Prediction models of coal thickness based on seismic attributions and their applications
基于地震属性的煤层厚度预测模型及其应用

As a technology used widely in lithology and structural interpretation, seismic attribute technology has been playing an important role in coal and oil exploration. Based on 3_D seismic exploration data of coal seam 13-1 in the Xieqiao colliery, Huainan coal field of China, 28 seismic attributes are extracted. Through analysis of seismic attributes, four usable seismic attributes, such as average-peak-amplitude, kurtosis-in-amplitude, maximum-absolute-amplitude and slope rate of instantaneous-frequency, are selected as the basic analysis parameters of prediction models of coal thickness. Combined with the real drill data, the prediction models between coal thickness and multi attributes are established by using analytical methods of multivariant polynomial regression and BP neural networks(BPNN), and error analysis of predicting coal thickness is carried out. From the comparison of prediction results of coal thickness of coal seam 13-1 in the Xieqiao colliery, Huainan coal field of China by using these two models, it is concluded that the BPNN model has higher accuracy in predicting coal thickness.