International Journal of Electrical and Computer Engineering (IJECE) Vol. 8, No. 6, December 2018, pp. 4584~4592 ISSN: 2088-8708, DOI: 10.11591/ijece.v8i6.pp4584-4592  4584 Journal homepage: http://iaescore.com/journals/index.php/IJECE MetOp Satellites Data Processing for Air Pollution Monitoring in Morocco Mohamed Akram Zaytar, Chaker El Amrani Faculty of Science and Technology in Tangier, Abdelmalek Essaadi University, Laboratory of Informatics Systems and Telecommunications (LIST), Morocco Article Info ABSTRACT Article history: Received Jun 9, 2018 Revised Jul 1, 2018 Accepted Jul 20, 2018 This paper presents a data processing system based on an architecture comprised of multiple stacked layers of computational processes that transforms Raw Binary Pollution Data coming directly from Two EUMETSAT MetOp satellites to our servers, into ready to interpret and visualise continuous data stream in near real time using techniques varying from task automation, data preprocessing and data analysis to machine learning using feedforward artificial neural networks. The proposed system handles the acquisition, cleaning, processing, normalizing, and predicting of Pollution Data in our area of interest of Morocco. Keyword: Air pollution Data aggregation Data analysis Data processing Deep learning Copyright © 2018 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Mohamed Akram Zaytar, Department of Informatics, Laboratory of Informatics Systems and Telecommunications (LIST), Abdelmalek Essaadi University, PO. Box 416, Tangier, Morocco. Email: MedAkramZaytar@gmail.com 1. INTRODUCTION Over the last decade, Air Pollution environmental threats significantly increased [1]-[4], and Climate change effects became many and wide ranging [5]. There is no doubt that excessive levels of air pollution are causing a lot of damage to human and animal health as well as to the wider environment. For these reasons, careful scientific research and monitoring of air pollutants is a necessity that must be exercised with a great deal of attention and precision. Nowadays, as much as we want to quickly evaluate and conclude from existing pollution and climate data, most of the problems we face center around preparing, cleaning, processing, and transforming the large amounts of raw environmental data we receive from satellites in near real time. In our case, the raw data takes multiple primitive formats such as BUFR (Binary Universal Form for the Representation of meteorological data), GRIB 2, HRIT/LRIT, HRPT/LRPT. in this paper, we are going to present a system for processing BUFR based binary files coming directly from the satellite’s sensors and transform it into a data set that is ready for data analysis specific tasks likes inference and visualisation. The main source of the data we process is EUMETSAT. EUMETSAT is an intergovernmental operational satellite agency with a total of 30 European Member States. The organization’s mission statement is to gather accurate and reliable satellite data on weather, climate and the environment around the clock, and to deliver them to its member and cooperating states, international partners, and to users world-wide [6]. The data we are most interested in comes directly from a type of satellites named Metop. Metop is a series of three polar orbiting meteorological satellites, we currently get data from two of them, Metop-A and Metop-B, they both are in a lower polar orbit, at an altitude of approximately 817 kilometres, they provide