Neural Nets: Applications in Geography

One — Looks and Uses.- 1.0 Origins and Growth.- 1.1 Conceptual Overview.- 1.2 Neural Net Structures.- 1.3 Implementing the Neural Net.- 1.4 Inevitable Caveats and Cautions.- 1.5 Where Next?.- Two — Neural Networks and their Applications.- 2.0 Introduction.- 2.1 Neural Network Language and Basic Operation.- 2.2 Multilayer Perceptrons and the Backpropagation of Error Algorithm.- 2.3 Kohonen’s Self-Organizing Feature Maps.- 2.4 Neural Networks and System Identification.- 2.5 Areas of Current Research.- Three — Neuro Classification of Spatial Data.- 3.0 Towards a Computational Geography.- 3.1 Whither Neuroclassification?.- 3.2 Review of Potential Neuroclassifier Architectures.- 3.3 Competitive Learning Nets.- 3.4 Self-Organizing Map.- 3.5 Adaptive Resonance Theory.- 3.6 Associative Memory Nets.- 3.7 Comparisons With Conventional Classifiers.- 3.8 Kohonen’s Self-Organizing Map.- 3.9 Conclusions.- ChapterChapter Four — Self Organizing Maps — Application to Census Data.- 4.0 South African Census Records.- 4.1 Net Classification.- 4.2 Interpretation of the Mapping Surface.- 4.3 Interpretation of Regions in the Mapping —The ‘Black’ Population.- 4.4 Spatial Distribution of the Mapping.- 4.5 Conclusions.- Five - Predicting Snowfall from Synoptic Circulation: A Comparison of Linear Regression and Neural Network Methodologies.- 5.0 Introduction.- 5.1 Data Preparation and Methodology.- 5.2 Principal Component Analysis — 700 mb Data.- 5.3 SNOTEL Data Preparation.- 5.4 Stepwise Multiple Regression Analyses.- 5.5 Five-Day Smoothed Results.- 5.6 Neural Network Analysis.- 5.7 Conclusions.- Six - Neural Computing and the Aids Pandemic: The Case of Ohio.- 6.0 The AIDS Pandemic, circa, 1993.- 6.1 Spatiotemporal Neural Forecasting.- 6.2 Neural Forecasting of the AIDSEpidemic.- 6.3 A Sensitivity Analysis.- 6.4 Neural Spatiotemporal Forecasting: Qualified Conclusions.- Seven - Precipitation Controls in Southern Mexico.- 7.0 The Issue.- 7.1 Southern Mexico Precipitation.- 7.2 Climate Representation in the Data Set.- 7.3 Neural Net Design and Training.- 7.4 Neural Net Interpretation-Theory.- 7.5 Neural Net Interpretation — Implementation.- 7.6 Precipitation Onset.- 7.7 Early Established Summer Rains.- 7.8 Late Summer Precipitation Maximum.- 7.9 Decay of the Summer Rains.- 7.10 Conclusions.- Eight - Classification of Arctic Cloud and Sea Ice Features in Multi-Spectral Satellite Data.- 8.0 Introduction.- 8.1 Cloud Detection and Classification.- 8.2 Cloud Pattern Analysis Using Texture.- 8.3 Discussion.- 8.4 Other Neural Network Applications to Cloud Classification.- 8.5 Sea Ice Fracture Patterns.- 8.6 Neural Network Approach.- 8.7 Conclusions.- Appendix I - Neural Network Resources.- Appendix II - Fortran 77 Listing for Kohonen Self Organizing Map.