基于人工神经网络的地震活动性研究

人工神经网络通过神经元之间的相互作用来完成整个网络的信息处理,具有自学习和自适应等一系列优点,因而用它来进行地震活动性研究是可行的。针对地震活动性问题,初步建立了基于人工神经网络的计算分析系统,给出了应用实例。     

人工智能和专家系统在测绘科学中的应用

讨论了人工智能和专家系统应用于测绘科学的优越性,分析了其在测绘科学中应用的主要内容,对其发展趋势进行了探讨。     

Study on ann-based multi-step prediction model of short-term climatic variation

In the context of 1905-1995 series from Nanjing and Hangzhou, study is undertaken of establishing a predictive model of annual mean temperature in 1996-2005 to come over the Changjiang (Yangtze River) delta region through mean generating function and artificial neural network in combination. Results show that the established model yields mean error of 0.45℃ for their absolute values of annual mean temperature from 10 yearly independent samples (1986-1995) and the difference between the mean predictions and related measurements is 0.156℃. The developed model is found superior to a mean generating function regression model both in historical data fitting and independent sample prediction.     

云南天文台人造卫星观测与相关应用研究

回顾了过去２０年，特别是近１０年来云南天文台人造卫星的观测与应用情况。介绍在观测仪器的研制、改进和观测方法研究以及有关激光测月资料的归算与应用方面所作过的工作。根据既有的条件，就今后若干年内可能进行的几项工作提出了粗浅的看法。     

运用BP网络预测地下水位

人工神经网络是一门新兴的交叉学科，是处理非线性问题的有效方法。本文把影响地下水位的因素集作为网络的输入向量，地下水位本身作为网络的输出向量，构成了预测地下水位的ＢＰ网络模型。一个实例的应用实践表明，用ＢＰ网络预测地下水位较准确地反映了客观实际，比其它方法如回归模型具有较高的拟合精度和预测精度。     

流域年均含沙量的B-P网络预测模型及其效果检验

应用误差反向传播算法的人工神经网络，建立了流域年均含沙量的预测模型。该模型用于某流域年均含沙量预测的拟合率达９０％以上，预留检验预报的准确率为７５％。     

A combined theory for zonal harmonic and resonance perturbations of a near-circular orbit with applications to COSMOS 1603 (1984-106A)

Theory for the motion of a satellite in a near-circular orbit and perturbed by zonal and resonance terms in the Earth's gravity field is developed. Commensurability with respect to both primary and secondary terms is considered with the solution dependent on the depths of the resonances. The theory is applied to the motion of COSMOS 1603 (1984-106A) which approached 14 : 1 resonance in 1987. Values of lumped harmonics derived from least-squares analysis are in close agreement with previous studies of 1984-106A and global gravity field models. The theory is finally extended to incorporate the effects of air drag.     

A particle classification system for the PAMELA calorimeter

In this paper we propose a particle classification system for the imaging calorimeter of the PAMELA satellite-borne experiment. The system consist of three main processing phases. First, a segmentation of the whole signal detected by the calorimeter is performed to select a Region of Interest (RoI); this step allows to retain bounded and space invariant portions of data for the following analysis. In the next step, the RoIs are characterized by means of nine discriminating variables, which measure event properties useful for the classification. The third phase (the classification step) relies on two different supervised algorithms, Artificial Neural Networks and Support Vector Machines. The system was tested with a large simulated data set, composed by 40 GeV/c momentum electrons and protons. Moreover, in order to study the classification power of the calorimeter for experimental data, we have also used biased simulated data. A proton contamination in the range 10⁻⁴–10⁻⁵ at an electron efficiency greater than 95% was obtained. The results are adequate for the PAMELA imaging calorimeter and show that the approach to the classification based on soft computing techniques is complementary to the traditional analysis performed using optimized cascade cuts on different variables.     

Modelling the cross-shore profiles of sand beaches using artificial neural networks

Abstract

Artificial neural networks (ANN) have been widely used successfully to solve coastal engineering problems. In this article, they are used to model the cross-shore profile of sandy beaches taking into account the possible effect of marine vegetation (Posidonia oceanica). Sixty ANNs were generated by modifying both the inputs and the number of neurons in the hidden layer. The best results were obtained with the following inputs: wave height perpendicular to the coast and the associated period and probability of occurrence, median sediment size, profile slope, and energy reduction factor due to P. oceanica. With these inputs and 10 neurons in the hidden layer, a mean absolute error of 0.22?m during training and 0.21?m during the test was obtained, which represents an improvement of 81.2% and 55.5% compared to models without and with P. oceanica.