Author(s): Mohammadreza Moslemi; Darko Joksimovic
Linked Author(s): Darko Joksimovic
Keywords: Rtificial Neural Networks; Quality Control; Rain Gauge; Rainfall
Abstract: Due to advancements in instrumentation and communication technologies, monitoring of water infrastructure is experiencing a significant growth worldwide and water managers are increasingly deploying monitoring equipment for decision-making purposes. Hydrological events and relevant datasets including rainfall data are of a complex nature and are potentially susceptible to errors from various sources. Hence, it is essential to develop efficient methods for the quality control of the acquired data. The present work introduces an artificial neural network-based approach for real-time quality control and infilling of rain gauge data. Available rainfall measurements from neighboring rain gauges are employed to train and develop the neural network model. Trained artificial neural network model was able to validate up to about 97% of the data using 95% confidence intervals. This finding suggests that artificial neural networks can be successfully implemented for erroneous data identification/correction and reconstruction of missing data points. Given its short processing time and reportedly superior performance to traditional quality control strategies, neural network methodology can be deployed as an efficient tool for the processing and control of large sets of timeseries with complex natures including precipitation data.
Year: 2018