A new methodology for identification of potential pay zones from well logs: Intelligent system establishment and application in the Eastern Junggar Basin, China

In recent years, as the exploration practices extend into more complicated formations, conventional well log interpretation has often shown its inaccuracy and limitations in identifying hydrocarbons. The Permian Wutonggou Formation hosts typical clastic reservoirs in the Eastern Junggar Basin. The sophisticated lithology characteristics cause complex pore structures and fluid properties. These all finally cause low well testing agreement rate using conventional methods. Eleven years＇ recent statistics show that 12 out of 15 water layers have been incorrectly identified as being oil or oil/water layers by conventional well log interpretation. This paper proposes a methodology called intelligent prediction and identification system （IPIS）. Firstly, parameters reflecting lithological, petrophysical and electrical responses which are greatly related to reservoir fluids have been selected carefully. They are shale content （Vsh）, numbered rock type （RN）, porosity （φ）, permeability （K）, true resistivity （RT） and spontaneous-potential （SP）. Secondly, Vsh, φ and K are predicted from well logs through artificial neural networks （ANNs）. Finally, all the six parameters are input into a neuro-fuzzy inference machine （NFIM） to get fluids identification results. Eighteen new layers of 145.3 m effective thickness were examined by IPIS. There is full agreement with well testing results. This shows the system＇s accuracy and effectiveness.

Bivariate macro-level safety analysis of non-motorized vehicle crashes and crash-involved road users

The high risk of injury resulting from non-motorized vehicle(NMV)crashes has created the goal of using the 3E strategy to comprehensively improve NMV safety.Traditional safety improvement methods identify hot zones generally by crash frequency or density,which is effective for roadway engineering improvements but neglects characteristics related to other improvements such as safety education.As safety education would be more effective if targeted at the residences of crash-involved road users,the traditional approach to hot zones may therefore provide biased results for such alternative countermeasures.After confirming that 77.17%of NMV crashes occurred outside the involved riders’areas of residence,this study compared the differences between the locations of crashes and the residences of NMV crash-involved riders in safety influencing factors and hot zone identification.A Poisson lognormal bivariate conditional autoregressive(PLN-BCAR)model was developed to account for potential correlations between crashes and involved riders.The model was compared with the univariate Poisson lognormal conditional autoregressive(UPLN-CAR)model and the bivariate Poisson lognormal conditional autoregressive(BPLNCAR)model;the PLN-BCAR model outperformed the other two models in its better interpretation of the influencing factors and its more efficient parameter estimation.Model results indicated that crashes were mainly associated with roadway and land use characteristics,while involved road users were mainly associated with socioeconomic and land use characteristics.The potential for safety improvement method was adopted to identify hot zones for countermeasure implementation.Results showed over 60%of the identified hot zones were inconsistent:they needed improvement in either engineering or education but not both.These findings can help target the type of improvement to better utilize resources for NMV safety.