Publicação
Employing explainable AI techniques for air pollution: an ante-hoc and post-hoc approach in dioxide nitrogen forecasting
| Resumo: | With the advancement of Artificial Intelligence (AI) techniques in different areas of our society, namely with the use of Machine and Deep Learning models, some challenges must be faced. One of these challenges is responding to the lack of transparency in these models, which makes it difficult to explain the results they obtained. This research centres on predicting the concentration of nitrogen dioxide (NO2), a critical air pollutant, using a Long Short-Term Memory model (LSTM) along with applying Explainable AI (XAI) techniques to understand the predictions made. Two explainability techniques were applied: an ante-hoc approach with an Attention layer and a post-hoc approach using Shapley Additive Explanations (SHAP). The Attention layer identified carbon monoxide (CO) and NO2 as the most powerful features, while the SHAP analysis highlighted NO2 as the predominant contributor to the predictions, followed by particulate matter (PM2.5) and CO. The results demonstrated that the target value significantly impacts the model’s forecast for both XAI techniques. |
|---|---|
| Autores principais: | Oliveira, P. |
| Outros Autores: | Franco, Francisco; Bessa, Afonso; Durães, Dalila; Novais, Paulo |
| Assunto: | Air pollution Explainable artificial intelligence Long short-term memory Time series |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso restrito |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | With the advancement of Artificial Intelligence (AI) techniques in different areas of our society, namely with the use of Machine and Deep Learning models, some challenges must be faced. One of these challenges is responding to the lack of transparency in these models, which makes it difficult to explain the results they obtained. This research centres on predicting the concentration of nitrogen dioxide (NO2), a critical air pollutant, using a Long Short-Term Memory model (LSTM) along with applying Explainable AI (XAI) techniques to understand the predictions made. Two explainability techniques were applied: an ante-hoc approach with an Attention layer and a post-hoc approach using Shapley Additive Explanations (SHAP). The Attention layer identified carbon monoxide (CO) and NO2 as the most powerful features, while the SHAP analysis highlighted NO2 as the predominant contributor to the predictions, followed by particulate matter (PM2.5) and CO. The results demonstrated that the target value significantly impacts the model’s forecast for both XAI techniques. |
|---|