Filters








434 Hits in 5.3 sec

Neural Networks and Spectral Feature Selection for Retrieval of Hot Gases Temperature Profiles

E. Garcia-Cuesta, I.M. Galvan, A.J. de Castro
International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06)  
Temperature profile retrieval will be obtained from the measurement of the spectral distribution of energy radiated by the hot gases (combustion products) at wavelengths corresponding to the infrared region  ...  In this paper the capability of neural networks to retrieve the temperature profile in a combustion environment is proposed.  ...  In this work, a combination of MLP and a feature selection has been used with the purpose of approximate the temperature profile of the hot gas and to allow working with high spectral resolution.  ... 
doi:10.1109/cimca.2005.1631449 dblp:conf/cimca/Garcia-CuestaGC05 fatcat:jjurxz5mgvh6tflsnoeiurrcwu

Spectral High Resolution Feature Selection for Retrieval of Combustion Temperature Profiles [chapter]

Esteban García-Cuesta, Inés M. Galván, Antonio J. de Castro
2006 Lecture Notes in Computer Science  
In this paper, the capability to retrieve the temperature prof le in a combustion environment using neural networks jointly with this spectral high resolution feature selection method is studied.  ...  The use of high spectral resolution measurements to obtain a retrieval of certain physical properties related with the radiative transfer of energy leads a priori to a better accuracy.  ...  The use of high spectral feature selection jointly with neural networks can contribute in an efficien way to retrieve the temperature profile with some advantages over classical physical-statistical techniques  ... 
doi:10.1007/11875581_91 fatcat:zavulggcjjdyvnmidalbagshva

Multilayer perceptron as inverse model in a ground-based remote sensing temperature retrieval problem

Esteban García-Cuesta, Inés M. Galván, Antonio J. de Castro
2008 Engineering applications of artificial intelligence  
The introduction of a selection subset of features is mandatory due to the problems related to the high dimensionality data and the worse performance of MLPs with this high input dimensionality.  ...  In this paper, a combustion temperature retrieval approximation for high-resolution infrared ground-based measurements has been developed based on a multilayer perceptron (MLP) technique.  ...  Acknowledgements This research is supported by the Spanish MEC projects-TRA2005-08892-C02-01 and OPLINK::UC3M, Ref: TIN2005-08818-C04-02.  ... 
doi:10.1016/j.engappai.2007.03.005 fatcat:msvajj7dobghfmzq3txq4kcr3q

Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements

Tao Ren, Michael F. Modest, Alexander Fateev, Gavin Sutton, Weijie Zhao, Florin Rusu
2019 Applied Energy  
Two types of temperature profiles were tested for different gas path lengths and different CO 2 spectral bands.  ...  By measuring spectral intensity of the CO 2 4.3 µm band, temperature profiles were retrieved in a number of ways [19, 20] .  ...  Acknowledgment The third and forth authors gratefully acknowledge the support from the European Metrology Programme for Innovation and Research (EMPIR) and the European Union's Horizon 2020 Research and  ... 
doi:10.1016/j.apenergy.2019.113448 fatcat:772lipim5redvjhvrdniwyrfqe

DREAMING OF ATMOSPHERES

I. P. Waldmann
2016 Astrophysical Journal  
The RobERt algorithm is based on deep belief neural (DBN) networks trained to accurately recognise molecular signatures for a wide range of planets, atmospheric thermal profiles and compositions.  ...  Reconstructions of the learned features, also referred to as 'dreams' of the network, indicate good convergence and an accurate representation of molecular features in the DBN.  ...  The similarities between 'dreamed' and real spectral features are striking. This indicates a good representation of molecular features in the neural network.  ... 
doi:10.3847/0004-637x/820/2/107 fatcat:xaj6qz2zj5ejfodjcat3duo4tq

A General Framework for Global Retrievals of Trace Gases From IASI: Application to Methanol, Formic Acid, and PAN

B. Franco, L. Clarisse, T. Stavrakou, J.‐F Müller, M. Van Damme, S. Whitburn, J. Hadji‐Lazaro, D. Hurtmans, D. Taraborrelli, C. Clerbaux, P.‐F Coheur
2018 Journal of Geophysical Research - Atmospheres  
The OEM retrieval requires a priori vertical profiles for each of the retrieved gases.  ...  Figure 1 . 1 Conceptual flowchart of the ANNI (Artificial Neural Network for IASI) retrieval method of trace gases. IASI = Infrared Atmospheric Sounding Interferometer. Figure 2 . 2 Figure 2.  ...  The authors acknowledge the Aeris data infrastructure (https://www.aeris-data.fr/) for providing access to the IASI Level-1C data and Level-2 temperature data used in this study.  ... 
doi:10.1029/2018jd029633 fatcat:xjdpwc6zpjh6jdozxk5i6c2xwm

MIIDAPS-AI: An Explainable Machine-Learning Algorithm for Infrared and Microwave Remote Sensing and Data Assimilation Preprocessing - Application to LEO and GEO Sensors

Eric Sean Maddy, Sid-Ahmed Boukabara
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The algorithm produces vertical profiles of temperature and moisture as well as surface temperature, surface emissivity and cloud parameters.  ...  Additional products from hyperspectral infrared sensors include selected trace gases.  ...  manuscript prior to publication, and Narges Shahroudi and Adam Neiss for their work in extending MIIDAPS-AI to hypothetical sensors.  ... 
doi:10.1109/jstars.2021.3104389 fatcat:dh7afoj7qnei5emb3bfz4icbza

Study of Climate Change Detection in North East Africa using Machine learning and Satellite Data

Sara K. Ibrahim, Ibrahim Ziedan, Ayman Ahmed
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The used models are long shortterm memory, autoencoders, and convolutional neural network.  ...  The relationship between the emission of greenhouse gases (GHGs) and climate change is an important factor to understand.  ...  Convolutional Neural Network A Convolutional Neural Network (CNN) is the basis of most computer vision technologies.  ... 
doi:10.1109/jstars.2021.3120987 fatcat:3oo7b3lckrfm3jykyfsshveppi

A flexible and robust neural network IASI-NH3retrieval algorithm

S. Whitburn, M. Van Damme, L. Clarisse, S. Bauduin, C. L. Heald, J. Hadji-Lazaro, D. Hurtmans, M. A. Zondlo, C. Clerbaux, P.-F Coheur
2016 Journal of Geophysical Research - Atmospheres  
A flexible and robust neural network IASI-NH3 retrieval algorithm.  ...  The method is based on the calculation of a spectral hyperspectral range index (HRI) and subsequent conversion to NH 3 columns via a neural network.  ...  The and z 0 values which are used in the retrieval process are derived from the fitting of the single NH 3 profiles used for land and sea in the LUT-based HRI method (see section 3.3) and will be distributed  ... 
doi:10.1002/2016jd024828 fatcat:zkt5bf5jcffvnpmuxj22es6cdu

Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals [article]

Kai Hou Yip, Quentin Changeat, Nikolaos Nikolaou, Mario Morvan, Billy Edwards, Ingo P. Waldmann, Giovanna Tinetti
2021 arXiv   pre-print
Several works have attempted to perform fast retrievals of atmospheric parameters with the use of machine learning algorithms like deep neural networks (DNNs).  ...  Finally, we perform a perturbation-based sensitivity analysis to identify to which features of the spectrum the outcome of the retrieval is most sensitive.  ...  Acknowledgements We appreciate suggestions from the anonymous reviewer, which has improved the quality of the manuscript. This project has received funding from  ... 
arXiv:2011.11284v2 fatcat:a3hbxifce5cjner363eqzhqzae

Automated determination of stellar parameters from simulated dispersed images for DIVA

P. G. Willemsen, C. A. L Bailer-Jones, T. A. Kaempf, K. S. de Boer
2003 Astronomy and Astrophysics  
Using neural network methods and by including simulated data of DIVA's UV telescope, we can determine T_eff to an average accuracy of about 2% for DISPIS from stars with 2000 K < T_eff < 20000 K and visual  ...  For low temperature stars with 2000 K < T_eff < 5000 K and for metallicities in the range -0.3 to +1 dex a determination of [Fe/H] is possible (to better than 0.2 dex) for these magnitudes.  ...  This project is carried out in preparation for the DIVA mission and we thank the DLR for financial support (Projectnr. 50QD0103).  ... 
doi:10.1051/0004-6361:20030195 fatcat:lewihsiuofgydgzrqhr26oajgi

A Multi-Channel Method for Retrieving Surface Temperature for High-Emissivity Surfaces from Hyperspectral Thermal Infrared Images

Xinke Zhong, Jelila Labed, Guoqing Zhou, Kun Shao, Zhao-Liang Li
2015 Sensors  
1200 cm −1 and a spectral sampling frequency of 0.25 cm −1 .  ...  The empirical methods for retrieving ST for high-emissivity surfaces from hyperspectral thermal infrared (HypTIR) images require spectrally continuous channel data.  ...  Acknowledgments The authors would like to thank the LMD ARA for providing TIGR dataset, to thank LMD, NOVELTIS and CNES for providing the 4A/OP software and.  ... 
doi:10.3390/s150613406 pmid:26061199 pmcid:PMC4507689 fatcat:mmw4iz5ux5e6jcju3qmmzhapb4

Hyperspectral Earth Observation from IASI: Five Years of Accomplishments

Fiona Hilton, Raymond Armante, Thomas August, Chris Barnet, Aurelie Bouchard, Claude Camy-Peyret, Virginie Capelle, Lieven Clarisse, Cathy Clerbaux, Pierre-Francois Coheur, Andrew Collard, Cyril Crevoisier (+31 others)
2012 Bulletin of The American Meteorological Society - (BAMS)  
GEISA currently covers the absorption features of 27 different atmospheric gases within IASI's spectral range.  ...  trace gases and allowing the resolution of even more atmospheric features.  ...  As greenhouse gas emissions and temperatures at the poles continue to rise, so do damages from extreme weather events affecting countless lives.  ... 
doi:10.1175/bams-d-11-00027.1 fatcat:kwwd77btlbctrphxburqfvut7a

Evaluation and Global-Scale Observation of Nitrous Oxide from IASI on Metop-A

Rémi Chalinel, Jean-Luc Attié, Philippe Ricaud, Jérôme Vidot, Yannick Kangah, Didier Hauglustaine, Rona Thompson
2022 Remote Sensing  
of methane, water vapour, temperature profiles together with surface temperature and emissivity within the 1240–1350 cm−1 window.  ...  Nitrous oxide (N2O) is a greenhouse gas difficult to estimate by satellite because of its weak spectral signature in the infra-red band and its low variability in the troposphere.  ...  We also thank the three anonymous reviewers for their encouraging and valuable comments that contribute to improve the paper. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs14061403 fatcat:7hs4d4tscve3terrivumedkmiu

Validation of a New Parametric Model for Atmospheric Correction of Thermal Infrared Data

E. Ellicott, E. Vermote, F. Petitcolin, S.J. Hook
2009 IEEE Transactions on Geoscience and Remote Sensing  
Accurate retrieval of surface temperature from satellite observations requires proper correction of the thermal channels for atmospheric emission and attenuation.  ...  Validation of surface temperatures derived using our model with in situ land and water temperature measurements exhibited accuracy (mean bias < 0.35 K) and low error (rmse < 1 K) for MODIS bands 31 and  ...  ACKNOWLEDGMENT The research described in this paper was carried out in part at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space  ... 
doi:10.1109/tgrs.2008.2006182 fatcat:n42xfeo7ubax5gt66pukeujjxu
« Previous Showing results 1 — 15 out of 434 results