Applicability of a Nu-Support Vector Regression Model for the Completion of Missing Data in Hydrological Time Series

Deep learning approach for prediction of exergy and emission parameters of commercial high by-pass turbofan engines

Aviation emissions originated from the fuel burn have been hot topics by engineers and policy-makers due to their harmful effects on the environment and thereby human health as well as sustainability. In this study, it is tried that several emission indexes (EIs) involving CO, HC and NOx as well as fuel flow of several commercial aircraft engines (CAEs) are predicted using support vector regression (SVR) and long short-term memory (LSTM) approaches for take-off phase. Moreover, exergo-environmental parameters involving exergy efficiency (ExEFF), wasted exergy ratio (WExR) and environmental effect factor (EEF) pertinent to CAEs are computed employing thermodynamics laws. While establishing the models, rated thrust, by-pass ratio, overall pressure ratio and combustion type of the CAEs are utilized as the model inputs. According to the findings of emission modelling, the coefficient of determination (R2) of EI NOx and EI CO of the CAEs is found as 0.929074 and 0.960277 with SVR, whereas their R2 values are elevated to 0.954878 and 0.989283 with LSTM approach, respectively. However, R2 of EI HC is determined lower with 0.632280 (by SVR) and 0.651749 (by LSTM). On the other hand, exergo-environmental parameters for the CAEs are estimated with high correctness at both models. Namely, R2 of ExEFF and EEF regarding the CAEs are computed as 0.991748 and 0.989067 by SVR; however, these are calculated as 0.994785 and 0.992797 by LSTM method. To model these parameters with low error by using significant design variables as model inputs could help in predicting emission and environmental metrics for new engine designs.

Reconstructing Missing and Anomalous Data Collected from High-Frequency In-Situ Sensors in Fresh Waters

In situ sensors that collect high-frequency data are used increasingly to monitor aquatic environments. These sensors are prone to technical errors, resulting in unrecorded observations and/or anomalous values that are subsequently removed and create gaps in time series data. We present a framework based on generalized additive and auto-regressive models to recover these missing data. To mimic sporadically missing (i) single observations and (ii) periods of contiguous observations, we randomly removed (i) point data and (ii) day- and week-long sequences of data from a two-year time series of nitrate concentration data collected from Arikaree River, USA, where synoptically collected water temperature, turbidity, conductance, elevation, and dissolved oxygen data were available. In 72% of cases with missing point data, predicted values were within the sensor precision interval of the original value, although predictive ability declined when sequences of missing data occurred. Precision also depended on the availability of other water quality covariates. When covariates were available, even a sudden, event-based peak in nitrate concentration was reconstructed well. By providing a promising method for accurate prediction of missing data, the utility and confidence in summary statistics and statistical trends will increase, thereby assisting the effective monitoring and management of fresh waters and other at-risk ecosystems.

Case Study: Reconstruction of Runoff Series of Hydrological Stations in the Nakdong River, Korea

Reliable runoff series is sine qua non for flood or drought analysis as well as for water resources management and planning. Since observed hydrological measurement such as runoff can sometimes show abnormalities, data quality control is necessary. Generally, the data of adjacent hydrological stations are used. However, difficulties are frequently encountered when runoff series of the adjacent stations have different flow characteristics. For instance, when the correlation between the up- and downstream locations in which the stations are located is used as the main criterion for quality control, difficulties can occur. Therefore, this study aims to suggest a method to reconstruct an abnormal daily runoff series in the Nakdong River, Korea. The variational mode decomposition (VMD) technique is applied to the runoff series of the three target stations: Goryeong County (Goryeong bridge) and Hapcheon County (Yulji bridge and Jeogpo bridge). These runoff series are also divided into several intrinsic mode functions (IMFs) that are governed by basin runoff and disturbed flow caused by the hydraulic structure. The decomposition results based on VMD show that the runoff components in a particular station that is influenced by hydraulic structures could be reconstructed using adjacent stations, but the residual mode could not. The runoff reconstruction model using an artificial neural network (ANN), the two “divided” modes, and the residual component is established and applied to the runoff series for the target station (Yulji bridge in Hapcheon County). The reconstructed series from the model show relatively good results, with R2 = 0.92 and RMSE = 99.3 in the validation year (2019). Abnormal runoff series for 2012 to 2013 at the Yulji bridge station in Hapcheon County are also reconstructed. Using the suggested method, a well-matched result with the observations for the period from 2014 onwards is produced and a reconstructed abnormal series is obtained.

Double Tensor-Decomposition for SCADA Data Completion in Water Networks

Supervisory Control And Data Acquisition (SCADA) systems currently monitor and collect a huge among of data from all kind of processes. Ideally, they must run without interruption, but in practice, some data may be lost due to a sensor failure or a communication breakdown. When it happens, given the nature of these failures, information is lost in bursts, that is, sets of consecutive samples. When this occurs, it is necessary to fill out the gaps of the historical data with a reliable data completion method. This paper presents an ad hoc method to complete the data lost by a SCADA system in case of long bursts. The data correspond to levels of drinking water tanks of a Water Network company which present fluctuation patterns on a daily and a weekly scale. In this work, a new tensorization process and a novel completion algorithm mainly based on two tensor decompositions are presented. Statistical tests are realised, which consist of applying the data reconstruction algorithms, by deliberately removing bursts of data in verified historical databases, to be able to evaluate the real effectiveness of the tested methods. For this application, the presented approach outperforms the other techniques found in the literature.

Different Approaches to SCADA Data Completion in Water Networks

This work contributes to the techniques used for SCADA (Supervisory Control and Data Acquisition) system data completion in databases containing historical water sensor signals from a water supplier company. Our approach addresses the data restoration problem in two stages. In the first stage, we treat one-dimensional signals by estimating missing data through the combination of two linear predictor filters, one working forwards and one backwards. In the second stage, the data are tensorized to take advantage of the underlying structures at five minute, one day, and one week intervals. Subsequently, a low-range approximation of the tensor is constructed to correct the first stage of the data restoration. This technique requires an offset compensation to guarantee the continuity of the signal at the two ends of the burst. To check the effectiveness of the proposed method, we performed statistical tests by deleting bursts of known sizes in a complete tensor and contrasting different strategies in terms of their performance. For the type of data used, the results show that the proposed data completion approach outperforms other methods, the difference becoming more evident as the size of the bursts of missing data grows.