基于GA-BP神经网络算法的高密度电法非线性反演

高密度电法技术在煤矿地质灾害勘探中发挥着重要的作用。近年来,以BP（Backpropagation）神经网络为代表的一类非线性反演方法被广泛运用到高密度电法的反演中。针对BP神经网络方法在高密度电法反演中存在的易陷入局部极小、收敛缓慢、反演精度差等问题,将BP神经网络算法与遗传算法（Genetic Algorithm,简称GA算法）联合演算,实现高密度电法的二维非线性反演。通过典型地电模型对该方法进行验证,结果表明遗传算法能有效优化BP神经网络的权值和阈值,提高了算法的全局寻优性。      

基于遗传算法优化的BP神经网络在密度界面反演中的应用

BP神经网络方法在二维密度界面的反演中取得了较好的效果,但在反演三维界面时,由于模型更复杂、参数更多,BP神经网络的收敛速度和反演精度都有一定程度的下降。为了改善反演效果,本文利用遗传算法对BP神经网络的权值、阈值选择过程进行优化,获得了更好的网络模型;并将此模型应用于密度界面模型的反演中,预测误差从上百米减小到数十米,同时迭代计算步数减少了近2/3,有效减少了计算时间,反演结果更准确。利用基于遗传算法优化的BP神经网络反演了法国某地区莫霍面深度,预测相对误差仅为1.8%,取得了较好的应用效果。基于遗传算法优化的BP神经网络在密度界面的反演中具有良好的应用价值和研究前景。     

小波神经网络在重磁资料反演中的应用前景

对BP神经网络在重力密度界面反演以及小波分析在位场分离上的应用进行了深入的研究,进而对小波神经网络在重磁资料反演中的应用前景进行了分析、评价。     

多隐层BP神经网络模型在径流预测中的应用

基于人工神经网络基本原理和方法,构建多隐层BP神经网络径流预测模型,以新疆伊犁河雅马渡站径流预测为例进行分析,并构建常规单隐层BP以及RBF、GRNN神经网络模型作为对比分析模型,将各模型预测结果与文献[1]中的预测结果进行比较,结果表明:(1)多隐层BP神经网络径流预测模型泛化能力强,预测精度高,算法稳定,模型精度优于IEA-BP网络模型,表明研究建立的多隐层BP神经网络模型用于径流预测是合理可行的,是一种可以应用于水文径流预测预报的新方法.(2)RBF、GRNN神经网络径流预测模型预测精度高于常规单隐层BP网络模型,且RBF与GRNN神经网络模型具有收敛速度快、预测精度高、调整参数少,不易陷入局部极小值等优点,可以更快地预测网络,具有较大的计算优势.     

重力异常AlexNet深度神经网络反演

针对传统反演方法存在的初始模型依赖、计算时间较长等问题,提出了一种新的基于AlexNet深度神经网络的重力异常反演方法。该方法首先借鉴经典的深度神经网络AlexNet设计了一种用于重力异常反演的Alex反演网络(AlexInvNet),接着设计大量密度异常体模型并通过正演计算得到带标签的数据集,然后用该数据集训练AlexInvNet网络,最后将重力异常数据输入训练好的AlexInvNet网络直接得到反演结果。理论模型反演结果表明,该方法相较于全连接网络深度学习反演方法,能够更好地反演出异常体的位置和密度,具有较好的泛化能力和抗噪声能力。实测数据反演结果表明,该方法能有效解决重力异常反演问题。     

新场气田开发方案寻优的遗传优化神经网络模型

在深入剖析遗传算法GA和BP神经网络优势的基础上,提出了改进的遗传优化BP神经网络模型(简称GABP模型).该原理是利用遗传算法(GA)对BP神经网络的结构和连接权进行全局优化学习,从而获取最佳的网络模型.经前人大量研究表明:遗传算法的适应性好,对搜索空间没有任何特殊要求,且全局优化能力强,可以有效地在整个解空间寻优,但遗传算法存在局部调节能力较弱、容错性较差的不足.而神经网络的容错性较强,具有自组织、自适应和分布式储存的特点,它可以通过学习乖训练,进行模型结构的自组织,适应不同信息或信息模糊,以及推理规则不明确问题的处理,但神经网络方法又有搜索能力较差,容易陷入局部解之中的缺点.从上述二种方法的优缺点出发,按照取其所长,克己所短的原则,将二种方法有机地结合起来,构建了GABP模型及其算法.通过对新场气田开发方案优选的决策应用,表明该模型的评价结果准确合理,可为类似研究借鉴参考.     

围岩力学参数反演的GSA-BP神经网络模型及应用

针对遗传算法（GA）存在早熟现象和局部寻优能力较差等缺陷,引入具有很强局部搜索能力的模拟退火算法（SA）,组成改进的遗传模拟退火算法（GSA）提高优化问题的能力和求解质量。针对BP神经网络容易陷入局部最小和收敛速度慢等方面的不足,应用改进的遗传模拟退火算法搜索BP神经网络的最优权值和阀值,提高BP神经网络的预测精度,建立了围岩力学参数反分析的GSA-BP神经网络模型。将该模型应用于乌东德水电站右岸地下厂房围岩力学参数的反演分析中,根据监测围岩变形数据反演围岩力学参数,反演所得参数应用到正计算分析中,得出的计算位移与实测值吻合较好,说明该方法的有效性和应用于该工程的可行性。     

基于BP神经网络的测井相分析及沉积相识别

测井相分析是研究地层沉积相的一种手段。利用基于BP神经网络的测井相分析进行沉积相识别研究,首先将已知地区地层剖面划分为有限的测井相,通过对岩心及其对应的沉积相进行研究,用数学方法及知识推理确定各个测井相到沉积相的映射转换关系,并利用这种关系,建立沉积相库。在此基础上,运用MATLAB中的工具箱建立BP神经网络模型,把已知沉积相的测井曲线特征作为样本进行训练学习,并将提取的测井曲线特征进行分类识别,从而确定地层的沉积相。应用表明,BP神经网络能够快速完成沉积相识别,可靠性较高,可以用于测井相分析及沉积相研究。      

基于CASI & SASI航空高光谱的雄安新区西南部农田土壤 重金属镍含量反演研究

农田土壤中重金属元素富集会严重制约农作物的生长,且对人类健康造成潜在威胁。高光谱遥感数据具有极高的光谱分辨率,因而可在土壤重金属污染元素信息的定量研究中发挥重要作用。本文以雄安新区西南部及其周边农田土壤作为研究对象,在实验室测定土壤重金属元素Ni的含量,并与土壤可见-近红外高光谱数据建立土壤重金属Ni含量的定量估测模型,进一步基于CASI&SASI航空高光谱数据快速反演研究区农田土壤重金属Ni的含量,获取其分布特征。本文研究并建立了研究区土壤重金属元素基于不同光谱变换形式的多元逐步回归、偏最小二乘回归和BP神经网络统计估算模型,通过模型验证与对比,探索研究区土壤重金属Ni元素含量的最优反演模型。研究结果表明: （1）基于各光谱变换的BP神经网络模型的建模和预测精度整体上大于偏最小二乘法和多元逐步回归法模型,模型拟合精度高,预测能力较好;（2）综合来看,一阶微分处理能普遍改善模型预测效果,其中BP神经网络模型的一阶微分变换结果最佳,对于Ni元素建模精度R2高达97.1%,验证集精度R2高达98%以上;（3）选用精度最好的BP神经网络模型,通过CASI&SASI高光谱数据对研究区重金属Ni含量进行反演,反演结果与实测Ni含量数据一致性很好。     

基于T-S模型的模糊神经网络在边坡稳定评价中的应用

受地质、工程等众多因素的影响,岩土质边坡稳定性具有未确知性、随机性、模糊性、可变性等特点,很难用简单的力学、数学模型描述。提出了用基于Takagi-Sugeno模型的模糊神经网络来对边坡稳定性进行评价,该模型同时兼具神经网络和模糊逻辑二者的优点,既可以比较容易地处理模糊性的实际问题,又具有较好的学习能力。将此模型与BP神经网络模型同时应用于80个实际边坡样本进行训练和预测,结果表明该模型具有预测精度更高、收敛速度更快、预测结果与实际结果吻合度更高的特点     

Lithological facies identification in Iranian largest gas field: A comparative study of neural network methods

Determination of different facies in an underground reservoir with the aid of various applicable neural network methods can improve the reservoir modeling. Accordingly facies identification from well logs and cores data information is considered as the most prominent recent tasks of geological engineering. The aim of this study is to analyze and compare the five artificial neural networks (ANN) approaches with identification of various structures in a rock facies and evaluate their capability in contrast to the labor intensive conventional method. The selected networks considered are Backpropagation Neural Networks (BPNN), Radial Basis Function (RBF), Probabilistic Neural Networks (PNN), Competitive Learning (CL) and Learning Vector Quantizer (LVQ). All these methods have been applied in four wells of South Pars field, Iran. Data of three wells were employed for the networks training purpose and the fourth one was used to test and verify the trained network predictions. The results have demonstrated that all approaches have the ability of facies modeling with more than 65% of precision. According to the performed analysis, RBF, CL and LVQ methods could model the facies with the accuracy between 66 and 68 percent while PNN and BPNN techniques are capable of making predictions with more than 72% and 88.5% of precision, respectively. It can be concluded that the BPNN can generate most accurate results in comparison to the other type of networks but it is important to note that the other factors such as consuming the amount of time taken, simplicity and the less adjusted parameters as well as the acquired precisions should be considered. As a result, the model evaluation analysis used in this study can be useful for prospective surveys and cost benefit facies identification.     

An attention-constrained neural network with overall cognition for landslide spatial prediction

The occurrence of landslides is affected by various environmental factors. When predicting landslides, conventional neural networks optimize parameters using global connectivity, which limits their efficiency in extracting features of contributing factors. In this study, we developed an attention-constrained neural network with overall cognition (OC-ACNN) to focus on important features from the complex data. The method has four steps: (1) extract the overall cognition as the prior input based on historical landslide distribution and contributing factors, (2) embed an attention mechanism in hidden layers to allocate more weight to noteworthy features, (3) update weights and fit the nonlinear relationship by the back-propagation neural network (BPNN), and (4) generate prediction results using a classifier. This model was applied to the Sichuan-Tibet Highway, considering 10 predisposing factors and 1449 historical landslides. The evaluation results indicate that OC-ACNN (0.822) had a higher predictive capability than multiple linear regression (MLR, 0.734) and BPNN (0.789) in terms of the area under the receiver operating characteristic curve (AUC). Further, we compared different attention patterns and score functions for use with the proposed model. The results show that OC-ACNN offered greater predictive performance than Self-ACNN (without OC, 0.803) and that the improved cosine (0.822) score function had better results and stability than others (0.819 highest).

     

补偿模糊神经网络在储层参数预测中的应用

为了克服常规BP神经网络法在预测储层参数中出现学习速度慢、无法结合专家知识等不足，我们引入了补偿模糊神经网络。它是一个结合了补偿模糊逻辑和神经网络的混合系统，由面向控制和面向决策的神经元组成，其模糊运算采用动态的、全局优化运算，学习速度快、学习过程稳定，将其用于储层参数预测效果良好。     

Prediction of agriculture derived groundwater nitrate distribution in North China Plain with GIS-based BPNN

In recent years, nitrate contamination of groundwater has become a growing concern for people in rural areas in North China Plain (NCP) where groundwater is used as drinking water. The objective of this study was to simulate agriculture derived groundwater nitrate pollution patterns with artificial neural network (ANN), which has been proved to be an effective tool for prediction in many branches of hydrology when data are not sufficient to understand the physical process of the systems but relative accurate predictions is needed. In our study, a back propagation neural network (BPNN) was developed to simulate spatial distribution of NO₃-N concentrations in groundwater with land use information and site-specific hydrogeological properties in Huantai County, a typical agriculture dominated region of NCP. Geographic information system (GIS) tools were used in preparing and processing input–output vectors data for the BPNN. The circular buffer zones centered on the sampling wells were designated so as to consider the nitrate contamination of groundwater due to neighboring field. The result showed that the GIS-based BPNN simulated groundwater NO₃-N concentration efficiently and captured the general trend of groundwater nitrate pollution patterns. The optimal result was obtained with a learning rate of 0.02, a 4-7-1 architecture and a buffer zone radius of 400 m. Nitrogen budget combined with GIS-based BPNN can serve as a cost-effective tool for prediction and management of groundwater nitrate pollution in an agriculture dominated regions in North China Plain.     

Inversion of quasi-3D DC resistivity imaging data using artificial neural networks

The objective of this paper is to investigate the applicability of artificial neural networks in inverting quasi-3D DC resistivity imaging data. An electrical resistivity imaging survey was carried out along seven parallel lines using a dipole-dipole array to confirm the validation of the results of an inversion using an artificial neural network technique. The model used to produce synthetic data to train the artificial neural network was a homogeneous medium of 100Ωm resistivity with an embedded anomalous body of 1000Ωm resistivity. The network was trained using 21 datasets (comprising 12159 data points) and tested on another 11 synthetic datasets (comprising 6369 data points) and on real field data. Another 24 test datasets (comprising 13896 data points) consisting of different resistivities for the background and the anomalous bodies were used in order to test the interpolation and extrapolation of network properties. Different learning paradigms were tried in the training process of the neural network, with the resilient propagation paradigm being the most efficient. The number of nodes, hidden layers, and efficient values for learning rate and momentum coefficient have been studied. Although a significant correlation between results of the neural network and the conventional robust inversion technique was found, the ANN results show more details of the subsurface structure, and the RMS misfits for the results of the neural network are less than seen with conventional methods. The interpreted results show that the trained network was able to invert quasi-3D electrical resistivity imaging data obtained by dipole-dipole configuration both rapidly and accurately.     

基于卷积神经网络的磁异常反演

针对传统反演方法存在的初始模型依赖、计算时间较长等问题,提出一种基于卷积神经网络的磁异常反演方法。该方法首先设计大量磁异常体模型,进行正演模拟产生样本数据集;接着借鉴经典的卷积神经网络VGG-13设计了一种全新的VGG磁异常反演网络(VGGINV);然后使用样本数据集训练该网络,并优化网络参数;最后对理论模型和实测数据进行反演实验。实验结果表明,该方法可以准确地反演出磁异常体的位置和磁化强度,具有较强的学习能力和一定的泛化能力,能有效解决磁异常数据反演问题。     

Modeling of the Shale Volume in the Hendijan Oil Field Using Seismic Attributes and Artificial Neural Networks

Petrophysical properties have played an important and definitive role in the study of oil and gas reservoirs, necessitating that diverse kinds of information are used to infer these properties. In this study, the seismic data related to the Hendijan oil field were utilised, along with the available logs of 7 wells of this field, in order to use the extracted relationships between seismic attributes and the values of the shale volume in the wells to estimate the shale volume in wells intervals. After the overall survey of data, a seismic line was selected and seismic inversion methods (model-based, band limited and sparse spike inversion) were applied to it. Amongst all of these techniques, the model-based method presented the better results. By using seismic attributes and artificial neural networks, the shale volume was then estimated using three types of neural networks, namely the probabilistic neural network (PNN), multi-layer feed-forward network (MLFN) and radial basic function network (RBFN).