Water temperature prediction in a subtropical subalpine lake using soft computing techniques
Lake water temperature is one of the key parameters in determining the ecological conditions within a lake, as it influences both chemical and biological processes. Therefore, accurate prediction of water temperature is crucially important for lake management. In this paper, the performance of soft...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad Nacional de Colombia
2016-04-01
|
| Series: | Earth Sciences Research Journal |
| Subjects: | |
| Online Access: | https://revistas.unal.edu.co/index.php/esrj/article/view/43199 |
| _version_ | 1818491365629100032 |
|---|---|
| author | Saeed Samadianfard Honeyeh Kazemi Ozgur Kisi Wen-Cheng Liu |
| author_facet | Saeed Samadianfard Honeyeh Kazemi Ozgur Kisi Wen-Cheng Liu |
| author_sort | Saeed Samadianfard |
| collection | DOAJ |
| description | Lake water temperature is one of the key parameters in determining the ecological conditions within a lake, as it influences both chemical and biological processes. Therefore, accurate prediction of water temperature is crucially important for lake management. In this paper, the performance of soft computing techniques including gene expression programming (GEP), which is a variant of genetic programming (GP), adaptive neuro fuzzy inference system (ANFIS) and artificial neural networks (ANNs) to predict hourly water temperature at a buoy station in the Yuan-Yang Lake (YYL) in north-central Taiwan at various measured depths was evaluated. To evaluate the performance of the soft computing techniques, three different statistical indicators were used, including the root mean squared error (RMSE), the mean absolute error (MAE), and the coefficient of correlation (R). Results showed that the GEP had the best performances among other studied methods in the prediction of hourly water temperature at 0, 2 and 3 meter depths below water surface, but there was a different trend in the 1 meter depth below water surface. In this depth, the ANN had better accuracy than the GEP and ANFIS. Despite the error (RMSE value) is smaller in ANN than GEP, there is an upper bound in scatter plot of ANN that imposes a constant value, which is not suitable for predictive purposes. As a conclusion, results from the current study demonstrated that GEP provided moderately reasonable trends for the prediction of hourly water temperature in different depths.
Resumen
La temperatura del agua es uno de los parámetros básicos para determinar las condiciones ecológicas de un lago, ya que está influenciada por procesos químicos y biológicos. Además, la exactitud en la predicción de la temperatura del agua es esencial para el manejo del lago. En este artículo se evalúa el desempeño de técnicas de soft computing como la Programación de Expresiones de Genes (PEG), que es una variante de la Programación Genética (PG), el Sistema Neuro-fuzzy de Inferencia Adaptativa (Anfis, en inglés) y las Redes Neuronales Artificiales (RNA) para predecir la temperatura del agua en diferentes niveles de una estación flotante del lago Yuan-Yang (YYL), en el centro-norte de Taiwán. Se utilizaron tres indicadores estadísticos, el Error Cuadrático Medio (ECM), el Error Absoluto Medio (MAE, en inglés) y el Coeficiente de Correlación (R) para evaluar el desempeño de las técnicas de computación. Los resultados muestran que la PEG es más exacta en la predicción de la temperatura del agua entre 0,2 y 3 metros de profundidad. Sin embargo, se evidencia una tendencia diferente a partir del metro de profundidad. A esta distancia de la superficie, las RNA son más exactas que la PEG y el Anfis. Los resultados de este estudio probaron claramente la usabilidad del PEG y las RNA en la predicción de la temperatura del agua a diferentes profundidades. |
| first_indexed | 2024-12-10T17:29:52Z |
| format | Article |
| id | doaj.art-81ba8d95e45b4baba6083b292adc04d5 |
| institution | Directory Open Access Journal |
| issn | 1794-6190 2339-3459 |
| language | English |
| last_indexed | 2024-12-10T17:29:52Z |
| publishDate | 2016-04-01 |
| publisher | Universidad Nacional de Colombia |
| record_format | Article |
| series | Earth Sciences Research Journal |
| spelling | doaj.art-81ba8d95e45b4baba6083b292adc04d52022-12-22T01:39:44ZengUniversidad Nacional de ColombiaEarth Sciences Research Journal1794-61902339-34592016-04-0120210.15446/esrj.v20n2.4319943753Water temperature prediction in a subtropical subalpine lake using soft computing techniquesSaeed Samadianfard0Honeyeh Kazemi1Ozgur Kisi2Wen-Cheng Liu3Department of Water Engineering, University of TabrizDepartment of Water Engineering, University of TabrizDepartment of Civil Engineering, Canik Basari UniversityDepartment of Civil and Disaster Prevention Engineering, National United UniversityLake water temperature is one of the key parameters in determining the ecological conditions within a lake, as it influences both chemical and biological processes. Therefore, accurate prediction of water temperature is crucially important for lake management. In this paper, the performance of soft computing techniques including gene expression programming (GEP), which is a variant of genetic programming (GP), adaptive neuro fuzzy inference system (ANFIS) and artificial neural networks (ANNs) to predict hourly water temperature at a buoy station in the Yuan-Yang Lake (YYL) in north-central Taiwan at various measured depths was evaluated. To evaluate the performance of the soft computing techniques, three different statistical indicators were used, including the root mean squared error (RMSE), the mean absolute error (MAE), and the coefficient of correlation (R). Results showed that the GEP had the best performances among other studied methods in the prediction of hourly water temperature at 0, 2 and 3 meter depths below water surface, but there was a different trend in the 1 meter depth below water surface. In this depth, the ANN had better accuracy than the GEP and ANFIS. Despite the error (RMSE value) is smaller in ANN than GEP, there is an upper bound in scatter plot of ANN that imposes a constant value, which is not suitable for predictive purposes. As a conclusion, results from the current study demonstrated that GEP provided moderately reasonable trends for the prediction of hourly water temperature in different depths. Resumen La temperatura del agua es uno de los parámetros básicos para determinar las condiciones ecológicas de un lago, ya que está influenciada por procesos químicos y biológicos. Además, la exactitud en la predicción de la temperatura del agua es esencial para el manejo del lago. En este artículo se evalúa el desempeño de técnicas de soft computing como la Programación de Expresiones de Genes (PEG), que es una variante de la Programación Genética (PG), el Sistema Neuro-fuzzy de Inferencia Adaptativa (Anfis, en inglés) y las Redes Neuronales Artificiales (RNA) para predecir la temperatura del agua en diferentes niveles de una estación flotante del lago Yuan-Yang (YYL), en el centro-norte de Taiwán. Se utilizaron tres indicadores estadísticos, el Error Cuadrático Medio (ECM), el Error Absoluto Medio (MAE, en inglés) y el Coeficiente de Correlación (R) para evaluar el desempeño de las técnicas de computación. Los resultados muestran que la PEG es más exacta en la predicción de la temperatura del agua entre 0,2 y 3 metros de profundidad. Sin embargo, se evidencia una tendencia diferente a partir del metro de profundidad. A esta distancia de la superficie, las RNA son más exactas que la PEG y el Anfis. Los resultados de este estudio probaron claramente la usabilidad del PEG y las RNA en la predicción de la temperatura del agua a diferentes profundidades.https://revistas.unal.edu.co/index.php/esrj/article/view/43199Soft computing techniquesstatistical indicatorssubalpine lakewater temperatureTécnicas soft computingindicadores estadísticoslago subalpinotemperatura del agua. |
| spellingShingle | Saeed Samadianfard Honeyeh Kazemi Ozgur Kisi Wen-Cheng Liu Water temperature prediction in a subtropical subalpine lake using soft computing techniques Earth Sciences Research Journal Soft computing techniques statistical indicators subalpine lake water temperature Técnicas soft computing indicadores estadísticos lago subalpino temperatura del agua. |
| title | Water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| title_full | Water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| title_fullStr | Water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| title_full_unstemmed | Water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| title_short | Water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| title_sort | water temperature prediction in a subtropical subalpine lake using soft computing techniques |
| topic | Soft computing techniques statistical indicators subalpine lake water temperature Técnicas soft computing indicadores estadísticos lago subalpino temperatura del agua. |
| url | https://revistas.unal.edu.co/index.php/esrj/article/view/43199 |
| work_keys_str_mv | AT saeedsamadianfard watertemperaturepredictioninasubtropicalsubalpinelakeusingsoftcomputingtechniques AT honeyehkazemi watertemperaturepredictioninasubtropicalsubalpinelakeusingsoftcomputingtechniques AT ozgurkisi watertemperaturepredictioninasubtropicalsubalpinelakeusingsoftcomputingtechniques AT wenchengliu watertemperaturepredictioninasubtropicalsubalpinelakeusingsoftcomputingtechniques |