Analyzed Data contains the results of the anomaly detection algorithms and are compiled/published in terms of maximum probability of groundwater quality changes (CMAX) in near real-time using USEPA’s CANARY software. This CMAX trend displays the probabilities of the monitoring data, stating the extent to which it could be anomalous. The three algorithms used are LPCF, MVNN and SPPE.
Graph: Place the cursor on the graph trend to see anomaly probabilities at that time.
Table: Choose the number of entries that you want to see on the same page, and click on the column name to sort the data based on your preference.
Graph: The closer the probability is to zero, there is no or minimal chance of contamination, meaning that groundwater quality has not changed. The closer the probability is to one, there is a higher chance of groundwater quality changes from normal condition. The changes can either be due to a natural change or due to contamination.
Table: Detection Probability shows the anomaly probabilities calculated by the algorithms. If probability is closer to zero, there is no or minimal chance of a contamination, meaning that groundwater quality has not changed. If the probability is closer to one, there is a higher chance that the groundwater quality has changed. The changes can be due to a natural change or due to contamination.
Parametershows the parameters that contributed to the anomaly, and Comments describes the source and cause for the analyzed anomaly.
For more information about the anomaly detection system, please visit here
For more details about the anomaly detection system, please visit here
CMAX: A consensus algorithm that reports the maximum probability from the probabilities of the anomaly detection algorithms
Event: A period of anomalous water quality
LPCF: Linear Prediction Coefficient Filter
MVNN: Multivariate Near-Neighbor
SPPE: Set-point Proximity