Remotely sensed soil data analysis using artificial neural networks. A case study of El-Fayoum depression, Egypt

AMATO, Filippo, Josef HAVEL, Abd-Alla GAD and Ahmed EL-ZEINY. Remotely sensed soil data analysis using artificial neural networks. A case study of El-Fayoum depression, Egypt. In ICRISSM 2014. 2014.

Basic information

• Original name: Remotely sensed soil data analysis using artificial neural networks. A case study of El-Fayoum depression, Egypt
• Authors: AMATO, Filippo (380 Italy, belonging to the institution), Josef HAVEL (203 Czech Republic, guarantor, belonging to the institution), Abd-Alla GAD (818 Egypt) and Ahmed EL-ZEINY (818 Egypt).
• Edition: ICRISSM 2014, 2014.

Other information

• Original language: English
• Type of outcome: Presentations at conferences
• Field of Study: 10406 Analytical chemistry
• Country of publisher: Egypt
• Confidentiality degree: is not subject to a state or trade secret
• RIV identification code: RIV/00216224:14310/14:00078217
• Organization unit: Faculty of Science
• Keywords in English: remote sensing; satellite data; artificial neural networks
• Tags: International impact, Reviewed

Abstract

Earth observation and monitoring of soil quality, long term changes of soil characteristics and deterioration processes such as degradation or desertification are among the most important objectives of remote sensing. The georeferenciation of such information contribute to the development and progress of Digital Earth project in the framework of information globalization process. Earth observation and soil quality monitoring via remote sensing are mostly based on the use of satellite spectral data. Advanced techniques are available to predict the soil or land use/cover categories from satellite imagery data. Artificial Neural Networks (ANNs) are among the most widely used tools for modeling and prediction purposes in various field of science. The assessment of satellite images quality and suitability for analysing the soil conditions (e.g., soil classification, land use/cover estimation, etc.) is fundamental. In this work, methodology for the preliminary data exploration and subsequent application of ANNs in remote sensing is presented. It consists of preliminary explorative data analysis and of ANNs application. The first stage is achieved via: (i) elimination of outliers, (ii) data pre-processing and (iii) the determination of the number of distinguishable soil “classes” via Eigenvalues Analysis (EA) and Principal Components Analysis (PCA). The next stage of ANNs use consists of: (i) building the training database, (ii) optimization of ANN architecture and database cleaning and (iii) training and verification of the network. Application of the proposed methodology will be given.

Links

• MSM0021622411, plan (intention): Name: Studium a aplikace plazmochemických reakcí v neizotermickém nízkoteplotním plazmatu a jeho interakcí s povrchem pevných látek

Investor: Ministry of Education, Youth and Sports of the CR, Study and application of plasma chemical reactions in non-isothermic low temperature plasma and its interaction with solid surface