ORCID Profile
0000-0002-0337-0395
Current Organisations
RMIT University
,
CSIRO
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Wiley
Date: 29-03-2023
DOI: 10.1002/HYP.14857
Abstract: Many water‐quality monitoring programs aim to measure turbidity to help guide effective management of waterways and catchments, yet distributing turbidity sensors throughout networks is typically cost prohibitive. To this end, we built and compared the ability of dynamic regression (auto‐regressive integrated moving average [ARIMA]), long short‐term memory neural nets (LSTM), and generalized additive models (GAM) to forecast stream turbidity one step ahead, using surrogate data from relatively low‐cost in‐situ sensors and publicly available databases. We iteratively trialled combinations of four surrogate covariates (rainfall, water level, air temperature and total global solar exposure) selecting a final model for each type that minimized the corrected Akaike information criterion. Cross‐validation using a rolling time‐window indicated that ARIMA, which included the rainfall and water‐level covariates only, produced the most accurate predictions, followed closely by GAM, which included all four covariates. However, according to the no‐free‐lunch theorems in machine learning, no single model has an advantage over all other models for all instances. Therefore, we constructed a meta‐model, trained on time‐series features of turbidity, to take advantage of the strengths of each model over different time points and predict the best model (that with the lowest forecast error one‐step prior) for each time step. The meta‐model outperformed all other models, indicating that this methodology can yield high accuracy and may be a viable alternative to using measurements sourced directly from turbidity‐sensors where costs prohibit their deployment and maintenance, and when predicting turbidity across the short term. Our findings also indicated that temperature and light‐associated variables, for ex le underwater illuminance, may hold promise as cost‐effective, high‐frequency surrogates of turbidity, especially when combined with other covariates, like rainfall, that are typically measured at coarse levels of spatial resolution.
Publisher: Mathematical Sciences Publishers
Date: 31-08-2012
Publisher: Public Library of Science (PLoS)
Date: 05-08-2020
Publisher: Elsevier BV
Date: 05-2019
DOI: 10.1016/J.SCITOTENV.2019.02.085
Abstract: Monitoring the water quality of rivers is increasingly conducted using automated in situ sensors, enabling timelier identification of unexpected values or trends. However, the data are confounded by anomalies caused by technical issues, for which the volume and velocity of data preclude manual detection. We present a framework for automated anomaly detection in high-frequency water-quality data from in situ sensors, using turbidity, conductivity and river level data collected from rivers flowing into the Great Barrier Reef. After identifying end-user needs and defining anomalies, we ranked anomaly importance and selected suitable detection methods. High priority anomalies included sudden isolated spikes and level shifts, most of which were classified correctly by regression-based methods such as autoregressive integrated moving average models. However, incorporation of multiple water-quality variables as covariates reduced performance due to complex relationships among variables. Classifications of drift and periods of anomalously low or high variability were more often correct when we applied mitigation, which replaces anomalous measurements with forecasts for further forecasting, but this inflated false positive rates. Feature-based methods also performed well on high priority anomalies and were similarly less proficient at detecting lower priority anomalies, resulting in high false negative rates. Unlike regression-based methods, however, all feature-based methods produced low false positive rates and have the benefit of not requiring training or optimization. Rule-based methods successfully detected a subset of lower priority anomalies, specifically impossible values and missing observations. We therefore suggest that a combination of methods will provide optimal performance in terms of correct anomaly detection, whilst minimizing false detection rates. Furthermore, our framework emphasizes the importance of communication between end-users and anomaly detection developers for optimal outcomes with respect to both detection performance and end-user application. To this end, our framework has high transferability to other types of high frequency time-series data and anomaly detection applications.
Publisher: Informa UK Limited
Date: 24-06-2020
Publisher: Elsevier BV
Date: 03-2016
Publisher: Springer Science and Business Media LLC
Date: 21-11-2020
Publisher: Unpublished
Date: 2020
Publisher: Elsevier BV
Date: 11-2023
Publisher: Elsevier BV
Date: 2015
Publisher: Unpublished
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Publisher: Informa UK Limited
Date: 28-09-2020
Publisher: Elsevier BV
Date: 09-2022
Publisher: Public Library of Science (PLoS)
Date: 30-08-2019
Publisher: Informa UK Limited
Date: 22-12-2021
Location: Australia
No related grants have been discovered for Sevvandi Kandanaarachchi.