Publication details

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


AMATO Filippo HAVEL Josef GAD Abd-Alla EL-ZEINY Ahmed

Year of publication 2014
Type Appeared in Conference without Proceedings
MU Faculty or unit

Faculty of Science

Description 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.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info