Sign in Subscribe
Air pollution

Enhanced Air Quality Prediction Using Artificial Intelligence and Principal Component Analysis for Sustainable Development Goals

Strategic Insights

— 1 min read

Research conducted at the National Taiwan University of Science and Technology has demonstrated the effectiveness of using artificial intelligence and principal component analysis in predicting air quality in Rouen, France. The study aimed to address the impact of poor air quality on climate action (SDG 13) by analyzing raw sensor measurement records. The researchers used feature extraction to increase the accuracy of predictions, achieving remarkable results, with a 96.72% to 99.35% improvement compared to similar experiments using confirmed data.

Key Takeaways:

  • The study employed principal component analysis to increase the accuracy of air quality predictions using actual sensor data from Rouen, France.
  • The research used feature extraction to reduce the risk of overfitting by selecting suitable data preparation methods.
  • The five machine learning and deep learning models used in the study showed a significant improvement in performance, with an increase of 96.72% to 99.35% compared to experiments using confirmed data.
  • The primary goal of the research was to address the impact of poor air quality on climate action (SDG 13) by analyzing raw sensor measurement records.
  • The study highlights the importance of feature extraction and data preparation in improving the accuracy of machine learning and deep learning models.
  • The researchers used a dataset containing nine observations from October 2021 to March 2022, which was prepared and analyzed using principal component analysis.
  • The results of the study demonstrate the potential of using artificial intelligence and principal component analysis in predicting air quality and addressing climate action.

Statistics:

  • 96.72% to 99.35% improvement in performance of the five machine learning and deep learning models used in the study.
  • 9 observations from October 2021 to March 2022 in the dataset used by the researchers.
  • The study used five machine learning and deep learning models to demonstrate the effectiveness of feature extraction and data preparation.

Sources:

  • E3S Web of Conferences (2025). An enhanced air quality prediction of low-cost air quality sensors dataset in Rouen (France) using artificial intelligence with principal component analysis as feature learning for Sustainable Development Goals (SDGs). E3S Web of Conferences, 2025, 640():01019.
  • National Taiwan University of Science and Technology Researchers Update Understanding of Sustainable Development [An enhanced air quality prediction of low-cost air quality sensors dataset in Rouen (France) using artificial intelligence with ...]. Ecology, Environment & Conservation. September 19, 2025; p 187.

Read more