About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Blog Post
Top solutions recognized in Global Challenge Round 2
Get caught up on the innovative AI solutions that took top prizes this Challenge Round
Round 2 of this year’s Call for Code Global Challenge ran from 1 May - 9 June. With submissions aimed at solving issues of global sustainability with IBM AI coming in from around the world, the following projects took home prizes for this round. At the end of the year, winners from all challenge rounds will compete for grand prizes.
Battery Spotter
Winning developer team: United Kingdom and Ireland region
Participant(s) location: United Kingdom
While batteries can provide cleaner energy, they can also create massive waste when they are no longer usable. Many countries have battery recycling options, but not all individuals have access or know how to dispose of batteries correctly. When used batteries are improperly discarded, they can leak toxic chemicals and heavy metals, or cause fires, posing significant environmental risks. Workers at processing facilities may not always spot batteries that have been incorrectly thrown away amongst other waste and recycled materials. The Battery Spotter solution uses machine learning and computer vision to alert workers in real time to the presence of batteries they might otherwise miss. By helping workers remove and properly dispose of batteries before they are crushed and processed with other waste, the solution can reduce costly and dangerous facility fires and reduce the air and soil pollution that improperly processed batteries can cause.
Key services used:
IBM Cloud Object Storage
Watson Machine Learning
TEAM STEM
Winning developer team: Middle East and Africa region
Participant(s) location: Nigeria
Improper waste sorting can have many negative effects on the environment and sustainable practices, from increased unnecessary waste in landfills, to increased costs and hazards for waste collectors and the community, and reduced opportunities for recycling and reuse of materials. TEAM STEM from Nigeria was inspired to address these issues when they saw waste piling up in their local community and knew they needed to act. Their idea was to better connect community members with a local network of trash collectors and recycling companies and incentivize all parties to take action for better real-time waste management. Their mobile app, called Shara, uses watsonx Assistant and provides home users comprehensive guidelines on how to sort different types of waste, educational resources to raise awareness about sustainable practices, and it even incentivizes proper waste sorting, allowing home owners to redeem reward points. The app can also be used on older mobile phones for those who do not have smart phones. Once the waste is properly sorted, users can schedule timely waste pickup from the appropriate option within a network of local waste and recycling collectors. Collectors then get real-time notifications on waste collection requests and details on optimized traffic routes for pickup. Shara allows a local community to connect and collaborate on more streamlined, sustainable waste management practices.
Key services used:
Watsonx Assistant
Traffic AI
Winning university team
University of Michigan
Traffic congestion caused by poor road design contributes to dangerous carbon emissions. A team from the University of Michigan with a passion for sustainability considered that, while advances have been made to reduce the amount of carbon cars emit, there has been less attention placed on reducing the time drivers spend on roads. They also saw a great untapped opportunity to apply AI in the field of civil engineering. Their machine learning solution called Traffic AI uses Watson Studio to simulate traffic flow and analyze various parameters including vehicle flow, congestion patterns, and carbon emission levels. It can provide valuable insights on the most efficient road configuration, signage, and traffic signaling to contractors, consultants, and governments. Through the Traffic AI solution new road designs can be optimized for better traffic flow, and existing roads can be analyzed to determine congestion-relieving strategies. In the future, the team would also like to integrate their solution with autonomous vehicles to help coordinate self-driving car traffic flows.
Key services used:
IBM API Connect
Watson Studio
There are only 2 more rounds in this year's Global Challenge! Register now to access free AI and other tech training and developer resources and submit your project for a chance to win prizes from a total pool of up to $1.4 million USD!