灰色预测法在南宁市可持续发展趋势分析中的应用

本文运用灰色系统理论 ,建立灰色预测模型 ,对南宁市社会、经济及生态环境发展趋势进行了分析 ,并针对南宁市发展中的不合理状况 ,提出相应的调控对策。     

COMPARATIVE EVALUATION OF STATISTICAL METHODS FOR WATER SUPPLY FORECASTING1

ABSTRACT: While the correlation coefficient and standard error of estimate are frequently used when comparing models of seasonal water yield, the following criteria may be more important in selecting one model from among several alternatives: rationality of the regression coefficients, the distribution of the residual errors, and the correctness of indicators of the relative importance of the predictor variables. These criteria were used to compare seasonal water yield models that were calibrated using multiple regression, stepwise regression, principal components regression, polynomial regression using a principal components rotation, and constrained pattern search. Hydrologic data from the Upper Sevier River basin in southern Utah were used to illustrate the comparative analysis process. The prediction equations used the April-July streamflow volume as the criterion variable.     

基于证据理论的煤矿瓦斯涌出组合预测

为提高煤矿瓦斯涌出量预测的准确度,引入证据理论组合预测方法。根据瓦斯涌出量及其主要影响因素间的实验数据,采用3个不同的粒子群神经网络模型对涌出量进行初步预测。并由BP、RBF网络对预测误差及预测点的影响因素进行分析建模,以获取每个模型的可信度。再利用证据理论对其进行合成,确定组合模型的权值,最终实现对瓦斯涌出量的组合预测。实例结果表明,该组合预测方法的平均绝对误差、均方误差分别为18.5%、5.8%,均小于神经网络组合法及等权平均法的相应预测误差,适用于煤矿瓦斯涌出量预测。     

城市安全生产影响因素及其预测分析——以上海为例

为研究我国城市安全生产的影响因素及预测城市安全生产的发展趋势,以上海市为例,对2004—2010年期间与安全生产相关的数据进行灰色关联度分析,提取影响安全生产状况的主要经济社会因素,并与工矿商贸死亡人数之间建立回归模型。研究结果表明,工矿商贸死亡人数与第二产业比重、GDP增长率、教育支出占GDP比重以及私营及个体工商户比例均呈现负相关。基于2007—2011年各月份上海市的安全生产死亡人数,运用Winters乘法模型,预测上海市安全生产发展趋势。     

空气质量多模式预报系统在中山市的应用

介绍了中山市空气质量多模式预报系统。对2015年3月—2016年2月的预报效果评估表明:系统可以较好地反映污染物的变化趋势但仍存在系统性偏差。通过对排放源清单的调整优化及对模式干沉降模块的改进使模式系统的偏差显著减小。总结并建立中山市污染天气案例库,发现在典型污染天气形势下,除O3-8 h外,其他污染物均值均能达到空气质量二级标准。未来将从2个方面提高中山市空气质量预报预警系统的实用性,包括逐步实现污染源排放清单的动态及时更新和提高极端气象条件下O3污染预报能力。     

Fecundity as a Basis for Risk Assessment of Nonindigenous Freshwater Molluscs

Abstract:  The most efficient way to reduce future damages from nonindigenous species is to prevent the introduction of harmful species. Although ecologists have long sought to predict the identity of such species, recent methodological advances promise success where previous attempts failed. We applied recently developed risk assessment approaches to nonindigenous freshwater molluscs at two geographic scales: the Laurentian Great Lakes basin and the 48 contiguous states of the United States. We used data on natural history and biogeography to discriminate between established freshwater molluscs that are benign and those that constitute nuisances (i.e., cause environmental and/or economic damage). Two statistical techniques, logistic regression and categorical tree analysis, showed that nuisance status was positively associated with fecundity. Other aspects of natural history and biogeography did not significantly affect likelihood of becoming a nuisance. We then used the derived statistical models to predict the chance that 15 mollusc species not yet in natural ecosystems would cause damage if they become established. We also tested whether time since establishment is related to the likelihood that nonindigenous mollusc species in the Great Lakes and United States would cause negative impacts. No significant relationship was evident at the U.S. scale, but recently established molluscs within the Great Lakes were more likely to cause negative impacts. This may reflect changing environmental conditions, changing patterns of trade, or may be an indication of "invasional meltdown." Our quantitative analyses could be extended to other taxa and ecosystems and offer a number of improvements over the qualitative risk assessments currently used by U.S. (and other) government agencies.     

机场环境下飞机LY12CZ结构腐蚀损伤预测方法研究

依据LY1 2CZ材料的EXCO溶液浸泡加速腐蚀试验数据、飞机LY 12CZ构件在机场环境下的真实腐蚀损伤数据以及腐蚀损伤等效原则和当量关系原理,获得了该材料在2种环境下腐蚀的当量因子均值(α) =0.023 6,构建了LY12CZ材料于EXCO溶液中浸泡腐蚀的神经网络腐蚀深度预测模型.在此基础上提出了利用所建的神经网...     

沱江流域主要污染负荷预测及时空分布特征

耦合社会-经济因子探究工业点源和生活污染源污染负荷未来变化趋势,可为优化水环境规划和管理方案提供理论依据。选取沱江流域为研究区域,采用经济增长预测法、工业点源传统统计法、人口趋势灰色模型预测法和排污系数法分别计算了2020-2025年该区域28个县(市、区)的工业GDP值,工业点源废水排放量及主要污染负荷(COD、NH₃-N、TN、TP),农村与城镇人口及生活污染源的主要污染负荷,并利用ArcGIS技术探究了工业点源和生活污染源主要污染负荷空间分布特征。结果表明:2020-2025年,工业GDP值总体呈逐年增加趋势,而工业废水排放量总体呈逐年减少趋势,预计到2025年,流域工业GDP值将增加至2.52×10¹²元,而工业废水排放量将减少至0.64×10⁸ t。工业点源主要污染负荷表现为COD>NH₃-N>TN>TP。沱江流域总人口数与生活污染源污染负荷呈逐年增加趋势,其中城镇人口与生活污染源污染负荷呈逐年增加趋势,农村人口与生活污染源污染负荷呈逐年减少趋势,且城镇人口及生活污染源污染负荷增加量大于农村人口及生活污染源污染负荷减少量。城镇、农村生活污染源的主要污染负荷表现为COD>NH₃-N>TN>TP。工业点源和生活污染源主要污染负荷在空间上存在高度异质性。2025年,来自工业点源的主要污染负荷均呈上游较少,中、下游较多的特征;来自城市生活污染源的主要污染负荷均呈中、上游较多,下游较少的特征;来自农村生活污染源的主要污染负荷均呈中游较多,上、下游较少的特征。笔者提出耦合社会-经济因子预测流域污染负荷的方法可以推广到其他与社会经济指标相关联的流域工业点源、生活污染源污染负荷的预测研究中,以期为未来流域水环境管理与治理提供科学参考。     

基于深度学习的大数据空气污染预报

为了更好地反映环境污染变化趋势,为环境管理决策提供及时、全面的环境质量信息,预防严重污染事件发生,开展城市空气质量预报研究是十分必要的.本文针对环境大数据时代下的城市空气质量预报,提出了一种基于深度学习的新方法.该方法通过模拟人类大脑的神经连接结构,将数据在原空间的特征表示转换到具有语义特征的新特征空间,自动地学习得到层次化的特征表示,从而提高预报性能.得益于这种方式,新方法与传统方法相比,不仅可以利用空气质量监测、气象监测及预报等环境大数据,充分考虑污染物的时空变化、空间分布,得到语义性的污染物变化规律,还可以基于其他空气污染预测方法的结果(如数值预报模式),自动分析其适用范围、优势劣势.因此,新方法通过模拟人脑思考过程实现更充分的大数据集成,一定程度上克服了现有方法的缺陷,应用上更加具有灵活性和可操作性.最后,通过实验证明新方法可以提高空气污染预报性能.     

Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions

Deep learning (DL) models are increasingly used to make accurate hindcasts of management-relevant variables, but they are less commonly used in forecasting applications. Data assimilation (DA) can be used for forecasts to leverage real-time observations, where the difference between model predictions and observations today is used to adjust the model to make better predictions tomorrow. In this use case, we developed a process-guided DL and DA approach to make 7-day probabilistic forecasts of daily maximum water temperature in the Delaware River Basin in support of water management decisions. Our modeling system produced forecasts of daily maximum water temperature with an average root mean squared error (RMSE) from 1.1 to 1.4°C for 1-day-ahead and 1.4 to 1.9°C for 7-day-ahead forecasts across all sites. The DA algorithm marginally improved forecast performance when compared with forecasts produced using the process-guided DL model alone (0%–14% lower RMSE with the DA algorithm). Across all sites and lead times, 65%–82% of observations were within 90% forecast confidence intervals, which allowed managers to anticipate probability of exceedances of ecologically relevant thresholds and aid in decisions about releasing reservoir water downstream. The flexibility of DL models shows promise for forecasting other important environmental variables and aid in decision-making.