Groundwater level forecasting by Artificial Neural Network
ABSTRACT
Following many applications artificial neural networks (ANNs) have found in hydrology, a question has been rising for quantification of the output uncertainty. A pre-optimized ANN simulated the hydraulic head change at two observation wells, having as input hydrological and meteorological parameters. In order to calculate confidence intervals (CI) for the ANN output two bootstrap methods were examined namely bootstrap percentile and BCa (Bias-Corrected and accelerated). The actual coverage of the CI was compared to the theoretical coverage for different certainty levels as a means of examining the method's reliability. The results of this work support the idea that the bootstrap methods provide a simple tool for confidence interval computation of ANNs. Comparing the two methods, the percentile requires fewer calculations and yields narrower intervals with similar actual coverage to that of BCa. Overall, the actual coverage was proved lower than desired when not modeled points were present in the data subset.
TABLE OF CONTENTS
ABSTRACT2
CHAPTER 1: INTRODUCTION4
Background of the Study4
Problem Statement6
Purpose of the study6
Theoretical Framework7
CHAPTER 2: LITERATURE REVIEW9
Network training and cross training14
Training parameters15
Data Preprocessing16
Applications in groundwater hydrology17
Groundwater remediation18
Subsurface characterization19
Prediction of groundwater levels20
Goundwater Pollution21
Parameter Estimation22
Highlights of applications23
CHAPTER 3: METHODOLOGY26
Deterministic ANN model26
Bootstrap methodology applied in ANNs28
CHAPTER 4: DAM RESERVOIR LEVEL MODELING BY NEURAL NETWORK APPROACH: A CASE STUDY33
Abstract (summary)33
Introduction33
Methodology of Artificial Neural Networks35
Tahtaköprü Dam Reservoir and Data35
Prediction of Tahtaköprü Dam reservoir level fluctuation37
Conclusions38
CHAPTER 5: DISCUSSION AND RESULTS40
Percentile confidence intervals for 95% nominal coverage41
BCa confidence intervals for 95% nominal coverage42
Actual coverage for different certainty levels44
CHAPTER 6: SUMMARY AND CONCLUSIONS47
REFERENCES49
CHAPTER 1: INTRODUCTION
Background Of The Study
Intensive use of groundwater is becoming a common situation in many areas of the world, especially in semiarid and arid areas, and in small islands and coastal zones. When studying groundwater it is necessary to consider that it is not only an important mineral resource (in recent years geologists often call groundwater the 'number one mineral resource') but a component of the total water resources and water balance and is one of the main components of the environment (Zektser et al., 2009). Groundwater level is an indicator of groundwater availability, groundwater flow, and the physical characteristics of an aquifer or groundwater system. A choice of a method for prediction depends on the complexity of hydrogeological conditions, volume of information, water demand, purpose of calculations made and experience in exploitation of operating well fields. In recent years, Artificial Neural Network (ANN) has shown a great ability in forecasting nonlinear and nonstationary time series in hydrology due to the highly flexible function estimator that has self-learning and self-adaptive feature, therefore it has been widely applied in the hydrology and water resource engineering.
Forecasting the ground water level fluctuations is an important requirement for planning conjunctive use in any basin. The most appropriate set of input variables to the model are selected through a combination of domain knowledge and statistical analysis of the available data series. Several ANN models are developed that forecasts the water level of two observation wells. Groundwater is one of the major sources of supply ...