Downscaled XCO2 Estimation Using Data Fusion and AI-Based Spatio-Temporal Models
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers Inc.
Abstract
One of the well-known greenhouse gases (GHGs) produced by anthropogenic human activity is carbon dioxide (CO<inf>2</inf>). Understanding the carbon cycle and how negatively it affects the ecosystem requires analysis of the rise in CO<inf>2</inf> concentration. This work aims to map CO<inf>2</inf> concentration for the entire surface, making it useful for regional carbon cycle analysis. Here, column-averaged CO<inf>2</inf> dry mole fraction, called XCO<inf>2</inf>, measured by the orbiting carbon observatory-2 (OCO-2) satellite, is used. Because of spectral interference by the clouds and aerosols, there are many missing footprints in the Level-2 swath of OCO-2, making it disruptive to understand any assessment related to the carbon cycle. The objective of this work is to predict 1 km2 XCO<inf>2</inf> using data resampling and machine learning models. This work achieves a minimum mean absolute error (MAE) and root mean square error (RMSE) of 0.3990 and 0.8090 ppm, using the monthly models. © 2004-2012 IEEE.
Description
Keywords
Analytical models, Data fusion, Greenhouse gases, Interpolation, Learning systems, Orbits, Remote sensing, Satellites, >, Computational modelling, Data resampling, Down-scaling, Gap filling, Kriging, Land cover, Machine-learning, ODIAC, Orbiting carbon observatory-2, Predictive models, Regressor, Resampling, SIF<sub xmlns:ali=", Spatial resolution, XCO<sub xmlns:ali=", Xmlns:mml=", Xmlns:xlink=", Xmlns:xsi=", Carbon dioxide, artificial intelligence, carbon cycle, downscaling, estimation method, human activity, interpolation, kriging, machine learning, satellite imagery, spatiotemporal analysis
Citation
IEEE Geoscience and Remote Sensing Letters, 2024, 21, , pp. 1-5