High-Resolution Estimation of Daily PM<sub>2.5</sub> Levels in the Contiguous US Using Bi-LSTM with Attention

High-Resolution Estimation of Daily PM<sub>2.5</sub> Levels in the Contiguous US Using Bi-LSTM with Attention

Estimating surface-level PM<sub>2.5</sub> concentrations at any given location is crucial for public health monitoring and cohort studies. Existing models and datasets for this purpose have limited precision, especially on high-concentration days. Additionally, due to the lack of open-so...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongying Wang, James L. Crooks, Elizabeth Anne Regan, Morteza Karimzadeh
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Remote Sensing
Subjects:
air pollution
PM<sub>2.5</sub>
deep learning
spatiotemporal modeling
public dataset
Online Access:https://www.mdpi.com/2072-4292/17/1/126
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Estimating surface-level PM<sub>2.5</sub> concentrations at any given location is crucial for public health monitoring and cohort studies. Existing models and datasets for this purpose have limited precision, especially on high-concentration days. Additionally, due to the lack of open-source code, generating estimates for other areas and time periods remains cumbersome. We developed a novel deep learning-based model that improves the surface-level PM<sub>2.5</sub> concentration estimates by capitalizing on the temporal dynamics of air quality. Specifically, we improve the estimation precision by developing a Long Short-Term Memory (LSTM) network with Attention and integrating multiple data sources, including in situ measurements, remotely sensed data, and wildfire smoke density observations, which improve the model’s ability to capture high-concentration events. We rigorously evaluate the model against existing products, demonstrating a 2.2% improvement in overall RMSE, and a 9.8% reduction in RMSE on high-concentration days, highlighting the superior performance of our approach, particularly on high-concentration days. Using the model, we have produced a comprehensive dataset of PM<sub>2.5</sub> estimates from 2005 to 2021 for the contiguous United States and are releasing an open-source framework to ensure reproducibility and facilitate further adaptation in air quality studies.
ISSN:2072-4292

Similar Items