Prediction of dust fall concentrations in urban atmospheric environment through support vector regression

Support vector regression （SVR） method is a novel type of learning machine algorithms, which is seldom applied to the development of urban atmospheric quality models under multiple socio-economic factors. This study presents four SVR models by selecting linear, radial basis, spline, and polynomial functions as kernels, respectively for the prediction of urban dust fall levels. The inputs of the models are identified as industrial coal consumption, population density, traffic flow coefficient, and shopping density coefficient. The training and testing results show that the SVR model with radial basis kernel performs better than the other three both in the training and testing processes. In addition, a number of scenario analyses reveal that the most suitable parameters （insensitive loss function e, the parameter to reduce the influence of error C, and discrete level or average distribution of parameters σ） are 0.001, 0.5, and 2 000, respectively.

Atmospheric Environmental Quality Prediction Based on Support Vector Machine

The economic development bring serious environmental problems to China, the quality of atmospheric environment has an important bearing on the forecast. Be aimed at the complexity and non-linear of the quality of atmospheric environment, chaos theory has been put forward which takes full advantage of using date information. Based on the reconstruction of time-series phase space of the quality of atmospheric environment with the use of least squares support vector machine theory, the atmospheric environment prediction model was built up, and 25 years of historical data viewed as the raw data of the quality of the environment in Benxi City, giving a practical example, it shows that the results forecasted by the least squares support vector machine and the actual results match the better the forecast accuracy also meet the engineering application.

Experimental study on removal nitrogen oxide of flue gas by using solid absorbents

With the rapid development of modem industry and increase of consumption of the coal, petroleum and natural gas etc., emission of nitrogen oxide （NOx） from flue gas has air environment quality worsen day by day. This research work is experimental study on removal low concentration NOx of flue gas by using solid absorbents. The experiment result shown that denification rate by modified activated carbon is higher than that of modified zeolite and rectorite. Average denitrification rate is 65.47% and maximum denitrification rate is 95.82% for activated carbon; average denitrification rate is respectively as 43.29% and 36.18%, maximum denitrification rate is respectively as 87.51% and 79.47% for modified zeolite and rectorite. Experiment results indicated that NO adsorption process of activated carbon can be described by Freudlich adsorption mode, K=0.143 and n=2.842 and Freudlich adsorption isotherm equation is： q = 0.143MO^0.3519.

The Analysis of Gas Absorption into a Stationary Droplet in Atmospheric Environment

Absorption of gaseous species into stationary droplets is a fundamental interest of mass transfer between liquid droplets and ambient gas, which plays a key role in atmospheric environment control and many industrial applications. In this paper, two different considerations including equilibrium and non-equilibrium relations at the interface are used to analyze and predict the absorption time for a physical absorption at a relatively low solubility of gas. For the equilibrium pattern, in the beginning period of absorption, the mass transfer rate is considerably rapid and afterward becomes slower and slower and finally comes to almost zero as the droplet concentration closes to the saturated value. Differently, when the non-equilibrium model is adopted, the interfacial concentration increases gradually with the bulk concentration of liquid droplet, and the absorption rate mildly decelerates with the increase of bulk one throughout the process, which leads to a longer absorption time. Based on the diffusion equation of species, the concentration distribution within the droplet at different times is computed. A solution for CO2 absorption into a small water droplet is given.

长三角区域大气污染防治协作机制启动

由长三角三省一市和国家八部委组成的长三角区域大气污染防治协作机制日前启动,并在上海召开第一次工作会议。这次会议明确了协作机制的五项具体职能,以及近期要着重抓好的十个方面协作和联合行动。会议明确了"协商统筹、责任共担、信息共享、联防联控"的协作原则,同时明确五项具体职能:一是协调推进党中央、国务院关于大气污染防治的方针、政策和重要部署在长三角区域的贯彻落实;

张家港计量测试所参与完成油气回收第二阶段验收工作

近日,张家港计量测试所派相关人员参加了由环保局牵头,质监、财政、经信委、安监、消防等各部门联合参与的加油站油气回收工程第二阶段现场验收。在验收现场,各部门对今年完成改造的数十家加油站进行认真细致地审核,对改造的硬件设施进行拍照核对,对部分油气回收改造装置提出了一些整改建议;同时听取了加油站负责人对已投入运行的油气回收装置使用状况的介绍。从验收情况来看,张家港市油气回收工程改造规范,硬件设施到位,人员培训有效落实。