基于计算岩石物理方法的页岩储层弹性参数提取

发展了应用数值计算方法获取页岩储层的速度、各向异性参数的计算岩石物理系列方法.该系列方法包括了大尺度精细地质模型数值建模、计算网格尺度的地球物理建模和地震波数值模拟提取岩石物理弹性参数.本文方法利用储层的统计数据而不是具体岩心的测量数据,可获得储层岩石物理弹性参数的变化规律.相比于基于岩心测试的岩石物理方法,本文方法可精细考虑实际储层的非均匀特征,可得到岩心测试难以求取的与尺寸效应高度相关的弹性参数,也避免了求取弹性参数变化规律时获取不同地质特征岩心的困难.本文发展了计算岩石物理方法,为计算岩石物理面临的大尺度地质建模和计算能力限制问题提供了有效的解决方案.文中以胜利罗家的页岩储层为例,求得了储层TOC含量从3%到21%变化情况下储层的P波、S波速度以及各向异性参数变化规律.     

River flow time series prediction with a range-dependent neural network

Abstract

Artificial neural networks provide a promising alternative to hydrological time series modelling. However, there are still many fundamental problems requiring further analyses, such as structure identification, parameter estimation, generalization, performance improvement, etc. Based on a proposed clustering algorithm for the training pairs, a new neural network, namely the range-dependent neural network (RDNN) has been developed for better accuracy in hydrological time series prediction. The applicability and potentials of the RDNN in daily streamflow and annual reservoir inflow prediction are examined using data from two watersheds in China. Empirical comparisons of the predictive accuracy, in terms of the model efficiency R² and absolute relative errors (ARE), between the RDNN, back-propagation (BP) networks and the threshold auto-regressive (TAR) model are made. The case studies demonstrated that the RDNN network performed significantly better than the BP network, especially for reproducing low-flow events.     

Extreme learning machine for the displacement prediction of landslide under rainfall and reservoir level

Landslide prediction is always the emphasis of landslide research. Using global positioning system GPS technologies to monitor the superficial displacements of landslide is a very useful and direct method in landslide evolution analysis. In this paper, an EEMD–ELM model [ensemble empirical mode decomposition (EEMD) based extreme learning machine (ELM) ensemble learning paradigm] is proposed to analysis the monitoring data for landslide displacement prediction. The rainfall data and reservoir level fluctuation data are also integrated into the study. The rainfall series, reservoir level fluctuation series and landslide accumulative displacement series are all decomposed into the residual series and a limited number of intrinsic mode functions with different frequencies from high to low using EEMD technique. A novel neural network technique, ELM, is employed to study the interactions of these sub-series at different frequency affecting landslide occurrence. Each sub-series extracted from accumulative displacement of landslide is forecasted respectively by establishing appropriate ELM model. The final prediction result is obtained by summing up the calculated predictive displacement value of each sub. The EEMD–ELM model shows the best accuracy comparing with basic artificial neural network models through forecasting the displacement of Baishuihe landslide in the Three Gorges reservoir area of China.     

基于改进U-Net卷积神经网络的储层预测

传统的U-Net卷积神经网络大多存在深层网络梯度消失的问题。本文在U-Net卷积神经网络中加入残差模块,提出了一种改进U-Net卷积神经网络。残差模块保证了U-Net卷积神经网络在误差反向传播过程中梯度的存在,在一定程度上可以缓解梯度消失的问题。最后将改进U-Net卷积神经网络应用于实际储层预测中,实际数据测试结果表明基于改进U-Net卷积神经网络在岩性识别以及“甜点”预测上均能取得较好的效果。      

A comparative study of extensive machine learning models for predicting long-term monthly rainfall with an ensemble of climatic and meteorological predictors

Rainfall prediction is of vital importance in water resources management. Accurate long-term rainfall prediction remains an open and challenging problem. Machine learning techniques, as an increasingly popular approach, provide an attractive alternative to traditional methods. The main objective of this study was to improve the prediction accuracy of machine learning-based methods for monthly rainfall, and to improve the understanding of the role of large-scale climatic variables and local meteorological variables in rainfall prediction. One regression model autoregressive integrated moving average model (ARIMA) and five state-of-the-art machine learning algorithms, including artificial neural networks, support vector machine, random forest (RF), gradient boosting regression, and dual-stage attention-based recurrent neural network, were implemented for monthly rainfall prediction over 25 stations in the East China region. The results showed that the ML models outperformed ARIMA model, and RF relatively outperformed other models. Local meteorological variables, humidity, and sunshine duration, were the most important predictors in improving prediction accuracy. 4-month lagged Western North Pacific Monsoon had higher importance than other large-scale climatic variables. The overall output of rainfall prediction was scalable and could be readily generalized to other regions.     

Wavelet analysis-based projection pursuit autoregression model and its application in the runoff forecasting of Li Xiangjiang basin

ABSTRACT

The wavelet analysis technique was combined in this study with the projection pursuit autoregression (PPAR) model, and a new mid- and long-term runoff forecasting model, the wavelet analysis-based PPAR (PPAR-WA) is proposed, which realizes runoff forecasting from the perspective of the internal mechanism of a sequence. The runoff forecasting of the leading hydropower station in the Li Xianjiang cascade reservoirs in China was carried out to test the performance of the proposed model, and the accuracy and stability of the forecasting results were evaluated and analysed. The results show that the average relative error of the forecasting period can reach 9.6%, and the best relative error is less than 5% in some years. In addition, compared with PPAR, a back-propagation neural network and autoregression moving average model through three evaluation indexes, the results of PPAR-WA have higher accuracy and stronger stability. So, it has a certain value of popularization and application.     

Fracture-frequency prediction from borehole wireline logs using artificial neural networks

Borehole-wall imaging is currently the most reliable means of mapping discontinuities within boreholes. As these imaging techniques are expensive and thus not always included in a logging run, a method of predicting fracture frequency directly from traditional logging tool responses would be very useful and cost effective. Artificial neural networks (ANNs) show great potential in this area. ANNs are computational systems that attempt to mimic natural biological neural networks. They have the ability to recognize patterns and develop their own generalizations about a given data set. Neural networks are trained on data sets for which the solution is known and tested on data not previously seen in order to validate the network result. We show that artificial neural networks, due to their pattern recognition capabilities, are able to assess the signal strength of fracture-related heterogeneity in a borehole log and thus fracture frequency within a borehole. A combination of wireline logs (neutron porosity, bulk density, P-sonic, S-sonic, deep resistivity and shallow resistivity) were used as input parameters to the ANN. Fracture frequency calculated from borehole televiewer data was used as the single output parameter. The ANN was trained using a back-propagation algorithm with a momentum learning function. In addition to fracture frequency within a single borehole, an ANN trained on a subset of boreholes in an area could be used for prediction over the entire set of boreholes, thus allowing the lateral correlation of fracture zones.     

Comparison of daily streamflow forecasts using extreme learning machines and the random forest method

ABSTRACT

Daily streamflow forecasting is a challenging and essential task for water resource management. The main goal of this study was to compare the accuracy of five data-driven models: extreme learning machine (basic ELM), extreme learning machine with kernels (ELM-kernel), random forest (RF), back-propagation neural network (BPNN) and support vector machine (SVR). The results show that the ELM-kernel model provided a superior alternative to the other models, and the basic ELM model had the poorest performance. To further evaluate the predictive capacities of the five models, the estimations of low flow and high flow in the testing dataset were compared. The RF model was slightly superior to the other models in predicting the peak flows, and the ELM-kernel model showed the highest prediction precision of low flows. There was no single model that showed obvious advantages over the other models in this study. Therefore, further exploration is required for the hydrological forecasting problems.     

龙马溪组页岩数字岩心LSM-RVM数值建模方法研究及TOC含量影响分析

页岩气储层中含有大量有机碳(TOC),其丰度与成熟度对页岩力学特性有重要影响.建立包含TOC的精细数值模型,将有助于探索页岩微结构与矿物组分含量对等效弹性模量的作用程度,是“甜点区”预测的重要理论基础.本文提出了一种离散数值建模方法,基于高精度成像技术,采用晶格弹簧-随机孔隙耦合模型(LSM-RVM)模拟包含多种矿物组分及不同成熟度干酪根的数字岩心,分析TOC成熟度及含量对弹性参数的影响.在该模型中,参数设置(数值阻尼与加载应变速率)至关重要,选取不当会对计算精度造成一定影响.研究结果表明,LSM-RVM能够生成符合TOC及多种矿物实际分布特征的数值模型,是一种精细数值建模方法.     

New method for prediction of shale gas content in continental shale formation using well logs

Shale needs to contain a sufficient amount of gas to make it viable for exploitation. The continental heterogeneous shale formation in the Yan-chang (YC) area is investigated by firstly measuring the shale gas content in a laboratory and then investigating use of a theoretical prediction model. Key factors controlling the shale gas content are determined, and a prediction model for free gas content is established according to the equation of gas state and a new petrophysical volume model. Application of the Langmuir volume constant and pressure constant obtained from results of adsorption isotherms is found to be limited because these constants are greatly affected by experimental temperature and pressures. Therefore, using measurements of adsorption isotherms and thermodynamic theory, the influence of temperature, total organic carbon (TOC), and mineralogy on Langmuir volume constants and pressure constants are investigated in detail. A prediction model for the Langmuir pressure constant with a correction of temperatures is then established, and a prediction model for the Langmuir volume constant with correction of temperature, TOC, and quartz contents is also proposed. Using these corrected Langmuir constants, application of the Langmuir model determined using experimental adsorption isotherms is extrapolated to reservoir temperature, pressure, and lithological conditions, and a method for the prediction of shale gas content using well logs is established. Finally, this method is successfully applied to predict the shale gas content of the continental shale formation in the YC area, and practical application is shown to deliver good results with high precision.     

Quantitative characterization of reservoir space in the Lower Silurian Longmaxi Shale,southern Sichuan,China

Based on the drilling data of the Upper Ordovician Wufeng Shale and the Lower Silurian Longmaxi Shale in southern Sichuan Basin,the construction of matrix pores and the development condition of fractures in a marine organic-rich shale are quantitatively evaluated through the establishment of the reservoir petrophysical models and porosity mathematical models.Our studies show that there are four major characteristics of the Longmaxi Shale confirmed by the quantitative characterization:(1)the pore volume of per unit mass is the highest in organic matter,followed in clay minerals,finally in brittle minerals;(2)the porosity of the effective shale reservoir is moderate and equal to that of the Barnett Shale,and the main parts of the shale reservoir spaces are interlayer pores of clay minerals and organic pores;(3)the porosity of the organic-rich shale is closely related to TOC and brittle mineral/clay mineral ratio,and mainly increases with TOC and clay mineral content;(4)fractures are developed in this black shale,and are mainly micro ones and medium-large ones.In the Longmaxi Shale,the fracture density increases from top to bottom,reflecting the characteristics with high brittle mineral content,high Young’s modulus,low Poisson's ratio and high brittleness at its bottom.     

New proposed method for prediction of reservoir sedimentation distribution

Prediction of sediment distribution in reservoirs is an important issue for dam designers to determine the reservoir active storage capacity.Methods proposed to calculate sediment distribution are varied,and mainly empirical.Among all the methods currently available,only area-reduction and areaincrement methods are considered as the principal methods for prediction of sediment distribution.In this paper,data of 16 reservoirs in the United States are used to propose a new empirical method for prediction of sediment distribution in reservoirs.In the proposed method,reservoir sediment distribution is related to sediment volume and original reservoir characteristics.To validate the accuracy of the new proposed method,obtained results are compared with survey data for two reservoirs.The results of this investigation showed that the proposed method has an acceptable accuracy.     

Seismic activity prediction using computational intelligence techniques in northern Pakistan

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar’s statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.     

Prediction of effective porosity from seismic attributes using locally linear model tree algorithm

In this study, a locally linear model tree algorithm was used to optimize a neuro‐fuzzy model for prediction of effective porosity from seismic attributes in one of Iranian oil fields located southwest of Iran. Valid identification of effective porosity distribution in fractured carbonate reservoirs is extremely essential for reservoir characterization. These high‐accuracy predictions facilitate efficient exploration and management of oil and gas resources. The multi‐attribute stepwise linear regression method was used to select five out of 26 seismic attributes one by one. These attributes introduced into the neuro‐fuzzy model to predict effective porosity. The neuro‐fuzzy model with seven locally linear models resulted in the lowest validation error. Moreover, a blind test was carried out at the location of two wells that were used neither in training nor validation. The results obtained from the validation and blind test of the model confirmed the ability of the proposed algorithm in predicting the effective porosity. In the end, the performance of this neuro‐fuzzy model was compared with two regular neural networks of a multi‐layer perceptron and a radial basis function, and the results show that a locally linear neuro‐fuzzy model trained by a locally linear model tree algorithm resulted in more accurate porosity prediction than standard neural networks, particularly in the case where irregularities increase in the data set. The production data have been also used to verify the reliability of the porosity model. The porosity sections through the two wells demonstrate that the porosity model conforms to the production rate of wells. Comparison of the locally linear neuro‐fuzzy model performance on different wells indicates that there is a distinct discrepancy in the performance of this model compared with the other techniques. This discrepancy in the performance is a function of the correlation between the model inputs and output. In the case where the strength of the relationship between seismic attributes and effective porosity decreases, the neuro‐fuzzy model results in more accurate prediction than regular neural networks, whereas the neuro‐fuzzy model has a close performance to neural networks if there is a strong relationship between seismic attributes and effective porosity. The effective porosity map, presented as the output of the method, shows a high‐porosity area in the centre of zone 2 of the Ilam reservoir. Furthermore, there is an extensive high‐porosity area in zone 4 of Sarvak that extends from the centre to the east of the reservoir.     

基于随机森林算法的陆相沉积烃源岩定量地震刻画:以东海盆地长江坳陷为例

烃源岩的定量地震刻画对于勘探开发区块的优选、盆地油气资源量的估算都具有重要意义.陆相沉积环境下的浅湖或半深湖相的烃源岩横向变化快,其空间展布需要依靠钻井约束下的反射地震进行刻画,但是其地震弹性特征与岩性和有机质含量的映射关系呈现高度非线性化,因而很难利用传统基于地震岩石物理模型驱动的烃源岩地震预测方法进行有效刻画.本文...     

支持向量机及其在地震预报中的应用前景

统计学习理论(SLT)是研究小样本情况下机器学习规律的理论。支持向量机(SVM)基于统计学习理论,可以处理高度非线性分类和回归等问题,不但较好地解决了小样本、过学习、高维数、局部最小等实际难题,而且具有很强的泛化(预测)能力。本文介绍了支持向量机的分类、回归方法,分析了这一方法的特点,讨论了该方法在地震预报中的应用前景。     

Prediction of the spatial distribution of the modified mercalli intensity using neural networks

This paper presents the development of an adaptive, non-parametric forecast model for the direct prediction of the spatial distribution of the Modified Mercalli Intensity (MMI) corresponding to an earthquake scenario. The model is based on recent advances in neural networks computation, and is constructed through supervised learning using historical earthquake and regional geological data as training sets. A MMI forecast model for moderate earthquakes with magnitudes between 6 and 7 was developed based on data from the Loma Prieta, Coalinga and Morgan Hill earthquakes. For these data sets, the neural networks forecast model is shown to have excellent data synthesis capability; multiple sets of data can be encapsulated by a relatively simple network architecture. Limited comparison of forecasts made by the neural networks model and conventional models demonstrates that improved accuracy can be achieved. Implementation and operational advantages of the neural networks approach such as general input features, minimum preconceived knowledge of the data sets, the ability to learn and to adapt incrementally and the autonomous and automatic synthesis of the structure underlying the data sets, have been illustrated.     

页岩气储层纵横波叠前联合反演方法

杨氏模量与密度乘积(Eρ)能够突显页岩气储层的异常特征,泊松比能够指示储层的含流体性.与常规叠前弹性参数反演相比,基于Eρ、泊松比和密度的叠前纵横波联合反演可以获得更加精确的弹性参数,为页岩气储层识别和流体预测提供可靠的依据.首先,推导了基于Eρ、泊松比和密度的纵波和转换波反射系数近似方程,利用典型模型对新推导的反射系数方程做精度分析,当入射角小于30°时,新推导的反射系数公式具有较高的精度;其次,充分利用纵波和转换波的信息,在贝叶斯的框架下,建立叠前纵横波联合反演流程,进行Eρ、泊松比和密度的直接反演,避免了间接反演带来的累积误差;最后,利用实际工区井模型数据进行算法测试,结果表明,该反演方法所获得的Eρ、泊松比和密度的估计值与真实值吻合较好,满足精细地震反演的精度要求.     

A new fluid factor and its application using a deep learning approach

Amplitude interpretation for hydrocarbon prediction is an important task in the oil and gas industry. Seismic amplitude is dominated by porosity, the volume of clay, pore-filled fluid type and lithology. A few seismic attributes are proposed to predict the existence of hydrocarbon. This paper proposes a new fluid factor by adding a correct item based on the J attribute. The algorithm is verified through stochastic Monte Carlo modelling that contains various rock physical properties of sand and shale. Both gas and oil responses are separated by the new fluid factor. Furthermore, an approach based on the neural network model is trained using the deep learning method to predict the new fluid factor. The confusion matrix shows that this model performs well. This model allows the application of the new fluid factor in the seismic data. In this study, the Marmousi II data set is used to examine the performance of the new fluid factor, and the result is good. Most hydrocarbon reservoirs are identified in the shale–sandstone sequences. The combination of deep learning and the new fluid factor provides a more accurate way for hydrocarbon prediction.