Ozone Modeling Using Neural Networks

Narasimhan, Ramesh; Keller, Joleen; Subramaniam, Ganesh; Raasch, Eric; Croley, Brandon; Duncan, Kathleen E.; Potter, William T.

doi:10.1175/1520-0450(2000)039<0291:omunn>2.0.co;2

Cited by 13 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The imperfection of the comparison notwithstanding, the slope of the straight line fit in the lower panel of their Figure 1 is ∼2.4 ppb K−1 (based on estimating from the graphics ozone concentrations of 16 and 79 ppb at 10 and 36 • C, respectively). Roughly similar GLO temperature dependences are reported by Bloomfield et al [(1996); from the lower-left panels of their Figure 2, we estimate ∼3.3 ppb K −1 ] or Narasimhan et al [(2000), Figure 4]. That is, reported slopes are 2-5 times steeper than those we found in IL.…”

Section: Three-dimensional Effectssupporting

confidence: 84%

Relationship Between Large-Scale Atmospheric States, Subsidence, Static Stability and Ground-Level Ozone in Illinois, USA

Eshel

Bernstein

2006

Water Air Soil Pollut

View full text Add to dashboard Cite

We analyze ground level ozone pollution in Illinois. We find that during elevated ground level ozone conditions, Illinois is located to the south-west of a high pressure system centered over south-eastern Canada. This state causes weakening of the climatological westerlies, near-surface southerlies and upper troposphere northerlies. This results in corresponding weakening of both lower troposphere heating and upper troposphere cooling by lateral advective heat flux divergence. Heat balance is restored primarily by enhanced subsidence, most notably between the surface and ∼400 mb. The strengthened subsidence suppresses boundary layer deepening by upward surface heat fluxes, resulting in a shallower than normal boundary layer during times of elevated ground level ozone. We argue that subsidence induced boundary layer suppression, aided by elevated temperatures, is the primary cause of the elevated ground level ozone events. The enhanced subsidence during those times also dries the lower troposphere, reducing the probability of moist convection, and thus slowing boundary layer ventilation.

show abstract

Section: Three-dimensional Effectssupporting

confidence: 84%

Relationship Between Large-Scale Atmospheric States, Subsidence, Static Stability and Ground-Level Ozone in Illinois, USA

Eshel

Bernstein

2006

Water Air Soil Pollut

View full text Add to dashboard Cite

show abstract

“…Neural Networks (NN) do not address the problem of access to information remarked above with the standard techniques: an ever increasing number of papers have been published on the subject (see, for example, Hsieh and Tang, 1998;Marzban and Stumpf, 1998;Shao, 1998;Hall et al, 1999;Koizumi, 1999;Narasimhan, 2000;Tang et al, 2000) and new results are readily available in the open literature. However, obtaining a better performance by a NN than with standard techniques may be not simple.…”

Section: Produced Bymentioning

confidence: 99%

Linear and nonlinear post-processing of numerically forecasted surface temperature

Casaioli

Mantovani

Scorzoni

et al. 2003

Nonlin. Processes Geophys.

View full text Add to dashboard Cite

Abstract. In this paper we test different approaches to the statistical post-processing of gridded numerical surface air temperatures (provided by the European Centre for MediumRange Weather Forecasts) onto the temperature measured at surface weather stations located in the Italian region of Puglia. We consider simple post-processing techniques, like correction for altitude, linear regression from different input parameters and Kalman filtering, as well as a neural network training procedure, stabilised (i.e. driven into the absolute minimum of the error function over the learning set) by means of a Simulated Annealing method. A comparative analysis of the results shows that the performance with neural networks is the best. It is encouraging for systematic use in meteorological forecast-analysis service operations.

show abstract

“…Once trained, the models are not limited severely by spatial or temporal inaccuracies and data gaps. Most importantly, models trained on specific data sets can be used to evaluate the dependency of specific parameters under specified conditions (Narasimhan et al 2000).…”

Section: Introductionmentioning

confidence: 99%

Prediction of daily ground-level ozone concentration maxima over New Delhi

Mahapatra

2009

Environ Monit Assess

View full text Add to dashboard Cite

The pollution levels in New Delhi from industrial, residential, and transportation sources are continuously growing. As one of the major pollutants, ground-level ozone is responsible for various adverse effects on both humans and foliage. The present study aims to predict daily ground-level ozone concentration maxima over a site situated in New Delhi through neural networks (NN) and multiple-regression (MR) analysis. Although these methodologies are case and site specific, they are being developed and used widely. Therefore, to test these methodologies for New Delhi where no such study is available for ground-level ozone, six models have been developed based on NNs and MR using the same input data set. The changes in the performance capability of the two methods are sensitive to the selection of input parameters. The results are encouraging, and remarkable improvements in the performance of the models have been observed.

show abstract

Ozone Modeling Using Neural Networks

Cited by 13 publications

References 3 publications

Relationship Between Large-Scale Atmospheric States, Subsidence, Static Stability and Ground-Level Ozone in Illinois, USA

Relationship Between Large-Scale Atmospheric States, Subsidence, Static Stability and Ground-Level Ozone in Illinois, USA

Linear and nonlinear post-processing of numerically forecasted surface temperature

Prediction of daily ground-level ozone concentration maxima over New Delhi

Contact Info

Product

Resources

About