中长期径流预报模型优选研究

【目的】对中长期径流预报模型进行比较和优选,为中长期径流预报模型的应用及提高预报精度提供参考。【方法】以黄河流域黑石关、龙门、民和水文站年径流为研究对象,利用灰色预测进行趋势分析、逐步回归进行周期分析,两者耦合建立灰色-逐步回归周期模型;利用逐步回归分析确定均生函数的周期性基函数,耦合建立均生函数-逐步回归模型;利用灰色-逐步回归中的趋势项和周期项作为预报因子,建立投影寻踪回归模型;利用前4年的实测径流数据预报当年径流,建立BP神经网络模型,并通过信息熵原理进行站点模型的综合评价和优选。【结果】建模期除黑石关水文站BP神经网络模型外,各站点拟合预报的平均相对误差均小于11.0%,合格率均大于90%。验证期除民和水文站灰色-逐步回归周期模型外,各站点平均相对误差均小于20%,合格率等于或大于80%,满足精度要求。【结论】均生函数-逐步回归径流预报模型可作为黑石关水文站的优选模型,BP神经网络径流预报模型可作为龙门和民和水文站的优选模型。     

不同滴灌灌溉制度对绿洲棉田土壤水热分布及产量的影响

【目的】探究不同滴灌灌溉制度对绿洲棉田土壤水热分布状况及对产量的影响。【方法】于2017年在策勒地区开展田间试验,设置了2种灌水模式:基于计算机模型的预报灌溉与基于土壤墒情的灌溉,每种灌水模式设置2种灌溉梯度:充分灌溉(100%)和非充分灌溉(75%的充分灌溉)。【结果】预报灌溉的土壤含水率和贮水量在花蕾与花铃期显著高于墒情灌溉;不同灌溉制度各剖面的土壤温度变化趋势一致,整个生育期的表层土壤平均温度表现为墒情亏缺最高,预报充分最低。作物产量在一定范围内随灌溉量的增加而增加,预报充分的产量较预报亏缺,墒情充分,墒情亏缺分别提高13.7%、12.1%、47.6%。水分利用效率表现为预报亏缺最高,且产量与预报充分的产量无显著差异。【结论】在策勒绿洲地区,预报亏缺灌溉可达到节水增产的目的。     

基于变分模态分解-BA-LSSVM算法的配电网短期负荷预测

配电台区日负荷序列呈现为既包含变化趋势、又含有波动细节的不规则曲线,该文借助变分模态分解(variational mode decomposition,VMD)将包含这些信息的原始日负荷序列分解为不同频率尺度的子序列,并结合一系列复杂的环境因素,分别利用不同的最小二乘支持向量机(least squares support vector machine,LSSVM)模型进行负荷预测,最后将基于不同频率分量的预测结果相加得到最终的日负荷预测结果。为了提高LSSVM预测能力,采用蝙蝠算法(bat algorithm,BA)对各LSSVM的参数进行寻优,同时,该文分析了影响负荷变化的环境因素,设计了一套因素归一化方法,预测过程考虑了环境因素的影响。仿真结果表明,该文提出的考虑复杂环境因素的预测思想及对历史日负荷进行VMD分解、BA优化、LSSVM预测的组合预测方法能有效提高短期日负荷预测的准确性。     

一种基于花授粉算法的WRF风速集合预报新模型

基于不同水平分辨率和边界层参数化方案的集合预报思路,应用花授粉算法与不限制负值的约束理论(FPA-NNCT)进行权重平均,提出一种新的风速集合预报模型(FPA-NNCT-WRF-E).利用山东省代表山地和海滨下垫面的2个风电场风速实测数据,将新模型与传统算术集合模型(M-WRF-E)以及FPA模型(FPA-WRF-E)的风速预报结果进行对比评估.结果表明:FPA-NNCT-WRF-E预报明显优于M-WRF-E和FPA-WRF-E的风速预报,与M-WRF-E相比, FPA-WRF-E将风速平均绝对误差(MAE)减小了20%以上,而新模型FPA-NNCT-WRF-E将MAE减小了38%以上.预报的准确性得到了提高.     

Modelling and forecasting epidemics of apple powdery mildew (Podosphaera leucotricha)

A model developed to simulate epidemics of powdery mildew on vegetative shoots of apple generates two types of output. Firstly, it forecasts disease severity (percentage of host tissue infected) by incorporating effects on disease development of the amount of healthy susceptible tissue and current infectious (sporulating) disease, the level of initial inoculum (overwintered 'primary' mildew) and weather conditions. The effects of weather variables are considered on only two aspects of the fungal life cycle: initial spore germination and the subsequent development during the incubation period. Secondly, the model generates indices of the relative favourability of weather conditions on disease development by incorporating effects of weather on conidial production/dispersal and germination. On each day, forecasts of the (relative) severity of new infection and total current infectious disease are given for both types of output. The model was evaluated by comparing its predictions with the mildew epidemics observed in two unsprayed orchards over four years. In all the years, the temporal patterns of the predicted and the observed disease were generally similar. The pattern of the disease severity forecasts was marginally closer to the observed than that derived from two weather indices. Potential roles of the model in practical management of apple powdery mildew are discussed.     

降水对高原鼠兔种群消长的影响

就降水对高原鼠兔种群消长的影响进行了研究。结果表明,降水量的变化与高原鼠兔种群数量消长间存在着一定的相关关系;通过对年降水量、三季度降水量和一季度降水量的综合分析,同时参考特殊降水因素的影响,即可对高原鼠兔种群数量的发展趋势作出预测。     

灰色模型GM(1,1)与GM(2,1)的改进和探讨

修正了 Ｇ Ｍ （２,１）灰色模型．利用 Ｚ 变换给出 Ｇ Ｍ （１,１）、 Ｇ Ｍ （２,１）的时间响应序列,改进了灰色预测模型,同时证明该时间响应序列具有自回归性．     

动力负熵场及其在短期天气预报中的应用

把纬圈气流虚拟平衡态原理具体应用到短期预报中,因时效短的缘故,决定了虚拟平衡态应在低层大气中寻找,倘若时效达到一定天数,则平衡态应在中层大气中定义。按照涡动原理计算出动力负熵值,由动力负熵值构成动力负熵场,其由正熵区,负熵区、０值线三部分组成,正熵区为无降水区,负熵区又分为负熵有效区和负熵无效区,前者为未来的降水区域,降水强度与负熵中心值和梯度的大小成正比。     

基于模糊神经网络的农村电力短期负荷预测

为提高负荷预测精度,提出了一种新的模糊神经网络短期负荷预测模型。该模型将模糊系统和神经网络的优点融合在一起,并利用小生境遗传算法优化模糊神经网络参数,提升网络运算性能。某农村地区电力短期负荷预测的计算结果表明,该方法具有较好的预测效果。     

Application of modified Deep Belief Network in Forecasting Cotton Diseases and Insect Pests

[Objective] The occurrence and development of cotton diseases and insect pests are mainly related to environmental information. Because this environmental information is various, complex and unstable, the study on the prediction methods of cotton diseases and insect pests is a certain challenge. This study aims to establish a forecasting model for the timely and accurate prediction of cotton diseases and insect pests. [Method] A forecasting model of cotton diseases and insect pests is proposed based on environmental information and a modified Deep Belief Network (DBN) that is constructed by a three-layer restricted Boltzmann machine (RBM) and a supervised back-propagation (BP) network. In the method, the RBM is used to transform the original environmental information vectors into a new feature space related to the diseases and pests; the BP network is trained to classify and forecast the features generated by the last RBM layer and two rules of dynamic learning and comparison and dispersion are adopted to accelerate the training process of RBM. The proposed model was validated on a dataset of cotton bollworm, aphids, spider, cotton Verticillium wilt, and Fusarium wilt in a recent six-year period. [Result] Compared with the traditional prediction models of cotton diseases and insect pests, the proposed model can deeply explore the extensive correlation between the occurrence of cotton diseases and pests and environmental information. The results show that the proposed model has a higher accuracy compared with the classical predictive models, and the average forecasting accuracy is above 83%. [Conclusion] The proposed method is an effective crop disease and pest forecasting method that can provide a technical support for preventing cotton disease and insect pests.