# Comparative Evaluation of ANN- and SVM-Time Series Models for Predicting Freshwater-Saltwater Interface Fluctuations

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. FSL Monitoring

#### 2.1. Study Area

^{2}, where the mean annual air temperature is 16.2 °C and total annual precipitation is 1710 mm.

#### 2.2. Monitoring Device and Data

## 3. FSL Prediction Model Development

#### 3.1. Aritificial Neural Network (ANN)

#### 3.2. Suport Vector Machine (SVM)

#### 3.3. Time Series Modeling Strategy

## 4. Results and Discussion

#### 4.1. Direct Prediction of FSL

#### 4.2. Recursive Prediction of FSL

## 5. Summary and Conclusions

## Acknowledgments

## Author Contributions

## Conflicts of Interest

## References

- Kim, K.; Seong, H.; Kim, T.; Park, K.; Woo, N.; Park, Y.; Koh, G.; Park, W. Tidal effects on variations of fresh-saltwater interface and groundwater flow in a multilayered coastal aquifer on a volcanic island (Jeju Island, Korea). J. Hydrol.
**2006**, 330, 525–542. [Google Scholar] [CrossRef] - Liu, C.K.; Dai, J.J. Seawater intrusion and sustainable yield of basal aquifers. J. Am. Water Resour. Assoc.
**2012**, 48, 861–870. [Google Scholar] [CrossRef] - Kim, Y.; Yoon, H.; Kim, K.P. Development of a novel method to monitor the temporal change in the location of the freshwater-saltwater interface and time series models for the prediction of the interface. Environ. Earth Sci.
**2016**, 75, 882–891. [Google Scholar] [CrossRef] - Gingerich, S.B.; Voss, C.I. Thee-dimensional variable-density flow simulation of a coastal aquifer in southern Oahu, Hawaii, USA. Hydrogeol. J.
**2005**, 13, 436–450. [Google Scholar] [CrossRef] - Wener, A.D.; Gallagher, M.R. Characterization of sea-water intrusion in the Pioneer Valley, Australia using hydrochemistry and three-dimensional numerical modelling. Hydrogeol. J.
**2006**, 14, 1452–1469. [Google Scholar] [CrossRef] - Guo, W.; Langevin, C.D. User’s Guide to SEWAT: A Computer Program for Simulation of Three-Dimensional Variable-Density Ground-Water Flow; United States Geological Survey: Tallahassee, FL, USA, 2002; p. 73.
- Rozell, D.J.; Wong, T. Effects of climate change on groundwater resources at Shelter Island, New York State, USA. Hydrogeol. J.
**2010**, 18, 1657–1665. [Google Scholar] [CrossRef] - Yechieli, Y.; Shalev, E.; Wollman, S.; Kiro, Y.; Kafri, U. Response of the Mediterranean and Dead Sea coastal aquifers to sea level variations. Water Resour. Res.
**2010**, 46, W12550. [Google Scholar] [CrossRef] - Bardossy, A. Calibration of hydrological model parameters for ungauged catchments. Hydrol. Earth Syst. Sci.
**2007**, 11, 703–710. [Google Scholar] [CrossRef] - Pollacco, J.A.P.; Ugalde, J.M.S.; Angulo-Jaramillo, R.; Braud, I.; Saugier, B. A linking test to reduce the number of hydraulic parameters necessary to simulate groundwater recharge in unsaturated zone. Adv. Water Resour.
**2008**, 31, 355–369. [Google Scholar] [CrossRef] - Zealand, C.M.; Burn, D.H.; Simonovic, S.P. Short-term streamflow forecasting using artificial neural networks. J. Hydrol.
**1999**, 214, 32–48. [Google Scholar] [CrossRef] - Akhtar, M.K.; Corzo, G.A.; van Andel, S.J.; Jonoski, A. River flow forecasting with artificial neural networks using satellite observed precipitation pre-processed with flow length and travel time information: Case study of the Ganges river basin. Hydrol. Earth Syst. Sci.
**2009**, 13, 1607–1618. [Google Scholar] [CrossRef] - Hu, T.S.; Lam, K.C.; Ng, S.T. A modified neural network for improving river flow prediction. Hydrol. Sci. J.
**2005**, 50, 299–318. [Google Scholar] [CrossRef] - Coulibaly, P.; Anctil, F.; Aravena, R.; Bobee, B. Artificial neural network modeling of water table depth fluctuations. Water Resour. Res.
**2001**, 37, 885–896. [Google Scholar] [CrossRef] - Coppola, E.; Rana, A.J.; Poulton, M.M.; Szidarovszky, F.; Uhl, V.V. A neural network model for predicting aquifer water level elevations. Groundwater
**2005**, 43, 231–241. [Google Scholar] [CrossRef] [PubMed] - Mohanty, S.; Jha, M.K.; Kumar, A.; Sudheer, K.P. Artificial neural network modeling for groundwater level forecasting in a river island of eastern India. Water Resour. Manag.
**2010**, 24, 1845–1865. [Google Scholar] [CrossRef] - Liong, S.Y.; Sivapragasam, C. Flood stage forecasting with support vector machines. J. Am. Water Resour. Assoc.
**2002**, 38, 173–186. [Google Scholar] [CrossRef] - Yu, P.S.; Chen, S.T.; Chang, I.F. Support vector regression for real-time flood stage forecasting. J. Hydrol.
**2006**, 328, 704–716. [Google Scholar] [CrossRef] - Asefa, T.; Kemblowski, M.W.; Urroz, G.; McKee, M.; Khalil, A. Support vectors-based groundwater head observation networks design. Water Resour. Res.
**2004**, 40, W1150901. [Google Scholar] [CrossRef] - Gill, M.K.; Asefa, T.; Kaheil, Y.; McKee, M. Effect of missing data on performance of learning algorithms for hydrologic prediction: Implication to an imputation technique. Water Resour. Res.
**2007**, 43, W07416. [Google Scholar] [CrossRef] - Yoon, H.; Hyun, Y.; Ha, K.; Lee, K.K.; Kim, G.B. A method to improve the stability and accuracy of ANN- and SVM-based time series models for long-term groundwater level predictions. Comput. Geosci.
**2016**, 90, 144–155. [Google Scholar] [CrossRef] - Krishna, B.; Satyaji Rao, Y.R.; Vijaya, T. Modelling groundwater levels in an urban coastal aquifer using artificial neural networks. Hydrol. Process.
**2008**, 22, 1180–1188. [Google Scholar] [CrossRef] - Nayak, P.C.; Satyaji Rao, Y.R.; Sudheer, K.P. Groundwater level forecasting in a shallow aquifer using artificial neural network approach. Water Resour. Manag.
**2006**, 20, 77–90. [Google Scholar] [CrossRef] - Yoon, H.; Jun, S.-C.; Hyun, Y.; Bae, G.-O.; Lee, K.-K. A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J. Hydrol.
**2011**, 396, 128–138. [Google Scholar] [CrossRef] - Yang, X.; Zhang, H.; Zhou, H. A hybrid methodology for salinity time series forecasting based on wavelet transform and NARX neural networks. Arab. J. Sci. Eng.
**2014**, 39, 6895–6905. [Google Scholar] [CrossRef] - Wan, Y.; Wan, C.; Hedgepeth, M. Elucidating multidecadal saltwater intrusion vegetation dynamics in a coastal floodplain with artificial neural networks and aerial photography. Ecohydology
**2015**, 8, 309–324. [Google Scholar] [CrossRef] - ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. Artificial neural networks in hydrology I: Preliminary concepts. J. Hydrol. Eng.
**2000**, 5, 115–123. [Google Scholar] - Maier, H.R.; Dandy, G.C. Neural networks for the prediction and forecasting of water resources variables: A review of modeling issues and applications. Environ. Model. Softw.
**2000**, 15, 101–124. [Google Scholar] [CrossRef] - Rumelhart, D.E.; McClelland, J.L. The PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructure of Cognition; MIT Press: Cambridge, MA, USA, 1986. [Google Scholar]
- Vapnik, V.N. The Nature of Statistical Learning Theory; Springer: New York, NY, USA, 1995. [Google Scholar]
- Platt, J.C. Fast training of support vector machines using sequential minimal optimization. In Advances in Kernel Methods-Support Vector Learning, 2nd ed.; Schölkopf, B., Burges, C., Smola, A., Eds.; MIT Press: Cambridge, MA, USA, 1998. [Google Scholar]
- Scholkopf, B.; Smola, A.J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond; MIT Press: Cambridge, MA, USA, 2002. [Google Scholar]
- Ji, Y.; Hao, J.; Reyhani, N.; Lendasse, A. Direct and recursive prediction of time series using mutual information selection. In Proceedings of the International Work-Conference on Artificial Neural Networks, Barcelona, Spain, 8–10 June 2005; Volume 3512, pp. 1010–1017. [Google Scholar]
- Herrera, L.J.; Pomares, H.; Rojas, I.; Guillen, A.; Prieto, A.; Valenzuela, O. Recursive prediction for long term time series forecasting using advanced models. Neurocomputing
**2007**, 70, 2870–2880. [Google Scholar] [CrossRef]

**Figure 3.**Schematic diagram of the freshwater-saltwater interface level (FSL) monitoring system using the interface egg (modified from Kim et al. [3]).

**Figure 4.**Time series data of groundwater level (GWL), upper and lower FSL, rainfall and tide level at the HD2 observatory.

**Figure 5.**Schematic diagrams of the (

**a**) artificial neural network (ANN) and (

**b**) support vector machine (SVM) structure.

**Figure 10.**Comparison of RP-DP ratio values for ANN and SVM models: (

**a**) T-R-F type model for upper FSL; (

**b**) T-R-G-F type model for upper FSL; (

**c**) T-R-F model for lower FSL; (

**d**) T-R-G-F type model for lower FSL.

**Table 1.**Results of cross correlation analysis for measured time series data at the HD2 observatory.

Variables | Max. Correlation Coefficient | Lag Time (Hour) |
---|---|---|

T-G | 0.85 | 2 |

R-G | 0.14 | 43 |

T-F (upper) | 0.83 | 2 |

R-F (upper) | 0.11 | 47 |

G-F (upper) | 0.97 | 0 |

T-F (Lower) | 0.56 | 6 |

R-F (Lower) | 0.27 | 19 |

G-F (Lower) | 0.54 | 4 |

**T**: tide;

**R**: rainfall;

**G**: groundwater level;

**F**: interface level.

Input Structures (Model Type) | Number of Components for Variables | |||||
---|---|---|---|---|---|---|

T | R | G | F | Total | ||

Upper FSL | T-R | 4 | 4 | – | – | 8 |

T-R-F | 4 | 4 | – | 4 | 12 | |

T-R-G | 4 | 4 | 3 | – | 15 | |

T-R-G-F | 4 | 4 | 3 | 4 | 19 | |

Lower FSL | T-R | 8 | 4 | – | – | 12 |

T-R-F | 8 | 4 | – | 4 | 16 | |

T-R-G | 8 | 4 | 5 | – | 17 | |

T-R-G-F | 8 | 4 | 5 | 4 | 21 |

**T**: tide;

**R**: rainfall;

**G**: groundwater level;

**F**: interface level.

Data Type | Data Allocation | ||
---|---|---|---|

Model Building | Model Validation | ||

Upper FSL | Num. data | 250 | 247 |

Time | 7:00 15 September–12:00 21 September | 13:00 21 September–23:00 5 October | |

Lower FSL | Num. data | 300 | 197 |

Time | 7:00 15 September–17:00 27 September | 18:00 27 September–23:00 5 October |

Model Type | ANN | SVM | |||||
---|---|---|---|---|---|---|---|

HN | LR | MM | C | Eps | Sig | ||

Upper FSL | T-R | 2 | 0.001 | 0.0 | 7.0 | 0.13 | 3.0 |

T-R-F | 15 | 0.020 | 0.0 | 5.0 | 0.05 | 2.5 | |

T-R-G | 2 | 0.005 | 0.3 | 7.0 | 0.10 | 3.0 | |

T-R-G-F | 5 | 0.005 | 0.0 | 10.0 | 0.05 | 3.0 | |

Lower FSL | T-R | 15 | 0.001 | 0.9 | 3.0 | 0.11 | 2.0 |

T-R-F | 15 | 0.001 | 0.3 | 5.0 | 0.13 | 3.0 | |

T-R-G | 20 | 0.001 | 0.9 | 0.5 | 0.13 | 2.5 | |

T-R-G-F | 10 | 0.001 | 0.0 | 5.0 | 0.13 | 3.0 |

Model | Index | T-R | T-R-F | T-R-G | T-R-G-F | Average |
---|---|---|---|---|---|---|

ANN | RMSE (m) | 0.061 | 0.034 | 0.042 | 0.032 | 0.042 |

MARE (%) | 10.329 | 5.901 | 7.083 | 5.613 | 7.232 | |

CORR | 0.888 | 0.965 | 0.935 | 0.964 | 0.938 | |

SVM | RMSE (m) | 0.072 | 0.029 | 0.038 | 0.023 | 0.040 |

MARE (%) | 12.335 | 4.959 | 6.221 | 3.944 | 6.865 | |

CORR | 0.882 | 0.982 | 0.954 | 0.980 | 0.949 |

Model | Index | T-R | T-R-F | T-R-G | T-R-G-F | Average |
---|---|---|---|---|---|---|

ANN | RMSE (m) | 0.034 | 0.020 | 0.040 | 0.020 | 0.028 |

MARE (%) | 15.314 | 8.438 | 18.494 | 8.623 | 12.717 | |

CORR | 0.593 | 0.885 | 0.549 | 0.908 | 0.734 | |

SVM | RMSE (m) | 0.028 | 0.022 | 0.030 | 0.021 | 0.025 |

MARE (%) | 12.630 | 9.229 | 12.654 | 9.104 | 10.904 | |

CORR | 0.777 | 0.859 | 0.733 | 0.867 | 0.809 |

Model | Index | T-R | T-R-F | T-R-G | T-R-G-F | Average |
---|---|---|---|---|---|---|

ANN | RMSE (m) | 0.061 | 0.061 | 0.042 | 0.056 | 0.055 |

MARE (%) | 10.329 | 10.582 | 7.083 | 9.852 | 9.462 | |

CORR | 0.888 | 0.965 | 0.935 | 0.892 | 0.902 | |

SVM | RMSE (m) | 0.072 | 0.069 | 0.038 | 0.040 | 0.055 |

MARE (%) | 12.335 | 12.255 | 6.221 | 7.043 | 9.463 | |

CORR | 0.882 | 0.920 | 0.954 | 0.943 | 0.925 |

Model | Index | T-R | T-R-F | T-R-G | T-R-G-F | Average |
---|---|---|---|---|---|---|

ANN | RMSE (m) | 0.034 | 0.042 | 0.040 | 0.034 | 0.037 |

MARE (%) | 15.314 | 16.837 | 18.494 | 14.937 | 16.395 | |

CORR | 0.593 | 0.420 | 0.549 | 0.806 | 0.592 | |

SVM | RMSE (m) | 0.028 | 0.034 | 0.030 | 0.035 | 0.032 |

MARE (%) | 12.630 | 14.347 | 12.654 | 14.773 | 13.601 | |

CORR | 0.777 | 0.611 | 0.733 | 0.592 | 0.678 |

© 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Yoon, H.; Kim, Y.; Ha, K.; Lee, S.-H.; Kim, G.-P.
Comparative Evaluation of ANN- and SVM-Time Series Models for Predicting Freshwater-Saltwater Interface Fluctuations. *Water* **2017**, *9*, 323.
https://doi.org/10.3390/w9050323

**AMA Style**

Yoon H, Kim Y, Ha K, Lee S-H, Kim G-P.
Comparative Evaluation of ANN- and SVM-Time Series Models for Predicting Freshwater-Saltwater Interface Fluctuations. *Water*. 2017; 9(5):323.
https://doi.org/10.3390/w9050323

**Chicago/Turabian Style**

Yoon, Heesung, Yongcheol Kim, Kyoochul Ha, Soo-Hyoung Lee, and Gee-Pyo Kim.
2017. "Comparative Evaluation of ANN- and SVM-Time Series Models for Predicting Freshwater-Saltwater Interface Fluctuations" *Water* 9, no. 5: 323.
https://doi.org/10.3390/w9050323