基于PSR-WSVM模型的边坡位移预测     

李建新  刘小生  肖钢  周文  刘仁志 《大地测量与地球动力学》2020,40(6):577-580

为建立高精度的边坡位移预测模型，采用相空间重构（PSR）将边坡位移时间序列数据转换为多维数据，同时构造小波核函数改进的支持向量机模型，建立PSR-WSVM模型并应用于边坡位移预测。将PSR-WSVM模型预测结果与传统支持向量机（SVM）模型、小波支持向量机（WSVM）模型和基于相空间重构的支持向量机（PSR-SVM）模型预测结果进行对比，通过平均绝对误差（MAE）、平均绝对误差百分比（MAPE）和均方根误差（RMSE）3个精度评价指标验证PSR-WSVM模型的可行性。工程实例结果表明，PSR-WSVM模型预测结果的3个精度评价指标都优于另外3种模型，边坡位移预测的精度明显提升。  相似文献   

A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing     

Peng Yue  Fan Gao  Boyi Shangguan  Zheren Yan 《International journal of geographical information science》2020,34(11):2243-2274

ABSTRACT

High performance computing is required for fast geoprocessing of geospatial big data. Using spatial domains to represent computational intensity (CIT) and domain decomposition for parallelism are prominent strategies when designing parallel geoprocessing applications. Traditional domain decomposition is limited in evaluating the computational intensity, which often results in load imbalance and poor parallel performance. From the data science perspective, machine learning from Artificial Intelligence (AI) shows promise for better CIT evaluation. This paper proposes a machine learning approach for predicting computational intensity, followed by an optimized domain decomposition, which divides the spatial domain into balanced subdivisions based on the predicted CIT to achieve better parallel performance. The approach provides a reference framework on how various machine learning methods including feature selection and model training can be used in predicting computational intensity and optimizing parallel geoprocessing against different cases. Some comparative experiments between the approach and traditional methods were performed using the two cases, DEM generation from point clouds and spatial intersection on vector data. The results not only demonstrate the advantage of the approach, but also provide hints on how traditional GIS computation can be improved by the AI machine learning.  相似文献   

Radiation exposure and Mission Strategies for Interplanetary Manned Missions (REMSIM)   总被引：1，自引：0，他引：1  

C. Cougnet  N. B. Crosby  S. Eckersley  C. Foullon  V. Guarnieri  S. Guatelli  D. Heynderickx  A. Holmes-Siedle  C. Lobascio  S. Masiello  P. Nieminen  G. Parisi  P. Parodi  M. A. Perino  M. G. Pia  R. Rampini  P. Spillantini  V. Tamburini  E. Tracino 《Earth, Moon, and Planets》2004,94(3-4):279-285

Cosmic radiation is an important problem for human interplanetary missions. The “Radiation Exposure and Mission Strategies for Interplanetary Manned Missions–REMSIM” study is summarised here. They are related to current strategies and countermeasures to ensure the protection of astronauts from radiation during interplanetary missions, with specific reference to: radiation environment and its variability; radiation effects on the crew; transfer trajectories and associated fluences; vehicle and surface habitat concepts; passive and active shielding concepts; space weather monitoring and warning systems.  相似文献   

Automatic Determination of Stellar Atmospheric Parameters Using Neural Networks and Instance-Based Machine Learning     

Olac Fuentes 《Experimental Astronomy》2001,12(1):21-31

In this article we show how machine learning methods can beeffectively applied to the problem of automatically predictingstellar atmospheric parameters from spectral information, a veryimportant problem in stellar astronomy. We apply feedforwardneural networks, Kohonen's self-organizing maps andlocally-weighted regression to predict the stellar atmosphericparameters effective temperature, surface gravity and metallicityfrom spectral indices. Our experimental results show that thethree methods are capable of predicting the parameters with verygood accuracy. Locally weighted regression gives slightly betterresults than the other methods using the original dataset asinput, while self-organizing maps outperform the other methods when significant amounts of noise are added. We also implemented a heterogeneous ensemble of predictors, combining the results given by the three algorithms. This ensemble yields better results than any of the three algorithms alone, using both the original and the noisy data.  相似文献   

Prediction of Stellar Atmospheric Parameters using Instance-Based Machine Learning and Genetic Algorithms   总被引：1，自引：0，他引：1  

J. Federico Ramírez  Olac Fuentes  Ravi K. Gulati 《Experimental Astronomy》2001,12(3):163-178

In this article we present a method for the automated prediction of stellar atmospheric parameters from spectral indices. This method uses a genetic algorithm (GA) for the selection of relevant spectral indices and prototypical stars and predicts their properties, using the k-nearest neighbors method (KNN). We have applied the method to predict the effective temperature, surface gravity, metallicity, luminosity class and spectral class of stars from spectral indices. Our experimental results show that the feature selection performed by the genetic algorithm reduces the running time of KNN up to 92%, and the predictive accuracy error up to 35%. This revised version was published online in July 2006 with corrections to the Cover Date.  相似文献   

1999年8月11日日全食期间的重力吸引效应研究     

刘少明 《大地测量与地球动力学》2004,24(4):13-19

对1999年8月11日日全食阴影扫过欧洲期间,设在Annelles,Uccle,Walferdange和Bondy弹簧和超导重力仪的记录进行了分析.为了确定月亮对太阳万有引力可能的遮挡效应的极限,对超导和弹簧重力仪记录进行了比较.同时也对LCR和阿斯卡尼亚重力仪观测结果进行了讨论.结论是如果日食重力吸引效应存在,它应在超导重力仪±1 nm/s2(0.1×10-8ms-2)的观测精度范围之内.研究发现在以上情形下,弹簧和超导重力仪都在它们的精度范围内工作,并且日食引起的异常环境干扰可能使重力信号有重大的改变.  相似文献   

Interpretation of aeromagnetic data across the central crystalline shield area of Nigeria     

D. E. Ajakaiye  D. H. Hall  T. W. Millar 《Geophysical Journal International》1985,83(2):503-517

Summary. A residual map of the total magnetic field (above 25 000 nT base) is presented for a portion of the central crystalline shield area of Nigeria and overlapping small portions of the Chad basin and the Benue rift (8°30'−12° 00'lat, and 7°−10°30' long). The map (based on a dataset digitized from recently released aeromagnetic sheets of Nigeria) leads to four results. (1) A magnetic boundary, evident on the map, separates the Younger Granite complexes into two groups. The groups are petrologically different, and the boundary may be a fault line with uplift to the south. (2) South of the boundary the map is dominated by a system of sub-parallel anomalies striking NE–SW, possibly representing major tectonic trends, and a set of fractures through which the Younger Granite complexes were intruded. The trend of the system parallels the Benue rift and lineaments in the oceanic crust off West Africa. (3) Negative magnetic anomalies lie over most of the known ring complexes, and over some suspected buried ring complexes and other intrusions. (4) 2½-and 3-D modelling shows that the larger complexes extend to 12 km depth, and the smaller ones to 6 km. They have nearly vertical sides, and magnetization contrasts range from 0.3 to 0.5 A m⁻¹.  相似文献   

A 3D finite element simulation model for TBM tunnelling in soft ground     

Thomas Kasper  Günther Meschke 《国际地质力学数值与分析法杂志》2004,28(14):1441-1460

  相似文献   

Crustal and upper mantle structures of the brazilian coast     

Jorge Luis De Souza 《Pure and Applied Geophysics》1991,136(2-3):245-264

The Rayleigh wave phase and group velocities in the period range of 24–39 sec, obtained from two earthquakes which occurred in northeastern brazil and which were recorded by the Brazilian seismological station RDJ (Rio de Janeiro), have been used to study crustal and upper mantle structures of the Brazilian coastal region. Three crustal and upper mantle models have been tried out to explain crustal and upper mantle structures of the region. The upper crust has not been resolved, due basically to the narrow period range of the phase and group velocities data. The phase velocity inversions have exhibited good resolutions for both lower crust and upper mantle, with shear wave velocities characteristic of these regions. The group velocity data inversions for these models have showed good results only for the lower crust. The shear wave velocities of the lower crust (3.86 and 3.89 km/sec), obtained with phase velocity inversions, are similar to that (=3.89 km/sec) found byHwang (1985) to the eastern South American region, while group velocity inversions have presented shear velocity (=3.75 km/sec) similar to that (=3.78 km/sec) found byLazcano (1972) to the Brazilian shield. It was not possible to define sharply the crust-mantle transition, but an analysis of the phase and group velocity inversions results has indicated that the total thickness of the crust should be between 30 and 39 km. The crustal and upper mantle model, obtained with phase velocity inversion, can be used as a preliminary model for the Brazilian coast.  相似文献   

基于AGA的SVM需水预测模型研究   总被引：1，自引：0，他引：1  

张灵  陈晓宏  刘丙军  王兆礼 《水文》2008,28(1):38-42,46

需水预测是一个由城市人口、工业水平、社会经济水平共同作用的多因素、多层次的复杂非线性系统.其结果将直接影响受区域水资源承载力约束的产业结构、布局形态等决策.作为一种集中参数预报方法,支持向量机方法具有对未来样本的较好的泛化性能,对于这类资料缺乏、系统结构尚欠清晰的问题可以取得较好的模拟和预测结果.基于此,本文将支持向量机方法引入需水预测领域,建立了需水预测支持向量机模型.同时,本文将加速遗传算法和支持向量机方法耦合起来,构造了支持向量机模型参数的自适应优化算法.模型在珠海市的应用实例表明:与简单遗传算法比较,AGA的模型参数寻优效率更高;与BP神经网络模型相比,SVM模型较好地解决了小样本、经验性等问题,并取得了较高的预测精度.  相似文献