Showing posts with the label Water and Wastewater

Predicting floods using models for Covid and other infectious diseases

  What do Covid-19, social networks, traffic congestion and floods have in common? On the face of it, the answer would seem to be - nothing. But interestingly enough, all these systems can be represented in similar fashions - as nodes and networks with spatial and temporal effects.   So, scientists and researchers often try to see if models and ideas developed to solve problems in fields with similar representations can be adapted to problems in other fields.   A really interesting study was published in Nature   a couple of months ago, where researchers explored what happened when they adapted models used in understanding how infectious diseases like Covid spread to predicting floods in cities and urban systems.   How have floods and their impacts typically been modeled and why do people care? To start with, people care about flooding because it directly impacts their lives - when do areas have to be evacuated, how long should the evacuation last, and what are potential health consequ

Oceans, Ships and Data Science

  What comprises the water sector? If you asked ten people working in the sector, you’d probably get ten different opinions! And that’s because there are so many aspects of working with water and water technology.   There’s drinking water - which involves figuring out how much water is available (water resources management), how to treat it, how to deliver it effectively and at an acceptable price to customers. Then there’s wastewater - how do you treat, remove and recycle wastewater, both residential and industrial, to acceptable levels. Next, we come to the interactions between water and other built systems - hydropower and irrigation being the largest. Then, there’s the impact of water-related disasters - floods and tsunamis for example. Finally, we’ve got natural resources management - where we explore, monitor and evaluate the condition of natural water bodies - lakes, rivers, glaciers and the ocean - and how they interact with other systems.   The fun part about working with wate

Innovation In The Water Sector

  I was at   Imagine H2O’s “Water Innovation Week” conference   this week - virtually, of course! Imagine H2O is a wonderful resource and accelerator for startups in the water space, and their program this week was an excellent representation of water’s central role, not just in our daily lives, but also in the clean technology sector in general.     In most of the developed world, water isn’t really at the forefront of most people’s minds. Turn on the tap, you get clean, free flowing water - and unless you’re in the water sector, you’re probably not thinking about things like aging water infrastructure, budgets and how to fund water infrastructure, how to ensure that water is used efficiently, that wastewater is effectively treated and that tradeoffs between the water allocated to different sectors are discussed and managed equitably. In fact, unless there’s a storm or a flood or a leak in the water pipes in your house - water is not your primary concern.   And that is how it should b

Building Models With Missing Data

  Have you ever worked with a real-world problem where you have all the data that you need in a form that you could easily use to build models?   In the case of most problems, we find that data are missing, or there are errors in how the data are measured, or we’re faced with different types of data that need to be integrated. That’s been especially true in many clean technology fields - water, energy, climate, sustainability, ecosystem restoration and agriculture among them.   So, how do we deal with data with so many challenges?     One way is to see if there are alternative ways of measuring the data. One possibility is to identify surrogate datasets that can be calibrated and used as alternatives for the primary measurement. A second possibility is using cheaper, more widely distributed sensor data such as Purple Air sensors for air quality monitoring in combination with the primary data sources so that models can be developed. A third alternative is to use modeling techniques like

Data Science and Clean Technology: Updated Market Analysis

  If you were to ask people why they’re interested in applying data science in clean technology - the chances are that you’ll come across three answers. 1) They want to make a difference to the planet and help people 2) They think it’s cool technology and want to be at the forefront of innovation and 3) They’ve heard it’s a hot and upcoming field with lots of jobs and opportunities and want to get in at the ground level.   Now, one and two are both pretty obvious - but what about the third reason? Is the intersection of clean technology and data science really such a growing field?     To answer that question, let’s take a look at some numbers. Now, about five years ago, when the field was in its infancy, there was a lot of speculation about the field being anywhere from a   multi-billion dollar market to a multi-trillion dollar market . How did those estimates hold up, now as we look at what the next five years may bring?   As it turns out, the estimates held up pretty well.   Clean t

Not just another machine learning algorithm - how solving clean technology applications forces adaptations in basic machine learning techniques.

  One of the first questions I get about workshops on this topic is - why do we need to talk about machine learning again? There are tons of online courses available already, lots of free material on the web and libraries in Python that are easy enough to get started with. So, why look at this stuff once more? Why not just point us to the best existing resources and let us get on with it?   And the answer is - yes, there are lots of excellent resources (free and paid) on machine learning and yes, we’ll have a list of those resources available for additional reference. But, and this is a big but - many of these resources are targeted to problems faced in the high-tech sector, where the data and types of problems are very different. When we’re solving problems in clean technology, the kind of data we have and the questions we’re faced with are often quite different. That means that machine learning algorithms have to be adapted to work in our sector - and the way they get adapted is a fu

Go wide or go deep? Data and models in clean technology

  When faced with a question about agriculture, water, energy, air or another clean technology system, how do you decide to model it? Do you dive down deep into the subject matter and try and figure out what would work? Or do you go wide, look at the interactions between different systems and see how different types of data and models can be combined? Or do you do a mix of both?     Like many other challenges in the data science and clean technology fields, it really depends on the question you’re trying to answer - and the data that are available. If the question you’re trying to answer has a relatively well defined process and sufficient data - then it makes sense to start by diving deep into the subject and looking at different processes and interactions within a relatively narrow field. For example, let’s say that we’re trying to understand the chemical interactions in a water treatment plant process and if there’s a problem with how effectively the treatment process removes a cert

Startups, Funding and Disruption In The Wastewater Sector

  Today, we’ll conclude our series on data science in the wastewater sector with a look at the market size and some of the startups that are disrupting the sector.   The global market for wastewater treatment was $48 billion in 2019 and is expected to grow to $65 billion by 2023, an annualized growth rate of about 6%.   This includes both municipal wastewater and wastewater from industrial plants such as oil and gas, paper, chemical manufacturing, food and mining. The market consists of engineering design and construction, operations, maintenance and process control of wastewater infrastructure, including sewer pipes and treatment plants.     While wastewater treatment is necessary in all countries, the size of the market by country is typically dependent on the regulations and environmental requirements. Europe and North America have the largest municipal wastewater treatment markets, but demand is rapidly growing in China, India and other developing countries. Some of the largest com

How Do Wastewater, Origami, Covid-19 and Remote Sensing Fit Together?

  When you hear the words “remote sensing”, what do you think about? Drones taking pictures of streets? Spy satellites?     The chances are that if you’re in the clean technology field, you’re thinking about land use and land cover, mapping crop productivity, estimating water accessibility, monitoring air pollution - all very typical cases where data from satellites, drones, UAVs and cameras are used to observe environmental conditions and make predictions.   But, what about wastewater?   Now wastewater is typically the poor cousin of the water sector - we all need it, but we’d much rather not think about it at all! But it’s really important and as we’ve seen recently, can be used for more than just waste disposal.   Right now, cities and countries around the world are monitoring wastewater to detect the spread of Covid-19.   So far, sampling methods have focused on collecting traditional grab samples at the wastewater treatment plant or at other inlets in the sewer system. However, th

Spatial and Temporal, Small and Big: Using wastewater data to monitor the spread of Covid-19

  Have you been monitoring the news about Covid-19 obsessively? And wondering when the economy will open and if it’s safe to go out and resume normal activities?     If you have, you’ve probably been hearing a lot about how testing people to detect the presence of the virus, tracing the spread through contacts and monitoring outbreak clusters, is critical to being able to tell how the pandemic is progressing and if it’s safe to resume normal activities and thus open up the economy. But in many countries, including the United States, testing has been a bottleneck - either there haven’t been enough tests or the infection has spread to such an extent that actually testing people and tracing their contacts simply isn’t feasible anymore.   Further, even in countries like Germany and South Korea that have successfully deployed testing and tracing strategies, it is still expensive to conduct these tests and continue tracing contacts. And until a vaccine and/or some form of treatment is develo