scholarly journals A neural network approach to estimating a posteriori distributions of Bayesian retrieval problems

2018 ◽  
Vol 11 (8) ◽  
pp. 4627-4643 ◽  
Author(s):  
Simon Pfreundschuh ◽  
Patrick Eriksson ◽  
David Duncan ◽  
Bengt Rydberg ◽  
Nina Håkansson ◽  
...  
Keyword(s):  
Neural Network ◽  
Monte Carlo ◽  
Monte Carlo Integration ◽  
A Posteriori ◽  
Retrieval Performance ◽  
Neural Network Approach ◽  
Novel Approach ◽  
Uncertainty Estimates ◽  
Non Gaussian ◽  
Similar Accuracy

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.

scholarly journals A neural network approach to estimate a posteriori distributions of Bayesian retrieval problems

2018 ◽  
Author(s):  
Simon Pfreundschuh ◽  
Patrick Eriksson ◽  
David Duncan ◽  
Bengt Rydberg ◽  
Nina Håkansson ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Monte Carlo ◽  
Monte Carlo Integration ◽  
A Posteriori ◽  
Retrieval Performance ◽  
Neural Network Approach ◽  
Novel Approach ◽  
Uncertainty Estimates ◽  
Similar Accuracy

Abstract. This work is concerned with the retrieval of physical quantities from remote sensing measurements. A neural network based method, Quantile Regression Neural Networks (QRNNs), is proposed as a novel approach to estimate the a posteriori distribution of Bayesian remote sensing retrievals. The advantage of QRNNs over conventional neural network retrievals is that they not only learn to predict 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 as 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.

scholarly journals Content based Image Retrieval System using Combination of Color and Shape Features, and Siamese Neural Network

2019 ◽  
Vol 9 (2S) ◽  
pp. 71-77
Keyword(s):  
Neural Network ◽  
World Wide ◽  
Retrieval System ◽  
Image Features ◽  
Shape Features ◽  
Retrieval Performance ◽  
Novel Approach ◽  
Learning Technique ◽  
Image Retrieval System ◽  
Similar Images

With an advent of technologya huge collection of digital images is formed as repositories on world wide web (WWW). The task of searching for similar images in the repository is difficult. In this paper, retrieval of similar images from www is demonstrated with the help of combination of image features as color and shape and then using Siamese neural network which is constructed to the requirement as a novel approach. Here, one-shot learning technique is used to test the Siamese Neural Network model for retrieval performance. Various experiments are conducted with both the methods and results obtained are tabulated. The performance of the system is evaluated with precision parameter and which is found to be high.Also, relative study is made with existing works.

scholarly journals Pesquisa sobre empresas multinacionais brasileiras: análises descritivas e preditivas

Internext ◽  
2015 ◽  
Vol 10 (2) ◽  
pp. 64
Author(s):  
Mario Henrique Ogasavara ◽  
Gilmar Masiero ◽  
Marcio De Oliveira Mota ◽  
Lucas Souza
Keyword(s):  
Neural Network ◽  
Citation Analysis ◽  
Multinational Enterprises ◽  
Descriptive Analysis ◽  
Predictive Analysis ◽  
The Novel ◽  
Neural Network Approach ◽  
Novel Approach ◽  
The Neural Network ◽  
Eclectic Paradigm

<p><em>T</em>his study attempts to review recent research on the internationalization of Brazilian multinational enterprises (I-BMNEs) based on an analysis of the 174 published articles that have appeared in international and Brazilian academic journals, books, and conference proceedings. The descriptive analysis seeks to undertake a citation analysis as well as to provide a typology of the leading researchers and school affiliations, the predominating theoretical and methodological approaches. This paper also proposes a predictive analysis based on a novel approach of neural network in order to classify features of a manuscript and predict the fit of its publication. We find that the research on I-BMNEs is driven by a small number of leading institutions and researchers which utilize case studies as their research method and have the Uppsala and Eclectic Paradigm models as theoretical framework. The citation analysis shows that authors of foreigner origin are cited from journal publications or translated books. The novel technique and design of the neural network approach was modeled to fit for bibliometric studies and the outcomes of the predictive analysis were able to classify correctly 56.25% of the manuscripts. We conclude by providing a set of recommendations to advance the research on I-BMNEs.</p>

scholarly journals XCO<sub>2</sub> estimates from the OCO-2 measurements using a neural network approach

2021 ◽  
Vol 14 (1) ◽  
pp. 117-132
Author(s):  
Leslie David ◽  
François-Marie Bréon ◽  
Frédéric Chevallier
Keyword(s):  
Neural Network ◽  
Surface Pressure ◽  
Atmospheric Transport ◽  
Retrieval Algorithm ◽  
Neural Network Approach ◽  
Weather Model ◽  
Pros And Cons ◽  
Air Sample ◽  
Similar Accuracy ◽  
Better Than

Abstract. The Orbiting Carbon Observatory (OCO-2) instrument measures high-resolution spectra of the sun's radiance reflected at the earth's surface or scattered in the atmosphere. These spectra are used to estimate the column-averaged dry air mole fraction of CO2 (XCO2) and the surface pressure. The official retrieval algorithm (NASA's Atmospheric CO2 Observations from Space retrievals, ACOS) is a full-physics algorithm and has been extensively evaluated. Here we propose an alternative approach based on an artificial neural network (NN) technique. For training and evaluation, we use as reference estimates (i) the surface pressures from a numerical weather model and (ii) the XCO2 derived from an atmospheric transport simulation constrained by surface air-sample measurements of CO2. The NN is trained here using real measurements acquired in nadir mode on cloud-free scenes during even-numbered months and is then evaluated against similar observations during odd-numbered months. The evaluation indicates that the NN retrieves the surface pressure with a root-mean-square error better than 3 hPa and XCO2 with a 1σ precision of 0.8 ppm. The statistics indicate that the NN trained with a representative set of data allows excellent accuracy that is slightly better than that of the full-physics algorithm. An evaluation against reference spectrophotometer XCO2 retrievals indicates similar accuracy for the NN and ACOS estimates, with a skill that varies among the various stations. The NN–model differences show spatiotemporal structures that indicate a potential for improving our knowledge of CO2 fluxes. We finally discuss the pros and cons of using this NN approach for the processing of the data from OCO-2 or other space missions.

scholarly journals Artificial neural network for Gaussian and non-Gaussian random fatigue loading analysis

2019 ◽  
Vol 233 (23-24) ◽  
pp. 7525-7544
Author(s):  
JF Durodola
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Frequency Domain ◽  
Fatigue Loading ◽  
Neural Network Approach ◽  
Frequency Domain Methods ◽  
Artificial Neural ◽  
Non Gaussian ◽  
Random Fatigue ◽  
Loading Analysis

There has been a lot of work done on the analysis of Gaussian loading analysis perhaps because its occurrence is more common than non-Gaussian loading problems. It is nevertheless known that non-Gaussian load occurs in many instances especially in various forms of transport, land, sea and space. Part of the challenge with non-Gaussian loading analysis is the increased number of variables that are needed to model the loading adequately. Artificial neural network approach provides a versatile means to develop models that may require many input variables in order to achieve applicable predictive generalisation capabilities. Artificial neural network has been shown to perform much better than existing frequency domain methods for random fatigue loading under stationary Gaussian load forms especially when mean stress effects are included. This paper presents an artificial neural network model with greater predictive capability than existing frequency domain methods for both Gaussian and non-Gaussian loading analysis. Both platykurtic and leptokurtic non-Gaussian loading cases were considered to demonstrate the scope of application. The model was also validated with available SAE experimental data, even though the skewness and kurtosis of the signal in this case were mild.

A machine learning approach for faster and more accurate precipitation retrievals

2020 ◽  
Author(s):  
Patrick Eriksson ◽  
Simon Pfreundschuh ◽  
Teo Norrestad ◽  
Christian Kummerow
Keyword(s):  
Machine Learning ◽  
Monte Carlo ◽  
Spatial Information ◽  
Monte Carlo Integration ◽  
Learning Approach ◽  
Ancillary Data ◽  
Validation Data ◽  
Surface Precipitation ◽  
Uncertainty Estimates ◽  
Machine Learning Approach

&lt;p&gt;A novel method for the estimation of surface precipitation using passive observations from the GPM constellation is proposed. The method, which makes use of quantile regression neural networks (QRNNs), is shown to provide a more accurate representation of retrieval uncertainties, high processing speed and simplifies the integration of ancillary data into the retrieval. With that, it overcomes limitations of traditionally used methods, such as Monte Carlo integration as well as standard usage of machine learning.&lt;/p&gt;&lt;p&gt;The bulk of precipitation estimates provided by the Global Precipitation Measurement mission (GPM) is based on passive microwave observations. These data are produced by the GPROF algorithm, which applies a Bayesian approach denoted as Monte Carlo integration (MCI). In this work, we investigate the potential of using QRNNs as an alternative to MCI by assessing the performance of both methods using identical input databases.&lt;/p&gt;&lt;p&gt;The methods agree well regarding point estimates, but QRNN provides better estimates of the retrieval uncertainty at the same time as reducing processing times by an order of magnitude. As QRNN gives more precise uncertainty estimates than MCI, it gives an improved basis for further processing of the data, such as identification of extreme precipitation and areal integration.&lt;/p&gt;&lt;p&gt;Results so far indicate that a single network can handle all data from a sensor, which is in contrast to MCI where observations over oceans and different land types have to be treated separately. Moreover, the flexibility of the machine-learning approach opens up opportunities for further improvements of the retrieval: ancillary information can be easily incorporated and QRNN can be applied on multiple footprints, to make better use of spatial information. The effects of these improvements are investigated on independent validation data from ground-based precipitation radars.&lt;/p&gt;&lt;p&gt;QRNN is here shown to be a highly interesting alternative for GPROF, but being a general approach it should be of equally high interest for other precipitation and clouds retrievals.&lt;/p&gt;

scholarly journals Neural network cloud top pressure and height for MODIS

2018 ◽  
Vol 11 (5) ◽  
pp. 3177-3196 ◽  
Author(s):  
Nina Håkansson ◽  
Claudia Adok ◽  
Anke Thoss ◽  
Ronald Scheirer ◽  
Sara Hörnquist
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Infrared Imaging ◽  
Orthogonal Polarization ◽  
Climate Data ◽  
Neural Network Approach ◽  
European Organization ◽  
Error Distributions ◽  
The Neural Networks ◽  
Non Gaussian

Abstract. Cloud top height retrieval from imager instruments is important for nowcasting and for satellite climate data records. A neural network approach for cloud top height retrieval from the imager instrument MODIS (Moderate Resolution Imaging Spectroradiometer) is presented. The neural networks are trained using cloud top layer pressure data from the CALIOP (Cloud-Aerosol Lidar with Orthogonal Polarization) dataset. Results are compared with two operational reference algorithms for cloud top height: the MODIS Collection 6 Level 2 height product and the cloud top temperature and height algorithm in the 2014 version of the NWC SAF (EUMETSAT (European Organization for the Exploitation of Meteorological Satellites) Satellite Application Facility on Support to Nowcasting and Very Short Range Forecasting) PPS (Polar Platform System). All three techniques are evaluated using both CALIOP and CPR (Cloud Profiling Radar for CloudSat (CLOUD SATellite)) height. Instruments like AVHRR (Advanced Very High Resolution Radiometer) and VIIRS (Visible Infrared Imaging Radiometer Suite) contain fewer channels useful for cloud top height retrievals than MODIS, therefore several different neural networks are investigated to test how infrared channel selection influences retrieval performance. Also a network with only channels available for the AVHRR1 instrument is trained and evaluated. To examine the contribution of different variables, networks with fewer variables are trained. It is shown that variables containing imager information for neighboring pixels are very important. The error distributions of the involved cloud top height algorithms are found to be non-Gaussian. Different descriptive statistic measures are presented and it is exemplified that bias and SD (standard deviation) can be misleading for non-Gaussian distributions. The median and mode are found to better describe the tendency of the error distributions and IQR (interquartile range) and MAE (mean absolute error) are found to give the most useful information of the spread of the errors. For all descriptive statistics presented MAE, IQR, RMSE (root mean square error), SD, mode, median, bias and percentage of absolute errors above 0.25, 0.5, 1 and 2 km the neural network perform better than the reference algorithms both validated with CALIOP and CPR (CloudSat). The neural networks using the brightness temperatures at 11 and 12 µm show at least 32 % (or 623 m) lower MAE compared to the two operational reference algorithms when validating with CALIOP height. Validation with CPR (CloudSat) height gives at least 25 % (or 430 m) reduction of MAE.

Sign in / Sign up

Export Citation Format

Share Document