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.     

Effect of Moisture on the Pollutant Concentration Measurement

The effects of removing moisture from gaseous samples on the measurement of pollutant concentration were studied. Simple mathematical analysis was conducted to derive the formula for correcting the measured results. It was found that the error increases with increase in relative humidity or increase in temperature. The error may become significant under extreme conditions.     

A new approach to characterize biodegradation of organics by molecular mass distribution in landfill leachate

This study provides biodegradability of organics in leachate according to their molecular mass distributions (<0.5, 0.5 to 1, 1 to 3, 10, and >10 KDa). Organics with molecular mass values lower than 0.5 KDa were the predominant species in the raw leachate filtrate, and the aerated lagoon process was very effective in treating these highly biodegradable organics; the Fenton's oxidation process was very effective in treating not-so-biodegradable organics with molecular mass values higher than 0.5 KDa, but a portion of these organics were converted into organics <0.5 KDa after Fenton's oxidation. An oxygen uptake measurement using a respirometer was more sensitive than a conventional biochemical oxygen demand measurement to evaluate bioactivities, especially when bioactivities were low.