Machine Learning-Based Intelligent Snowfall Prediction: A Method Based on Meteorological Pattern Analysis

Read full text Summarise with VIRAT
Cited by: 0
References: 3

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Since unforeseen snow occurrences can have a major influence on public safety, infrastructure stability, transportation networks, and agricultural operations, accurate snowfall prediction is an essential part of contemporary weather forecasting systems.Conventional statistical forecasting methods frequently fall short of capturing the intricate and nonlinear interactions that exist among meteorological variables since they mainly rely on linear assumptions and established atmospheric equations.These drawbacks emphasise the necessity of clever data-driven strategies that can more accurately simulate complex weather patterns.In order to better identify snowfall and non-snowfall events, this study suggests a machine learning-based snowfall prediction system that makes use of past meteorological data.Key climatic characteristics that are known to affect snow formation conditions, such as temperature, humidity, wind speed, and atmospheric pressure, are included in the dataset utilised in this study.Comprehensive data preprocessing, such as data cleaning, feature scaling normalisation, and correlation analysis to comprehend inter-feature interactions, was carried out prior to model building.To guarantee an objective assessment of the model, the dataset was then separated into training and testing subsets.Three supervised learning algorithms-Logistic Regression, Decision Tree, and Support Vector Machine (SVM)-were used and evaluated in order to identify the best prediction model.While the Decision Tree model offered hierarchical rule-based classification, Logistic Regression was used as a baseline linear classifier to assess the data's separability.Because of its excellent ability to handle nonlinear boundaries through kernelbased modifications, the Support Vector Machine was chosen.Confusion matrices and common classification measures like recall, accuracy, and precision were used to evaluate the model's performance.According to experimental results, the Support Vector Machine fared better than the other models in differentiating between snowfall and non-snowfall circumstances, exhibiting a higher capacity for generalisation and a lower rate of misclassification.The top-performing model was included into a Djangobased web application to improve practical use and provide real-time snowfall forecast via an intuitive user interface.The suggested method shows the efficacy of machine learning approaches in meteorological prediction problems and provides an intelligent, scalable, and accessible solution for precise snowfall forecasting.

Fields of Study & Subjects

Hydrological Forecasting Using AI Data Mining and Machine Learning Applications Meteorological Phenomena and Simulations

Publication details

Journal / source
International Research Journal of Modernization in Engineering Technology and Science
Publication date
25 March 2026
Language
EN