FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK
Aim. In the present investigation artificial neural network (ANN) and ARIMA-model are compared for forecasting of data of colour of water.Methods. Data corresponds to the colour of water of groundwater and drinking water of water intake of south-east region of the Republic of Belarus. The definition...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Kamerton
2019-04-01
|
| Series: | Юг России: экология, развитие |
| Subjects: | |
| Online Access: | https://ecodag.elpub.ru/ugro/article/view/1528 |
| _version_ | 1797880580868669440 |
|---|---|
| author | D. V. Makarov E. A. Kantor N. A. Krasulina A. V. Greb Z. Z. Berezhnova |
| author_facet | D. V. Makarov E. A. Kantor N. A. Krasulina A. V. Greb Z. Z. Berezhnova |
| author_sort | D. V. Makarov |
| collection | DOAJ |
| description | Aim. In the present investigation artificial neural network (ANN) and ARIMA-model are compared for forecasting of data of colour of water.Methods. Data corresponds to the colour of water of groundwater and drinking water of water intake of south-east region of the Republic of Belarus. The definition of colour was carried out for the period from 2009 to 2017. twice a day, the time series of values included 5215 values. The parameters of the models were estimated by 85% of the time series values, and the remaining 15% of the values (the test period) compared the forecast values with the actual ones. Optimal configurations of ARIMA-models were determined from the results of comparing the averaged values of the root mean squared errors (RMSE); optimal configurations of ANN were determined from the results of comparing the averaged values of RMSE and correlation coefficients (CC) on the test periods.Results. Comparison of forecasting methods was carried out on the basis of the averaged values of mean absolute error and mean relative error on the test periods. It was revealed that ANN allows to obtain the predicted values of colour of water more accurate than ARIMA-model.Main conclusions. Software implementation of ANN in the MATLAB environment empowers with sufficient accuracy get forecast values of groundwater and drinking water for 100 values. |
| first_indexed | 2024-04-10T03:05:31Z |
| format | Article |
| id | doaj.art-39fe625714fb4e4bb6b2061c5be18e8a |
| institution | Directory Open Access Journal |
| issn | 1992-1098 2413-0958 |
| language | Russian |
| last_indexed | 2024-04-10T03:05:31Z |
| publishDate | 2019-04-01 |
| publisher | Kamerton |
| record_format | Article |
| series | Юг России: экология, развитие |
| spelling | doaj.art-39fe625714fb4e4bb6b2061c5be18e8a2023-03-13T07:36:01ZrusKamertonЮг России: экология, развитие1992-10982413-09582019-04-0114115916810.18470/1992-1098-2019-1-159-1681040FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORKD. V. Makarov0E. A. Kantor1N. A. Krasulina2A. V. Greb3Z. Z. Berezhnova4Уфимский государственный нефтяной технический университетУфимский государственный нефтяной технический университетУфимский государственный нефтяной технический университетУфимский государственный нефтяной технический университетУфимский государственный нефтяной технический университетAim. In the present investigation artificial neural network (ANN) and ARIMA-model are compared for forecasting of data of colour of water.Methods. Data corresponds to the colour of water of groundwater and drinking water of water intake of south-east region of the Republic of Belarus. The definition of colour was carried out for the period from 2009 to 2017. twice a day, the time series of values included 5215 values. The parameters of the models were estimated by 85% of the time series values, and the remaining 15% of the values (the test period) compared the forecast values with the actual ones. Optimal configurations of ARIMA-models were determined from the results of comparing the averaged values of the root mean squared errors (RMSE); optimal configurations of ANN were determined from the results of comparing the averaged values of RMSE and correlation coefficients (CC) on the test periods.Results. Comparison of forecasting methods was carried out on the basis of the averaged values of mean absolute error and mean relative error on the test periods. It was revealed that ANN allows to obtain the predicted values of colour of water more accurate than ARIMA-model.Main conclusions. Software implementation of ANN in the MATLAB environment empowers with sufficient accuracy get forecast values of groundwater and drinking water for 100 values.https://ecodag.elpub.ru/ugro/article/view/1528подземные водыпоказатели качества водыцветностьискусственные нейронные сетиarima-модель |
| spellingShingle | D. V. Makarov E. A. Kantor N. A. Krasulina A. V. Greb Z. Z. Berezhnova FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK Юг России: экология, развитие подземные воды показатели качества воды цветность искусственные нейронные сети arima-модель |
| title | FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK |
| title_full | FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK |
| title_fullStr | FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK |
| title_full_unstemmed | FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK |
| title_short | FORECASTING VALUES OF CHROMATICITY OF DRINKING AND SOURCE WATERS USING ARIMA MODEL AND NEURAL NETWORK |
| title_sort | forecasting values of chromaticity of drinking and source waters using arima model and neural network |
| topic | подземные воды показатели качества воды цветность искусственные нейронные сети arima-модель |
| url | https://ecodag.elpub.ru/ugro/article/view/1528 |
| work_keys_str_mv | AT dvmakarov forecastingvaluesofchromaticityofdrinkingandsourcewatersusingarimamodelandneuralnetwork AT eakantor forecastingvaluesofchromaticityofdrinkingandsourcewatersusingarimamodelandneuralnetwork AT nakrasulina forecastingvaluesofchromaticityofdrinkingandsourcewatersusingarimamodelandneuralnetwork AT avgreb forecastingvaluesofchromaticityofdrinkingandsourcewatersusingarimamodelandneuralnetwork AT zzberezhnova forecastingvaluesofchromaticityofdrinkingandsourcewatersusingarimamodelandneuralnetwork |