Estimating the Shapes of Gravity Sources through Optimized Support Vector Classifier (SVC)

In gravity interpretation methods, an initial guess for the approximate shape of the gravity source is necessary. In this paper, the support vector classifier (SVC) is applied for this duty by using gravity data. It is shown that using SVC leads us to estimate the approximate shapes of gravity sources more objectively. The procedure of selecting correct features is called feature selection (FS).In this research, the proper features are selected using inter/intra class distance algorithm and also FS is optimized by increasing and decreasing the number of dimensions of features space. Then, by using the proper features, SVC is used to estimate approximate shapes of sources from the six possible shapes, including: sphere, horizontal cylinder, vertical cylinder, rectangular prism, syncline, and anticline. SVC is trained using 300 synthetic gravity profiles and tested by 60 other synthetic and some real gravity profiles (related to a well and two ore bodies), and shapes of their sources estimated properly.     

Test of the Hypothesis for an Unknown Distant Massive Planet in the Solar System Applying Tisserand’s Criterion to a System of Long-Period Comets

Earth, Moon, and Planets - One meter class telescopes could bring important contributions in the acquisition of lightcurves of near earth asteroids (NEAs), based on which rotations and other...     

利用支持向量分类(SVC)估算断层深度和特征选择(英文)

地下断层深度的估算是重力解释难题之一,我们试利用支持向量分类(SVC)法进行计算。使用正演和非线性反演技术,通过相关误错使检测地下断层深度成为可能。但必要有一个深度初始猜测值,而且这猜测值通常不是由重力资料得。本文我们介绍以SVC作为利用重力数据估算断层深度的一种手段。在这项研究中,我们假设一种地下断层深度可归为一种类型,SVC作为一个分类算法。为了有效地利用此SVC算法,我们基于一个正确的特征选择算法去选择正确的深度特征。本次研究中我们建立了一套基于不同深度地下断层的合成重力剖面训练集,用以训练用于计算实际的地下断层深度的SVC代码。然后用其它合成重力剖面训练集测试我们训练的SVC代码,同时也用实际资料验证了我们的训练SVC代码。