Institutional Repository of Vilnius University
Oro kokybės prognozavimas dirbtiniais neuroniniais tinklais /
Abstract
dc:descriptionAir pollution is a major environmental and public health problem. This paper focuses on the application of recurrent neural networks: long-short term memory and gated recurrent unit neural networks to predict air quality (pollutant concentrations) from weather data in Lithuania. The study constructs neural network models and compares their performance in predicting air quality indicators under different meteorological conditions. The methodology includes data processing, model training and validation against actual values of air quality indicators from September to December 2023. The results of the study show that the long-short term memory model is more accurate in terms of mean-squared error and the gated recurrent units model in terms of graphs. The potential of machine learning methods to improve air quality forecasts is highlighted and possible ways to improve forecasting models are suggested.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Volkova, Anastasija,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210642666&prefLang=en_US