Unsupervised neural networks such as the Kohonen Self-Organizing Maps （SOM） have been widely used for searching natural clusters in multidimensional and massive data. One example where the data available for analysi...Unsupervised neural networks such as the Kohonen Self-Organizing Maps （SOM） have been widely used for searching natural clusters in multidimensional and massive data. One example where the data available for analysis can be extremely large is seismic interpretation for hydrocarbon exploration. In order to assist the interpreter in identifying characteristics of interest confined in the seismic data, the authors present a set of data attributes that can be used to train a SOM in such a way that zones of interest can be automatically identified or segmented, reducing time in the interpretation process. The authors show how to associate SOM to 2D color maps to visually identify the clustering structure of the input seismic data, and apply the proposed technique to a 2D synthetic seismic dataset of salt structures.展开更多
The classical multidimensional scaling(MDS) method is introduced and applied in the study of the hour-to-hour ionospheric variability based on the ionospheric fo F2 observed at three ionosonde stations in East-Asia in...The classical multidimensional scaling(MDS) method is introduced and applied in the study of the hour-to-hour ionospheric variability based on the ionospheric fo F2 observed at three ionosonde stations in East-Asia in 2002 and 2007. Results from the matrix eigen decompositions indicate that the annual part of the ionospheric variation is large in middle latitude and solar maximum period(2002) while low in the low latitude and solar minimum period(2007). The connectivity maps of the hour-to-hour ionospheric variability based on MDS method show some common diurnal features. The ionospheric connectivity between adjacent hours near noon hours and near midnight hours is high. The ionospheric connectivity between adjacent hours near sunrise hours and near sunset hours is poor, especially for the sunrise hours. Also there are latitudinal and solar activity dependences in this kind of connectivity. These results revealed from the ionospheric connectivity maps are useful physically and in practice for the ionospheric forecasting on the hour-to-hour scale.展开更多
文摘Unsupervised neural networks such as the Kohonen Self-Organizing Maps （SOM） have been widely used for searching natural clusters in multidimensional and massive data. One example where the data available for analysis can be extremely large is seismic interpretation for hydrocarbon exploration. In order to assist the interpreter in identifying characteristics of interest confined in the seismic data, the authors present a set of data attributes that can be used to train a SOM in such a way that zones of interest can be automatically identified or segmented, reducing time in the interpretation process. The authors show how to associate SOM to 2D color maps to visually identify the clustering structure of the input seismic data, and apply the proposed technique to a 2D synthetic seismic dataset of salt structures.
基金supported by the National Natural Science Foundation of China(Grant Nos.41174134,41274156)the National Basic Research Program of China(Grant No.2011CB811405)
文摘The classical multidimensional scaling(MDS) method is introduced and applied in the study of the hour-to-hour ionospheric variability based on the ionospheric fo F2 observed at three ionosonde stations in East-Asia in 2002 and 2007. Results from the matrix eigen decompositions indicate that the annual part of the ionospheric variation is large in middle latitude and solar maximum period(2002) while low in the low latitude and solar minimum period(2007). The connectivity maps of the hour-to-hour ionospheric variability based on MDS method show some common diurnal features. The ionospheric connectivity between adjacent hours near noon hours and near midnight hours is high. The ionospheric connectivity between adjacent hours near sunrise hours and near sunset hours is poor, especially for the sunrise hours. Also there are latitudinal and solar activity dependences in this kind of connectivity. These results revealed from the ionospheric connectivity maps are useful physically and in practice for the ionospheric forecasting on the hour-to-hour scale.
