Results 1 - 10
of
19
Single hidden layer artificial neural network models versus multiple linear regression model in forecasting the time series of total ozone
, 2007
"... ..."
Comparative Study between ADMS and CFD in Modeling Dust Dispersion from a Blasting Events in Quarry
"... Two frequently used methods in atmospheric dispersion modeling (ADMS and CFD) were compared in this study to predict pit retention within an open quarry. Conventional Gaussian plume models developed by CERC, ADMS 3 and ADMS 4, were used to predict the pit retention. This study mimicked Fluent CFD mo ..."
Abstract
- Add to MetaCart
Two frequently used methods in atmospheric dispersion modeling (ADMS and CFD) were compared in this study to predict pit retention within an open quarry. Conventional Gaussian plume models developed by CERC, ADMS 3 and ADMS 4, were used to predict the pit retention. This study mimicked Fluent CFD modeling of dust dispersion of a blasting event in Old Moor Quarry. A single blast event that liberated a typical 25,000 tons of rock released 1,900 kg of Total Suspended Particle (TSP). The emission source geometry was defined as a three dimensional block volume source of 70 m normal to the face, 80 m in width and 20 m in height. It was also assumed the TSP liberated over one hour had an emission rate of 4.71x10-3 g/m3/s. The four particle sizes were defined as 2.5, 10, 30 and 75 m at mass fractions of 0.05, 0.45, 0.3 and 0.2 respectively and the particles were assumed have uniform limestone density of 2600 kg/m3. The results indicated that ADMS and model based on CFD indicates similar trend, that is, pit retention is proportional to distance from source to pit edge along wind direction and proportional to inverse quarry gradient.
Urban air pollution forecasting using artiicial intelligence-based tools 195 X Urban air pollution forecasting using artificial intelligence-based tools
"... ..."
(Show Context)
URBAN OZONE CONCENTRATION FORECASTING WITH ARTIFICIAL NEURAL NETWORK IN CORSICA
"... Abstract: Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France), needs to develop a short-term prediction model to lead its mission of information towards the publ ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France), needs to develop a short-term prediction model to lead its mission of information towards the public. Various deterministic models exist for local forecasting, but need important computing resources, a good knowledge of atmospheric processes and can be inaccurate because of local climatical or geographical particularities, as observed in Corsica, a mountainous island located in the Mediterranean Sea. As a result, we focus in this study on statistical models, and particularly Artificial Neural Networks (ANNs) that have shown good results in the prediction of ozone concentration one hour ahead with data measured locally. The purpose of this study is to build a predictor realizing predictions of ozone 24 hours ahead in Corsica in order to be able to anticipate pollution peaks formation and to take appropriate preventive measures. Specific meteorological conditions are known to lead to particular pollution event in Corsica (e.g. Saharan dust events). Therefore, an ANN model will be used with pollutant and meteorological data for operational forecasting. Index of agreement of this
Reproducing human decisions in reservoir management: the case of lake Lugano
"... The objective of this study is to identify a model able to represent the behavior of the historical decision maker (DM) in the management of lake Lugano, during the period 1982–2002. The DM decides every day how much water to release from the lake. We combine hydrological knowledge and machine learn ..."
Abstract
- Add to MetaCart
(Show Context)
The objective of this study is to identify a model able to represent the behavior of the historical decision maker (DM) in the management of lake Lugano, during the period 1982–2002. The DM decides every day how much water to release from the lake. We combine hydrological knowledge and machine learning techniques to properly develop the model. As a predictive tool we use lazy learning, namely local linear regression. We setup a daily predictor, which achieves good accuracy, with a mean absolute percentage error around 8.5%. Yet, the behavior of the model is not fully satisfactory during the floods. In fact, from an interview with a domain expert, it appears that the DM can even update the release decision every 6 hours during emergencies. We have therefore developed a refined version of the model, which works with a variable time step: it updates the release decision once a day in normal conditions, and every 6 hours during emergencies. This turns out to be a sensible choice, as the error during emergencies (which represent about 5 % of the data set) decreases from 9 to 3 m 3 /sec. Reproducing human decisions in reservoir management 253 1.
URBAN OZONE CONCENTRATION FORECASTING WITH ARTIFICIAL NEURAL NETWORK IN CORSICA
"... Abstract: Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France), needs to develop a short-term prediction model to lead its mission of information towards the publ ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France), needs to develop a short-term prediction model to lead its mission of information towards the public. Various deterministic models exist for local forecasting, but need important computing resources, a good knowledge of atmospheric processes and can be inaccurate because of local climatical or geographical particularities, as observed in Corsica, a mountainous island located in the Mediterranean Sea. As a result, we focus in this study on statistical models, and particularly Artificial Neural Networks (ANNs) that have shown good results in the prediction of ozone concentration one hour ahead with data measured locally. The purpose of this study is to build a predictor realizing predictions of ozone 24 hours ahead in Corsica in order to be able to anticipate pollution peaks formation and to take appropriate preventive measures. Specific meteorological conditions are known to lead to particular pollution event in Corsica (e.g. Saharan dust events). Therefore, an ANN model will be used with pollutant and meteorological data for operational forecasting. Index of agreement of this
Prediction of Ungulates Abundance Through Local Linear Algorithms
, 2006
"... We use a local learning algorithm to predict the abundance of the Alpine ibex population living in the Gran Paradiso National Park, Northern Italy. Population abundance, recorded for a period of 40 years, have been recently analyzed by Jacobson et al. (2004), who showed that the rate of increase of ..."
Abstract
- Add to MetaCart
We use a local learning algorithm to predict the abundance of the Alpine ibex population living in the Gran Paradiso National Park, Northern Italy. Population abundance, recorded for a period of 40 years, have been recently analyzed by Jacobson et al. (2004), who showed that the rate of increase of the population depends both on its density and snow depth. In the same paper, a threshold linear model is proposed for predicting the population abundance. In this paper,
PM 10 forecasting with a local linear approach M. Bianchi°, G. Corani*°, G. Guariso*
"... Local linear models are developed and tested in this paper to predict the next day PM10 concentrations in two urban sites in Lombardy. The fast implementation of the algorithm, developed by IRIDIA, Brussels, and called lazy learning, is exploited to analyse several alternative combinations of meteor ..."
Abstract
- Add to MetaCart
Local linear models are developed and tested in this paper to predict the next day PM10 concentrations in two urban sites in Lombardy. The fast implementation of the algorithm, developed by IRIDIA, Brussels, and called lazy learning, is exploited to analyse several alternative combinations of meteorological and air quality input variables and to determine their relative importance. Most state-of-the-art modelling approaches, both physically based and black-box, such as feed-forward neural networks, are based on a unique relation between a number of input variables and the required output, namely the predicted concentration of a pollutant at a given point. However, such relations are difficult to assess and, apart from
unknown title
, 2013
"... Abstract: Continuous measurements of surface ozone (O3) and nitrogen oxides (NOX) at an urban site (39°37′N, 118°09′E) in Tangshan, the largest heavy industry city of North China during summertime from 2008 to 2011 are presented. The pollution of O3 was serious in the city. The daily maximum 1 h mea ..."
Abstract
- Add to MetaCart
Abstract: Continuous measurements of surface ozone (O3) and nitrogen oxides (NOX) at an urban site (39°37′N, 118°09′E) in Tangshan, the largest heavy industry city of North China during summertime from 2008 to 2011 are presented. The pollution of O3 was serious in the city. The daily maximum 1 h means (O3_1-hr max) reached 157 ± 55, 161 ± 54, 120 ± 50, and 178 ± 75 μg/m3 corresponding to an excess over the standard rates of 21%, 27%, 10%, and 40 % in 2008–2011, respectively. The total oxidant level (OX = O3 + NO2) was high, with seasonal average concentrations up to 100 μg/m3 in summer. The level of OX at a given location was made up of NOX-independent and NOX-dependent contributions. The independent part can be considered as a regional contribution and was about 100 μg/m3 in Tangshan. Statistical early warning analysis revealed that the O3 levels would exceed the standard rate by 50 % on the day following a day when the daily average ozone concentration (O3_mean) exceeded 87 μg/m 3
Research Article Short-term load forecasting using mixed lazy learning method
"... Abstract: A novel short-term load forecasting method based on the lazy learning (LL) algorithm is proposed. The LL algorithm's input data are electrical load information, daily electricity consumption patterns, and temperatures in a specied region. In order to verify the ability of the proposed ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: A novel short-term load forecasting method based on the lazy learning (LL) algorithm is proposed. The LL algorithm's input data are electrical load information, daily electricity consumption patterns, and temperatures in a specied region. In order to verify the ability of the proposed method, a load forecasting problem, using the Pennsylvania-New Jersey-Maryland Interconnection electrical load data, is carried out. Three LL models are proposed: constant, linear, and mixed models. First, the performances of the 3 developed models are compared using the root mean square error technique. The best technique is then selected to compete with the state-of-the-art neural network (NN) load forecasting models. A comparison is made between the performances of the proposed mixed-model LL as the superior LL model and the radial basis function and multilayer perceptron NN models. The results reveal signicant improvements in the precision and eciency of the proposed forecasting model when compared with the NN techniques.
