Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval
First published in Remote Sensing . Source at https://doi.org/10.3390/rs10050775 . Ocean Color remote sensing has a great importance in monitoring of aquatic environments. The number of optical imaging sensors onboard satellites has been increasing in the past decades, allowing to retrieve informati...
Published in: | Remote Sensing |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/14038 https://doi.org/10.3390/rs10050775 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/14038 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/14038 2023-05-15T14:27:10+02:00 Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval Blix, Katalin Eltoft, Torbjørn 2018-05-17 https://hdl.handle.net/10037/14038 https://doi.org/10.3390/rs10050775 eng eng MDPI Blix, K. (2019). Machine Learning Water Quality Monitoring. (Doctoral thesis). https://hdl.handle.net/10037/16502 . Remote Sensing info:eu-repo/grantAgreement/RCN/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Blix, K. & Eltoft, T. (2018). Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval. Remote Sensing, 10(5). https://doi.org/10.3390/rs10050775 FRIDAID 1585510 doi:10.3390/rs10050775 2072-4292 https://hdl.handle.net/10037/14038 openAccess VDP::Mathematics and natural science: 400::Physics: 430 VDP::Matematikk og Naturvitenskap: 400::Fysikk: 430 ocean color remote sensing model selection feature ranking regression Journal article Tidsskriftartikkel Peer reviewed 2018 ftunivtroemsoe https://doi.org/10.3390/rs10050775 2021-06-25T17:56:10Z First published in Remote Sensing . Source at https://doi.org/10.3390/rs10050775 . Ocean Color remote sensing has a great importance in monitoring of aquatic environments. The number of optical imaging sensors onboard satellites has been increasing in the past decades, allowing to retrieve information about various water quality parameters of the world’s oceans and inland waters. This is done by using various regression algorithms to retrieve water quality parameters from remotely sensed multi-spectral data for the given sensor and environment. There is a great number of such algorithms for estimating water quality parameters with different performances. Hence, choosing the most suitable model for a given purpose can be challenging. This is especially the fact for optically complex aquatic environments. In this paper, we present a concept to an Automatic Model Selection Algorithm (AMSA) aiming at determining the best model for a given matchup dataset. AMSA automatically chooses between regression models to estimate the parameter in interest. AMSA also determines the number and combination of features to use in order to obtain the best model. We show how AMSA can be built for a certain application. The example AMSA we present here is designed to estimate oceanic Chlorophyll-a for global and optically complex waters by using four Machine Learning (ML) feature ranking methods and three ML regression models. We use a synthetic and two real matchup datasets to find the best models. Finally, we use two images from optically complex waters to illustrate the predictive power of the best models. Our results indicate that AMSA has a great potential to be used for operational purposes. It can be a useful objective tool for finding the most suitable model for a given sensor, water quality parameter and environment. Article in Journal/Newspaper Arctic University of Tromsø: Munin Open Research Archive Remote Sensing 10 5 775 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Mathematics and natural science: 400::Physics: 430 VDP::Matematikk og Naturvitenskap: 400::Fysikk: 430 ocean color remote sensing model selection feature ranking regression |
spellingShingle |
VDP::Mathematics and natural science: 400::Physics: 430 VDP::Matematikk og Naturvitenskap: 400::Fysikk: 430 ocean color remote sensing model selection feature ranking regression Blix, Katalin Eltoft, Torbjørn Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
topic_facet |
VDP::Mathematics and natural science: 400::Physics: 430 VDP::Matematikk og Naturvitenskap: 400::Fysikk: 430 ocean color remote sensing model selection feature ranking regression |
description |
First published in Remote Sensing . Source at https://doi.org/10.3390/rs10050775 . Ocean Color remote sensing has a great importance in monitoring of aquatic environments. The number of optical imaging sensors onboard satellites has been increasing in the past decades, allowing to retrieve information about various water quality parameters of the world’s oceans and inland waters. This is done by using various regression algorithms to retrieve water quality parameters from remotely sensed multi-spectral data for the given sensor and environment. There is a great number of such algorithms for estimating water quality parameters with different performances. Hence, choosing the most suitable model for a given purpose can be challenging. This is especially the fact for optically complex aquatic environments. In this paper, we present a concept to an Automatic Model Selection Algorithm (AMSA) aiming at determining the best model for a given matchup dataset. AMSA automatically chooses between regression models to estimate the parameter in interest. AMSA also determines the number and combination of features to use in order to obtain the best model. We show how AMSA can be built for a certain application. The example AMSA we present here is designed to estimate oceanic Chlorophyll-a for global and optically complex waters by using four Machine Learning (ML) feature ranking methods and three ML regression models. We use a synthetic and two real matchup datasets to find the best models. Finally, we use two images from optically complex waters to illustrate the predictive power of the best models. Our results indicate that AMSA has a great potential to be used for operational purposes. It can be a useful objective tool for finding the most suitable model for a given sensor, water quality parameter and environment. |
format |
Article in Journal/Newspaper |
author |
Blix, Katalin Eltoft, Torbjørn |
author_facet |
Blix, Katalin Eltoft, Torbjørn |
author_sort |
Blix, Katalin |
title |
Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
title_short |
Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
title_full |
Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
title_fullStr |
Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
title_full_unstemmed |
Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval |
title_sort |
machine learning automatic model selection algorithm for oceanic chlorophyll-a content retrieval |
publisher |
MDPI |
publishDate |
2018 |
url |
https://hdl.handle.net/10037/14038 https://doi.org/10.3390/rs10050775 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Blix, K. (2019). Machine Learning Water Quality Monitoring. (Doctoral thesis). https://hdl.handle.net/10037/16502 . Remote Sensing info:eu-repo/grantAgreement/RCN/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Blix, K. & Eltoft, T. (2018). Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval. Remote Sensing, 10(5). https://doi.org/10.3390/rs10050775 FRIDAID 1585510 doi:10.3390/rs10050775 2072-4292 https://hdl.handle.net/10037/14038 |
op_rights |
openAccess |
op_doi |
https://doi.org/10.3390/rs10050775 |
container_title |
Remote Sensing |
container_volume |
10 |
container_issue |
5 |
container_start_page |
775 |
_version_ |
1766300771639361536 |