Abstract
Abstract. A neural-network-based method, quantile regression neural networks (QRNNs), is proposed as a novel approach to estimating the a posteriori distribution of Bayesian remote sensing retrievals. The advantage of QRNNs over conventional neural network retrievals is that they learn to predict not only a single retrieval value but also the associated, case-specific uncertainties. In this study, the retrieval performance of QRNNs is characterized and compared to that of other state-of-the-art retrieval methods. A synthetic retrieval scenario is presented and used as a validation case for the application of QRNNs to Bayesian retrieval problems. The QRNN retrieval performance is evaluated against Markov chain Monte Carlo simulation and another Bayesian method based on Monte Carlo integration over a retrieval database. The scenario is also used to investigate how different hyperparameter configurations and training set sizes affect the retrieval performance. In the second part of the study, QRNNs are applied to the retrieval of cloud top pressure from observations by the Moderate Resolution Imaging Spectroradiometer (MODIS). It is shown that QRNNs are not only capable of achieving similar accuracy to standard neural network retrievals but also provide statistically consistent uncertainty estimates for non-Gaussian retrieval errors. The results presented in this work show that QRNNs are able to combine the flexibility and computational efficiency of the machine learning approach with the theoretically sound handling of uncertainties of the Bayesian framework. Together with this article, a Python implementation of QRNNs is released through a public repository to make the method available to the scientific community.
Highlights
The retrieval of atmospheric quantities from remote sensing measurements constitutes an inverse problem that generally does not admit a unique, exact solution
The results presented indicate that quantile regression neural networks (QRNNs) can, at least under idealized conditions, be used to estimate the a posteriori distribution of Bayesian retrieval problems
Quantile regression neural networks have been proposed as a method to estimate a posteriori distributions of Bayesian remote sensing retrievals
Summary
The retrieval of atmospheric quantities from remote sensing measurements constitutes an inverse problem that generally does not admit a unique, exact solution. In the Bayesian formulation (Rodgers, 2000), the solution of the inverse problem is given by the a posteriori distribution p(x|y), i.e., the conditional distribution of the retrieval quantity x given the observation y. The posterior distribution represents all available knowledge about the retrieval quantity x after the measurement, accounting for all considered retrieval uncertainties. Bayes’ theorem states that the a posteriori distribution is proportional to the product p(y|x)p(x) of the a priori distribution p(x) and the conditional probability of the observed measurement p(y|x). The a priori distribution p(x) represents knowledge about the quantity x that is available before the measurement and can be used to aid the retrieval with supplementary information
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
