ARIMA与SVM组合模型在害虫预测中的应用

害虫发生是一种复杂、 动态时间序列数据, 单一预测模型都是基于线性或非线性数据, 不能同时捕捉害虫发生的线性和非线性规律, 很难达到理想的预测精度。本研究首先采用差分自回归移动平均模型对昆虫发生时间序列进行线性建模, 然后采用支持向量机对非线性部分进行建模, 最后得到两种模型的组合预测结果。将组合模型应用到松毛虫Dendrolimus punctatus发生面积的预测, 实验结果表明组合模型的预测精度明显优于单一模型, 发挥了两种模型各自的优势。组合模型是一种切实可行的害虫预测预报方法。     

Dispersal of Amaranthaceae and Chenopodiaceae pollen in the atmosphere of Extremadura (SW Spain)

A study over six consecutive years of the pollination dynamics of the Amaranthaceae and Chenopodiaceae in Badajoz, and a comparative study over three years with stations in Mérida and Cáceres showed that there were different factors affecting this process. Thus, the proximity of croplands was found to be important in determining the magnitude of the concentrations, and this was also confirmed with a study of the concentrations measured directly in the croplands. Autumn and summer rainfall was found to affect, and also to have a certain influence on the length of the flowering period. The daily variations in pollen levels were studied in relation to meteorological parameters, finding a correlation that was positive with respect to temperature and negative with respect to atmospheric humidity and the distance travelled by the wind, i.e. airflow measured in hm with a revolving-cup anemometer. These correlations were the same in all three of the localities studied. The direction of the wind, however, was found to have different effects according to the locality studied. This is explained by their positions relative to the irrigation zones in the region. The pattern of diurnal pollen release from these taxa shows the greatest levels to be reached between 10:00 and 12:00 hours in Mérida as well as in Badajoz. In Cáceres, however, the distribution throughout the day was very even, with few hourly variations. This may be due to the sparse representation of these species in the neighbourhood of the Cáceres trap, with the pollen having been transported from sources that were farther away.     

Modeling nonstationary longitudinal data

An important theme of longitudinal data analysis in the past two decades has been the development and use of explicit parametric models for the data's variance-covariance structure. A variety of these models have been proposed, of which most are second-order stationary. A few are flexible enough to accommodate nonstationarity, i.e., nonconstant variances and/or correlations that are not a function solely of elapsed time between measurements. We review five nonstationary models that we regard as most useful: (1) the unstructured covariance model, (2) unstructured antedependence models, (3) structured antedependence models, (4) autoregressive integrated moving average and similar models, and (5) random coefficients models. We evaluate the relative strengths and limitations of each model, emphasizing when it is inappropriate or unlikely to be useful. We present three examples to illustrate the fitting and comparison of the models and to demonstrate that nonstationary longitudinal data can be modeled effectively and, in some cases, quite parsimoniously. In these examples, the antedependence models generally prove to be superior and the random coefficients models prove to be inferior. We conclude that antedependence models should be given much greater consideration than they have historically received.     

基于ARIMA模型的生态足迹动态模拟和预测——以甘肃省为例

生态足迹(EF)是一种定量测量人类对自然利用程度的方法。然而目前对其发展趋势准确的定量分析尚不多见。可采用自回归综合移动平均模型(ARIMA)来模拟并预测区域生态足迹。综合运用生态足迹方法和ARIMA模型对甘肃省1949-2009年的生态足迹和生态承载力进行了动态模拟和分析,在此基础上预测了2010-2015年的生态足迹变化趋势。结果表明:1949-2009年,人均生态足迹呈现上升趋势,预计2010-2015年上升趋势明显加快,2015年会增加到2.6051 hm²/人,是2009年的1.67倍;1997-2004年人均生态承载力逐年减少,2005年之后逐年增加,预计2010-2015年仍会增加;预计2010-2015年所有人均生态足迹组成类型均呈现上升趋势,尤以人均化石能源生态足迹增长显著;1997-2009年人均生态承载力均小于人均生态足迹,导致生态赤字,甘肃省生态环境处于不可持续状态,预计2010-2015年人均生态承载力略有增长,但仍小于人均生态足迹,生态赤字不断增大,预计2015年增长到-2.0468 hm²/人,约为2009年(-1.0262 hm²/人)的两倍,甘肃省生态环境不断恶化;经济的发展依赖于化石能源的消耗而造成对自然资源的过度利用,大量耕地转换为建设用地,草地荒漠化是引起甘肃省生态赤字的主要原因;改变经济发展和资源消费模式,控制人口规模,减少人均生态足迹消耗,优化配置和集约节约利用自然资源,提高生态承载力是促进社会经济和资源环境可持续发展的有效途经。     

中国水产品贸易生态足迹时空演变与动态预测

国际贸易下的生态输入与输出在一定程度上会重新配置国家及地区之间的生态环境资源。中国在大力发展水产品贸易的同时,也面临着由此带来的生态资源损失等问题。基于生态足迹模型测算2001-2020年中国与35个主要国家和地区的水产品贸易生态足迹和生态净值进行现状评价,通过ArcGIS揭示生态净值的时空演变特征,并运用ARIMA模型预测其未来变化趋势。研究结果表明:(1)中国水产品进口与出口生态足迹值较大,不同种类水产品贸易生态足迹值差距较大。(2)中国水产品贸易生态净值虽然近期呈现显著上升趋势,但整体生态净值态势不稳定,而且不同种类水产品贸易生态净值差别较大。(3)中国水产品贸易生态净值在时间维度上整体变化程度不高,但在空间维度上存在明显的异质性问题,并且集中程度变化较为明显。(4)中国水产品出口贸易生态足迹和进口贸易生态足迹主要国家分布基本保持稳定,但是少数主要国家变化明显,水产品出口贸易和进口贸易集中度均较高。(5)预测2021-2025年中国水产品出口和进口生态足迹处于明显不平衡状态,2025年中国水产品贸易生态净值空间分布依然存在明显的异质性问题。因此,本研究从优化水产品贸易结构、畅通产业双循环路径、提升海洋科技创新能力、深化多边贸易合作体制等不同维度提出优化中国水产品贸易生态足迹的相关对策建议,为中国水产品贸易可持续发展提供现实依据。     

Population dynamics and economic losses caused by Zeuzera pyrina,a cryptic wood‐borer moth,in an olive orchard in Egypt

相似文献