Regression Analysis for Estimating Watershed Potentialities and Environmental Indicators Cover/Use Surface in Loukkos, Tangerois and Mediterranean Coastal Basin in Morocco
Ridouane Chalh1, Zohra Bakkoury2, Driss Ouazar3, Moulay Driss Hasnaoui4, Abdelkrim El Mouatasim5
1Ridouane Chalh, Ph.D Student, AMIPS Laboratory, Department of Computer Science, Ecole Mohammadia d’Ingénieurs, Mohammed V University, Rabat Morocco.
2Zohra Bakkoury, Dr. Professor, AMIPS Laboratory, Department of Computer Science, Ecole Mohammadia d’Ingénieurs, Mohammed V University, Rabat Morocco.
3Driss Ouazar, Dr. Professor, LASH Laboratory, Department of Civil Engineering, Ecole Mohammadia d’Ingénieurs, Mohammed V University, Rabat Morocco.
4Moulay Driss Hasnaoui, Dr. and Head, Department of Water Resources, Division Ministry Delegate Minister of Energy, Mines, Water Environment, Water, Rabat Morocco.
5Abdelkrim El Mouatasim, Dr. Professor, LabSI Laboratory, Department of Mathematic, FPO, Ibn Zohr University – Morocco
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 784-793 | Volume-8 Issue-5, March 2019 | Retrieval Number: E2900038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In domain of environmental science especially water resources discipline, the very interesting and challenging task is how to analyze, extract and visualize knowledge from large scale data sets. The recent evolution of science computer precisely web technology provides an important tool for data collection and analysis. This paper presents different scenarios of modeling technics represented by simple linear regression analysis applied to environment indicators data set up to 14.9 million lines analyzed and extracted from satellite image of Loukkos, Tangerois and Mediterranean Coastal (LTMC) Basin in Morocco. The purpose of this work is to estimates regression model’s parameters, using an optimization method represented by R function of simple linear regression so that the error of the sum for multiple and adjusted R-square is minimized. In this study an application on real data set analyzed and extracted from classified satellite image of (LTMC) basin. The classification of this satellite image contains different class of data sets such as: Agglomeration, dams, watercourses, crop lands, bare soils and forests…etc. The regression analysis is very important statistics method for analysis that enables the characterization of relationships among multiple relevant risk factors; also it enables the calculation of risk scores. The purpose of statistical evaluation of environmental indicators data set is often to describe relationships between two variables or among several variables. For example, in our case study one would like to know potentiality and cover/user surface of environmental indicators as cited. Y is The variable to be explained, or alternatively, the response variable, in our real data set represented by Altitude; and one or more variable that explain it, is called independent variable or predictor variable X in our real data set represented by combined surface area.
Keyword: Simple Linear Regression, R, Environmental Indicators Distribution, Satellite Image, Watershed Potentialities.
Scope of the Article: Regression and Prediction