Solution Overview & Team Lead Details

Solution name.

Breathe Space by AQAI

Provide a one-line summary of your solution.

At AQAI, we deliver real-time, hyper local air pollution models which measure and detect air pollutants to enable operations that monitor and adjust their ventilation systems. Our tools help you

What specific problem are you trying to solve?

Air pollution costs the planet $8.1 trillion annually, being the leading risk factor in the global burden of diseases. 93% of children’s health globally is directly affected due to the heavy resource requirements for sensor deployment and maintenance. However, Humanitarian organisations lack the availability of local, high-granularity air pollution measurements, leading to uncertainty concerning the level of exposure to harmful particulate matter. When working with UNICEF Program Manager’s, we saw how challenging it was to track progress toward air-pollution strategic monitoring and mitigation goals. Although they are aware of air pollution monitoring stations under different initiatives in the city, they do not know how to extract and analyze the data to best represent the population and evaluate the impact on the community. 

In addition to the impact on health, the changing industrial and transportation emissions sources and natural sources such as wildfires and weather patterns results in wide geographic variations and ambient pollution concentrations, increasing the logistical challenge and measurement cost of air pollution. Measurement challenges increase the difficulty of identifying pollution sources and developing effective solutions. 

For example, data centers consume an estimated 100 billion kilowatt-hours of electricity, a whopping two percent of all electricity use in the US, and 2% of GHG emissions globally. Air pollution poses a pressing threat to the sustainability of a data center due to the corrosion of electronic components, which can directly lead to a mechanical or system failure. Pollutants that are drawn in from the outside through ventilation systems and through doorways that open when employees enter or depart the facility typically cause this corrosion. Although a variety of noxious gases can lead to corrosion, the most common contaminants that infiltrate a data center are sulfur dioxide, hydrogen sulfide and particulate matter, also known as PM.

Elevator pitch

What is your solution?

At AQAI, we deliver real-time, hyper local air pollution models which measure and detect air pollutants to enable operations that monitor and adjust their ventilation systems. Our tools help you optimize air filtration at data centers resulting in lower electricity usage and installation and replacement costs. Data centers consume an estimated 100 billion kilowatt-hours of electricity, a whopping two percent of all electricity use in the US, and 2% of GHG emissions globally, using AQAI technology can result in 3.8 billion in savings in electricity use alone.

Who does your solution serve? In what ways will the solution impact their lives?

Air pollution costs the planet $8.1 trillion annually, being the leading risk factor in the global burden of diseases. 93% of children’s health globally is directly affected due to the heavy resource requirements for sensor deployment and maintenance. We enable UNICEF regional offices, National Governments and academic insitutions to gather data on potential cost and carbon savings from air pollution management. We intend to use this data to onboard large data warehousing firms such as AWS to sustainably manage air filtration in large data warehousing units to scale up. An example of how we serve one of these target populations is as follows: Humanitarian organisations lack the availability of local, high-granularity air pollution measurements, leading to uncertainty concerning the level of exposure to harmful particulate matter. When working with UNICEF Program Manager’s, we saw how challenging it was to track progress toward air-pollution strategic monitoring and mitigation goals. Although they are aware of air pollution monitoring stations under different initiatives in the city, they do not know how to extract and analyze the data to best represent the population and evaluate the impact on the community. We are serving this target user by building open, scrutinizeable models that enable our clients to trust our approach. AQAI’s core end-to-end Machine learning products are on track to be DPG (digitial public good https://digitalpublicgoods.net/standard) allowing us the capability to partner with UN organisations and governments globally.

How are you and your team well-positioned to deliver this solution?

The team’s solution has won the AGU 2022 NASA Grand Challenge (https://dusp-mit-edu.ezproxy.canberra.edu.au/news/christina-last-named-agu-grand-prize-winner-data-visualization)  and the 2022 OpenAI Climate AI Hackathon (https://climatepolicyradar.org/latest/hacking-ai-for-climate-policy). The UNICEF Office of Innovation currently backs us in a pre-seed round (https://www.unicefinnovationfund.org/broadcast/updates/aqai-machine-learning-powered-predictive-model-monitoring-air-quality). 

Yong Yan (Crystal) Liang is a sophomore undergrad at MIT studying electrical engineering and computer science. She is part of the MIT Terrascope community and is passionate about sustainability and entrepreneurship. She is also hoping to concentrate in Urban Studies in the future after taking a class called Crowd Sourced City, where she worked on a team to develop a website to collect data regarding air quality in Philadelphia and educate the citizens there. Crystal has previous experience with software development, having taught some web development classes in the past and interning at Amazon. Crystal hopes to continue utilizing her knowledge in these fields to support her team and make an impact on the world's air quality.​

Christina Last is the CTO of AQAI and is currently earning a Master's in Urban Science at MIT, studying the impact of air pollution exposure through pedestrian modeling. She is both a Fulbright Fellow and a Legatum Fellow, which support her work developing data science tools to measure the impact on climate and air pollution using open geospatial data. She has presented her research to executives at Google, International Governments at COP27, and policy researchers at Harvard. Previously, as a Data Scientist at the UK's Official Institute for AI, she built machine learning algorithms for the Greater London Authority to predict real-time air pollution. Previously at Carnegie Mellon University, Christina developed AI tools alongside former US President Obama's Chief Scientist.  

Prithviraj Pramanik is the CEO of AQAI and is a Ph.D. Candidate and a Fulbright Fellow who has studied cost-effective urban air quality measurement techniques extensively. A serial entrepreneur, he previously co-founded a technology start-up dealing with alternative communication technologies for post-disaster management. This was adjudicated by the Indian government as one of the top ten start-ups in the country that works in the field of disaster management. Mr. Pramanik has worked on one of the dense real-time air quality sensor networks in the US deployed across Chicago.   

What steps have you taken to understand the needs of the population you want to serve?

During the COVID-19 pandemic, I volunteered as a pro-bono data scientist with UNICEF, to understand how, shifting patterns of travel behavior have meant there is a lack of an accurate way to monitor fluctuating air quality levels globally, leading to uncertainty among public health professionals on children’s exposure to air pollutants. I understood from this volunteering how difficult it is for humanitarian organizations, and local partners to monitor air pollution accurately, resulting in insufficient evidence to justify investing in respiratory health improvement projects. I identified a need for humanitarian organizations, governments and insurance providers to monitor air pollution exposure and assess its health impact on populations. Since joining UNICEF’s venture fund as one of their DS/AI cohort of companies, we have solicited advice from over 50 stakeholders including technical and business advisers, and potential users to help us develop our first deployed end-to-end machine learning driven model to predict the impact of air pollution at every location on the planet.

Which aspects of the Challenge does your solution most closely address?

Improving healthcare access and health outcomes; and reducing and ultimately eliminating health disparities (Health)

What is your solution’s stage of development?

Growth: An organization with an established product, service, or business model rolled out in at least one community, which is poised for further growth

In what city, town, or region is your solution team located?

Kolkata, West Bengal, India

Who is the Team Lead for your solution?

Crystal Lliang

More About Your Solution

What makes your solution innovative?

We built AQAI with a mission to help governments and humanitarian organizations reduce the impact of air pollution on the prevalence of acute respiratory diseases in children. Globally, 93% of children live in places where air pollution levels exceed World Health Organization guidelines. Now, with the full backing of UNICEF’s Office for Innovation, AQAI are the first venture to expose the locations where children are exposed to high pollution concentrations to justify investing in air quality improvement and carbon reduction projects.

To do this, AQAI have developed a production-grade, end-to-end machine learning pipeline to predict hyperlocal air pollution concentrations at any location on the planet, using a combination of satellite imagery global air pollution sensor networks. We are using this MVP to onboard our first five customers, consisting of UNICEF regional offices, National Governments and academic insitutions to gather data on potential cost and carbon savings from air pollution management.

What are your impact goals for the next year, and how will you achieve them?

The team’s solution has won the AGU 2022 NASA Grand Challenge (https://dusp-mit-edu.ezproxy.canberra.edu.au/news/christina-last-named-agu-grand-prize-winner-data-visualization)  and the 2022 OpenAI Climate AI Hackathon (https://climatepolicyradar.org/latest/hacking-ai-for-climate-policy ). The UNICEF Office of Innovation currently backs us in a pre-seed round (https://www.unicefinnovationfund.org/broadcast/updates/aqai-machine-learning-powered-predictive-model-monitoring-air-quality ). In the next year we are deploying our AI-based technology in Cairo, Egypt, Mongolia and Belize, to help them monitor progress toward improving respiratory health, COP27 and Vision 2030 sustainability goals. 

In the next year, we intend to use our predictive models to onboard large data warehousing firms such as AWS to sustainably manage air filtration in large data warehousing units. A warehouse, data company or air filter replacement company can monitor air pollution and filter performance using our subscription as a service API, giving hyper local, daily concentrations and associated performance indicators. We take a piece of the savings, which from just 20% improvement in operational efficiency of air filtering could result in $200MM savings. In the process, AQAI are creating a new asset class of green data centers that improve air pollution and optimise operational efficiency.

Describe the core technology that powers your solution.

AQAI is delivering the world's first open-source model measuring air pollution exposure anywhere in the world. We are developing a machine learning solution that helps predict where the highest concentrations of fine particulate matter are (PM2.5 or fine particulate matter is the air pollutant that poses the greatest risk to health globally) to augment accurate but limited air pollution data collected using ground sensors. A user can access air pollution data for 169,101,933 PM2.5 measurements and use our trained machine learning to predict air pollution concentrations for any 1km in 158 countries.

Please select the technologies currently used in your solution:

  • Artificial Intelligence / Machine Learning
  • Big Data
  • GIS and Geospatial Technology
  • Imaging and Sensor Technology

How many people does your solution currently serve, and how many do you plan to serve in the next year? If you haven’t yet launched your solution, tell us how many people you plan to serve in the next year.

Current number of people predicted 1 million PM2.5 predictions globally 

750 million    Children exposed to high air pollution

Current scale of Impact

 3,500 children engaged in reporting air pollution in schools in Belize engaged

What barriers currently exist for you to accomplish your goals in the next year?

ESG Data is a major requirement currently to enable sustainable development. There are several air quality-based data challenges that still need to be addressed. A brarrier to expanding into the ESG certification space is the lack of connections we have in this market. Therefore, we would like to connect further with ESG fund managers/Impact investors to understand the current methodology on how building utility teams handle utilities based on the environmental factors in data centers is critical to reducing the cost in the long run.

Your Team

How many people work on your solution team?

3

How long have you been working on your solution?

1 year

What organizations do you currently partner with, if any? How are you working with them?

UNICEF, The George Institute for Global Health, OpenAQ, NASA

Business Model

What is your business model?

The UNICEF Office of Innovation currently backs with $100,000 of non-dilutive financing (https://www.unicefinnovationfund.org/broadcast/updates/aqai-machine-learning-powered-predictive-model-monitoring-air-quality). We are using this to develop a production-grade, end-to-end machine learning pipeline to predict hyperlocal air pollution concentrations, we are using this MVP to onboard our first 5 customers, consisting of UNICEF regional offices, National Governments and academic insitutions to gather data on potential cost and carbon savings from air pollution management. We intend to use this data to onboard large data warehousing firms such as AWS and energe management firms such as Schenider Electric to sustainably manage air filtration in large data warehousing units to scale up.

A warehouse, data company or air filter replacement company can monitor air pollution and filter performance using our subscription as a service API, giving hyper local, daily concentrations and associated performance indicators. We take a piece of the savings, which from just 20% improvement in operational efficiency of  air filtering could result in $200MM savings. In the process, we are creating a new asset class of green data centers that improve air pollution and optimise operational efficiency. With the success of PaaS and IaaS we see could computing continue to grow, we want to line up transactions now with big development finance institutions, climate funds, commercial banks and leasing companies to invest in companies deploying Green Data Center technology, or in companies directly switching their compute toward these assets.

What is your path to financial sustainability?

AQAI works on an Integrated business model:

  • The UNICEF Office of Innovation currently backs with $100,000 of non-dilutive financing and we have used this to build our initial MVP of an end-to-end machine learning pipeline. This funding has enabled us to develop the technology to be able to demo the tools we have built to start attracting our initial customers. 

  • Through UNICEF Office of Innovation, we are developing a partnership with UNICEF Mongolia and expect to receive bridge funding to continue developing our solution with expected revenue to continue working with them. We are collecting data on the programmes we launch to understand how people use our model, what are the potential use cases to develop bespoke revenue generating features.

  • With the MVP we are now approaching new clients such as health insurers, ESG Funds, and energy management firms, and Oil and Gas, to understand if our API can be integrated within their existing data platforms. We are developing a pricing model that enables us to capture a percentage of the monetary savings generated from the reduction in energy usage dedicated to running smart HVAC and air-exchange systems using real-time air pollution concentrations.

Solution Team

 
    Back
to Top