Explainable AI for Atmospheric Temperature Prediction Using Air Quality and Meteorological Parameters at Dublin International Airport, Ireland
Open Access
- 9 November 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (21) , 11066
Abstract
Airports are dynamic but pose complex environmental concerns because of their air quality. The air quality in the vicinity of the airports can deteriorate due to heavy vehicular traffic and aircraft handling. The air quality interacts with meteorological conditions; thus, understanding these links would benefit any mitigation activities in the search for sustainable solutions. However, these interactions are complex and nonlinear. Therefore, interpretable machine learning techniques can effectively be used to understand complex environmental scenarios. This study examines atmospheric temperature prediction at Dublin Airport, Ireland, using combined air quality and meteorological observations. Hourly data resulting in 3319 observations were used in training, testing, and validating the developed machine learning prediction models. Among the tested machine learning algorithms, namely K-Nearest Neighbours (KNN), Support Vector Regression (SVR), Random Forest (RF), Multi-Layer Perceptron (MLP), and Decision Tree (DT), KNN was selected as the best model based on its validation performance, achieving R2 = 0.85, RMSE = 1.73 °C and MAE = 1.19 °C in the testing stage. This accuracy mainly reflects the estimation of temperature within the observed period. Shapley Additive Explanations (SHAP) revealed the black-box nature and found that CO, SO2, O3, and wind direction were the most influential variables contributing to atmospheric temperature predictions. The findings can then be used as a foundation for any future studies relating to aviation-related emissions, greenhouse gases, air quality, and atmospheric temperature. This study demonstrates the potential for developing similar prediction models for other busy airports and then incorporating necessary policy decisions to mitigate any adverse effects.Keywords
This publication has 40 references indexed in Scilit:
- Smart grid electricity demand forecasting using weather-based MIDAS and machine learning models: the case of New ZealandJapanese Journal of Statistics and Data Science, 2026
- Game-Theoretic Explainable AI for Ensemble-Boosting Models in Early Malware Prediction for Computer SystemsInternational Journal of Computational Intelligence Systems, 2025
- Air Quality Index Prediction: Comparative Study Based on Various Hyper Parameter TuningIranian Journal of Science, 2025
- Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced PredictionWater, Air, & Soil Pollution, 2025
- Forecasting of monthly air quality index and understanding the air pollution in the urban city, India based on machine learning models and cross-validationJournal of Atmospheric Chemistry, 2024
- Increased impacts of aircraft activities on PM2.5 concentration and human health in ChinaEnvironment International, 2024
- Revisiting the importance of temperature, weather and air pollution variables in heat-mortality relationships with machine learningEnvironmental Science and Pollution Research, 2024
- Air quality prediction by machine learning models: A predictive study on the indian coastal city of VisakhapatnamChemosphere, 2023
- A systematic review of the impact of commercial aircraft activity on air quality near airportsCity and Environment Interactions, 2021
- Identifying the impact of large urban airports on local air quality by nonparametric regressionAtmospheric Environment, 2004