Stephen Dorling

Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences

Artificial neural networks are appearing as useful alternatives to traditional statistical modelling techniques in many scientific disciplines. This paper presents a general introduction and discussion of recent applications of the multilayer perceptron, one type of artificial neural network, in the atmospheric sciences.

Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London

Multilayer perceptron (MLP) neural networks were trained to model hourly NOx and NO2 pollutant concentrations in Central London from basic hourly meteorological data. Results have shown that the models perform well when compared to previous attempts to model the same pollutants using regression based models. This work also illustrates that MLP neural networks are capable of resolving complex patterns of source emissions without any explicit external guidance.

Cluster analysis: A technique for estimating the synoptic meteorological controls on air and precipitation chemistry: Method and applications

Abstract Combining the pattern recognition capabilities of cluster analysis with isobaric air trajectory data is a useful way of quantifying the influence of synoptic meteorology on the pollution climatology at a site. A non-hierarchial clustering of 1000 mb isobaric trajectories, using squared Euclidean distance as a similarity measure, leads to the identification of a finite number of distinct synoptic patterns. Typical airbore and aqueous pollutant concentrations associated with each of these patterns may then be established. By considering 3-day air trajectories in this study, the “history” of an air parcel is captured in an improved manner, when compared with attempts to use individual day weather “types” to characterize meterological situations.

Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki

Five neural network (NN) models, a linear statistical model and a deterministic modelling system (DET) were evaluated for the prediction of urban NO2 and PM10 concentrations. The model evaluation work considered the sequential hourly concentration time series of NO2 and PM10, which were measured at two stations in central Helsinki, from 1996 to 1999. The models utilised selected traffic flow and pre-processed meteorological variables as input data. An imputed concentration dataset was also created, in which the missing values were replaced, in order to obtain a harmonised database that is well suited for the inter-comparison of models. Three statistical criteria were adopted: the index of agreement (IA), the squared correlation coefficient (R2) and the fractional bias. The results obtained with various non-linear NN models show a good agreement with the measured concentration data for NO2; for instance, the annual mean of the IA values and their standard deviations range from 0.86±0.02 to 0.91±0.01. In the case of NO2, the non-linear NN models produce a range of model performance values that are slightly better than those by the DET. NN models generally perform better than the statistical linear model, for predicting both NO2 and PM10 concentrations. In the case of PM10, the model performance statistics of the NN models were not as good as those for NO2 over the entire range of models considered. However, the currently available NN models are neither applicable for predicting spatial concentration distributions in urban areas, nor for evaluating air pollution abatement scenarios for future years.

Statistical surface ozone models : an improved methodology to account for non-linear behaviour

Using UK data as a case study, this paper demonstrates that statistical models of hourly surface ozone concentrations require interactions and non-linear relationships between predictor variables in order to accurately capture the ozone behaviour. Comparisons between linear regression, regression tree and multilayer perceptron neural network models of hourly surface ozone concentrations quantify these effects. Although multilayer perceptron models are shown to more accurately capture the underlying relationship between both the meteorological and temporal predictor variables and hourly ozone concentrations, the regression tree models are seen to be more readily physically interpretable.

A rigorous inter-comparison of ground-level ozone predictions

Novel statistical approaches to prediction have recently been shown to perform well in several scientific fields but have not, until now, been comprehensively evaluated for predicting air pollution. In this paper we report on a model inter-comparison exercise in which 15 different statistical techniques for ozone forecasting were applied to ten data sets representing different meteorological and emission conditions throughout Europe. We also attempt to compare the performance of the statistical techniques with a deterministic chemical trajectory model. Likewise, our exercise includes comparisons of sites, performance indices, forecasting horizons, etc. The comparative evaluation of forecasting performance (benchmarking) produced 1340 yearly time series of daily predictions and the results are described in terms of predefined performance indices. Through analysing associations between the performance indices, we found that the success index is of outstanding significance. For models that are excellent in predicting threshold exceedances and have a high success index, we also observe high performance in the overall goodness of fit. The 8-h average ozone concentration forecast accuracy was found to be superior to the 1-h mean ozone concentration forecast, which makes the former very significant for operational forecasting. The best forecasts were achieved for sites located in rural and suburban areas in Central Europe unaffected by extreme emissions (e.g. from industries). Our results demonstrate that a particular technique is often excellent in some respects but poor in others. For most situations, we recommend neural network and generalised additive models as the best compromise, as these can handle nonlinear associations and can be easily adapted to site specific conditions. In contrast, nonlinear modelling of the dynamical development of univariate ozone time-series was not profitable.

Statistical models to assess the health effects and to forecast ground-level ozone

By means of statistical approaches we attempt to bridge both aspects of the ground-level ozone problem: assessment of health effects and forecasting and warning. Disagreement has been highlighted in the literature recently regarding the adverse health effects of tropospheric ozone pollution. Based on a panel study of children in Leipzig we identified a non-linear (quadratic) concentration-response relationship between ozone and respiratory symptoms. Our results indicate that using ozone as a linear covariate might be a misspecification of the model, which might explain non-uniform results of several field studies in health effects of ozone. We conclude that there is urgent demand for forecasting episodes of high ozone that may help susceptible persons to avoid high exposure. Novel approaches to statistical modelling and data mining are helpful tools in operational smog forecasting. We present a rigorous assessment of the performance of 15 different statistical techniques in an inter-comparison study based on data sets from 10 European regions. To evaluate the results of the inter-comparison exercise we suggest an integrated assessment procedure, which takes the unbalanced study design into consideration. This procedure is based on estimating a statistical model for the performance indices depending on predefined factors, such as site, forecasting technique, forecasting horizon, etc. We find that the best predictions can be achieved for sites located in rural and suburban areas in Central Europe. For application in operational air pollution forecasting we may recommend neural network and generalised additive models, which can handle non-linear associations between atmospheric variables. As an example we demonstrate the application of a Generalised Additive Model (GAM). GAMs are based on smoothing splines for the covariates, i.e., meteorological parameters and concentrations of other pollutants. Finally, it transpired that respiratory symptoms are associated with the daily maximum of the 8-h average ozone concentration, which in turn is best predicted by means of non-linear statistical models. The new air quality directive of the European Commission (Directive 2002/3/EC) accounts for the special relevance of the 8h mean ozone concentration.

Modelling SO2 concentration at a point with statistical approaches

In this paper, the results obtained by inter-comparing several statistical techniques for modelling SO2 concentration at a point such as neural networks, fuzzy logic, generalised additive techniques and other recently proposed statistical approaches are reported. The results of the inter-comparison are the fruits of collaboration between some of the partners of the APPETISE project funded under the Framework V Information Societies and Technologies (IST) programme. Two different cases for study were selected: the Siracusa industrial area, in Italy, where the pollution is dominated by industrial emissions and the Belfast urban area, in the UK, where domestic heating makes an important contribution. The different kinds of pollution (industrial/urban) and different locations of the areas considered make the results more general and interesting. In order to make the inter-comparison more objective, all the modellers considered the same datasets. Missing data in the original time series was filled by using appropriate techniques. The inter-comparison work was carried out on a rigorous basis according to the performance indices recommended by the European Topic Centre on Air and Climate Change (ETC/ACC). The targets for the implemented prediction models were defined according to the EC normative relating to limit values for sulphur dioxide. According to this normative, three different kinds of targets were considered namely daily mean values, daily maximum values and hourly mean values. The inter-compared models were tested on real cases of poor air quality. In the paper, the inter-compared techniques are ranked in terms of their capability to predict critical episodes. A ranking in terms of their predictability of the three different targets considered is also proposed. Several key issues are illustrated and discussed such as the role of input variable selection, the use of meteorological data, and the use of interpolated time series. Moreover, a novel approach referred to as the technique of balancing the training pattern set, which was successfully applied to improve the capability of ANN models to predict exceedences is introduced. The results show that there is no single modelling approach, which generates optimum results in terms of the full range of performance indices considered. In view of the implementation of a warning system for air quality control, approaches that are able to work better in the prediction of critical episodes must be preferred. Therefore, the artificial neural network prediction models can be recommended for this purpose. The best forecasts were achieved for daily averages of SO2 while daily maximum and hourly mean values are difficult to predict with acceptable accuracy.

Visibility trends in the UK 1950-1997

Visibility data have been examined for eight UK Meteorological Office surface network sites. Trends from 1950 to 1997 have been constructed using four different statistical methods; ridit analysis, cumulative percentiles, frequency of “very good” visibility and annual and seasonal means. Improvements in visibility have been experienced at the majority of the sites studied. Major improvements can be observed at many of the sites after 1973 and this is attributed to changes in personal behaviour, fuel use and vehicle fleet efficiency during the 1970s and especially after the 1973 oil crisis. Improvements in visibility at the Scottish sites studied are much less than at the other sites due to their locations in less populated and less polluted areas. Aldergrove, near Belfast in Northern Ireland, has also experienced less improvement in the visibility distance than the other sites.

Meteorologically adjusted trends in UK daily maximum surface ozone concentrations

A methodology to meteorologically adjust daily UK surface ozone data is presented which reveals the impact of longer-term variations in precursor emissions more clearly. Based on this approach a general site-dependant decline in meteorologically adjusted summer daily maximum ozone concentrations has occurred between 1994 and 1998 and is between 0.7 and 2.3 ppb yr−1.