Scholarlink

The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R2), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nemarugommula Pranav,
  • Vishal Ganapathy,
  • B. Geedhavarshini,
  • Kashmira Nigade,
  • S. Shreya,
  • Jagalingam Pushparaj,
  • Sujay Raghavendra Naganna,
  • Sindhu Sreeranga

摘要

The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R2), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.