Physics‐Guided CNN‐LSTM Model With Multi‐Head Attention for Aerosol Optical Depth Prediction
Abstract Accurate aerosol optical depth (AOD) prediction remains challenging due to complex aerosol‐radiation interactions and highly variable spatio‐temporal patterns. Three critical scientific issues motivate this work: understanding whether and how physical principles can enhance deep learning predictions, identifying which aerosol properties most ...
Liu Zeyang +7 more
wiley +1 more source
Application of CMAQ at a hemispheric scale for atmospheric mercury simulations [PDF]
Abstract. Application of a regional model to study of fate and transport of a global pollutant such as mercury in the atmosphere can be challenging and improper usage of models may lead to questionable results. The difficulties in such application stem from the fact that regional models are usually used in relatively small domains and rely heavily on ...
Pongprueksa, P. +5 more
openaire +2 more sources
How Will China's Surface Ozone Evolve Under Carbon Neutrality Target and Global Climate Warming?
Abstract Surface ozone (O3) has complex relationships with its precursors and is also highly sensitive to meteorological variation and climate change. In China, ground‐level ozone pollution remains a persistent air quality concern despite decreasing concentrations of other air pollutants in recent years.
Yue Tan +5 more
wiley +1 more source
An investigation into atmospheric nitrous acid (HONO) processes in South Korea [PDF]
Nitrous acid (HONO) is a main precursor of hydroxyl radicals (OH), which contribute to the formation of numerous secondary air pollutants in the troposphere.
K. Kim +10 more
doaj +1 more source
Preparation of GEOS-Chem Emissions from CMAQ
This notebook takes SMOKE outputs, which are CMAQ-ready emissions and converts them for use in GEOS-Chem. The tutorial uses "gridded reports", which contain annual data. To make this operational, you instead repeat the process for each month.
Henderson, Barron, Freese, Lyssa
core +1 more source
LSTM‐Based Hybrid Deep Learning Models for Visibility Prediction: A Data‐Driven Approach
Accurate visibility prediction is crucial for aviation safety, transportation operations, and environmental monitoring. This study proposes a data‐driven forecasting framework based on long short‐term memory (LSTM) neural networks and their hybrid variants.
Hsiu-Min Chuang +3 more
wiley +1 more source
Investigation of NOx emissions and NOx-related chemistry in East Asia using CMAQ-predicted and GOME-derived NO2 columns [PDF]
In this study, NO2 columns from the US EPA Models-3/CMAQ model simulations carried out using the 2001 ACE-ASIA (Asia Pacific Regional Aerosol Characterization Experiment) emission inventory over East Asia were compared with the GOME-derived NO2 columns ...
J. Y. Kim +9 more
doaj
Constraining African Fire CO2 Emissions During 2015–2016 Using Satellite XCO2 Retrievals
Abstract Fire CO2 emissions are a critical component of the global carbon cycle, yet their estimates remain highly uncertain. This study introduces a satellite‐constrained inversion framework that jointly optimizes fire emissions and net ecosystem exchange using OCO‐2 XCO2 retrievals.
Guoyuan Lv +13 more
wiley +1 more source
Evaluation of the Offline-Coupled Gfs-Cmaq in Recent Wildfires in Northern California
As wildfires become more frequent and severe under climate change, there is a growing need to simulate the impact of fires on air quality and human health using numerical models.
Leung, Joyce
core +1 more source
Regional, state, and local environmental regulatory agencies often use Eulerian models to investigate the potential impacts on pollutant deposition and air quality from changes in land use, anthropogenic and natural emissions, and climate.
Patrick C. Campbell +2 more
doaj +1 more source

