Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China
Modeling of hydrological time series is essential for sustainable development and management of lake water resources. This study aims to develop an efficient model for forecasting lake water level variations, exemplified by the Poyang Lake (China) case study. A random forests (RF) model was first ap...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2016-12-01
|
| Series: | Hydrology Research |
| Subjects: | |
| Online Access: | http://hr.iwaponline.com/content/47/S1/69 |
| _version_ | 1817997597681385472 |
|---|---|
| author | Bing Li Guishan Yang Rongrong Wan Xue Dai Yanhui Zhang |
| author_facet | Bing Li Guishan Yang Rongrong Wan Xue Dai Yanhui Zhang |
| author_sort | Bing Li |
| collection | DOAJ |
| description | Modeling of hydrological time series is essential for sustainable development and management of lake water resources. This study aims to develop an efficient model for forecasting lake water level variations, exemplified by the Poyang Lake (China) case study. A random forests (RF) model was first applied and compared with artificial neural networks, support vector regression, and a linear model. Three scenarios were adopted to investigate the effect of time lag and previous water levels as model inputs for real-time forecasting. Variable importance was then analyzed to evaluate the influence of each predictor for water level variations. Results indicated that the RF model exhibits the best performance for daily forecasting in terms of root mean square error (RMSE) and coefficient of determination (R2). Moreover, the highest accuracy was achieved using discharge series at 4-day-ahead and the average water level over the previous week as model inputs, with an average RMSE of 0.25 m for five stations within the lake. In addition, the previous water level was the most efficient predictor for water level forecasting, followed by discharge from the Yangtze River. Based on the performance of the soft computing methods, RF can be calibrated to provide information or simulation scenarios for water management and decision-making. |
| first_indexed | 2024-04-14T02:40:47Z |
| format | Article |
| id | doaj.art-fc929db4533c4d12b214b91053cf0f48 |
| institution | Directory Open Access Journal |
| issn | 1998-9563 2224-7955 |
| language | English |
| last_indexed | 2024-04-14T02:40:47Z |
| publishDate | 2016-12-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Hydrology Research |
| spelling | doaj.art-fc929db4533c4d12b214b91053cf0f482022-12-22T02:17:09ZengIWA PublishingHydrology Research1998-95632224-79552016-12-0147S1698310.2166/nh.2016.264264Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in ChinaBing Li0Guishan Yang1Rongrong Wan2Xue Dai3Yanhui Zhang4 Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China E-mail: gsyang@niglas.ac.cn Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China E-mail: gsyang@niglas.ac.cn Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China E-mail: gsyang@niglas.ac.cn Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China E-mail: gsyang@niglas.ac.cn Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, China E-mail: gsyang@niglas.ac.cn Modeling of hydrological time series is essential for sustainable development and management of lake water resources. This study aims to develop an efficient model for forecasting lake water level variations, exemplified by the Poyang Lake (China) case study. A random forests (RF) model was first applied and compared with artificial neural networks, support vector regression, and a linear model. Three scenarios were adopted to investigate the effect of time lag and previous water levels as model inputs for real-time forecasting. Variable importance was then analyzed to evaluate the influence of each predictor for water level variations. Results indicated that the RF model exhibits the best performance for daily forecasting in terms of root mean square error (RMSE) and coefficient of determination (R2). Moreover, the highest accuracy was achieved using discharge series at 4-day-ahead and the average water level over the previous week as model inputs, with an average RMSE of 0.25 m for five stations within the lake. In addition, the previous water level was the most efficient predictor for water level forecasting, followed by discharge from the Yangtze River. Based on the performance of the soft computing methods, RF can be calibrated to provide information or simulation scenarios for water management and decision-making.http://hr.iwaponline.com/content/47/S1/69artificial neural networkslake water levelpoyang lakerandom forestssupport vector regressionvariable importance analysis |
| spellingShingle | Bing Li Guishan Yang Rongrong Wan Xue Dai Yanhui Zhang Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China Hydrology Research artificial neural networks lake water level poyang lake random forests support vector regression variable importance analysis |
| title | Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China |
| title_full | Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China |
| title_fullStr | Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China |
| title_full_unstemmed | Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China |
| title_short | Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China |
| title_sort | comparison of random forests and other statistical methods for the prediction of lake water level a case study of the poyang lake in china |
| topic | artificial neural networks lake water level poyang lake random forests support vector regression variable importance analysis |
| url | http://hr.iwaponline.com/content/47/S1/69 |
| work_keys_str_mv | AT bingli comparisonofrandomforestsandotherstatisticalmethodsforthepredictionoflakewaterlevelacasestudyofthepoyanglakeinchina AT guishanyang comparisonofrandomforestsandotherstatisticalmethodsforthepredictionoflakewaterlevelacasestudyofthepoyanglakeinchina AT rongrongwan comparisonofrandomforestsandotherstatisticalmethodsforthepredictionoflakewaterlevelacasestudyofthepoyanglakeinchina AT xuedai comparisonofrandomforestsandotherstatisticalmethodsforthepredictionoflakewaterlevelacasestudyofthepoyanglakeinchina AT yanhuizhang comparisonofrandomforestsandotherstatisticalmethodsforthepredictionoflakewaterlevelacasestudyofthepoyanglakeinchina |