A Simple Neural Network for Estimating Emission Rates of Hydrogen Sulfide and Ammonia from Single Point Sources

Abstract

Neural networks have shown tremendous promise in modeling complex problems. This work describes the development and validation of a neural network for the purpose of estimating point source emission rates of hazardous gases. This neural network approach has been developed and tested using experimental data obtained for two specific air pollutants of concern in West Texas, hydrogen sulfide and ammonia. The prediction of the network is within 20% of the measured emission rates for these two gases at distances of less than 50 m. The emission rate estimations for ground level releases were derived as a function of seven variables: downwind distance, crosswind distance, wind speed, downwind concentration, atmospheric stability, ambient temperature, and relative humidity. A backpropagation algorithm was used to develop the neural network and is also discussed here. The experimental data were collected at the Wind Engineering Research Field Site located at Texas Tech University in Lubbock, Texas. Based on the results of this study, the use of neural networks provides an attractive and highly effective tool to model atmospheric dispersion, in which a large number of variables interact in a nonlinear manner. INTRODUCTIONThe modeling of atmospheric dispersion has been actively researched for many decades. However, because of the vast number of variables involved and the arbitrary variations in wind

Real-Time Identification of Indoor Pollutant Source Positions Based on Neural Network Locator of Contaminant Sources and Optimized Sensor Networks

“…24 On the basis of the existing studies, NN applications are promising for predictions of outdoor contaminant distributions. 3,25 Although NNs had several promising applications, an extensive literature review did not reveal any study considering the use of NNs in the case of indoor contamination. The existing NN applications in building systems include predictions of building energy consumption and controls of heating, ventilation, and air-conditioning (HVAC) systems.…”

“…An example of a NN application for solving the inverse problem in outdoor environments was successfully demonstrated for hydrogen sulfide and ammonia releases in west Texas. 3 In addition, several studies computed the time-dependent contaminant concentration distributions from a known source using numerical simulations such as computational fluid dynamics (CFD). In indoor environments, CFD was typically used to examine building ventilation system performance and contaminant transport through the ventilation system.…”

A Simple Feedforward Neural Network for the PM10 Forecasting: Comparison with a Radial Basis Function Network and a Multivariate Linear Regression Model

“…Rege and Tock (1996) describe the development and validation of a neural network for the evaluation of polluting emissions deriving from a single gaseous source.…”

Combining Neural Network Models to Predict Spatial Patterns of Airborne Pollutant Accumulation in Soils around an Industrial Point Emission Source

“…Given their successful use in various areas of air quality, [3][4][5][6] there also has been some interest in adopting such approaches as alternatives to numerical modeling when investigating air-terrestrial receptor relationships (e.g., terrestrial emissions to air and airborne pollutant accumulation in urban and rural settings). [7][8][9][10] A major disadvantage of NNs, however, is their instability, especially under conditions of sparse, noisy, and limited data sets. In such cases, NNs are sensitive to small changes in the learning set and to the initial conditions of training.…”