Identification of the best architecture of a multilayer perceptron in modeling daily total ozone concentration over Kolkata, India (original) (raw)
Related papers
International Journal of Environmental Science & Technology, 2007, Volume 4, Issue 1, pp 141-149 , 2007
Present paper endeavors to develop predictive artificial neural network model for forecasting the mean monthly total ozone concentration over Arosa, Switzerland. Single hidden layer neural network models with variable number of nodes have been developed and their performances have been evaluated using the method of least squares and error estimation. Their performances have been compared with multiple linear regression model. Ultimately, single-hidden-layer model with 8 hidden nodes have been identified as the best predictive model.
Meteorological Applications, 2009
This paper explores the observation made by the Earth Probe Total Ozone Mapping Spectrometer (EP/TOMS) to analyse the predictability of daily total ozone concentration over Kolkata, India. Latitude, longitude, aerosol index, reflectivity, sulphur dioxide index and total ozone concentration of a given day have been used as independent variables to predict total ozone concentration of the next day. Artificial neural network in the forms of a multilayer perceptron, generalized feed forward neural network, a radial basis function network and a modular neural network have been trained to generate predictive models. Performances of the models in the test cases have been judged with the help of four statistical parameters. Finally the models have been compared with multiple linear regression and the potential of generalized feed forward neural network has been established over the other proposed models. Copyright © 2008 Royal Meteorological Society
2013
Complexity of total ozone is well-documented in literature. The present paper has attempted to model total ozone in univariate manner through artificial neural network through an autoregressive approach. The number of predictors has been determined through autocorrelation function and backpropagation learning has been executed on multilayer perceptron. Also, convensional regression has been carried out on the same predictors. The prediction skills have been assessed through various statistics.
Mathematics
This study considers the usage of multilinear regression and artificial neural network modelling to forecast ozone concentrations with regard to weather-related indicators (wind speed, wind direction, relative humidity and temperature). Initial data were obtained by measuring the meteorological parameters using the PC Radio Weather Station. Ozone concentrations near high-voltage lines were measured using RS1003 and at a 220 m distance using ML9811. Neural network models such as the multilayer perceptron and radial basis function neural networks were constructed. The prognostic capacities of the designed models were assessed by comparing the result data by way of the square of the coefficient of multiple correlations (R2) and mean square error (MSE) values. The number of hidden neurons was optimised by decreasing an error function that recorded the number of units in the hidden layers to the precision of the expanded networks. The neural software IBM SPSS 26v was used for artificial ...
International Journal of Remote Sensing, 2007
Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.
Journal of Scientific …, 2008
In this paper, lower tropospheric ozone concentration was modeled using artificial neural networks (ANNs) according to 1 day, 3 days and 7 days time periods to determine best prediction period. In model formation, data that was taken from ozone measuring stations and Government Meteorology Works Office was daily averages of last 6 months of 2003 and first 6 months of 2004. Air pollutant parameters (6) and meteorological parameters (8) were used in ANN architecture for Anatolian and European sides of Istanbul separately. Correlation factor was determined to examine model effectiveness for each time period. Weekly average prediction model has been observed with highest correlation factor and three day's correlation factor was higher than daily's.
Environmental Pollution, 1996
This paper presents the first results of a research project aimed at building a pollution peaks predictor using Artificial Neural Networks (ANNs) with data measured locally. We focus more particularly on the ozone concentration prediction in the Corsica Island at horizon "h+1". We mainly look at the Multi-Layer Perceptron (MLP) network which is the most used of ANNs architectures both in the Environment domain and in the time series forecasting. We have demonstrated that an optimized MLP with endogenous, exogenous and time indicator inputs can forecast hourly ozone concentration with acceptable accuracy. The final results indicate that our predictor has an average Mean Absolute Percentage Error (MAPE) equal to 10.5%. Knowing that the devices measurement accuracy is around 10%, these results are considered as very convincing by "Qualitair Corse", regional organization responsible for monitoring air quality. We have also tested in "real conditions" our predictor: indeed, several ozone pollution peaks occurred during the months of June and August 2010. While PREV'AIR, the national air quality forecasting and mapping system, cannot predict the August's peaks, it appears that our optimized MLP is able to predict them in both cases.
Prediction of Tropospheric Ozone Concentration by Employing Artificial Neural Networks
Http Dx Doi Org 10 1089 Ees 2007 0183, 2008
In this paper, lower tropospheric ozone concentration was modeled using artificial neural networks (ANNs) according to 1 day, 3 days and 7 days time periods to determine best prediction period. In model formation, data that was taken from ozone measuring stations and Government Meteorology Works Office was daily averages of last 6 months of 2003 and first 6 months of 2004. Air pollutant parameters (6) and meteorological parameters (8) were used in ANN architecture for Anatolian and European sides of Istanbul separately. Correlation factor was determined to examine model effectiveness for each time period. Weekly average prediction model has been observed with highest correlation factor and three day's correlation factor was higher than daily's.
Analysis of Tropospheric Ozone by Artificial Neural Network Approach in Beijing
Journal of Geoscience and Environment Protection, 2018
Higher concentration of tropospheric ozone in atmosphere reveals its adverse effects on human health, plants, and on environment. So, there is a need for atmospheric pollutants analysis and their concentration variation, which is a key factor for air quality management in urban areas. The Beijing Olympic center site was used as area of study and five recorded meteorological parameters temperature, dew point, wind speed, pressure, and relative humidity were employed as inputs imputes. Nitrogen Dioxide (NO 2) and hour of day are also considered as input parameters for modeling of tropospheric ozone concentrations. Several deterministic methods are available for local air quality forecasting and prediction. But, in this study, multilayer perceptron (MLP) and generalized regression neural model (GRNM) were considered for prediction of ozone ground level concentration. The root mean squared errors (RMSE) and mean absolute error (MAE) value for MLP model were lower, which confirms its fitness for forecasting purpose. Regression coefficient for MLP in this study was calculated 0.91 and for GRNM model provides 0.76 value. The dew point and relative humidity were the most dominant input imputes found by model, which results in higher concentration of tropospheric ozone.
Advances in Environmental Research, 2001
This paper presents an artificial neural network model that is able to predict ozone concentrations as a function of meteorological conditions and precursor concentrations. The network was trained using data collected during a period of 60 days near an industrial area in Kuwait. A mobile monitoring station was used for data collection. The data were collected at the same site as the ozone measurements. The data fed to the neural network were divided into two sets: a training set and a testing set. Various architectures were tried during the training process. A network of one hidden layer of 25 neurons was found to give good predictions for both the training and testing data set. In addition, the predictions of the network were compared to measurements taken during other times of the year. The Ž inputs to the neural network were meteorological conditions wind speed and direction, relative humidity, tempera-. Ž ture, and solar intensity and the concentration of primary pollutants methane, carbon monoxide, carbon dioxide, . nitrogen oxide, nitrogen dioxide, sulfur dioxide, non-methane hydrocarbons, and dust . A backpropagation algorithm with momentum was used to prepare the neural network. A partitioning method of the connection weights of the network was used to study the relative % contribution of each of the input variables. It was found that the precursors carbon monoxide, carbon dioxide, nitrogen oxide, nitrogen dioxide, and sulfur dioxide had the most effect on the predicted ozone concentration. In addition, temperature played an important role. The performance of the neural network model was compared against linear and non-linear regression models that were prepared based on the present collected data. It was found that the neural network model consistently gives superior predictions. Based on the results of this study, artificial neural network modeling appears to be a promising technique for the prediction of pollutant concentrations. ᮊ