Neural network-based study for predicting ground-level ozone concentration in large urban areas, applied to the Sao Paulo metropolitan area

Guardani, Roberto; Nascimento, Cláudio Augusto Oller do

doi:10.1504/ijep.2004.005680

Cited by 9 publications

(5 citation statements)

References 19 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More recently focus has shifted to air pollution dispersion modelling as demonstrated by air pollution models applied to Hong Kong (Li et al, 2004;Xia and Leung, 2001a,b), Sao Paolo (Guardani, 2004;Ereitas et al, 2005), Delhi (Gokhale and Khare, 2005), Coimbatore (Meenakshi and Saseetharan, 2004) and Kaohsiung (Tsai and Chen, 2004).…”

Section: Air Quality and Pollutionmentioning

confidence: 99%

Review of urban climate research in (sub)tropical regions

Roth

2007

Intl Journal of Climatology

340

210

View full text Add to dashboard Cite

Abstract:Over the last 50 years the developing world, much of which is located in (sub)tropical regions, has seen a dramatic growth of its urban population associated with serious degradation of environmental quality. The total number of (sub)tropical urban climate studies, however; is still small (<20% of all urban climate studies). The available work is further biased towards descriptive studies rather than process work that seeks to indicate the physical climatology of (sub)tropical cities. The available results allow for a preliminary comparison with data from temperate latitudes. Urban heat island (UHI) intensities are generally lower compared to those of temperate cities with comparable population and show a seasonal variation with lower (higher) intensities during the wet (dry) season. (Sub)tropical population-based relations may exist but insufficient appropriate data is available to confirm a logarithmic relationship or systematic differences between different climate types. The (sub)tropical energy balance studies are biased towards dry, clear sky conditions. The amount of net radiation dissipated by sensible heat during daytime is about 40% which is similar to values observed in (sub)urban areas of cities located in temperate climates. Energy partitioning is modulated by water availability and higher percentage of vegetation promotes latent heat flux at the expense of surface heat storage. The apparent strong influence of vegetation and water availability on the energy partitioning irrespective of the climate type, suggests vegetation to be an effective means to reduce heat storage uptake during daytime and hence has the potential to effectively mitigate the nocturnal heat island. It is important to ensure that the rapidly expanding cities of the developing world incorporate climatological concerns in their design to provide a better living and working environment for a large segment of the world's inhabitants. Copyright  2007 Royal Meteorological Society KEY WORDS tropical urban climatology; tropical urban heat island; tropical urban energy balance

show abstract

Section: Air Quality and Pollutionmentioning

confidence: 99%

Review of urban climate research in (sub)tropical regions

Roth

2007

Intl Journal of Climatology

340

210

View full text Add to dashboard Cite

show abstract

“…The model was applied to hourly and daily predictions, and strong correlations between measured and modeled O 3 concentrations were shown. Guardani and Nascimento 92 have reported results of an extension of the neural network model for O 3 to data collected from 1997 through 2001 at one of the air monitoring sites in the São Paulo metropolitan area. When the model is used to describe hourly average O 3 concentrations, NO and NO 2 concentrations are the most important variables, with radiation, temperature and relative humidity also being of importance.…”

Section: Atmospheric Carboxylic Acidsmentioning

confidence: 99%

Ethanol fuel use in Brazil: air quality impacts

Anderson

2009

Energy Environ. Sci.

View full text Add to dashboard Cite

Brazil has a long history in the development of ethanol for use as a liquid fuel for vehicles. They have developed one of most efficient and economical systems for producing ethanol in the world. Brazil provides an example that many other countries would like to emulate. Using ethanol as a vehicle fuel has significant potential air quality impacts. This paper will review the available air quality and vehicle emissions data in Brazil, specifically focusing on vehicle related pollutants that may be impacted by the use of large quantities of ethanol in the fuel. The atmospheric concentrations of acetaldehyde (CH 3 CHO) and ethanol in Brazil are much higher than those in other areas of the world, while the concentrations of the single ring aromatic compounds and small carboxylic acids are more typical of observations elsewhere. Acetaldehyde and ethanol increase in vehicle emissions and nitrogen oxides (NO x) may increase when ethanol fuels are used. Both CH 3 CHO and NO x are very important contributors to photochemical air pollution and ozone (O 3) formation. There are very significant O 3 air quality problems in Brazil, most studied in the larger cities of São Paulo and Rio de Janeiro. These are issues that must be evaluated for other areas of the world that are considering the use of high ethanol content vehicle fuels.

show abstract

“…The use of neural networks to simulate the behavior of complex systems has been the focus of other works by the present authors. − In the present study, feedforward NN models with one hidden layer of neurons, illustrated in Figure , were fit to the experimental data, which were divided into two sets: a learning set, used in model fitting, and a test set, used in model validation. Each neuron in the hidden layer (see Figure ) first calculates the weighted sum S j of all interconnected signals from the input layer plus a bias term, eq 1, and then generates an output by means of an activation function.…”

Section: Neural Network Fittingmentioning

confidence: 99%

Prediction of Emulsion Stability via a Neural Network-Based Mapping Technique

Souza¹,

Quina²,

Guardani³

2007

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Stability is a key property related to the production and use of a number of products that are commercialized in the form of emulsions. However, because of the complexity of these systems, in most cases there is no readily available means to predict emulsion stability. Thus, product formulation development is based on laboratory evaluations of emulsion stability, e.g., by measuring the time required for the emulsion to break according to standardized procedures. These tests are time-consuming and subject to visual inaccuracies between different operators. In this work, a neural network-based model is tested as a tool for predicting the emulsification properties of mixtures of surfactants, organic solvents, and organic compounds used as active ingredients in pesticide formulations. The model is able to predict the emulsion-breaking height, a standard measure of the system's stability. Six physicochemical properties were used as descriptors for the active ingredients: octanol/water partition coefficient, molar volume, refractive index, density, Hildebrand solubility parameter, and Henry's constant. The solvents and their mixtures were described by their density, Hildebrand solubility parameter, and surface tension. Other input variables include water hardness and the concentrations of active ingredient and surfactant. The output variable was the volume percentage of cream formation after dispersion of the emulsifiable concentrate in water, represented by the “emulsion-breaking height”, predicted by the neural network model. In a different approach, nonionic surfactants were described by their average hydrophilic−lipophilic balance (HLB) number. The loss of information in the neural network resulted in inaccurate estimates of cream formation. Nevertheless, with this approach, the neural network was able to discriminate between regions of emulsion stability and instability. Application of the method enabled the construction of phase diagrams for the prediction of the optimum surfactant mixture(s) for emulsification of a given combination of solvent and active ingredient. The method can reduce the time needed for formulation development, minimize the exposure of the formulator to chemicals, and avoid unnecessary production of effluent in product test facilities.

show abstract

Neural network-based study for predicting ground-level ozone concentration in large urban areas, applied to the Sao Paulo metropolitan area

Cited by 9 publications

References 19 publications

Review of urban climate research in (sub)tropical regions

Review of urban climate research in (sub)tropical regions

Ethanol fuel use in Brazil: air quality impacts

Prediction of Emulsion Stability via a Neural Network-Based Mapping Technique

Contact Info

Product

Resources

About