Today is World Water Day, and this year the theme is “Leaving no one behind.” This is a phrase oft-invoked, but it is particularly important when it comes to water because we are currently leaving 900 million people – much of the world’s population – behind when it comes to safe drinking water, and we’re trending in the wrong direction.
The UN predicts that by 2030, the world may face a 40 percent shortfall in available water. The causes? Climate change is making an already precious resource even more scarce, as rainfall becomes increasingly erratic with temperature changes. Demand is spiking, as the global population grows and consumes more water for farming, industry and personal consumption.
It is a daunting challenge, but a solvable one. It will require far greater understanding of the current state of water on the planet – the location, quantity and quality of freshwater reserves – and how (and how much) is currently being used and by whom. Then, we can use this information to drive efficiencies in delivery and consumption, incentivize behavior change on a local and global level and drive even greater innovation.
Water everywhere and not a drop to drink
Solving the water challenge begins with understanding where the most challenged areas are. Organizations like the World Resources Institute (WRI) and The Nature Conservancy are doing a great deal of work on this issue. The Nature Conservancy’s Protecting Water Atlas aims to drive better decision-making by showing the benefits of investments in water. WRI’s Aqueduct Water Risk Atlas shows both current and future conditions of where water-related risks are most severe, helping decision-makers understand and plan for potential changes in water availability due to climate change and economic development. Microsoft uses the WRI tool in both our global real estate portfolio planning and management and our climate resilience assessments, and supports The Nature Conservancy’s coastal resilience toolkit through AI for Earth and Azure credits.
It’s not just measuring risk – it’s about managing it through proactive approaches. This includes effective conservation measures. Water leakage is one area where improvements could make a big difference. In England and Wales alone, nonprofit organization Discover Water estimates that 3,183 million liters of water are leaked each day. That’s equivalent to filling 1,273 Olympic swimming pools per day! This isn’t a U.K. problem, it’s a global problem. The World Bank estimates that on average, 25 to 30 percent of a utility’s water is lost in the network, and in developing countries as much as 45 million cubic meters are said to be lost daily through leaks.
This prompted Powel, a European software solutions provider, to work with Microsoft to create an Internet of Things solution called SmartWater that can provide the ability to discover and react to these leakages early. The solution monitors water flow into a distribution system and in near real time, with the help of machine learning, detects anomalies so action can be taken.
Beyond conservation, some organizations are looking at water replenishment efforts motivated by the data. Microsoft is one of them. Through our early-stage initiative, we are identifying water-stressed areas around the world, the best partners in that region to collaborate with, and are making investments in projects that improve water conditions and alleviate water stress in those areas. That’s why one fall day last year, some Microsoft employees built beaver dams in Washington state. These beaver dam analogs offer water availability and quality benefits and represented our first public investment in this area.
We’re also engaging in collaborative platforms, such as the UN CEO Water Mandate, to identify opportunities to advance collective action to align and amplify the commitments of individual companies to contribute to achieving Sustainable Development Goal 6.
Beyond conservation to transformation
Water is one of the four key issue areas of our AI for Earth program, a $50 million, 5-year commitment to providing AI tools to researchers around the globe working on environmental challenges. More than 230 grantees are doing work, enabled by AI, in more than 60 countries on challenges related to water, as well as agriculture, biodiversity and climate change. Ultimately, these issues are interrelated – it’s difficult to solve any of the challenges in these areas without addressing others. Here are three grantees that are working across those disciplines, with AI, to drive new insights and behaviors, from algae blooms to precision agriculture with an eye toward water availability to predicting events like floods when we have too much water:
Providing early warning of harmful algal bloom outbreaks
For many years, the waters of Lake Atitlán in the Guatemalan highlands were pristine, a landmark for natural beauty and biodiversity. However, in 2009 the lake experienced the first of several harmful algal blooms (HABs) – out-of-control colonies of algae that suck oxygen out of the water and make it potentially toxic to life.
Africa Flores describes that first HAB in Lake Atitlán as a wake-up call for action to preserve its precious biodiversity. But Guatemala has limited resources and means to investigate and better understand the causes and help predict and prevent future outbreaks. Thankfully, Flores’ work as a research scientist at the Earth System Science Center at the University of Alabama in Huntsville allows her to focus on this very issue.
Flores and her team will conduct deep analyses on image datasets from different satellites. Machine learning will help them to identify the variables that could predict future algal blooms. Knowledge on what those triggers are can turn into precise preventative action, not just in the lake in Flores’ home country but also in other freshwater bodies with similar conditions in Central and South America.
Improving agricultural water use efficiency with AI
As climate change disrupts weather patterns, rainfall is becoming more unreliable. Farmers are drilling more wells for center-pivot irrigation – a method where crops are watered with sprinklers rotating around a central source. However, this approach can lead to lowered or even drained water tables, salination of coastal aquifers, land subsidence and disruption to ecosystems.
Kelly Caylor, a professor of ecohydrology at the University of California, Santa Barbara, is investigating how much water is being used from these groundwater sources. He is developing a web tool that uses machine learning to identify active crop fields in satellite imagery and geospatial analysis tools to monitor how crops change over time. Knowing where the crops are growing and for how long, and then correlating that to weather data, the system can also infer how much water is being used.
With a better understanding of how much groundwater is used by center-pivot irrigation will come opportunities to develop more optimal and efficient practices, as well as policies for better water stewardship. With the online map and tools, farmers, water resource managers, policymakers and the public will be better able to make agriculture more land and water efficient.
Improving long-range forecasts for flood prediction
Climate change disruption to weather patterns sometimes means drought and sometimes means flooding. Already, a United Nations study has shown an increase in weather-related disasters since 1995, with floods accounting for nearly half. Climate change projections suggest that the frequency and severity of floods will increase in years to come as temperatures rise. And flooding threatens the most people in some of the countries least able to predict or prevent the devastation.
To make these regions more resilient, long-range forecasts for precipitation and flooding risk must be improved. Existing weather forecast models have been shown to routinely underestimate precipitation even the day before, and neither amount nor location can be predicted accurately five days in advance. But professors Wei Ding and Shafiqul Islam are leading a small team to develop machine learning models with the goal of accurately predicting floods up to 15 days in advance.
The team’s approach is to process enormous historical weather data sets and look for patterns that precede flooding. With this analysis, they plan to build a new forecasting model that can give early flood warnings to vulnerable populations around the world. More accurate and timely predictions will help reduce the overall impact of these disasters.
Transformations don’t have to be fueled by AI to make a difference. Microsoft is also making it easy for you to get engaged – just watch some Minecraft! Our team has been hard at work at the “Village and Pillage” update, which includes a redesign of water wells. This weekend, we’re supporting the nonprofit Charity: Water effort to bring clean water to people around the world through their “Weekend for Water.” All you have to do is tune in to livestreams of Minecraft players – you can make donations, the streamers will be giving away Minecoins, and the money raised will help dig wells to provide clean water around the globe.
So this World Water Day, I encourage you to take action, and encourage your friends, neighbors, employers and government officials to take action as well. It will take all of us to ensure no one is left behind, and that work should begin today.
Tags: AI for Earth, Environmental Sustainability