Spanish scientists design software to predict source of faecal pollution in water: Microbilogist says identifying source would help in resolving conflicts about who is responsible for faecal pollution of a river, a farm, an abattoir or a sewage treatment plant.
New Software To Predict Pollution In Water
Spanish scientists have designed software that is capable of predicting the source of faecal pollution in water bodies. The software, called Ichnaea (Greek for tracker), makes use of automatic learning and analysis of different biological indicators to make extremely effective assumptions about water pollution.
Faecal contamination of rivers and reservoirs is becoming a serious health concern. Increase in population and urbanization are mainly to blame. Taking into account the worsening situation, a multidisciplinary team of IT experts and Spanish biologists took the initiative of developing the novel software. They believe that knowing the source of pollution is extremely important from a health-risk perspective, given that human pathogens are more harmful than those of animal origin.
“Identifying the species to which the traces belong would help in resolving conflicts about who is responsible for the faecal pollution of a river – a farm, an abattoir, a sewage treatment plant or a human population nucleus, for example,” said Anicet R. Blanch, a microbiologist at the University of Barcelona, and co-director of the project, along with Lluis Belanche of the Polytechnic University of Catalonia.
Software Analyses Chemical, Microbial And Eukaryotic Indicators
Blanch explained that Ichnaea is “based on the development of prediction models from the analysis of a series of microbial, chemical or eukaryotic indicators”. This form of analysis allows the system to establish the exact source of the contamination – even in complex situations where the faecal pollution has been diluted or deteriorated.
In order for the software to make accurate assumptions, standard information regarding different parameters of polluted water samples with a solitary known source of faecal pollution have to be fed into its system.
How the Software to predict pollution in water can help? “Using this data, the software determines the relevant indicators, which when analysed in water samples with an unknown source of faecal pollution, would allow its source to be determined,” Blanch further explained.
“Up until now, each research group proposed the indicators which they believed to be the most important, but Ichnaea eliminates the subjectivity by selecting the most essential for a reliable prediction from among the different variable parameters,” the researcher added.
Some of the microbial indicators that were used included bacteriophages (viruses which infect bacteria) that were linked to a single species. Others, related to bifidobacteria (group of bacteria that reside inside the intestine) usually appeared on the mitochondrial DNA of specimens.
Reliability And Consistency
The degree of reliability depends on the quantity and quality of the samples used to create a standard profile in the systems learning models, taking into account the degree of variability among bacterial populations in different geographical locations. The freshness of the sample and its degree of dilution also play a part in the consistency of results.
Scientists compared the reliability of predictions on three locations with varying degree of faecal contamination (human and cattle sources). The system was rightfully able to predict areas of high and low levels of contamination.
Funding For Moving Software To The Cloud
The prototype software is yet to be refined. Different and more diverse learning modules need to be incorporated into a single platform for the prediction of faecal contamination.
“The idea is that anyone can access the system from any computer, even a tablet, because the calculation is done from a remote machine,” Blanch envisions.
The researchers aim that the user will be able to optimize the software according to their geographical location with the help of the customized settings and known samples.
The users can then provide the software with unknown samples and get accurate predications accordingly. On the contrary, the system’s existing database could also be used to optimize the software – the user could select samples from similar geographical areas and adapt the software.