FN Archimer Export Format
PT J
TI Predicting sea surface salinity in a tidal estuary with machine learning
BT 
AF Guillou, Nicolas
   Chapalain, Georges
   Petton, Sébastien
AS 1:1;2:1;3:2;
FF 1:;2:;3:PDG-RBE-PFOM-LPI;
C1 Cerema, DTecREM, HA, Technopôle Brest-Iroise, Plouzané, France
   Ifremer, University of Brest, CNRS, IRD, LEMAR, Argenton, France
C2 CEREMA, FRANCE
   IFREMER, FRANCE
SI ARGENTON
SE PDG-RBE-PFOM-LPI
UM LEMAR
IN WOS Ifremer UMR
   DOAJ
   copubli-france
IF 2.9
TC 4
UR https://archimer.ifremer.fr/doc/00787/89933/95421.pdf
LA English
DT Article
DE ;Multilayer;Support vector;Random forest;River plume;Numerical model;Bay of Brest;perceptron;regression
AB As an indicator of exchanges between watersheds, rivers and coastal seas, salinity may provide valuable information about the exposure, ecological health and robustness of marine ecosystems, including especially estuaries. The temporal variations of salinity are traditionally approached with numerical models based on a physical description of hydrodynamic and hydrological processes. However, as these models require large computational resources, such an approach is, in practice, rarely considered for rapid turnaround predictions as requested by engineering and operational applications dealing with the ecological monitoring of estuaries. As an alternative efficient and rapid solution, we investigated here the potential of machine learning algorithms to mimic the non-linear complex relationships between salinity and a series of input parameters (such as tide-induced free-surface elevation, river discharges and wind velocity). Beyond regression methods, the attention was dedicated to popular machine learning approaches including MultiLayer Perceptron, Support Vector Regression and Random Forest. These algorithms were applied to six-year observations of sea surface salinity at the mouth of the Elorn estuary (bay of Brest, western Brittany, France) and compared to predictions from an advanced ecological numerical model. In spite of simple input data, machine learning algorithms reproduced the seasonal and semi-diurnal variations of sea surface salinity characterised by noticeable tide-induced modulations and low-salinity events during the winter period. Support Vector Regression provided the best estimations of surface salinity, improving especially predictions from the advanced numerical model during low-salinity events. This promotes the exploitation of machine learning algorithms as a complementary tool to process-based physical models. 
PY 2023
PD APR
SO Oceanologia
SN 0078-3234
PU Elsevier BV
VL 65
IS 2
UT 000984422100001
BP 318
EP 332
DI 10.1016/j.oceano.2022.07.007
ID 89933
ER

EF