Snippets in Clean Technology and Data Science: Water
Today, let’s look at some of the ways in which sensors, machine learning and other data science tools are helping solve problems in the water sector
Water conservationis one of the largest components of the water sector. And with the droughts hitting California, New South Wales and South Africa recently, there’s been a lot of focus on education and changing people’s behavior through information. So how do we make it easy for people to do their best to minimize water use?Companies and organizations have tried several different approaches – public education programs about water use being one such example. Another being the water comparison report that water companies in California started sending out to their customers with the monthly bill. It’s a short summary that shows how your water usage compares with your neighbors and how much water you have used against your allocation. This is a fairly straightforward use of data science – it uses a nearest neighbor approach with a built in radius and constraints around house size and household type and compares aggregated water use. In other words, each individual house is compared against an average value – so privacy is protected.
Researchers in Germany decided to start using theInternet of Things (IoT)to provide real-time feedback and see how that compared with people’s behavior after receiving reports. They built sensors that monitored water use, water temperature and energy use and placed a digital display so that it would be visible while showering.What they found was that having this information readily available resulted in people changing their behavior to conserve more water and energy – so much that some of the highest water users actually reduced their usage by 22%.On the other hand, providing the information about the water and energy use after the shower was taken had no appreciable effect on people’s behavior. And not just that – people didn’t get tired and stop performing the action after using the sensors for two months – the effects were as pronounced at the end of the two month period as they were at the beginning.
Water monitoringis another billion dollar market that spans several sectors. Let’s take a look at how the government has been harnessing the power of data science to improve water quality in the United States.
Monitoring water, whether in streams or the ocean, requires a lot of sensors. Traditionally, the data collected by these sensors has been downloaded manually and then analyzed. Also, as sensors are expensive, scientists usually place sensors at locations where there is the most risk – for example, where algal blooms are the highest or where there is a possibility that lead in the ground water might reach houses with kids.
As hardware becomes cheaper and software more powerful, we start getting “smart sensors” or to use the latest buzzword – the Internet of Things. At theChesapeake Bay , a small number of smart sensors have been deployed to monitor weather, water conditions and water quality. These sensors collect data, transmit them wirelessly to the cloud where baseline analyses are done and the results presented in dashboards. The data can be followed in real-time, making these sensors invaluable for several businesses – recreational boating, fishing and education among others.
Even though the sensors deployed in the Bay are “smart”, they still only monitor localized conditions – that is, conditions near the sensor. Using these to monitor the whole Bay would be prohibitively expensive at this point in time! So,scientistshave started working on ways to supplement the data collected by the smart sensors with remote sensing data – data collected by aircraft or satellites. Remote sensing data may not be as accurate as the sensor data, but covers a much broader area and is thus a much more viable alternative for monitoring large water bodies. This makes it easier for policy makers, companies and non-profits to make decisions about the health and status of large lakes, streams and rivers.
Even more interesting things happen when different types of data are combined – but that work is just getting underway! If you’re someone interested in how data science can be used for the public good, the water sector is definitely one of the ones to watch.
The last couple of months have been interesting from a climate viewpoint - we’ve seen a record number of climate related disasters around the globe - drought, floods, fires, heat waves…..and it looks like this is probably going to be what our planet will look like in the near future. Add to that the COP26 conference that is scheduled for October 31st - and climate, sustainability and technology are front page news! So, let’s talk about one of the technologies in the news - artificial intelligence (AI) and its impact on climate, water, agriculture, energy, forestry, ecosystems and other sectors in clean technology . AI and its subset of tools - machine learning (ML), data science and statistics - are being touted as one of the key technologies in solving the problems facing the planet today. And while these technologies are certainly powerful - applying them effectively to solve problems in clean tech is another issue altogether. AI has been used by scientists in different clean tech se
We're in the processes of building a couple of fantastic new offerings that many folks in our community have asked for - so blog posts will be limited for a few months. Our jobs portal will still be updated regularly to make sure that all our members can keep up with what's happening in the sector. We can't wait to share what's happening at our end!
Will AI transform water, energy, agriculture, climate and all the other clean tech sectors? Can AI transform these sectors? Some version of these questions always gets asked at any meeting or conference in clean technology. Of course, part of that is because there’s been so much hype around AI and the whole “software is eating the world” interviews that came out a couple of years ago. But part of it is also because these tools are so powerful that professionals working in these sectors can see the potential - but just aren’t sure if it’s applicable to their sector yet. So, let’s start by asking a couple of fundamental questions. Why do we need AI at all? Or any models for that matter? Models are used to understand the world - to estimate the impacts of changes in systems and to try and predict what will happen in the future. Typically, the approaches used in building models can be classified into three broad categories - physical or mechanistic approaches, statistical approaches and