FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384993145> ?p ?o ?g. }

• W4384993145 endingPage "113706" @default.
• W4384993145 startingPage "113706" @default.
• W4384993145 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." @default.
• W4384993145 created "2023-07-22" @default.
• W4384993145 creator A5013626090 @default.
• W4384993145 creator A5030104268 @default.
• W4384993145 creator A5032490551 @default.
• W4384993145 creator A5036525287 @default.
• W4384993145 creator A5044583603 @default.
• W4384993145 creator A5047188759 @default.
• W4384993145 creator A5058488448 @default.
• W4384993145 creator A5064576529 @default.
• W4384993145 creator A5066543180 @default.
• W4384993145 date "2023-09-01" @default.
• W4384993145 modified "2023-10-14" @default.
• W4384993145 title "A hyperspectral inversion framework for estimating absorbing inherent optical properties and biogeochemical parameters in inland and coastal waters" @default.
• W4384993145 cites W1533208962 @default.
• W4384993145 cites W1548848902 @default.
• W4384993145 cites W1967906870 @default.
• W4384993145 cites W1973860676 @default.
• W4384993145 cites W1981614688 @default.
• W4384993145 cites W1985562997 @default.
• W4384993145 cites W1986141606 @default.
• W4384993145 cites W1988886499 @default.
• W4384993145 cites W1992857472 @default.
• W4384993145 cites W1995811252 @default.
• W4384993145 cites W1997101844 @default.
• W4384993145 cites W1999499567 @default.
• W4384993145 cites W2004899697 @default.
• W4384993145 cites W2008641145 @default.
• W4384993145 cites W2011117467 @default.
• W4384993145 cites W2011680715 @default.
• W4384993145 cites W2012352579 @default.
• W4384993145 cites W2014067483 @default.
• W4384993145 cites W2016029780 @default.
• W4384993145 cites W2016590586 @default.
• W4384993145 cites W2017089434 @default.
• W4384993145 cites W2018693664 @default.
• W4384993145 cites W2020972217 @default.
• W4384993145 cites W2021803101 @default.
• W4384993145 cites W2032316458 @default.
• W4384993145 cites W2034742150 @default.
• W4384993145 cites W2038277379 @default.
• W4384993145 cites W2040649777 @default.
• W4384993145 cites W2048956808 @default.
• W4384993145 cites W2050358717 @default.
• W4384993145 cites W2050764965 @default.
• W4384993145 cites W2060848616 @default.
• W4384993145 cites W2061522318 @default.
• W4384993145 cites W2064860163 @default.
• W4384993145 cites W2066708694 @default.
• W4384993145 cites W2067029077 @default.
• W4384993145 cites W2071869157 @default.
• W4384993145 cites W2072054148 @default.
• W4384993145 cites W2079608989 @default.
• W4384993145 cites W2081046435 @default.
• W4384993145 cites W2082714424 @default.
• W4384993145 cites W2082957928 @default.
• W4384993145 cites W2087886999 @default.
• W4384993145 cites W2092018381 @default.
• W4384993145 cites W2093298226 @default.
• W4384993145 cites W2095127991 @default.
• W4384993145 cites W2101294134 @default.
• W4384993145 cites W2105516696 @default.
• W4384993145 cites W2114164280 @default.
• W4384993145 cites W2114742640 @default.
• W4384993145 cites W2119320869 @default.
• W4384993145 cites W2119480846 @default.
• W4384993145 cites W2121951533 @default.
• W4384993145 cites W2127595139 @default.
• W4384993145 cites W2128877724 @default.
• W4384993145 cites W2128904410 @default.
• W4384993145 cites W2134213291 @default.
• W4384993145 cites W2134568103 @default.
• W4384993145 cites W2143329262 @default.
• W4384993145 cites W2149463205 @default.
• W4384993145 cites W2153619838 @default.
• W4384993145 cites W2155782014 @default.
• W4384993145 cites W2157481910 @default.
• W4384993145 cites W2157974429 @default.
• W4384993145 cites W2161523635 @default.
• W4384993145 cites W2169939759 @default.
• W4384993145 cites W2243583198 @default.
• W4384993145 cites W2288322163 @default.
• W4384993145 cites W2537839582 @default.
• W4384993145 cites W2572463531 @default.
• W4384993145 cites W2759754436 @default.
• W4384993145 cites W2763003374 @default.
• W4384993145 cites W2764084117 @default.
• W4384993145 cites W2765584310 @default.
• W4384993145 cites W2767892373 @default.
• W4384993145 cites W2781515835 @default.
• W4384993145 cites W2781763657 @default.
• W4384993145 cites W2789467013 @default.
• W4384993145 cites W2791202700 @default.
• W4384993145 cites W2808551570 @default.
• W4384993145 cites W2808645289 @default.
• W4384993145 cites W2811312756 @default.
• W4384993145 cites W2889489337 @default.
• W4384993145 cites W2891723768 @default.

• next