Skip to content
naulon

Not checkedNot checked for notices yet.

A new machine-learning-based analysis for improving satellite-retrieved atmospheric composition data: OMI SO 2 as an example

C. Li, C. Li, J. Joiner and 5 more

Atmospheric Measurement Techniques · 2022

doi:10.5194/amt-15-5497-2022 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

<p>Despite recent progress, satellite retrievals of anthropogenic SO<span class="inline-formula"><sub>2</sub></span> still suffer from relatively low signal-to-noise ratios. In this study, we demonstrate a new machine learning data analysis method to improve the quality of satellite SO<span class="inline-formula"><sub>2</sub></span> products. In the absence of large ground-truth datasets for SO<span class="inline-formula"><sub>2</sub></span>, we start from SO<span class="inline-formula"><sub>2</sub></span> slant column densities (SCDs) retrieved from the Ozone Monitoring Instrument (OMI) using a data-driven, physically based algorithm and calculate the ratio between the SCD and the root mean square (rms) of the fitting residuals for each pixel. To build the training data, we select presumably clean pixels with small SCD <span class="inline-formula"><math xmlns="http://www.w3.org/1998/Math/MathML" id="M7" display="inline" overflow="scroll" dspmath="mathml"><mo>/</mo></math><span><svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="8pt" height="14pt" class="svg-formula" dspmath="mathimg" md5hash="36bd7baae116a5efc17e692d563c2b51"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="amt-15-5497-2022-ie00001.svg" width="8pt" height="14pt" src="amt-15-5497-2022-ie00001.png"/></svg:svg></span></span> rms ratios (SRRs) and set their target SCDs to zero. For polluted pixels with relatively large SRRs, we set the target to the original retrieved SCDs. We then train neural networks (NNs) to reproduce the target SCDs using predictors including SRRs for individual pixels, solar zenith, viewing zenith and phase angles, scene reflectivity, and O<span class="inline-formula"><sub>3</sub></span> column amounts, as well as the monthly mean SRRs. For data analysis, we employ two NNs: (1) one trained daily to produce analyzed SO<span class="inline-formula"><sub>2</sub></span> SCDs for polluted pixels each day and (2) the other trained once every month to produce analyzed SCDs for less polluted pixels for the entire month. Test results for 2005 show that our method can significantly reduce noise and artifacts over background regions. Over polluted areas, the monthly mean NN-analyzed and original SCDs generally agree to within <span class="inline-formula">±15</span> %, indicating that our method can retain SO<span class="inline-formula"><sub>2</sub></span> signals in the original retrievals except for large volcanic eruptions. This is further confirmed by running both the NN-analyzed and original SCDs through a top-down emission algorithm to estimate the annual SO<span class="inline-formula"><sub>2</sub></span> emissions for <span class="inline-formula">∼500</span> anthropogenic sources, with the two datasets yielding similar results. We also explore two alternative approaches to the NN-based analysis method. In one, we employ a simple linear interpolation model to analyze the original SCD retrievals. In the other, we develop a PCA–NN algorithm that uses OMI measured radiances, transformed and dimension-reduced with a principal component analysis (PCA) technique, as inputs to NNs for SO<span class="inline-formula"><sub>2</sub></span> SCD retrievals. While the linear model and the PCA–NN algorithm can reduce retrieval noise, they both underestimate SO<span class="inline-formula"><sub>2</sub></span> over polluted areas. Overall, the results presented here demonstrate that our new data analysis method can significantly improve the quality of existing OMI SO<span class="inline-formula"><sub>2</sub></span> retrievals. The method can potentially be adapted for other sensors and/or species and enhance the value of satellite data in air quality research and applications.</p>

Abstract licence: CC BY

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.