基于PSR-WSVM模型的边坡位移预测

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。     

Land Resource Carrying Capacity in Xilin Gol Grassland Transects: A Perspective on Food Nutritional Demand

Food safety is an important issue for the development of the national economy and society. Studying regional food supply and demand from the perspective of land resource carrying capacity can provide new references for regional resource sustainability. This study uses the data from farmer and herdsmen household questionnaires, statistical data, land use data, and other sources to construct a land resource carrying capacity (LCC) assessment framework, targeting the food supply and demand of residents in representative areas, specifically the typical grassland pastoral areas, sandy pastoral areas and agro-pastoral areas on the Xilin Gol grassland transects. The three food nutritional indicators of calories, protein and fat were selected for analyzing the balance of land resource carrying capacity. We found that: 1) Along the Xilin Gol grassland, the main local food supply showed a shift from meat and milk to grains, vegetables and fruits. 2) From north to south along the grassland transects, the calorie intake increased gradually, while the intake of protein and fat was highest in pastoral areas and lowest in agricultural areas. 3) The overall land resource carrying capacity of the Xilin Gol grassland transects was in a surplus state, but the land carrying capacity of typical grassland pastoral area was higher than the two other types of areas. This study provides an empirical reference for the sustainable development of regional food nutrition.     

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

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.     

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

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.     

Prediction of Stellar Atmospheric Parameters using Instance-Based Machine Learning and Genetic Algorithms

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.     

基于AGA的SVM需水预测模型研究

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.     

Isotopic variation of fishes in freshwater and estuarine zones of a large subtropical coastal lagoon

We used stable C and N isotope ratios of tissues from 29 fish species from a large subtropical lagoon in southern Brazil to examine spatial variability in isotopic composition and vertical trophic structure across freshwater and estuarine habitats. Nitrogen isotope ratios indicated a smooth gradation in trophic positions among species, with most fishes occupying the secondary and tertiary consumer level. Fish assemblages showed a significant shift in their carbon isotopic signatures between freshwater and estuarine sites. Depleted carbon signatures (from −24.7‰ to −17.8‰) were found in freshwater, whereas more enriched signatures (from −19.1‰ to −12.3‰) were obtained within the estuarine zone downstream. Based on our survey of the C₃ and C₄ plants and isotopic values for phytoplankton and benthic microalgae reported for ecosystems elsewhere, we hypothesized that the observed δ¹³C differences in the fish assemblage between freshwater and estuarine sites is due to a shift from assimilating organic matter ultimately derived from C₃ freshwater marsh vegetation and phytoplankton at the freshwater site (δ¹³C ranging from −25‰ to −19‰), to C₄ salt-marsh (e.g. Spartina) and widgeon grass (Ruppia maritima), benthic microalgae and marine phytoplankton at the estuarine sites (from −18‰ to −12‰). Our results suggested that fish assemblages are generally supported by autochthonous primary production. Freshwater fishes that likely were displaced downstream into the estuary during periods of high freshwater discharge had depleted δ¹³C values that were characteristic of the upper lagoon. These results suggest that spatial foodweb subsidies can occur within the lagoon.     

增氧机自动控制电路

介绍作者自行设计、研制的控制增氧机运行时间的自动控制电路及其原理．该电路采用ＣＭＯＳ集成芯片，结构简单、工作可靠，价格低，业经试验证实：各项性能指标均符合要求．     

Assessment of spatial variation in carbon utilization by benthic and pelagic invertebrates in a temperate South African estuary using stable isotope signatures

Stable isotope analyses (δ¹³C and δ¹⁵N) were used to evaluate the spatial variations in carbon flow from primary producers to consumers at two sites in the temperate and permanently open Kariega Estuary on the southeastern coast of South Africa during October 2005 and February 2006. One site was located opposite a salt marsh while the second was upstream of the marsh. Except for significantly enriched δ¹³C values of Zostera capensis and surface sediments near the salt marsh, the δ¹³C and δ¹⁵N signatures of the producers were similar between sites. The invertebrates were clustered into groups roughly corresponding to the predominant feeding modes. The suspension feeders showed δ¹³C values closest to the seston, whereas the deposit feeders, detritivores and scavengers/predators had more enriched δ¹³C values reflecting primary carbon sources that were likely a combination of seston, Spartina maritima and Z. capensis at the upstream site, with an increased influence of benthic algae and Z. capensis at the salt marsh site. The δ¹⁵N signatures of the consumers showed a stepwise continuum rather than distinct levels of fractionation, indicating highly complex trophic linkages and significant dietary overlap among the species. Consumers exhibited significantly enriched δ¹³C values at the salt marsh site, an effect that was attributed to enriched Z. capensis detritus in this region in addition to increased phytoplankton biomass in their diets compared with invertebrates living upstream. The data reinforce the concept that between-site variations in the stable isotope ratios of consumers can result not only from dietary shifts, but also from alterations in the isotope ratios of primary producers.     

秋季黄海中南部鱼类群落对饵料生物的摄食量

研究鱼类与饵料生物之间食物定量关系进而为多鱼种资源评估提供依据,2000~2002年秋季(10~11月)在黄海中南部海域进行了定点底拖网调查,应用Eggers模型,计算了带鱼(Trichiurus lepturus)、小黄鱼(Pseudosciaena polyactis)、黄(Lophius litulon)、细纹狮子鱼(Liparis tanakae)等23种鱼类在秋季对饵料生物的摄食量。结果表明:黄海中南部23种鱼类在秋季对饵料生物的总摄食量约为309万t,其中,鱼(Engraulis japonicus)的摄食量最高(在250万t以上),占总摄食量的80.9%。中上层和底层鱼类对饵料生物的摄食量分别为262万t和47万t左右,占总摄食量的84.7%和15.3%,鱼和细纹狮子鱼分别是中上层和底层鱼类中最主要的捕食者。磷虾类是中上层鱼类最主要的食物来源,其次是桡足类、端足类和毛颚类;虾类和鱼类是底层鱼类最主要的食物来源,其次是磷虾类。太平洋磷虾(Euphausia pacifica)、中华哲水蚤(Calanus sinicus)、细长脚虫戎(Themisto gracilipes)、脊腹褐虾(Crangon affinis)和鱼同时是黄海中南部被摄食量最高的5种饵料生物,它们被摄食的生物量之和约为233万t,占总摄食量的75.5%。