סמינר מחלקה של אסף פרס סטודנט לתואר שני - "חיזוי בזמן אמת של קוליפורמים צואתיים במי שתייה בעזרת רשת נוירונים"

School of Mechanical Engineering Seminar
Wednesday October 6.10.21 at 14:00 Room 206
 

Nowcasting of fecal coliform presence using an artificial neural network

Asaf Pras

M.Sc. student of Prof. Hadas Mamane

At least 2 billion people worldwide use drinking water sources that are contaminated with feces, causing waterborne diseases; poor sanitation, poor hygiene, and unsafe drinking water result in a daily death rate of more than 800 children under 5 years of age from diarrheal diseases. Therefore, Accurate information of biological contamination, in the form of fecal coliforms (FC) is an integral part of the management of water treatment systems. Whether in the developing world, where fecal coliforms contaminate drinking water sources, or the developed world, where stringent water quality standards apply to nearly all water sources, the analysis of biological contamination is a vital component for engineers and public health.

The limitation in delivering data is well known: there is a time delay between when a sample is taken, and when accurate data relating to its biological contamination (or potential for contamination) can be reported. This stands in contrast to many other kinds of assessment techniques, which can provide real-time data, based on physical and electrochemical sensors providing a near-constant data stream. The gap between these kinds of analyses and their costs places significant organizational stress on water authorities, a gap that leaves blank spaces in our understanding of the quality of the water around us.

This study aims to overcome this gap and to develop a FC sensor based on artificial intelligence (AI), which uses easy-to-monitor, real-time and in situ parameters as inputs. The sensor: can give a ‘nowcast’ of FC absence or presence in water sources; is a user-friendly sensor free from requirements for complex personnel training; can be used multiple times without disposables and lowers costs of water analysis in the long term, and broadening the insight required for safe water quality management