“Any industry that mislays 25-30% of its product in the process
of delivering it might reasonably be thought to have a problem.”

Between the water treatment plant and the tap in your kitchen, a lot can happen to water. Old pipes sometimes have slow leaks that are hard to detect, and sometimes there are bigger leaks that can waste a lot of potable water in a short time. According to a World Bank report published a few years ago, these leaks cost at least $14 billion a year.

On top of that, the environmental cost is high: treating water and pumping it uses a lot of energy, which comes from dirty sources of power most of the time, and in some areas, natural aquifers are rapidly getting depleted (ie. Las vegas). What can we do about this problem?

Software Isn’t Just Good for Data Pipes…
There is an Israeli firm called TaKaDu that offers what it calls “water infrastructure monitoring”. It allows water utilities to make sense of the mountain of data that comes in from various meters and sensors and, using complex statistical tools, to pinpoint leaks and detect them significantly faster than humans would on their own, thus saving a lot of water, money, and environmental headaches.

According to the Economist, “it seems to work. Early last year Thames Water, which supplies London, tested the system on 3,000km (2,000 miles) of mains. The detection engine proved able to identify minor leaks up to nine days earlier than Thames’s existing systems could manage, and even picked up major bursts as much as 3½ hours more quickly. In light of that success, Thames has now extended the detection engine’s reach over the whole 10,400km length of its urban mains network.”

Whether TaKaDu or other data mining companies (Google, you reading this?), if such systems really work, there’s no reason why all water distribution system don’t use this technique. I hope it will quickly catch on around the world, especially since it will pay for itself in savings and then provide additional savings once the original investment is recouped.