Contaminant classification using cosine distances based on multiple conventional sensors

Prediction of monthly dry days with machine learning algorithms: a case study in Northern Bangladesh

Dry days at varied scale are an important topic in climate discussions. Prolonged dry days define a dry period. Dry days with a specific rainfall threshold may visualize a climate scenario of a locality. The variation of monthly dry days from station to station could be correlated with several climatic factors. This study suggests a novel approach for predicting monthly dry days (MDD) of six target stations using different machine learning (ML) algorithms in Bangladesh. Several rainfall thresholds were used to prepare the datasets of monthly dry days (MDD) and monthly wet days (MWD). A group of ML algorithms, like Bagged Trees (BT), Exponential Gaussian Process Regression (EGPR), Matern Gaussian Process Regression (MGPR), Linear Support Vector Machine (LSVM), Fine Trees (FT) and Linear Regression (LR) were evaluated on building a competitive prediction model of MDD. In validation of the study, EGPR-based models were able to better capture the monthly dry days (MDD) over Bangladesh compared to those by MGPR, LSVM, BT, LR and FT-based models. When MDD were the predictors for all six target stations, EGPR produced highest mean R² of 0.91 (min. 0.89 and max. 0.92) with a least mean RMSE of 2.14 (min. 1.78 and max. 2.69) compared to other models. An explicit evaluation of the ML algorithms using one-year lead time approach demonstrated that BT and EGPR were the most result-oriented algorithms (R² = 0.78 for both models). However, having a least RMSE, EGPR was chosen as the best model in one year lead time. The dataset of monthly dry-wet days was the best predictor in the lead-time approach. In addition, sensitivity analysis demonstrated sensitivity of each station on the prediction of MDD of target stations. Monte Carlo simulation was introduced to assess the robustness of the developed models. EGPR model declared its robustness up to certain limit of randomness on the testing data. The output of this study can be referred to the agricultural sector to mitigate the impacts of dry spells on agriculture.

An Online Contaminant Classification Method Based on MF-DCCA Using Conventional Water Quality Indicators

Emergent contamination warning systems are critical to ensure drinking water supply security. After detecting the existence of contaminants, identifying the types of contaminants is conducive to taking remediation measures. An online classification method for contaminants, which explored abnormal fluctuation information and the correlation between 12 water quality indicators adequately, is proposed to realize comprehensive and accurate discrimination of contaminants. Firstly, the paper utilized multi-fractal detrended fluctuation analysis (MF-DFA) to select indicators with abnormal fluctuation, used multi-fractal detrended cross-correlation analysis (MF-DCCA) to measure the cross-correlation between indicators. Subsequently, the algorithm fused the abnormal probability of each indicator and constructed the abnormal probability matrix to further judge the abnormal fluctuation of indicators using D–S evidence theory. Finally, the singularity index of the cross-correlation function and the selected indicators were used to classification by cosine distance. Experiments of five chemical contaminants at three concentration levels were implemented, and analysis results show the method can weaken disturbance of water quality background noise and other interfering factors. It effectively improved the classification accuracy at low concentrations compared with another three methods, including methods using triple standard deviation threshold and single indicator fluctuation analysis-only methods without fluctuation analysis. This can be applied to water quality emergency monitoring systems to reduce contaminant misclassification.

Online Classification of Contaminants Based on Multi-Classification Support Vector Machine Using Conventional Water Quality Sensors

Water quality early warning system is mainly used to detect deliberate or accidental water pollution events in water distribution systems. Identifying the types of pollutants is necessary after detecting the presence of pollutants to provide warning information about pollutant characteristics and emergency solutions. Thus, a real-time contaminant classification methodology, which uses the multi-classification support vector machine (SVM), is proposed in this study to obtain the probability for contaminants belonging to a category. The SVM-based model selected samples with indistinct feature, which were mostly low-concentration samples as the support vectors, thereby reducing the influence of the concentration of contaminants in the building process of a pattern library. The new sample points were classified into corresponding regions after constructing the classification boundaries with the support vector. Experimental results show that the multi-classification SVM-based approach is less affected by the concentration of contaminants when establishing a pattern library compared with the cosine distance classification method. Moreover, the proposed approach avoids making a single decision when classification features are unclear in the initial phase of injecting contaminants.

A multivariate based event detection method and performance comparison with two baseline methods

Early warning systems have been widely deployed to protect water systems from accidental and intentional contamination events. Conventional detection algorithms are often criticized for having high false positive rates and low true positive rates. This mainly stems from the inability of these methods to determine whether variation in sensor measurements is caused by equipment noise or the presence of contamination. This paper presents a new detection method that identifies the existence of contamination by comparing Euclidean distances of correlation indicators, which are derived from the correlation coefficients of multiple water quality sensors. The performance of the proposed method was evaluated using data from a contaminant injection experiment and compared with two baseline detection methods. The results show that the proposed method can differentiate between fluctuations caused by equipment noise and those due to the presence of contamination. It yielded higher possibility of detection and a lower false alarm rate than the two baseline methods. With optimized parameter values, the proposed method can correctly detect 95% of all contamination events with a 2% false alarm rate.