Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia
Само за регистроване кориснике
2021
Аутори
Malinović-Milićević, SlavicaVyklyuk, Yaroslav
Stanojević, Gorica
Radovanović, Milan M.
Doljak, Dejan
Ćurčić, Nina B.
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
In this paper, we described generation and performances of feedforward neural network model that could be used for a day ahead predictions of the daily maximum 1-h ozone concentration (1hO3) and 8-h average ozone concentration (8hO3) at one traffic and one background station in the urban area of Novi Sad,
Serbia. The six meteorological variables for the day preceding the forecast and forecast day, ozone concentrations in the day preceding the forecast, the number of the day of the year, and the number of the weekday for which ozone prediction was performed were utilized as inputs. The three-layer perceptron neural network models with the best performance were chosen by testing with different numbers of neurons in the hidden layer and different activation functions. The mean bias error, mean absolute error, root mean squared error, correlation coefficient, and index of agreement or Willmott’s Index for the validation data for 1hO3 forecasting were 0.005 μg m−3, 12.149 μg m−3, 15.926 μg... m−3, 0.988, and 0.950, respectively, for the traffic station (Dnevnik), and − 0.565 μg m−3, 10.101 μg m−3, 12.962 μg m−3, 0.911, and 0.953, respectively, for the background station (Liman). For 8hO3 forecasting, statistical indicators were − 1.126 μg m−3, 10.614 μg m−3, 12.962 μg m−3, 0.910, and 0.948 respectively for the
station Dnevnik and − 0.001 μg m−3, 8.574 μg m−3, 10.741 μg m−3, 0.936, and 0.966, respectively, for the station Liman. According to the Kolmogorov–Smirnov test, there is no significant difference between measured and predicted data. Models showed a good performance in forecasting days with the high values over a certain threshold.
Кључне речи:
Air pollution / Tropospheric ozone / Neural networks / Novi Sad (Serbia)Извор:
Environmental Monitoring and Assessment, 2021, 193, 84Издавач:
- Switzerland : Springer Nature.
Институција/група
Географски институт „Јован Цвијић“ САНУ / Geographical Institute Jovan Cvijić SASATY - JOUR AU - Malinović-Milićević, Slavica AU - Vyklyuk, Yaroslav AU - Stanojević, Gorica AU - Radovanović, Milan M. AU - Doljak, Dejan AU - Ćurčić, Nina B. PY - 2021 UR - https://dais.sanu.ac.rs/123456789/13304 AB - In this paper, we described generation and performances of feedforward neural network model that could be used for a day ahead predictions of the daily maximum 1-h ozone concentration (1hO3) and 8-h average ozone concentration (8hO3) at one traffic and one background station in the urban area of Novi Sad, Serbia. The six meteorological variables for the day preceding the forecast and forecast day, ozone concentrations in the day preceding the forecast, the number of the day of the year, and the number of the weekday for which ozone prediction was performed were utilized as inputs. The three-layer perceptron neural network models with the best performance were chosen by testing with different numbers of neurons in the hidden layer and different activation functions. The mean bias error, mean absolute error, root mean squared error, correlation coefficient, and index of agreement or Willmott’s Index for the validation data for 1hO3 forecasting were 0.005 μg m−3, 12.149 μg m−3, 15.926 μg m−3, 0.988, and 0.950, respectively, for the traffic station (Dnevnik), and − 0.565 μg m−3, 10.101 μg m−3, 12.962 μg m−3, 0.911, and 0.953, respectively, for the background station (Liman). For 8hO3 forecasting, statistical indicators were − 1.126 μg m−3, 10.614 μg m−3, 12.962 μg m−3, 0.910, and 0.948 respectively for the station Dnevnik and − 0.001 μg m−3, 8.574 μg m−3, 10.741 μg m−3, 0.936, and 0.966, respectively, for the station Liman. According to the Kolmogorov–Smirnov test, there is no significant difference between measured and predicted data. Models showed a good performance in forecasting days with the high values over a certain threshold. PB - Switzerland : Springer Nature. T2 - Environmental Monitoring and Assessment T1 - Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia VL - 193 IS - 84 DO - 10.1007/s10661-020-08821-1 UR - https://hdl.handle.net/21.15107/rcub_dais_13304 ER -
@article{ author = "Malinović-Milićević, Slavica and Vyklyuk, Yaroslav and Stanojević, Gorica and Radovanović, Milan M. and Doljak, Dejan and Ćurčić, Nina B.", year = "2021", abstract = "In this paper, we described generation and performances of feedforward neural network model that could be used for a day ahead predictions of the daily maximum 1-h ozone concentration (1hO3) and 8-h average ozone concentration (8hO3) at one traffic and one background station in the urban area of Novi Sad, Serbia. The six meteorological variables for the day preceding the forecast and forecast day, ozone concentrations in the day preceding the forecast, the number of the day of the year, and the number of the weekday for which ozone prediction was performed were utilized as inputs. The three-layer perceptron neural network models with the best performance were chosen by testing with different numbers of neurons in the hidden layer and different activation functions. The mean bias error, mean absolute error, root mean squared error, correlation coefficient, and index of agreement or Willmott’s Index for the validation data for 1hO3 forecasting were 0.005 μg m−3, 12.149 μg m−3, 15.926 μg m−3, 0.988, and 0.950, respectively, for the traffic station (Dnevnik), and − 0.565 μg m−3, 10.101 μg m−3, 12.962 μg m−3, 0.911, and 0.953, respectively, for the background station (Liman). For 8hO3 forecasting, statistical indicators were − 1.126 μg m−3, 10.614 μg m−3, 12.962 μg m−3, 0.910, and 0.948 respectively for the station Dnevnik and − 0.001 μg m−3, 8.574 μg m−3, 10.741 μg m−3, 0.936, and 0.966, respectively, for the station Liman. According to the Kolmogorov–Smirnov test, there is no significant difference between measured and predicted data. Models showed a good performance in forecasting days with the high values over a certain threshold.", publisher = "Switzerland : Springer Nature.", journal = "Environmental Monitoring and Assessment", title = "Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia", volume = "193", number = "84", doi = "10.1007/s10661-020-08821-1", url = "https://hdl.handle.net/21.15107/rcub_dais_13304" }
Malinović-Milićević, S., Vyklyuk, Y., Stanojević, G., Radovanović, M. M., Doljak, D.,& Ćurčić, N. B.. (2021). Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia. in Environmental Monitoring and Assessment Switzerland : Springer Nature.., 193(84). https://doi.org/10.1007/s10661-020-08821-1 https://hdl.handle.net/21.15107/rcub_dais_13304
Malinović-Milićević S, Vyklyuk Y, Stanojević G, Radovanović MM, Doljak D, Ćurčić NB. Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia. in Environmental Monitoring and Assessment. 2021;193(84). doi:10.1007/s10661-020-08821-1 https://hdl.handle.net/21.15107/rcub_dais_13304 .
Malinović-Milićević, Slavica, Vyklyuk, Yaroslav, Stanojević, Gorica, Radovanović, Milan M., Doljak, Dejan, Ćurčić, Nina B., "Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia" in Environmental Monitoring and Assessment, 193, no. 84 (2021), https://doi.org/10.1007/s10661-020-08821-1 ., https://hdl.handle.net/21.15107/rcub_dais_13304 .