Use this url to cite publication: https://hdl.handle.net/20.500.14172/26185
Options
A hyperspectral inversion framework for estimating absorbing inherent optical properties and biogeochemical parameters in inland and coastal waters
Type of publication
Straipsnis Web of Science ir Scopus duomenų bazėje / Article in Web of Science and Scopus database (S1)
Type of document
text::journal::journal article::research article
Author(s)
O'Shea, Ryan E. | NASA Goddard Space Flight Center | US | Science Systems and Applications, Inc. (SSAI) | US |
Nima Pahlevan | NASA Goddard Space Flight Center | US | Science Systems and Applications, Inc. (SSAI) | US |
Brandon Smith | NASA Goddard Space Flight Center | US | Science Systems and Applications, Inc. (SSAI) | US |
Boss, Emmanuel | University of Maine | US | ||
Daniela Gurlin | Wisconsin Department of Natural Resources | US | ||
Krista Alikas | University of Maine | US | ||
Kersti Kangro | University of Tartu | EE | ||
Kudela, Raphael M. | University of California-Santa Cruz | US | ||
LT |
Title
A hyperspectral inversion framework for estimating absorbing inherent optical properties and biogeochemical parameters in inland and coastal waters
Publisher
New York : Elsevier Science
Date Issued
Date Issued | Volume | Issue | Start Page | End Page |
---|---|---|---|---|
2023-06-29 | vol. 295 | art. no. 113706 | 1 | 31 |
Is part of
Remote sensing of environment
Field of Science
Abstract
The simultaneous remote estimation of biogeochemical parameters (BPs) and inherent optical properties (IOPs) from hyperspectral satellite imagery of globally distributed optically distinct inland and coastal waters is a complex, unsolved, non-unique inverse problem. To tackle this problem, we leverage a machine-learning model termed Mixture Density Networks (MDNs). MDNs outperform operational algorithms by calculating the covariance between the simultaneously estimated products. We train the MDNs on a large (N = 8237) dataset of co-aligned, in situ measured, hyperspectral remote sensing reflectance (Rrs), BPs, and absorbing IOPs from globally representative optically distinct inland and coastal waters. The estimated IOPs include absorption due to phytoplankton (aph), chromophoric dissolved organic matter (acdom), and non-algal particles (anap). The estimated BPs include chlorophyll-a, total suspended solids, and phycocyanin (PC). MDNs dramatically reduce uncertainty in the retrievals, relative to operational algorithms, when using a 50/50 dataset split, where the MDNs are trained on a randomly selected half of the in situ dataset and validated on the other half. Our model is shown to have higher, or equivalent, generalization performance than the calculated operational algorithms available for all BPs and IOPs (except PC) via a leave-one-out cross-validation assessment. The MDNs are sensitive to uncertainties in the hyperspectral satellite Rrs, resulting from instrument noise and atmospheric correction; there is a difference of ∼37.4–62.8% (using median symmetric accuracy) between the MDNs' estimates derived from co-located satellite-derived Rrs and in situ Rrs. Of the IOPs, acdom and anap are less sensitive to uncertainties in hyperspectral satellite imagery relative to aph, with remote estimates of aph exhibiting incorrect spectral shape and magnitude relative to in situ measured IOPs. Despite the uncertainties in satellite derived Rrs, the spatial distributions of BPs and IOPs in MDN-derived product maps of Lake Erie and the Curonian Lagoon, based on imagery taken with the Hyperspectral Imager for the Coastal Ocean (HICO) and PRecursore IperSpettrale della Missione Applicativa (PRISMA), are confirmed via co-aligned in situ measurements and agree with the literature's understanding of these well-studied regions. The consistency and accuracy of the model on HICO and PRISMA imagery, despite radiometric uncertainties, demonstrate its applicability to future hyperspectral missions, such as the Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission, where the simultaneous estimation model will serve as a key part of phytoplankton community composition analysis.
ISSN (of the container)
0034-4257
1879-0704
WOS
001047689300001
Scopus
2-s2.0-85165365899
Coverage Spatial
Jungtinės Amerikos Valstijos / United States of America (US)
Language
Anglų / English (en)
Bibliographic Details
134
Access Rights
Atviroji prieiga / Open Access
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
REMOTE SENSING OF ENVIRONMENT | 13.5 | 5.833 | 5.5 | 6.5 | 3 | 2.146 | 2022 | Q1 |
Journal | IF | AIF | AIF (min) | AIF (max) | Cat | AV | Year | Quartile |
---|---|---|---|---|---|---|---|---|
REMOTE SENSING OF ENVIRONMENT | 13.5 | 5.833 | 5.5 | 6.5 | 3 | 2.146 | 2022 | Q1 |
5.833 | ||||||||
5.748 |
Journal | Cite Score | SNIP | SJR | Year | Quartile |
---|---|---|---|---|---|
Remote Sensing of Environment | 24.8 | 3.527 | 4.057 | 2022 | Q1 |