FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293222016> ?p ?o ?g. }

• W4293222016 endingPage "1244" @default.
• W4293222016 startingPage "1221" @default.
• W4293222016 abstract "Abstract. Despite the ever-growing number of ocean data, the interior of the ocean remains undersampled in regions of high variability such as the Gulf Stream. In this context, neural networks have been shown to be effective for interpolating properties and understanding ocean processes. We introduce OSnet (Ocean Stratification network), a new ocean reconstruction system aimed at providing a physically consistent analysis of the upper ocean stratification. The proposed scheme is a bootstrapped multilayer perceptron trained to predict simultaneously temperature and salinity (T−S) profiles down to 1000 m and the mixed-layer depth (MLD) from surface data covering 1993 to 2019. OSnet is trained to fit sea surface temperature and sea level anomalies onto all historical in situ profiles in the Gulf Stream region. To achieve vertical coherence of the profiles, the MLD prediction is used to adjust a posteriori the vertical gradients of predicted T−S profiles, thus increasing the accuracy of the solution and removing vertical density inversions. The prediction is generalized on a 1/4∘ daily grid, producing four-dimensional fields of temperature and salinity, with their associated confidence interval issued from the bootstrap. OSnet profiles have root mean square error comparable with the observation-based Armor3D weekly product and the physics-based ocean reanalysis Glorys12. The lowest confidence in the prediction is located north of the Gulf Stream, between the shelf and the current, where the thermohaline variability is large. The OSnet reconstructed field is coherent even in the pre-Argo years, demonstrating the good generalization properties of the network. It reproduces the warming trend of surface temperature, the seasonal cycle of surface salinity and mesoscale structures of temperature, salinity and MLD. While OSnet delivers an accurate interpolation of the ocean stratification, it is also a tool to study how the ocean stratification relates to surface data. We can compute the relative importance of each input for each T−S prediction and analyse how the network learns which surface feature influences most which property and at which depth. Our results demonstrate the potential of machine learning methods to improve predictions of ocean interior properties from observations of the ocean surface." @default.
• W4293222016 created "2022-08-27" @default.
• W4293222016 creator A5010528158 @default.
• W4293222016 creator A5014455136 @default.
• W4293222016 creator A5024011878 @default.
• W4293222016 creator A5030077747 @default.
• W4293222016 creator A5055062982 @default.
• W4293222016 creator A5071270211 @default.
• W4293222016 creator A5073521710 @default.
• W4293222016 creator A5075497720 @default.
• W4293222016 date "2022-08-25" @default.
• W4293222016 modified "2023-10-12" @default.
• W4293222016 title "Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks" @default.
• W4293222016 cites W1855709777 @default.
• W4293222016 cites W1964247113 @default.
• W4293222016 cites W1964959873 @default.
• W4293222016 cites W1977177161 @default.
• W4293222016 cites W197797489 @default.
• W4293222016 cites W1980542080 @default.
• W4293222016 cites W1983563991 @default.
• W4293222016 cites W1987755860 @default.
• W4293222016 cites W1989731792 @default.
• W4293222016 cites W1991862252 @default.
• W4293222016 cites W2000977051 @default.
• W4293222016 cites W2014012078 @default.
• W4293222016 cites W2019627954 @default.
• W4293222016 cites W2022748821 @default.
• W4293222016 cites W2023210859 @default.
• W4293222016 cites W2035486622 @default.
• W4293222016 cites W2051502425 @default.
• W4293222016 cites W2069197937 @default.
• W4293222016 cites W2079876722 @default.
• W4293222016 cites W2100621091 @default.
• W4293222016 cites W2118431311 @default.
• W4293222016 cites W2126105956 @default.
• W4293222016 cites W2129888542 @default.
• W4293222016 cites W2129913525 @default.
• W4293222016 cites W2130283783 @default.
• W4293222016 cites W2131373731 @default.
• W4293222016 cites W2141861439 @default.
• W4293222016 cites W2144276074 @default.
• W4293222016 cites W2153778794 @default.
• W4293222016 cites W2165804524 @default.
• W4293222016 cites W2171666055 @default.
• W4293222016 cites W2201182621 @default.
• W4293222016 cites W2245493112 @default.
• W4293222016 cites W2487898712 @default.
• W4293222016 cites W2512174018 @default.
• W4293222016 cites W2527672088 @default.
• W4293222016 cites W2594584909 @default.
• W4293222016 cites W2595920914 @default.
• W4293222016 cites W2604239613 @default.
• W4293222016 cites W2619624483 @default.
• W4293222016 cites W2625241797 @default.
• W4293222016 cites W2767793144 @default.
• W4293222016 cites W2782522152 @default.
• W4293222016 cites W2787462104 @default.
• W4293222016 cites W2790934709 @default.
• W4293222016 cites W2913323966 @default.
• W4293222016 cites W2946309465 @default.
• W4293222016 cites W2963645604 @default.
• W4293222016 cites W2981879507 @default.
• W4293222016 cites W2985480130 @default.
• W4293222016 cites W2991135507 @default.
• W4293222016 cites W2995497634 @default.
• W4293222016 cites W3013216831 @default.
• W4293222016 cites W3016099278 @default.
• W4293222016 cites W3023752866 @default.
• W4293222016 cites W3044843206 @default.
• W4293222016 cites W3082264085 @default.
• W4293222016 cites W3087160123 @default.
• W4293222016 cites W3112813418 @default.
• W4293222016 cites W3118731688 @default.
• W4293222016 cites W3121168429 @default.
• W4293222016 cites W3137413464 @default.
• W4293222016 cites W3158655122 @default.
• W4293222016 cites W3159801429 @default.
• W4293222016 cites W3173231467 @default.
• W4293222016 cites W3177453881 @default.
• W4293222016 cites W3177843959 @default.
• W4293222016 cites W3190223961 @default.
• W4293222016 cites W3205759305 @default.
• W4293222016 cites W3212741926 @default.
• W4293222016 cites W4206783989 @default.
• W4293222016 cites W4212883601 @default.
• W4293222016 cites W4225434025 @default.
• W4293222016 cites W4233045210 @default.
• W4293222016 doi "https://doi.org/10.5194/os-18-1221-2022" @default.
• W4293222016 hasPublicationYear "2022" @default.
• W4293222016 type Work @default.
• W4293222016 citedByCount "9" @default.
• W4293222016 countsByYear W42932220162022 @default.
• W4293222016 countsByYear W42932220162023 @default.
• W4293222016 crossrefType "journal-article" @default.
• W4293222016 hasAuthorship W4293222016A5010528158 @default.
• W4293222016 hasAuthorship W4293222016A5014455136 @default.
• W4293222016 hasAuthorship W4293222016A5024011878 @default.
• W4293222016 hasAuthorship W4293222016A5030077747 @default.

• next