【摘要】 随着地震属性种类的增加,地震属性优选技术在地震勘探中越加重要。文章阐述了基于模型正演的属性优选、基于数理统计的属性优选、基于人工智能的属性优选方法;重点阐述了基于支持向量机(SVM)的属性优选,并将SVM方法用于煤层气预测中。实际结果表明,针对地震勘探中已知钻孔较少时,基于SVM的属性优选是一种有效的方法。更多还原

【Abstract】 The paper presents attribute optimization methods based on forward modeling,numerical statistics,and artificial intelligence respectively.The study is focused on the attribute optimization on the support vector machine(SVM) and its application in the coalbed methane prediction.The results show that the fewer the given boreholes in the seismic detection,the more effective the attribute optimization on SVM.更多还原