What type of study is this?

August 17, 2025Atmospheric measurement techniquesOpen Access

Hourly surface nitrogen dioxide retrieval from GEMS tropospheric vertical column densities: benefit of using time-contiguous input features for machine learning models

View Full Paper

Ask AI

Bookmark

Authors

JGJanek GödekeUniversity of Bremen ARAndreas RichterUniversity of Bremen KLKezia LangeUniversity of Bremen

Discussion

Member takes

Implication

Analysis reveals significant improvements in nitrogen dioxide predictions in South Korea using machine learning models, suggesting input time-contiguity enhances performance.

Key Points

Hourly surface nitrogen dioxide concentration improves with time-contiguous machine learning inputs, leading to better predictions.
Pearson correlation and mean square error metrics show performance gains of 4.5-15% for machine learning models using GEMS data.
Random forests and linear regression methods utilized to analyze tropospheric nitrogen dioxide levels from GEMS observations.
Spatial cross-validation helps ensure the reliability of the trained models across diverse locations in South Korea.

Cite This Study

Gödeke et al. (2025) studied this question.

synapsesocial.com/papers/68a36f7d0a429f7973331f8a https://doi.org/10.5194/amt-18-3747-2025

View Full Paper

Ask AI

Bookmark

Implication

Analysis reveals significant improvements in nitrogen dioxide predictions in South Korea using machine learning models, suggesting input time-contiguity enhances performance.

Hourly surface nitrogen dioxide retrieval from GEMS tropospheric vertical column densities: benefit of using time-contiguous input features for machine learning models

Discussion

Member takes

Implication

Key Points

Cite This Study

Hourly surface nitrogen dioxide retrieval from GEMS tropospheric vertical column densities: benefit of using time-contiguous input features for machine learning models

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider