This improvement is evident not only on the training data but, more importantly, on the validation data. In each case, we see a continuous improvement in predictive power as we progress from single-attribute regression to linear multiattribute prediction to neural network prediction. The method is applied to two real data sets. The validation error, which is the average error for all hidden wells, is used as a measure of the likely prediction error when the transform is applied to the seismic volume. The prediction error for the hidden well is then calculated. In this process, each well is systematically removed from the training set, and the transform is rederived from the remaining wells. To estimate the reliability of the derived multiattribute transform, crossvalidation is used. Because of its mathematical simplicity, the PNN appears to be the network of choice. Two types of neural networks have been evaluated: the multilayer feedforward network (MLFN) and the probabilistic neural network (PNN). TOC volumes from multi seismic attribute.
#Emerge multi attribute hampson russell software
In the nonlinear mode, a neural network is trained, using the selected attributes as inputs. Power user of Hampson Russell software for preStack and postStack seismic inversion, EMERGE for log prediction (eg.
#Emerge multi attribute hampson russell series
In the linear mode, the transform consists of a series of weights derived by least-squares minimization. An extension of conventional crossplotting involves the use of a convolutional operator to resolve frequency differences between the target logs and the seismic data. The selected subset is determined by a process of forward stepwise regression, which derives increasingly larger subsets of attributes. The objective is to derive a multiattribute transform, which is a linear or nonlinear transform between a subset of the attributes and the target log values. From the 3-D seismic volume a series of sample-based attributes is calculated.
R., dan Smith, H., 1996, Applied regression analysis, John Wiley and Sons, Inc. Bren, F., 2011, Identifikasi Litologi dan Porositas Menggunakan Analisa Inversi dan Multi-Atribut Seismik, Studi Kasus Lapangan Blackfoot, Tesis, UI. Its best if you avoid using common keywords when searching for Hampson Russell Software. Anonim, 2009, EMERGE: Multi-Attribute Analysis Workshop, Hampson-Russell Software Service, Ltd., Bali. New downloads are added to the member section daily and we now have 306,251 downloads for our members, including: TV, Movies, Software, Games, Music and More. The target logs theoretically may be of any type however, the greatest success to date has been in predicting porosity logs. Hampson Russell Software was added to DownloadKeeper this week and last updated on 2. The analysis data consist of a series of target logs from wells which tie a 3-D seismic volume. We describe a new method for predicting well-log properties from seismic data.