[Paper review] An ensemble -based model of PM2.5 concentration across the contiguous United States with high spatio temporal resolution

Notion Web 페이지 게시

[Main Idea]

Gradient Boosting, Random Forest, Neural Network 기반의 Ensemble 학습을 통해 1KM x 1KM 격자 단위의 미국 전역에 대한 Daily PM₂.₅ Prediction을 수행

[Highlights]

• An ensemble model integrates three machine learning algorithms and estimates PM2.5.

• Satellite measurements, land-use terms, and many variables were predictors.

• Model predicts daily PM2.5 at 1 km × 1 km grid cells in the entire United States.

• Model predictions were downscaled to 100 m × 100 m level.

• Monthly uncertainty level of prediction was also estimated.