Analysis of pollutant levels in central Hong Kong applying neural network method with particle swarm optimization

Air pollution has emerged as an imminent issue in modernsociety. Prediction of pollutant levels is an importantresearch topic in atmospheric environment today. For fulfillingsuch prediction, the use of neural network (NN), and inparticular the multi-layer perceptrons, has presented to be acost-effective technique superior to traditional statisticalmethods. But their training, usually with back-propagation (BP)algorithm or other gradient algorithms, is often with certaindrawbacks, such as: 1) very slow convergence, and 2) easilygetting stuck in a local minimum. In this paper, a newlydeveloped method, particle swarm optimization (PSO) model, isadopted to train perceptrons, to predict pollutant levels, andas a result, a PSO-based neural network approach is presented. The approach is demonstrated to be feasible and effective bypredicting some real air-quality problems.     

Tree species in relation to soil moisture regime in northwestern Ontario,Canada

Selected data on site, vegetation cover, and soil, including soil moisture regime (SMR), were collected from 2 167 field plots in northwestern Ontario, Canada. SMR provides an estimate of an averaged, annualized soil moisture supply throughout a complete vegetation cycle. SMR is based upon a relative scale that subjectively ranks sites from , 0, and 1 through 9 along a soil moisture continuum which relates to a dry to wet gradient. SMR may be generally correlated to tree growth, stand composition, degree of competition, nutrient availability and overall site quality.This paper reports on relationships between SMR and major tree species. Results highlight relationships between SMR class and the broad ecological ranges of several tree species. In northwestern Ontario, the determination of SMR can help resource managers to better understand the ecology of boreal sites.     

Cadmium and zinc source assessment in the Sepetiba Bay and basin region

Industrial and weathering inputs of Cd and Zn to the Sepetiba Bay and basin were assessed, based on production parameters obtained from local environment and industry authorities, and literature data. The results are compared with similar evaluations from other coastal regions and field data obtained in measuring Zn and Cd transport by rivers, direct run-off and atmospheric deposition in the region. Cadmium and zinc inputs to the bay increased by three orders of magnitude relative to pre-industrial fluxes and presently reach up to 1.6 and 180 tonnes per year for Cd and Zn, respectively, which represents a large input-to-area ratio, and explains the high concentration of these metals previously reported in the estuarine biota and sediments of Sepetiba Bay. Industrial activities, mainly metallurgical and chemical, comprise 94% and 84% of the total Cd and Zn inputs to the Bay. This figure identifies the point sources as being responsible for the environmental contamination and for regional poisoning risks.     

Working backwards to move forwards: Graph-based connectivity metrics for reserve network selection

In this paper we apply graph theory in a reserve selection exercise to explore the tradeoffs between maintaining connectivity and minimizing the total area of a protected area network. Rather than focus on a single organism, we used a multi-species approach and looked at the tradeoff curves for organisms with varying dispersal abilities. We first generated the tradeoff curves using a graph-based metric to determine the importance of individual patches for maintaining connectivity. We then performed an analogous set of analyses using patch size as a surrogate measure of importance.     

Multi-objective, decision-based assessment of a water quality monitoring network in a river system

Water quality monitoring network design has historically tended to use experience, intuition and subjective judgement in locating monitoring stations. Better design procedures to optimize monitoring systems need to simultaneously identify significant planning objectives and consider a number of social, economic and environmental constraints. The consideration of multiple objectives may require further decision analysis to determine the preference weights associated with the objectives to aid in the decision-making process. This may require the application of an optimization study to extract such information from decision makers or experts and to evaluate the overall effectiveness of locating strategies. This paper assesses the optimal expansion and relocation strategies of a water quality monitoring network using a two-stage analysis. The first stage focuses on the information retrieval of preference weights with respect to the designated planning objectives. With the aid of a pre-emptive goal programming model, data analysis is applied to obtain the essential information from the questionnaire outputs. The second stage then utilizes a weighted multi-objective optimization approach to search for the optimal locating strategies of the monitoring stations in the river basin. Practical implementation is illustrated by a case study in the Kao-Ping River Basin, south Taiwan.     

Optimal and suboptimal control of anaerobic digesters

Anaerobic digester failure due to entry of inhibitors or sudden changes in the feed substrate concentration may be encompassed beneficially by applying optimal control theory. An almost proportional relationship between the dilution rate and the methane production rate leads to a simple suboptimal control law with only minor loss in performance, after the occurrence of the above mentioned events.     

Classification of local- and landscape-scale ecological types in the southern Appalachian Mountains

Five local ecological types based on vegetative communities and two landscape types based on groups of communities, were identified by integrating landform, soil, and vegetation components using multivariate techniques. Elevation and several topographic and soil variables were highly correlated with types of both scales. Landscape ecological types based only on landform and soil variables without vegetation did not correspond with types developed using vegetation. Models developed from these relationships could allow classification and mapping of extensive areas using geographic information systems.     

Parameter values to model the soil ingestion pathway

Soil ingestion is an important exposure pathway for contaminants that are not otherwise very mobile in the environment. Health of both humans and animals can be affected. This paper summarizes the literature and recommends models and probabilistic parameter values for risk assessment applications. Models of the pathway require estimates of the amounts of soil ingested, the concentration of contaminants relative to the original soil, and the bioavailability in the gut of the contaminants ingested with soil. Using a lead-contaminated sandbox as an example, the modelling recommendations suggest that a child typically may consume 50 mg d^–1 of the sandbox soil, the soil ingested will have a tenfold higher lead concentration than the original soil, and the lead will be as bioavailable as if ingested as inorganic lead in water.The Canadian Government right to retain a non-exclusive, royalty free licence in and to any copyright is acknowledged.     

The analysis of monitoring data with the aid of time-series analysis

Methods derived from time-series analysis are proposed for processing monitoring data. The necessity for the use of these methods is demonstrated. In a case study time-series analysis was applied to assess the impact of the closure of the Grevelingen estuary (S. W. Netherlands) in 1971 on a local wintering population of Oystercatchers (Haematopus ostralegus) in the adjacent Oosterschelde estuary.Communication No. 328 of the Delta Institute for Hydrobiological Research.