FLOOD STAGE FORECASTING WITH SUPPORT VECTOR MACHINES1

ABSTRACT: Machine learning techniques are finding more and more applications in the field of forecasting. A novel regression technique, called Support Vector Machine (SVM), based on the statistical learning theory is explored in this study. SVM is based on the principle of Structural Risk Minimization as opposed to the principle of Empirical Risk Minimization espoused by conventional regression techniques. The flood data at Dhaka, Bangladesh, are used in this study to demonstrate the forecasting capabilities of SVM. The result is compared with that of Artificial Neural Network (ANN) based model for one‐lead day to seven‐lead day forecasting. The improvements in maximum predicted water level errors by SVM over ANN for four‐lead day to seven‐lead day are 9.6 cm, 22.6 cm, 4.9 cm and 15.7 cm, respectively. The result shows that the prediction accuracy of SVM is at least as good as and in some cases (particularly at higher lead days) actually better than that of ANN, yet it offers advantages over many of the limitations of ANN, for example in arriving at ANN's optimal network architecture and choosing useful training set. Thus, SVM appears to be a very promising prediction tool.     

经济结构变动对环境污染物排放的影响分析

本文利用投入产出技术给出一类经济结构变动对环境污染物排放的影响分析模型,该方法着重分析了各产业部门的生产技术变动、最终需求变动及收入变动对环境污染物排放量的影响。     

Ecological tax reforms and environmental benefits in Italy and Sweden

The paper calculates the implications of including monetary measurements of environmental emission changes for the welfare impacts of ecological tax reforms in Italy and Sweden. Taxes on emissions of SO₂, NO_x and CO₂ are investigated. Country-specific computable equilibrium models are used for estimating net welfare changes of the introduction of these taxes, the incomes of which are used for reducing distorting labour taxes. The results indicate that the inclusion of environmental benefits reduces the costs of ecological tax reforms considerably for both countries, and may even turn into net welfare gains.     

某厂化学装置爆炸对设备房结构的损坏——调查与模拟分析

在对某厂化学爆炸所作的现场调查的基础上，对设备房钢筋混凝土框架结构构件的受损状况进行了分类描述，采用有限元方法对框架结构在静力和爆炸冲击荷载下的反应进行了模拟分析，分析结果与现场调查情况基本一致，给出了一些有意义的结论。     

烟台地区在业人口就业结构分析

根据人口普查资料，本文从行业和职业方面对烟台地区在业人口的就业结构现状及变动特点进行了系统分析，并在此基础上对农业剩余劳动力的转移问题作了深入探讨。     

The centers of gravity and dynamic types of body shape of terrestrial invertebrates

In the framework of dynamic morphology theory, the centers of gravity and geometric centers of projections have been determined for the bodies of more than 182 forms of invertebrates, and these data have been used to distinguish four types of dynamic body shapes. It has been demonstrated that specific dynamic types of body shape are characteristic of individual taxa. In addition, there are a group of “transformers,” which may assume any dynamic type of shape, and a group of invertebrates with one predominant dynamic type.     

新形势下我国环境管理与改革取向

在"十三五"我国经济新常态的大逻辑下,环境管理机遇和挑战并存。污染欠账多、污染随着产业转移、政策执行走样、排污收费覆盖面窄、收取率低等,制约环境管理和环保产业的发展。对环境污染的严重性和复杂性、生态环境形势的十分严峻性,以及对污染治理的艰巨性和长期性,应当有一个清醒认识。扭转环境保护与经济发展不协调、不可持续状况,满足城乡居民日益高涨的环境诉求,必须调整环境管理思路,加快改革步伐,扭转环境保护"弱势"格局,厘清环境管理、环境事业和环境市场之间的关系,形成以排污许可证为依据的管理主线、以环境标准为准绳的倒逼机制,以环境司法裁定为常态的终身责任追究制度,创造一个人人守法、企业自觉治理污染和保护环境的社会氛围。     

大气颗粒物中类腐殖酸的研究进展

类腐殖酸(HULIS)是一类广泛存在于云、雾、雨水和大气气溶胶颗粒中的大分子有机物.HULIS既可通过吸收和散射太阳辐射直接影响大气热平衡,又能参与云凝结核的形成间接影响全球气候,加之其重要的环境和健康效应,近年来引起科学界的广泛关注.本文综述了大气颗粒物中类腐殖酸的研究成果,主要包括HULIS的分离、提取和分析方法,HULIS的主要理化性质、浓度和季节变化,以及HULIS的来源和国内外研究现状,并对该领域的研究前景进行了分析和展望.     

单兵信息系统装备可靠性评估方法研究

首先介绍了士兵系统在环境适应性、信息安全、作战适应性、使用寿命等方面的需求,提出了一种可靠性设计方法,可有效解决单兵多模块信息系统可靠性评估问题,大幅提升士兵信息系统的设计效率。同时以典型士兵信息系统为例,进行了士兵结构可靠性、电气可靠性设计。