Modelling evaporation using an artificial neural network algorithm

This paper investigates the prediction of Class A pan evaporation using the artificial neural network (ANN) technique. The ANN back propagation algorithm has been evaluated for its applicability for predicting evaporation from minimum climatic data. Four combinations of input data were considered and the resulting values of evaporation were analysed and compared with those of existing models. The results from this study suggest that the neural computing technique could be employed successfully in modelling the evaporation process from the available climatic data set. However, an analysis of the residuals from the ANN models developed revealed that the models showed significant error in predictions during the validation, implying loss of generalization properties of ANN models unless trained carefully. The study indicated that evaporation values could be reasonably estimated using temperature data only through the ANN technique. This would be of much use in instances where data availability is limited. Copyright © 2002 John Wiley & Sons, Ltd.     

Fuzzy neural network models for liquefaction prediction

Integrated fuzzy neural network models are developed for the assessment of liquefaction potential of a site. The models are trained with large databases of liquefaction case histories. A two-stage training algorithm is used to develop a fuzzy neural network model. In the preliminary training stage, the training case histories are used to determine initial network parameters. In the final training stage, the training case histories are processed one by one to develop membership functions for the network parameters. During the testing phase, input variables are described in linguistic terms such as ‘high’ and ‘low’. The prediction is made in terms of a liquefaction index representing the degree of liquefaction described in fuzzy terms such as ‘highly likely’, ‘likely’, or ‘unlikely’. The results from the model are compared with actual field observations and misclassified cases are identified. The models are found to have good predictive ability and are expected to be very useful for a preliminary evaluation of liquefaction potential of a site for which the input parameters are not well defined.     

ARTIFICIAL NEURAL NETWORK CORRECTION OF ROUGH ERRORS OF OBSERVATIONS*

In the context of tower measured radiation datasets.following the correction principle meeting a diagnostic equation in data quality control and in terms of a technique for model construction on data and ANN (artificial neural network) retrieval for BP correction of radiation measurements with rough errors available,a BP model is presented.Evidence suggests that the developed model works well and is superior to a convenient multivariate linear regression model,indicating its wide applications.     

Use of Noise to Augment Training Data: A Neural Network Method of Mineral–Potential Mapping in Regions of Limited Known Deposit Examples

One of the main factors that affects the performance of MLP neural networks trained using the backpropagation algorithm in mineral-potential mapping isthe paucity of deposit relative to barren training patterns. To overcome this problem, random noise is added to the original training patterns in order to create additional synthetic deposit training data. Experiments on the effect of the number of deposits available for training in the Kalgoorlie Terrane orogenic gold province show that both the classification performance of a trained network and the quality of the resultant prospectivity map increasesignificantly with increased numbers of deposit patterns. Experiments are conducted to determine the optimum amount of noise using both uniform and normally distributed random noise. Through the addition of noise to the original deposit training data, the number of deposit training patterns is increased from approximately 50 to 1000. The percentage of correct classifications significantly improves for the independent test set as well as for deposit patterns in the test set. For example, using ±40% uniform random noise, the test-set classification performance increases from 67.9% and 68.0% to 72.8% and 77.1% (for test-set overall and test-set deposit patterns, respectively). Indices for the quality of the resultant prospectivity map, (i.e. D/A, D × (D/A), where D is the percentage of deposits and A is the percentage of the total area for the highest prospectivity map-class, and area under an ROC curve) also increase from 8.2, 105, 0.79 to 17.9, 226, 0.87, respectively. Increasing the size of the training-stop data set results in a further increase in classification performance to 73.5%, 77.4%, 14.7, 296, 0.87 for test-set overall and test-set deposit patterns, D/A, D × (D/A), and area under the ROC curve, respectively.     

企业网络发育程度与区域创新能力研究

本文从分析企业网络的发育和完善程度出发，探讨影响网络创新能力的因素。文章指出，网络发育程度与创新能力(创新数量、创新发生的频率)是正相关的。从宏观上讲网络越密集、各种正式和非正式联系越有效、网络联系越稳定、网络自我更新能力越强、网络的开放性越强、网络越能根植于当地的良好的区域环境，越容易激发创新；从微观上讲，网络中行为主体的学习能力越强，其创新发生频率越高，创新能力越强。     

Application of visual,statistical and artificial neural network methods in the differentiation of water from the exploited aquifers in Kuwait

The ability of artificial neural network to differentiate water samples from the two aquifers of Kuwait on the basis of their major ion chemistry has been demonstrated. The major ion concentration distribution in the groundwater of the Kuwait Group and the Dammam Formation aquifers of Kuwait appears very similar. Cross-plots, supported by the discriminant function analysis of the data, however, suggest that there are some subtle differences in the overall composition of the water from the two aquifers that make it possible to differentiate the water from the two aquifers in almost 80% of the cases. An artificial neural network improved the differentiation capability to 90% of the cases. It is also possible to estimate the fraction of Kuwait Group water in the flow stream of dually completed wells with the help of an artificial neural network developed for this purpose. Electronic Publication     

月降水量的神经网络混合预报模型研究

以均生函数表征预报量自身周期变化，结合500hPa月平均高度场和月平均海温场预报因子，采用神经网络方法建立了一种新的短期气候预报模型。分别以广西桂北、桂中和桂南6月降水量作为预报对象进行预报试验，结果表明，这种新的预报方法比均生函数回归预报模型及高度场、海温场预报因子的回归预报模型，具有更好的物理基础和预报能力。     

震后震型早期判定的人工神经网络方法

应用人工神经网络的方法，利用３０次强震震后１天和２天内的地震资料作为学习样本，对广西及其邻区发生的４次地震的震型作了早期预测判定，结果表明应用效果较好，正确率达７５％。该方法值得进一步研究。     

Generating fracture networks using iterated function systems

In order to model flow and transport in fractured rocks it is important to know the geometry of the fracture network. A stochastic approach is commonly used to generate a synthetic fracture network from the statistics measured at a natural fracture network. The approach presented herein is able to incorporate the structures found in a natural fracture network into the synthetic fracture network. These synthetic fracture networks are the images generated by Iterated Function Systems (IFS) as introduced by Barnsley (1988). The conditions these IFS have to fulfil to determine images resembling fracture networks and the effects of their parameters on the images are discussed. It is possible to define the parameters of the IFS in order to generate some properties of a fracture network. The image of an IFS consists of many single points and has to be suitably processed for further use.     

人工神经网络在岩体质量分级中的应用

结合四川省金沙江某水电站工程实例，应用BP人工神经网络方法建立3层BP网络模型，选取岩石单轴抗压强度等6个影响因素为输入变量，对坝基复杂岩体进行质量分级。通过机算机Visual C 语言编程实现神经网络模型，进行网络的学习和运算。以神经网络合理结构分析方法选取合理结构，确定合理隐层单元的数量，提高网络测试的精度。对测试结果的分析发现，经过优化的BP网络模型经多次学习后，测试精度提高，结果可靠，取得较好的实际应用效果。