A Comparison of Multiple Non-linear Regression and Neural Network Techniques for Sea Surface Salinity Estimation in the Tropical Atlantic Ocean Based on Satellite Data

نویسندگان

  • H. MOUSSA
  • M. A. BENALLAL
  • C. GOYET
  • N. LEFEVRE
  • F. TOURATIER
چکیده

Using measurements of Sea Surface Salinity and Sea Surface Temperature in the Western Tropical Atlantic Ocean, from 2003 to 2007 and 2009, we compare two approaches for estimating Sea Surface Salinity : Multiple Non-linear Regression and Multi Layer Perceptron. In the first experiment, we use 18,300 in situ data points to establish the two models, and 503 points for testing their extrapolation. In the second experiment, we use 15,668 in situ measurements for establishing the models, and 3,232 data points to test their interpolation. The results show that the Multiple Non-linear Regression is an admissible solution whether it be interpolation or extrapolation. Yet, the Multi Layer Perceptron can be used only for interpolation. Résumé. En utilisant des mesures de Salinité et de Température à la surface de la mer, dans l’ouest de l’océan Atlantique tropical, de 2003 à 2007 puis 2009, on compare deux approches pour la prédiction de la Salinité dans l’eau de mer de surface : la Régression Non-linéaire Multiple et le Perceptron Multi Couches. Dans la première expérience, 18 300 mesures in situ sont utilisées dans la construction des deux modèles et 503 points pour tester leur extrapolation. Dans la deuxième expérience, 15 668 mesures in situ sont utilisées pour établir les deux modèles et 3 232 points pour tester leur interpolation. Les résultats montrent que la Régression Non-linéaire Multiple peut être appliquée à la fois pour l’extrapolation et l’interpolation. Cependant, le Perceptron Multi Couches ne peut être utilisé que pour l’interpolation.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Study to determine the accuracy of satellite measurements for the salinity pattern and surface temperature of Persian Gulf using statistical method

The aim of this paper is to determine the sea surface salinity (SSS) and temperature (SST) of Persian Gulf by using the AMSU-B sensor data of NOAA-16 satellite. A multiple linear regression method was used by statistical computing software R on AMSU-B data and in-situ data. Based on the results, the correlation coefficient (R2) for salinity and temperature was 0.85 and 0.94, respectively. Also,...

متن کامل

Prediction of Soil Salinity Using Neural Network and Multivariate Regression Based on Remote Sensing Indices and Comparison: A Case Study of Qazvin plain's Salt Marsh

Introduction: The spatial and temporal distribution of salts in the soil, the great extent of the Iranian deserts, and the adverse climatic conditions prevailing over them make it difficult to accurately determine the parameters and field measurements in some cases. In the last two decades, the use of field techniques and their combination with remote sensing data has contributed significantly ...

متن کامل

Daily Pan Evaporation Estimation Using Artificial Neural Network-based Models

Accurate estimation of evaporation is important for design, planning and operation of water systems. In arid zones where water resources are scarce, the estimation of this loss becomes more interesting in the planning and management of irrigation practices. This paper investigates the ability of artificial neural networks (ANNs) technique to improve the accuracy of daily evaporation estimation....

متن کامل

Least Squares Techniques for Extracting Water Level Fluctuations in the Persian Gulf and Oman Sea

Extracting the main cyclic fluctuations from sea level changes of the Persian Gulf and Oman Sea is vital for understanding the behavior of tides and isolating non-tidal impacts such as those related to climate and changes in the ocean-sea circulations. This study compares two spectral analysis methods including: Least Squares Spectral Analysis (LSSA) and Least Squares Harmonic Estimation (LSHE)...

متن کامل

The optimized model of factors effecting on the Merger and Acquisition from multiple dimensions with neural network approach.

Nowadays, firms apply the merger and acquisition strategy for gaining synergy, increasing the wealth of stockholders, economics of scales, enhancing efficiency, increasing the ability to research and develop, developing the firm and decreasing the risk. Developing an optimized model with the ability to identify the effective variables on the merger and acquisition process has a significant ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015