A novel and generalized approach in the inversion of geoelectrical resistivity data using Artificial Neural Networks (ANN)

The non-linear apparent resistivity problem in the subsurface study of the earth takes into account the model parameters in terms of resistivity and thickness of individual subsurface layers using the trained synthetic data by means of Artificial Neural Networks (ANN). Here we used a single layer feed-forward neural network with fast back propagation learning algorithm. So on proper training of back propagation networks it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data with reference to the synthetic data trained in the appropriate network. During training, the weights and biases of the network are iteratively adjusted to make network performance function level more efficient. On adequate training, errors are minimized and the best result is obtained using the artificial neural networks. The network is trained with more number of VES data and this trained network is demonstrated by the field data. The accuracy of inversion depends upon the number of data trained. In this novel and specially designed algorithm, the interpretation of the vertical electrical sounding has been done successfully with the more accurate layer model.     

直流电阻率测深二维自适应正则化反演

直流电阻率测深二维反演中,正则化参数的选取影响反演结果分辨率及反演过程稳定性。利用主动约束平衡正则化因子,进行直流电阻率光滑约束最小二乘二维自适应反演,改善直流电阻率测深二维反演的分辨率与稳定性。在反演迭代过程中,正则化因子根据模型参数的空间展布函数进行自适应计算、正则化参数的自适应计算。模拟数据反演结果验证了该方法的有效性与可行性,反演结果能准确地反映地下模型的真实电性结构。     

Effects of galvanic distortions on magnetotelluric data: Interpretation and its correction using deep electrical data

The non-inductive galvanic disturbances due to surficial bodies, lying smaller than high frequency skin depth, cause serious interpretational errors in magnetotelluric data. These frequency independent distortions result in a quasi-static shift between the apparent resistivity curves known as static shift. Two-dimensional modelling studies, for the effects of surficial bodies on magnetotelluric interpretation, show that the transverse electric (TE) mode apparent resistivity curves are hardly affected compared to the transverse magnetic (TM) mode curves, facilitating the correction by using a curve shifting method to match low frequency asymptotes. But in the case of field data the problem is rather complicated because of the random distribution of geometry and conductivity of near surface inhomogeneities. Here we present the use of deep resistivity sounding (DRS) data to constrain MT static shift. Direct current sensitivity studies show that the behaviour of MT static shift can be estimated using DC resistivity measurements close to the MT sounding station to appreciable depths. The distorted data set is corrected using the MT response for DRS model and further subject to joint inversion with DRS data. Joint inversion leads to better estimation of MT parameters compared to the separate inversion of data sets.     

Hydrogeophysical investigation and estimation of groundwater potentials of the Lower Palaeozoic to Precambrian crystalline basement rocks in Keffi area, north-central Nigeria, using resistivity methods

The use of resistivity sounding and two-dimensional (2-D) resistivity imaging was investigated with the aim of delineating and estimating the groundwater potential in Keffi area. Rock types identified are mainly gneisses and granites. Twenty-five resistivity soundings employing the Schlumberger electrode array were conducted across the area. Resistivity sounding data obtained were interpreted using partial curve matching approach and 1-D inversion algorithm, RESIST version 1.0. The 2-D resistivity imaging was also carried out along two traverses using dipole–dipole array, and the data obtained were subjected to finite element method modeling using DIPRO inversion algorithm to produce a two-dimensional subsurface geological model. Interpretation of results showed three to four geoelectrical layers. Layer thickness values were generally less than 2 m for collapsed zone, and ranged from 5 to 30 m for weathered bedrock (saprolite). Two major aquifer units, namely weathered bedrock (saprolite) aquifer and fractured bedrock (saprock) aquifer, have been delineated with the latter usually occurring beneath the former in most areas. Aquifer potentials in the area were estimated using simple schemes that involved the use of three geoelectrical parameters, namely: depth to fresh bedrock, weathered bedrock (saprolite) resistivity and fractured bedrock (saprock) resistivity. The assessment delineated the area into prospective high, medium and low groundwater potential zones.     

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.     

基于时延三维电阻率反演的岩溶地下河管道空间分布识别物理模拟研究

岩溶地下河管道空间分布的识别对岩溶区的各类地球科学工作意义重大,文章阐述了采用时延三维电阻率反演技术,开展对地下河管道空间分布识别的研究,在室内灰岩介质下的物理模拟实验结果表明:对雨季管道充水和枯季管道干涸时采集的电阻率数据进行时延反演后,地下河管道的模拟三维空间分布被很好地突显出来,时延反演效果大大地优于对单次采集数据的反演效果,管道充填水时的反演效果次之,管道充填空气时的反演结果很难有效识别地下河管道的空间分布情况。物理模型试验成果可指导野外实践中对岩溶地下河管道的探测研究。      

Geoacoustic inversion using adaptive neuro-fuzzy inference system

The geoacoustic parameters form significant input for underwater acoustic propagation studies and geoacoustic modeling. Conventional inversion techniques commonly used as indirect approach for extraction of geoacoustic parameters from acoustic or seismic data are computationally intensive and time-consuming. In the present study, we have tried to exploit the advantage of soft computing techniques like, reasoning ability of fuzzy logic and learning abilities of neural networks, in inversion studies. The network model based on the combined approach called adaptive neuro-fuzzy inference system (ANFIS), is found to be very promising in inversion of the acoustic data. The network model once built is capable of invert a few thousand data sets instantaneously, to a reasonably good accuracy. In the case of conventional approaches, repetition of the entire inversion process with each new data set is required. A limited number of sensor’s data are sufficient for simulation of the network model and provides an advantage to use short hydrophone array data. Inversion results of a few hundred test data sets, representing different geoacoustic environments, show the prediction error is much less than 0.01 g/cc, 10 m/s, 10 m and 0.1 against first layer’s density, compressional sound speed, thickness and attenuation respectively for a three-layer geoacoustic model. However, the error is relatively large for the second- and third-layer parameters, which need to be improved. The model is efficient, robust and inexpensive.     

测井与地震资料联合反演预测K2灰岩及其含水性

阳煤五矿主要可采煤层15号煤层顶板发育的K₂灰岩不是良好的地震波反射界面,常规地震剖面很难连续追踪。测井曲线上的K₂灰岩表现为高密度和高视电阻率异常,采用密度与视电阻率两种测井曲线融合生成拟密度曲线,基于模型反演得到地层岩性数据体,从而识别灰岩的赋存形态与厚度;采用概率神经网络反演的方法,优选出9种地震属性,构成神经网络训练样本,对灰岩的孔隙度和视电阻率进行神经网络反演,预测灰岩的富水性。      

ANN技术在地下水含水量预测建模中的研究与应用

将人工神经网络(ANN)技术引入到地下水含水量预测工作,以华北平原和河套平原为试验场,以若干已知钻孔为验证,采用激电和电阻率测深等地面物探方法获取视电阻率ρS、视极化率ηS、半衰时Th、衰减度D和偏离度σ等参数为输入神经元对单孔单位涌水量建立人工神经网络预测模型。同时,为消除不同地区矿化度的影响,通过实验对比引入综合参数T",改良了输入神经元的配比。最终建立以半衰时Th、衰减度D、偏离度σ和综合参数T"为输入神经元的含水量预测模型,进一步提高了预测精度。通过检验,发现所建立的模型对平原地区进行含水量的定量预测有着较好的效果,为含水量预测工作研究与发展带来了新理念、打开了新思路。     

井地2.5维DC反演研究

开展了不同观测方式的井地2.5D直流电阻率反演研究。①从2.5维直流电阻率满足的边值问题出发,采用变分原理结合节点线性基函数推导了2.5维井地DC满足的积分弱解形式;②构建了二阶最大平滑稳定泛函的2.5维井地直流电阻率正则化目标函数,采用共轭梯度算法对正则化目标函数进行最优化求解,并采用逐步衰减正则化因子的求解策略来提高反演的稳定性;③设计了均匀半空间模型得到的数值解与解析解对比,电位的相对误差在2%以内,阐述正演算法的正确性和高精度。另外,分析了不同观测装置的2.5维井地直流电阻率异常体特征,并对不同观测方式对2.5维井地DC理论数据进行反演研究。研究结果表明,井中数据的引入提高了2.5DC对纵向探测的分辨率能力,同时提高了2.5DC反演有效性以及准确性。     

电偶源频率电磁测深中比值视电阻率和阻抗相位的联合反演

本文论述了电偶源频率电磁测深中,利用比值视电阻率和相应阻抗相位进行联合反演的必要性和可能的应用前景及具体实施方法。理论模型和实际观测资料的反演试验表明这一联合反演是可行和有效的,且明显地优于视电阻率和阻抗相位的单参量反演。     

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。      

重、磁、电联合反演在银额盆地定量解释中的应用

依据大地电磁测深连续二维反演结果初步确定构造与地层,通过综合分析区内物性特征给定地层与岩石的物性参数,建立正演地质一地球物理初始模型,在地质、钻井、地震资料约束下进行重、磁、电联合反演,不断修改地质一地球物理模型和大地电磁测深连续二维反演结果,使重、磁正演数据和实测数据拟合度达到最佳。在银额盆地构造与地层解释中的应用结果表明,重、磁、电联合反演可以有效克服单方法解释的多解性,准确识别地质层位,大大提高定量解释的精度。     

An intelligent neural network model for evaluating performance of immobilized cell biofilter treating hydrogen sulphide vapors

Biofiltration has shown to be a promising technique for handling malodours arising from process industries. The present investigation pertains to the removal of hydrogen sulphide in a lab scale biofilter packed with biomedia, encapsulated by sodium alginate and poly vinyl alcohol. The experimental data obtained under both steady state and shock loaded conditions were modelled using the basic principles of artificial neural networks. Artificial neural networks are powerful data driven modelling tools which has the potential to approximate and interpret complex input/output relationships based on the given sets of data matrix. A predictive computerised approach has been proposed to predict the performance parameters namely, removal efficiency and elimination capacity using inlet concentration, loading rate, flow rate and pressure drop as the input parameters to the artificial neural network model. Earlier, experiments from continuous operation in the biofilter showed removal efficiencies from 50 to 100 % at inlet loading rates varying up to 13 g H₂S/m³h. The internal network parameter of the artificial neural network model during simulation was selected using the 2^k factorial design and the best network topology for the model was thus estimated. The results showed that a multilayer network (4-4-2) with a back propagation algorithm was able to predict biofilter performance effectively with R² values of 0.9157 and 0.9965 for removal efficiency and elimination capacity in the test data. The proposed artificial neural network model for biofilter operation could be used as a potential alternative for knowledge based models through proper training and testing of the state variables.     

Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: A wavelet network approach

Although traditional artificial neural networks have been an attractive topic in modeling membrane filtration, lower efficiency by trial-and-error constructing and random initializing methods often accompanies neural networks. To improve traditional neural networks, the present research used the wavelet network, a special feedforward neural network with a single hidden layer supported by the wavelet theory. Prediction performance and efficiency of the proposed network were examined with a published experimental dataset of cross-flow membrane filtration. The dataset was divided into two parts: 62 samples for training data and 329 samples for testing data. Various combinations of transmembrane pressure, filtration time, ionic strength and zeta potential were used as inputs of the wavelet network so as to predict the permeate flux. Through the orthogonal least square alogorithm, an initial network with 12 hidden neurons was obtained which offered a normalized square root of mean square of 0.103 for the training data. The initial network led to a wavelet network model after training procedures with fast convergence within 30 epochs. Futher the wavelet network model accurately depicted the positive effects of either transmembrane pressure or zeta potential on permeate flux. The wavelet network also offered accurate predictions for the testing data, 96.4 % of which deviated the measured data within the ± 10 % relative error range. Moreover, comparisons indicated the wavelet network model produced better predictability than the back-forward backpropagation neural network and the multiple regression models. Thus the wavelet network approach could be employed successfully in modeling dynamic permeate flux in cross-flow membrane filtration.     

Inversion of GDS data of northwest Himalaya using EM2INV

This paper reviews the validity of earlier models obtained after quantitative interpretation of GDS data and presents a fresh model using the inversion scheme EM2INV. The 2-D inversion of data is more objective than the earlier interpretation performed by using trial and error method. The inversion results indicate that the present model differs from the earlier ones. The reason could be that available GDS data are sufficient only for deriving the horizontal variation of subsurface resistivity. In order to study the vertical resistivity variation additional MT sounding data would be required. It would therefore be desirable to carry out MT survey in the specified area. A more comprehensive/appropriate model could be derived from joint inversion of GDS and MT data.     

基于神经网络的大连东北海岸带碎石土地基强夯加固研究

以大连某实际工程作为研究场地,室内试验与原位测试所得碎石土地基物理力学参数与实测所得强夯处理沉降量作为样本,通过BP神经网络对样本的训练、学习,建立地基土力学参数与强夯处理的沉降量之间的映射关系,利用所得映射关系对场地实测的沉降量进行物理力学参数的反演分析。结果表明:经过训练的神经网络模型可快速得出所需参数,利用flac3d以反演所得参数进行计算,模拟沉降量与实测沉降量的误差为4.87%,在可接受的范围之内;基于神经网络的位移反分析方法可以省去繁琐的测试工作,但该方法的实现需要有充足的样本数据作为支撑。     

电偶源频率电磁测深中比值视电阻率和阻抗相位的联合反演

本文论述了电偶源频率电磁测深中，利用比值视电阻率和相应阻抗相位进行联合反演的必要性和可能的应用前景及具体实施方法。理论模型和实际观测资料的反演试验表明这一联合反演是可行和有效的，且明显地优于视电阻率和阻抗相位的单参量反演。     

激发极化法测深曲线反演方法及对比分析

在电阻率反演的基础上,运用等效电阻率进行激发极化法测深曲线的反演.通过对线性反演法、精确形式法、非线性反演法三种极化率反演方法的计算与分析,编制程序对水平层状模型进行反演,对比其在耗费时间和反演效果等方面的差别,认为非线性反演是理论上最好的方法,而在实际生产中建议采用线性反演方法.     

有限长导线源频率测深有限内存拟牛顿一维反演

本文采用有限内存拟牛顿法实现有限长导线源频率测深阻抗响应数据的一维反演。水平层状介质有限长导线源阻抗频率响应由基于虚界面法获得的地表水平正交电场和磁场计算得到;一维反演优化问题的求解利用有限内存拟牛顿法,结合光滑模型约束,直接对阻抗的频率响应数据进行反演。在反演过程中,正则化参数的调整采用目标函数自适应技术。反演模型剖分为多层,各层厚度自地表按比例增加。反演从均匀半空间开始,终止条件为目标函数相对变化小于10~(-4)。分别对理论模型和实际数据进行了反演模拟。为考察反演的稳定性,还对理论数据添加10%随机噪声后进行了反演。数值计算结果表明:有限内存拟牛顿方法可以用于有限长导线源频率测深阻抗频率响应的反演;该反演方法对初始模型的依赖性弱,从均匀半空间模型出发基本可以恢复到真实模型;反演初期收敛较快,后期收敛速度变慢,反演结束一般需要迭代40次左右。噪声数据反演结果表明,随机噪声对反演结果影响不大,说明有限内存拟牛顿法具有较好的抗干扰能力。本文研究成果给出了可控源电磁数据反演的一种新方法;同时,利用本文的研究成果,可以为二维或三维反演建立合适的初始模型。