Since 1994 the European Commission has been supporting activities under the Environment and Climate programme of research and technological de­ velopment, with the aim of developing cost-effective applications of satellite Earth observation (EO) for both environmental monitoring and research.

Open Questions in Neurocomputing for Earth Observation.- A Comparison of the Characterisation of Agricultural Land Using Singular Value Decomposition and Neural Networks.- Land Cover Mapping from Remotely Sensed Data with a Neural Network: Accommodating Fuzziness.- Geological Mapping Using Multi-Sensor Data: A Comparison of Methods.- Application of Neural Networks and Order Statistics Filters to Speckle Noise Reduction in Remote Sensing Imaging.- Neural Nets and Multichannel Image Processing Applications.- Neural Networks for Classification of Ice Type Concentration from ERS-1 SAR Images. Classical Methods versus Neural Networks.- A Neural Network Approach to Spectral Mixture Analysis.- Comparison Between Systems of Image Interpretation.- Feature Extraction for Neural Network Classifiers.- Spectral Pattern Recognition by a Two-Layer Perceptron: Effects of Training Set Size.- Comparison and Combination of Statistical and Neural Network Algorithms for Remote-Sensing Image Classification.- Integrating the Alisa Classifier with Knowledge-Based Methods for Cadastral-Map Interpretation.- A Hybrid Method for Preprocessing and Classification of SPOT Images.- Testing some Connectionist Approaches for Thematic Mapping of Rural Areas.- Using Artificial Recurrent Neural Nets to Identify Spectral and Spatial Patterns for Satellite Imagery Classification of Urban Areas.- Dynamic Segmentation of Satellite Images Using Pulsed Coupled Neural Networks.- Non-Linear Diffusion as a Neuron-Like Paradigm for Low-Level Vision.- Application of the Constructive Mikado-Algorithm on Remotely Sensed Data.- A Simple Neural Network Contextual Classifier.- Optimising Neural Networks for Land Use Classification.- High Speed Image Segmentation Using a Binary Neural Network.- Efficient Processing and Analysis of Images Using Neural Networks.- Selection of the Number of Clusters in Remote Sensing Images by Means of Neural Networks.- A Comparative Study of Topological Feature Maps Versus Conventional Clustering for (Multi-Spectral) Scene Identification in METEOSAT Imagery.- Seif Organised Maps: the Combined Utilisation of Feature and Novelty Detectors.- Generalisation of Neural Network Based Segmentation Results for Classification Purposes.- Remote Sensing Applications Which may be Addressed by Neural Networks Using Parallel Processing Technology.- General Discussion.

Application of neural networks in remote sensing - Combination of advanced computing techniques and operational remote sensing needs - Presentation of state of the art techniques used across Europe for remote sensing data analysis, with a considerable range of applications - Comprehensive assessment of the potential role of neural computation in the processing of data from earth observation satellites.