Low-level liquid cloud properties during ORACLES retrieved using airborne polarimetric measurements and a neural network algorithm
<p>In this study we developed a neural network (NN) that can be used to retrieve cloud microphysical properties from multiangular and multispectral polarimetric remote sensing observations. This effort builds upon our previous work, which explored the sensitivity of neural network input, archi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2020-06-01
|
| Series: | Atmospheric Measurement Techniques |
| Online Access: | https://www.atmos-meas-tech.net/13/3447/2020/amt-13-3447-2020.pdf |
| Summary: | <p>In this study we developed a neural network (NN) that can be used to retrieve cloud microphysical
properties from multiangular and multispectral polarimetric remote sensing observations. This
effort builds upon our previous work, which explored the sensitivity of neural network input,
architecture, and other design requirements for this type of remote sensing problem. In particular
this work introduces a framework for appropriately weighting total and polarized reflectances,
which have vastly different magnitudes and measurement uncertainties. The NN is trained using an
artificial training set and applied to research scanning polarimeter (RSP) data obtained during
the ORACLES field campaign (ObseRvations of Aerosols above CLouds and their intEractionS). The
polarimetric RSP observations are unique in that they observe the same cloud from a very large
number of angles within a variety of spectral bands, resulting in a large dataset that can be
explored rapidly with a NN approach. The usefulness of applying a NN to a dataset such as this one
stems from the possibility of rapidly obtaining a retrieval that could be subsequently applied as
a first guess for slower but more rigorous physical-based retrieval algorithms. This approach
could be particularly advantageous for more complicated atmospheric retrievals – such as when an
aerosol layer lies above clouds like in ORACLES. For RSP observations obtained during ORACLES
2016, comparisons between the NN and standard parametric polarimetric (PP) cloud retrieval give
reasonable results for droplet effective radius (<span class="inline-formula"><i>r</i><sub>e</sub></span>: <span class="inline-formula"><i>R</i>=0.756</span>,
<span class="inline-formula">RMSE=1.74 µm</span>) and cloud optical thickness (<span class="inline-formula"><i>τ</i></span>: <span class="inline-formula"><i>R</i>=0.950</span>,
<span class="inline-formula">RMSE=1.82</span>). This level of statistical agreement is shown to be similar to comparisons
between the two most well-established cloud retrievals, namely, the polarimetric and the
bispectral total reflectance cloud retrievals. The NN retrievals from the ORACLES 2017 dataset
result in retrievals of <span class="inline-formula"><i>r</i><sub>e</sub></span> (<span class="inline-formula"><i>R</i>=0.54</span>, <span class="inline-formula">RMSE=4.77 µm</span>) and <span class="inline-formula"><i>τ</i></span>
(<span class="inline-formula"><i>R</i>=0.785</span>, <span class="inline-formula">RMSE=5.61</span>) that behave much more poorly. In particular we found that our NN
retrieval approach does not perform well for thin (<span class="inline-formula"><i>τ</i><3</span>), inhomogeneous, or broken clouds. We
also found that correction for above-cloud atmospheric absorption improved the NN retrievals
moderately – but retrievals without this correction still behaved similarly to existing cloud
retrievals with a slight systematic offset.</p> |
|---|---|
| ISSN: | 1867-1381 1867-8548 |