dc.contributor.author | Blix, Katalin | |
dc.contributor.author | Eltoft, Torbjørn | |
dc.date.accessioned | 2019-03-19T14:31:29Z | |
dc.date.available | 2019-03-19T14:31:29Z | |
dc.date.issued | 2018-03-22 | |
dc.description.abstract | This paper evaluates two alternative regression techniques for oceanic chlorophyll-a (Chl-a) content estimation. One of
the investigated methodologies is the recently introduced Gaussian
process regression (GPR) model. We explore two feature ranking
methods derived for the GPR model, namely sensitivity analysis (SA) and automatic relevance determination (ARD). We also
investigate a second regression method, the partial least squares
regression (PLSR) for oceanic Chl-a content estimation. Feature
relevance in the PLSR model can be accessed through the variable importance in projection (VIP) feature ranking algorithm.
This paper thus analyzes three feature ranking models, SA, ARD,
and VIP, which are all derived from different fundamental principles, and uses the ranked features as inputs to the GPR and PLSR
to assess regression strengths. We compare the regression performances using some common performance measures, and show how
the feature ranking methods can be used to find the lowest number
of features to estimate oceanic Chl-a content by using the GPR and
PLSR models, while still producing comparable performance to
the state-of-the-art algorithms. We evaluate the models on a global
MEdium Resolution Imaging Spectrometer matchup dataset. Our
results show that the GPR model has the best regression performance for most of the input feature sets we used, and our conclusion
is this model can favorably be used for Chl-a content retrieval, already with two features, ranked by either the SA or ARD methods. | en_US |
dc.description | Accepted manuscript version. Published version available at <a href=https://doi.org/10.1109/JSTARS.2018.2810704>https://doi.org/10.1109/JSTARS.2018.2810704. </a> | en_US |
dc.identifier.citation | Blix, K. & Eltoft, T. (2018). Evaluation of feature ranking and regression methods for oceanic chlorophyll-a estimation. <i>IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11</i>(5), 1403-1418. https://doi.org/10.1109/JSTARS.2018.2810704 | en_US |
dc.identifier.cristinID | FRIDAID 1583174 | |
dc.identifier.doi | 10.1109/JSTARS.2018.2810704 | |
dc.identifier.issn | 1939-1404 | |
dc.identifier.issn | 2151-1535 | |
dc.identifier.uri | https://hdl.handle.net/10037/15028 | |
dc.language.iso | eng | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.relation.ispartof | Blix, K. (2019). Machine Learning Water Quality Monitoring. (Doctoral thesis). <a href=https://hdl.handle.net/10037/16502>https://hdl.handle.net/10037/16502</a>. | |
dc.relation.journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | |
dc.relation.projectID | info:eu-repo/grantAgreement/RCN/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ | en_US |
dc.rights.accessRights | openAccess | en_US |
dc.subject | Arctic | en_US |
dc.subject | environmental monitoring | en_US |
dc.subject | gaussian processes | en_US |
dc.subject | optical imaging | en_US |
dc.subject | ranking | en_US |
dc.subject | regression analysis | en_US |
dc.subject | VDP::Mathematics and natural science: 400::Physics: 430 | en_US |
dc.subject | VDP::Matematikk og Naturvitenskap: 400::Fysikk: 430 | en_US |
dc.title | Evaluation of feature ranking and regression methods for oceanic chlorophyll-a estimation | en_US |
dc.type | Journal article | en_US |
dc.type | Tidsskriftartikkel | en_US |
dc.type | Peer reviewed | en_US |