Enhancing carbon emission reduction strategies using OCO and ICOS data
(2025) In Scientific Reports 15.- Abstract
We propose a methodology to enhance local CO2 monitoring by integrating satellite data from the Orbiting Carbon Observatories (OCO-2 and OCO-3) with ground-level observations from the Integrated Carbon Observation System (ICOS) and weather data from the ECMWF Reanalysis v5 (ERA5). Unlike traditional methods that downsample national data, our approach uses multimodal data fusion for high-resolution CO2 estimations. We employ weighted K-nearest neighbor (KNN) interpolation with machine learning models to predict ground-level CO2 from satellite measurements, achieving a Root Mean Squared Error of 3.58 ppm. Our results show the effectiveness of integrating diverse data sources in capturing local emission... (More)
We propose a methodology to enhance local CO2 monitoring by integrating satellite data from the Orbiting Carbon Observatories (OCO-2 and OCO-3) with ground-level observations from the Integrated Carbon Observation System (ICOS) and weather data from the ECMWF Reanalysis v5 (ERA5). Unlike traditional methods that downsample national data, our approach uses multimodal data fusion for high-resolution CO2 estimations. We employ weighted K-nearest neighbor (KNN) interpolation with machine learning models to predict ground-level CO2 from satellite measurements, achieving a Root Mean Squared Error of 3.58 ppm. Our results show the effectiveness of integrating diverse data sources in capturing local emission patterns, highlighting the value of high-resolution atmospheric transport models. The developed model improves the granularity of CO2 monitoring, providing precise insights for targeted carbon mitigation strategies, and represents a novel application of neural networks and KNN in environmental monitoring, adaptable to various regions and temporal scales.
(Less)
- author
- Åström, Oskar
LU
; Geldhauser, Carina
; Grillitsch, Markus
LU
; Hall, Ola
LU
and Sopasakis, Alexandros
LU
- organization
-
- LTH Profile Area: Engineering Health
- Computer Vision and Machine Learning (research group)
- eSSENCE: The e-Science Collaboration
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- Centre for Mathematical Sciences
- Department of Human Geography
- LU Profile Area: Natural and Artificial Cognition
- LU Profile Area: Nature-based future solutions
- Partial differential equations (research group)
- Numerical Analysis and Scientific Computing (research group)
- publishing date
- 2025
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Reports
- volume
- 15
- article number
- 36297
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:105019063933
- pmid:41107401
- pmid:41107401
- ISSN
- 2045-2322
- DOI
- 10.1038/s41598-025-22022-1
- language
- English
- LU publication?
- yes
- id
- 004335c8-ee5c-4c33-a31f-03806e4554dd
- date added to LUP
- 2025-10-23 06:32:04
- date last changed
- 2026-01-24 03:16:14
@article{004335c8-ee5c-4c33-a31f-03806e4554dd,
abstract = {{<p>We propose a methodology to enhance local CO<sub>2</sub> monitoring by integrating satellite data from the Orbiting Carbon Observatories (OCO-2 and OCO-3) with ground-level observations from the Integrated Carbon Observation System (ICOS) and weather data from the ECMWF Reanalysis v5 (ERA5). Unlike traditional methods that downsample national data, our approach uses multimodal data fusion for high-resolution CO<sub>2</sub> estimations. We employ weighted K-nearest neighbor (KNN) interpolation with machine learning models to predict ground-level CO<sub>2</sub> from satellite measurements, achieving a Root Mean Squared Error of 3.58 ppm. Our results show the effectiveness of integrating diverse data sources in capturing local emission patterns, highlighting the value of high-resolution atmospheric transport models. The developed model improves the granularity of CO<sub>2</sub> monitoring, providing precise insights for targeted carbon mitigation strategies, and represents a novel application of neural networks and KNN in environmental monitoring, adaptable to various regions and temporal scales.</p>}},
author = {{Åström, Oskar and Geldhauser, Carina and Grillitsch, Markus and Hall, Ola and Sopasakis, Alexandros}},
issn = {{2045-2322}},
language = {{eng}},
publisher = {{Nature Publishing Group}},
series = {{Scientific Reports}},
title = {{Enhancing carbon emission reduction strategies using OCO and ICOS data}},
url = {{http://dx.doi.org/10.1038/s41598-025-22022-1}},
doi = {{10.1038/s41598-025-22022-1}},
volume = {{15}},
year = {{2025}},
}