Observations & remote sensing

Uncertainty‐Aware Machine Learning Bias Correction and Filtering for OCO‐2: 1

Steffen Mauceri, William Keely, Joshua L. Laughner, C. O’Dell, Steven T. Massie, Robert Nelson, David Baker, Matthäus Kiel, Otto Lamminpää, Jonathan Hobbs, Abhishek Chatterjee, Thomas E. Taylor et al.

Earth and Space Science · 01 July 2025 · California Institute of Technology (Caltech), Colorado State University (incl. CIRA), NASA, NSF NCAR / UCAR, University of Oklahoma (AI2ES)

PaperPDF

In one sentence. Random forest bias correction for OCO-2 column CO2 retrievals reduces unphysical variability and agrees better with TCCON, with quantified uncertainty for operational use.

Abstract

Abstract The Orbiting Carbon Observatory‐2 (OCO‐2) makes space‐based radiance measurements of reflected sunlight. Using a physics‐based retrieval algorithm, these measurements are inverted to estimate column‐averaged atmospheric carbon dioxide dry‐air mole fractions (XCO 2 ). However, biases are present in the retrieved XCO 2 due to sensor calibration errors and discrepancies between the physics‐based retrieval and nature. We propose a Random Forest (RF), a non‐linear, interpretable machine learning (ML) technique, to correct these biases. The approach is rigorously validated, comes with quantified uncertainties, and is derived independent of carbon flux models. Compared to the operational approach, our method reduces unphysical variability over land and ocean and shows closer agreement with independent ground‐based observations from the Total Carbon Column Observing Network. The RF‐bias correction is suitable for integration into the operational processing pipeline for the next version of OCO‐2 products, pending additional testing and validation. It is inherently generalizable to other existing and planned greenhouse gas monitoring missions. This paper (Part 1) describes the RF bias correction, while a second paper (Part 2) describes the development of a data filtering strategy specifically designed for a subset of retrievals exhibiting irreducible errors that remain inadequately corrected by the ML bias correction.

Labels

Topic

Observations & remote sensing, Explainability, uncertainty & physics

Type

New model or method

Method

Classical ML (trees, GP, linear, kernels)

Domain

Global

Data

Satellite, Station / in-situ

Status

Pre-operational / experimental

Identifiers

DOI:10.1029/2025ea004328 OpenAlex:W4412834827

Added

2026-10-22

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.