Abstract
Hydrometeorological data sets are usually incomplete due to different reasons (malfunctioning sensors, collected data storage problems, etc.). Missing data do not only affect the resulting decision-making process, but also the choice of a particular analysis method. Given the increase of extreme events due to climate change, it is necessary to improve the management of water resources. Due to the solution of this problem requires the development of accurate estimations and its application in real time, this work present two contributions. Firstly, different gap-filling techniques have been evaluated in order to select the most adequate one for river stage series: (i) cubic splines (CS), (ii) radial basis function (RBF) and (iii) multilayer perceptron (MLP) suitable for small processors like Arduino or Raspberry Pi. The results obtained confirmed that splines and monolayer perceptrons had the best performances. Secondly, a pre-validating Internet of Things (IoT) device was developed using a dynamic seed non-linear autoregressive neural network (NARNN). This automatic pre-validation in real time was tested satisfactorily, sending the data to the catchment basin process center (CPC) by using remote communication based on 4G technology.
Highlights
As in the case of hydrologic variables such as precipitation [1], complete historical records are necessary in river stage data sets
The goodness of fit found was with the application of the three methods suggests a ranking such as Splines > radial basis function (RBF) > multilayer perceptron (MLP)
The standard error of the estimate (SEE) values obtained for the spline technique and RBF methods are one order of magnitude lower than for MLP method (Table 4)
Summary
As in the case of hydrologic variables such as precipitation [1], complete historical records are necessary in river stage data sets. One of the main problems in the analysis of time series is the absence of data, with gaps of different widths, number of missing data and frequency, which makes the model identification harder and prevents the adoption of common validation procedures, usually applied to complete data sets [3,4,5,6]. These deficiencies in hydrologic time series are usually due to the malfunctioning of monitoring equipment, the occurrence of anomalous natural phenomena and data transmission storage and retrieval process issues [7]. The solution of these problems is not instantaneous, Sensors 2020, 20, 6354; doi:10.3390/s20216354 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
