A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and management.At present,using well logging data to estimate reservoir physical parameters is an important means for reservoir evaluation.Based on the characteristics of large quantity and complexity of estimating process,we have attempted to design a nonlinear back propagation neural network model optimized by genetic algorithm(BPNNGA)for reservoir porosity prediction.This model is with the advantages of self-learning and self-adaption of back propagation neural network(BPNN),structural parameters optimizing and global searching optimal solution of genetic algorithm(GA).The model is applied to the Chang 8 oil group tight sandstone of Yanchang Formation in southwestern Ordos Basin.According to the correlations between well logging data and measured core porosity data,5 well logging curves(gamma ray,deep induction,density,acoustic,and compensated neutron)are selected as the input neurons while the measured core porosity is selected as the output neurons.The number of hidden layer neurons is defined as 20 by the method of multiple calibrating optimizations.Modeling results demonstrate that the average relative error of the model output is 10.77%,indicating the excellent predicting effect of the model.The predicting results of the model are compared with the predicting results of conventional multivariate stepwise regression algorithm,and BPNN model.The average relative errors of the above models are 12.83%,12.9%,and 13.47%,respectively.Results show that the predicting results of the BPNNGA model are more accurate than that of the other two,and BPNNGA is a more applicable method to estimate the reservoir porosity parameters in the study area.
Lin ChenWeibing LinPing ChenShu JiangLu LiuHaiyan Hu
Tight oil sandstone reservoirs with low porosity and permeability, which are an unconventional petroleum resource, have been discovered in the Jurassic intervals of the central Junggar Basin, the northwestern China. To reveal the accumulation mechanism, a relatively comprehensive research was conducted, including oil-source correlation, porosity evolution, and hydrocarbon charging history. The results show that crude oil of these tight sandstone reservoirs were mainly from Permian source rocks with some contribution from Jurassic source rocks. The reservoirs were buried at shallow depth（〈3 100 m） and exposed to weak diagenesis, and thus had high porosity（18.5%） when the Permian-sourced oil from Permian source rock was charging, indicating high GOI values（〉5%）. In contrast, the sandstone reservoir had already become tight and did not provide available space to accumulate oil due to severe compaction and cementation when hydrocarbon from Jurassic source rock filled, evidenced by low GOI values（〈5%）. Therefore, reservoir porosity controls the oil accumulation within tight sandstone. Whether tight sandstone reservoirs accumulate oil depends on the reservoir quality when hydrocarbons charge. Before the exploration of tight oil sandstone reservoirs, it should be required to investigate the relationship between oil charging history and porosity evolution to reduce the exploration risk and figure out the available targets.
A systematic analysis of southwestern Ordos Basin's sedimentary characteristics,internal architectural element association styles and depositional model was illustrated through core statistics,well logging data and outcrop observations in Chang 8 oil-bearing group.This analysis indicates that shallow water delta sediments dominated by a fluvial system is the primary sedimentary system of the Chang 8 oil-bearing group of the Yanchang Formation in southwestern Ordos Basin.Four microfacies with fine grain sizes are identified: distributary channels,sheet sandstone,mouth bar and interdistributary fines.According to the sandbody's spatial distribution and internal architecture,two types of sandbody architectural element associations are identified: amalgamated distributary channels and thin-layer lobate sandstone.In this sedimentary system,net-like distributary channels at the delta with a narrow ribbon shape compose the skeleton of the sandbody that extends further into the delta front and shades into contiguous lobate distribution sheet sandstone in the distal delta front.The mouth bar is largely absent in this system.By analyzing the palaeogeomorphology,the palaeostructure background,sedimentary characteristics,sedimentary facies types and spatial distribution of sedimentary facies during the Chang 8 period,a distinctive depositional model of the Chang 8 shallow water fluvial-dominated delta was established,which primarily consists of straight multi-phase amalgamated distributary channels in the delta plain,net-like distributary channels frequently diverting and converging in the proximal delta front,sheet sandstones with dispersing contiguous lobate shapes in the distal delta front,and prodelta or shallow lake mudstones.
