Refining Altimeter-Derived Gravity Anomaly Model from Shipborne Gravity by Multi-Layer Perceptron Neural Network: A Case in the South China Sea

Shipborne gravity can be used to refine altimeter-derived gravity whose accuracy is low in shallow waters and areas with complex submarine topography. As altimeter-derived gravity only within a small radius around the shipborne data can be corrected by traditional methods, a new method based on multi-layer perceptron (MLP) neural network is proposed to refine the altimeter-derived gravity. Input variables of MLP include the positional information at observation points and geophysical information (from our own South China Sea gravity anomaly model (SCSGA) V1.0 and bathymetry model ETOPO1) at grid points around observation points. Output variables of MLP are the refined residual gravity anomalies at observation points. Training shipborne data are classified into four cases to train four MLP models, which are used to predict the refined gravity anomaly model SCSGA V1.1. Then all of the training shipborne data are used for training an MLP model to predict the refined gravity anomaly model SCSGA V1.2. Assessed by testing shipborne data, the accuracy of SCSGA V1.2 is 0.14 mGal higher than that of SCSGA V1.0, and similar to that of SCSGA V1.1. Compared with the original gravity anomaly model (SCSGA V1.0), the accuracy of the refined gravity anomaly model (SCSGA V1.2) by MLP is improved by 4.4% in areas where the training data are concentrated, and also improved by 2.2% in other areas. Therefore, the method of MLP can be used to refine the altimeter-derived gravity model by shipborne gravity, overcoming the problem of limited correction radius for traditional methods.

[1]  Mostafa Rabah,et al.  Comparison of Satellite Altimetric Gravity and Global Geopotential Models with Shipborne Gravity in the Red Sea , 2018 .

[2]  F. Paolo,et al.  Integrated marine gravity field in the Brazilian coast from altimeter-derived sea surface gradient and shipborne gravity , 2010 .

[3]  Walter H. F. Smith,et al.  New global marine gravity model from CryoSat-2 and Jason-1 reveals buried tectonic structure , 2014, Science.

[4]  A. Watts,et al.  On the accuracy of marine gravity measurements , 1988 .

[5]  Nikhil Ketkar,et al.  Deep Learning with Python , 2017 .

[6]  Jinyun Guo,et al.  Mean Sea Surface Model over the Sea of Japan Determined from Multi-Satellite Altimeter Data and Tide Gauge Records , 2020, Remote. Sens..

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  Yong Wang,et al.  Basement structures of East and South China Seas and adjacent regions from gravity inversion , 2016 .

[9]  Bathymetry from Space is Now Possible , 2003 .

[10]  A. Bobojć.  Application of Gravity Gradients in the Process of GOCE Orbit Determination , 2016, Acta Geophysica.

[11]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[12]  Jinyun Guo,et al.  Marine gravity determined from multi-satellite GM/ERM altimeter data over the South China Sea: SCSGA V1.0 , 2020, Journal of Geodesy.

[13]  Gilles Notton,et al.  Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions , 2014, ArXiv.

[14]  Jinyun Guo,et al.  How HY-2A/GM altimeter performs in marine gravity derivation: assessment in the South China Sea , 2019, Geophysical Journal International.

[15]  C. Amante,et al.  ETOPO1 arc-minute global relief model : procedures, data sources and analysis , 2009 .

[16]  Seafloor secrets revealed , 2014, Science.

[17]  Xiaoyun Wan,et al.  Seafloor Topography Estimation from Gravity Anomaly and Vertical Gravity Gradient Using Nonlinear Iterative Least Square Method , 2020, Remote. Sens..

[18]  Jinyun Guo,et al.  Performance of Jason-2/GM altimeter in deriving marine gravity with the waveform derivative retracking method: a case study in the South China Sea , 2020, Arabian Journal of Geosciences.

[19]  Walter H. F. Smith,et al.  Toward 1-mGal accuracy in global marine gravity from CryoSat-2, Envisat, and Jason-1 , 2013 .

[20]  Walter H. F. Smith,et al.  Gravity field recovery from geodetic altimeter missions , 2019, Advances in Space Research.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  R. Tenzer,et al.  Interpretation of the lithospheric structure beneath the Indian Ocean from gravity gradient data , 2019, Journal of Asian Earth Sciences.

[23]  Cyril Voyant,et al.  Multi-horizon solar radiation forecasting for Mediterranean locations using time series models , 2013, ArXiv.

[24]  Chengming Li,et al.  Local normal height connection across sea with ship-borne gravimetry and GNSS techniques , 2014, Marine Geophysical Research.

[25]  N. K. Pavlis,et al.  The development and evaluation of the Earth Gravitational Model 2008 (EGM2008) , 2012 .

[26]  P. Knudsen,et al.  The DTU17 Global Marine Gravity Field: First Validation Results , 2019, International Association of Geodesy Symposia.

[27]  P. Novák,et al.  Spatial and Spectral Analysis of Refined Gravity Data for Modelling the Crust–Mantle Interface and Mantle-Lithosphere Structure , 2012, Surveys in Geophysics.

[28]  Cheinway Hwang,et al.  Inverse Vening Meinesz formula and deflection-geoid formula: applications to the predictions of gravity and geoid over the South China Sea , 1998 .

[29]  Gerald Dibarboure,et al.  Gauging the Improvement of Recent Mean Sea Surface Models: A New Approach for Identifying and Quantifying Their Errors , 2018, Journal of Geophysical Research: Oceans.

[30]  Bang Yong Lee,et al.  Altimetry-Derived Gravity Predictions of Bathymetry by the Gravity-Geologic Method , 2011 .

[31]  Takeya Matsuda,et al.  The Goal of the “Integrated Ocean Resources Survey System (“INORSS”)” in the “Next-Generation Technology for Ocean Resources Exploration” of “SIP” , 2018, 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO).

[32]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[33]  David T. Sandwell,et al.  Inversion of marine gravity anomalies over southeastern China seas from multi-satellite altimeter vertical deflections , 2017 .

[34]  Emmanuel Prouff,et al.  Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures - Profiling Attacks Without Pre-processing , 2017, CHES.

[35]  Widyawan,et al.  Deep learning multilayer perceptron (MLP) for flood prediction model using wireless sensor network based hydrology time series data mining , 2017, 2017 International Conference on Innovative and Creative Information Technology (ICITech).

[36]  Yoshua Bengio,et al.  On the Expressive Power of Deep Architectures , 2011, ALT.

[37]  C. Hwang,et al.  Shallow‐water gravity anomalies from satellite altimetry: Case studies in the east china sea and Taiwan strait , 2008 .

[38]  Prem Kumar Kalra,et al.  Time Series Prediction with Multilayer Perceptron (MLP): A New Generalized Error Based Approach , 2008, ICONIP.

[39]  Marc A. Rosen,et al.  Application of sliding window technique for prediction of wind velocity time series , 2014 .

[40]  Rui Wang,et al.  Integrated data Processing for Multi-Satellite Missions and recovery of Marine Gravity Field , 2007 .

[41]  Cheinway Hwang,et al.  Gravity anomalies derived from Seasat, Geosat, ERS‐1 and TOPEX/POSEIDON altimetry and ship gravity: a case study over the Reykjanes Ridge , 1995 .

[42]  Christophe Macabiau,et al.  Low-Earth Orbit Determination from Gravity Gradient Measurements , 2016, ArXiv.