Clean Technology meets Data Science 101: Part 1

 Clean Technology was created as a “catch – all” term for several different fields that study and solve problems impacting the Earth and humanity’s ability to live sustainably on the planet. The fields of study range from environmental engineering, where systems to solve pollution in the environment are developed, to urban planning which includes designing sustainable cities and the infrastructure that powers them, to material science where researchers create new materials that can be used with less impact on the environment in extracting and disposing of them, to ecology which encompasses biodiversity, wildlife preservation and the study of the interactions between the Earth’s systems and human behavior.

All these fields developed as people grew interested in solving particular aspects of environmental problems. In many ways, they represent different ways of looking at and solving problems that affect the same system. As an example, if we were to look at water as a system – an ecologist might study the diversity of fish species in a river, an environmental engineer might be designing a purification system that improves the water chemistry – which in turn would affect the species, or a material scientist might be creating a new plastic that would be degraded easily and not accumulate in the bodies of the animals in the river.

Since there are so many interactions between the different fields in clean tech, I’ve chosen to explore the different functions in the Earth’s systems and human systems and see how data science is being used to solve problems in these areas.

The top 10 sectors based on these functions are

  1. Environmental remediation and restoration: This is where a lot of the sensor technology, statistics and machine learning are being used. There’s a lot of new academic research and several startups looking at how we can build better sensors that can monitor pollutants in the environment, transmit the data to the cloud and understand at a really granular level what is happening in our environment.
  2. Disaster management and resilience: A prime example of an area where big data and clean tech are meshing perfectly is in disaster management. Recently, we’ve seen many non-profits, government agencies and civilians use tools like Google Maps to pinpoint affected areas, manage relief supplies better and figure out where the biggest impacts are in cities when a natural disaster like a flood or a drought occurs.
  3. Sustainability accounting: This is what most people think about when they hear the term “sustainability”. How much material (water, energy, fuel etc.) is my company using – how is it being disposed of and can the footprint be reduced. A lot of the big companies are now collecting data at a very macro level – Facebook and Google for example have been monitoring the energy and water use at their data centers and understanding where they can make reductions or recycle the materials that they are using to improve their sustainability profile.
  4. Urban sustainability: If we were to look at some of the buzz words for 2016, “smart cities” would definitely be on the list. Here’s where sensor technology, data management and many of the tools used in data science are coming into play to build more sustainable cities. It’s transportation planning – with apps that manage car pools and parking in cities, and tools for city planners to build green spaces and look at how they are being used.
  5. Sustainable materials and biomimicry: Some of the most interesting applications that are happening are in how sustainable materials are being designed. Just as an example – there’s a lot of talk about “smart clothing” that has sensors built into them to help people monitor their fitness – but some of the science and research that underlies that also looks at how these materials can be recycled into useful products so that we have less waste.
  6. Climate change: This is probably the area that first started out as an intersection of big data and clean technology. Just developing the science underlying our understanding of climate change has required massive amounts of computing power and the ability to extract insights from large streams of data about different interacting systems.
  7. Ecosystem services and biodiversity: This is another area where sensors and big data play an essential role. Wildlife monitoring, understanding the spread and dangers of fires, forestry management are some of the applications where data science is being used to understand ecosystems.
  8. Water: This is a vast arena and the applications, companies and projects being developed are extremely different. There are companies looking at providing data about ocean chemistry, shipping routes and ocean diversity as well as projects and non-profits looking at water conservation, water treatment and water management in general. It’s where sensors, predictive models, statistics and understanding the mechanics of water flow come together.
  9. Agriculture: This is one of the “hot” areas in clean tech and big data these days. Predicting the yield of crops has been the goal of a lot of academic research and the early startups in this space, but it’s also included management of farm operations and using sensors, drones and machine learning to better manage farm health.
  10. Energy: This is the original big data play by companies in the clean tech space. Many of the startups that first entered the clean tech and big data space began as companies focused on energy efficiency, renewable energy production and electric cars. Tesla, Solar City, Opower and others have an underlying layer of data – data about the energy use, hotspots where consumer behavior can be changed and where manufacturing can be improved.

What our community are reading

Moonshots, Models, IoT and Machine Learning in Agriculture

How much water should an email consume? Data centers and water use

Our online community space is now live!