Wastewater-based epidemiology (WBE) has been widely deployed for the detection and monitoring of COVID-19 through wastewater sampling and analysis of SARS-CoV-2 virus in many countries, including those in the Asia-pacific region. WBE can potentially provide a nearly real-time, objective, and low-cost approach to monitor the COVID-19 prevalence in the community. However, there is a lack of accurate and reliable method to back-estimate the number of cases from the virus concentration in wastewater samples.
An accurate and reliable estimation of community prevalence (number of infected cases) can be critical for the governments to implement timely control measures to further avoid the spread of this virus. Current detection of COVID-19 through clinical testing of individuals is highly time-consuming and might be cost-prohibitive and region-biased especially in resource-poor regions. It was also reported that more and more people infected with SARS-CoV-2 exhibited no known clinical symptoms. Even after infection speaks within a population, the ongoing circulation of SARS-CoV-2 is likely to remain as a public health threat to the community. Consequently, a systematic platform with accurate prevalence estimation using WBE data will be of great benefit for timely prevention and appropriate response actions.
This WATMOC project aims to develop an online machine learning model for the application of a data-driven approach to the WBE dataset for the calculation of COVID-19 prevalence rate in the community. To enable the machine learning model, we will need lots of WBE data to optimize the estimation accuracy and robustness.
We thus plead worldwide researchers or public health departments, especially those in the Asia-Pacific regions, to become a member of the WATMOC network and submit your WBE data to us. WBE data of SARS-CoV-2 submitted using the Excel template (see downloads below) will be stored in the WATMOC database system. We understand the sensitivity and privacy of data, only those data with permission of the provider will be publicly available in the database. The database allows information sharing on the latest data of SARS-CoV-2 in wastewater across Asia-Pacific and internationally.
The WATMOC database will be used to train a machine learning model using Google Cloud AutoML platform. The trained model is available on this website and can provide predictions for anyone with such requirements to estimate community prevalence of COVID-19 by inputting their WBE data and other environmental variables.
For information and conditions for the inclusion of your data in the WATMOC database, please contact Dr Guangming Jiang (email@example.com). To share and store data to the WATMOC database, please use the Excel template file to format your WBE data. The template can be downloaded below. The formatted data file should be sent to the WATMOC team: A/Prof Guangming Jiang (firstname.lastname@example.org), for further processing and upload to the database.
We have curated a database from systematic literature review, plus 10,000+ rows of data from the Utah and Wisconsin state COVID sewage surveillance program (as described in our published paper on Water Research, see below).
If you would like to use this dataset for your research, please contact A/Prof Guangming Jiang (email@example.com).
Jiang, G., Wu, J., Weidhaas, J., Li, X., Chen, Y., Mueller, J., Li, J., Kumar, M., Zhou, X., Arora, S., Haramoto, E., Sherchan, S., Orive, G., Lertxundi, U., Honda, R., Kitajima, M. and Jackson, G. 2022. Artificial neural network-based estimation of COVID-19 case numbers and effective reproduction rate using wastewater-based epidemiology. Water Research 218, 118451.
The Excel template will guide you in formatting your data .
We can also share our collection of data to any research collaborators.
If you have any questions in how to use the template, or if you like to use the database for your research, please contact A/Prof Guangming Jiang (firstname.lastname@example.org).