Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing
Abstract—Neural networks have the ability to represent and learn complex regression functions and are very suitable for retrieval of geophysical parameters from remotely sensed data. Neural networks trained to minimize the mean square error are able to estimate the conditional expectation of target...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.5316 http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.348.5316 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.348.5316 2023-05-15T13:06:07+02:00 Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing Kosta Ristovski Slobodan Vucetic Zoran Obradovic The Pennsylvania State University CiteSeerX Archives 2012 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.5316 http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.5316 http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf text 2012 ftciteseerx 2016-01-08T00:12:25Z Abstract—Neural networks have the ability to represent and learn complex regression functions and are very suitable for retrieval of geophysical parameters from remotely sensed data. Neural networks trained to minimize the mean square error are able to estimate the conditional expectation of target variables. In many remote sensing applications, it is also critical to provide estimates of prediction uncertainty. In this paper, we evaluate an approach that, in addition to training a neural network for retrievals, also trains a neural-network-based estimator of retrieval uncertainty. The uncertainty estimator is built under the assumption that uncertainty is a function of input variables. The methodology was evaluated on aerosol-optical-depth retrieval. The data set consists of 38 238 collocated Moderate Resolution Imaging Spectrometer (MODIS) satellite instrument and Aerosol Robotic Network ground-based instrument measurements collected over the entire Earth during two years (in 2005–2006). The results indicate that a neural network ensemble is more accurate than the operational MODIS retrieval algorithm called Collection 5 and that the retrieval uncertainty of the ensemble can be estimated with satisfactory accuracy. Index Terms—Regression, remote sensing, uncertainty. I. Text Aerosol Robotic Network Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
description |
Abstract—Neural networks have the ability to represent and learn complex regression functions and are very suitable for retrieval of geophysical parameters from remotely sensed data. Neural networks trained to minimize the mean square error are able to estimate the conditional expectation of target variables. In many remote sensing applications, it is also critical to provide estimates of prediction uncertainty. In this paper, we evaluate an approach that, in addition to training a neural network for retrievals, also trains a neural-network-based estimator of retrieval uncertainty. The uncertainty estimator is built under the assumption that uncertainty is a function of input variables. The methodology was evaluated on aerosol-optical-depth retrieval. The data set consists of 38 238 collocated Moderate Resolution Imaging Spectrometer (MODIS) satellite instrument and Aerosol Robotic Network ground-based instrument measurements collected over the entire Earth during two years (in 2005–2006). The results indicate that a neural network ensemble is more accurate than the operational MODIS retrieval algorithm called Collection 5 and that the retrieval uncertainty of the ensemble can be estimated with satisfactory accuracy. Index Terms—Regression, remote sensing, uncertainty. I. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Kosta Ristovski Slobodan Vucetic Zoran Obradovic |
spellingShingle |
Kosta Ristovski Slobodan Vucetic Zoran Obradovic Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
author_facet |
Kosta Ristovski Slobodan Vucetic Zoran Obradovic |
author_sort |
Kosta Ristovski |
title |
Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
title_short |
Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
title_full |
Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
title_fullStr |
Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
title_full_unstemmed |
Uncertainty analysis of neural-network-based aerosol retrieval,” Geoscience and Remote Sensing |
title_sort |
uncertainty analysis of neural-network-based aerosol retrieval,” geoscience and remote sensing |
publishDate |
2012 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.5316 http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_source |
http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.5316 http://www.dabi.temple.edu/%7Ezoran/papers/RistovskiGRS.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766403531278909440 |