforGeeks. – URL: https://www.geeksforgeeks.org/deep-learning/multi-layer-perceptron-asupervised-neural-network-model-using-sklearn.
14. Gutta S. Machine Learning Metrics in simple terms. Medium.
URL: https://medium.com/analytics-vidhya/machine-learning-metrics-in-simple-termsd58a9c85f9f6.