📣 STARTING SOON 📣
19 June 2022 - 05 September 2022

AI for Earth 2 - Inland Floods Prediction

Combine hydrological sensor data with satellite images to predict flood propagation with machine learning.

50

AI for Good Engineers

8

working groups

10

weeks to MVP

4,000

hours of engineering

Changing the world, one AI for Good Challenge at a time

A flooded forest
📣 starting soon 📣
Challenge
Application Deadline: 19 June 2022

AI for Earth 2 - Forest Health

Detect excess water in European forests endangering the fragile balance of one of the largest woodland ecosystems via open satellite data.
People in a flooded city wearing plastic around their legs to keep themselves dry
📣 starting soon 📣
Challenge
Application deadline: 19 June 2022

AI for Earth 2 - Inland Floods Prediction

Combine hydrological sensor data with satellite images to predict flood propagation with machine learning.
AI for Greener Cities
📣 starting soon 📣
Challenge
Application deadline: 12 June 2022

AI for Greener Cities

Harvest driving video data from urban areas to gain insight into the state of the environment of our cities. Use this data to come up with solutions to improve the sustainability of a city.
AI for Health - Heart Failure Detection
📣 starting soon 📣
Challenge
Application deadline: 25 May 2022

AI for Health: Heart Failure Detection

Developing a machine learning model to predict blood values from electrocardiograms as an indication of heart failure.

Submit an AI for Good Challenge

Do you have a problem that can be solved by applying machine learning technology? We’ll crowdsource an AI solution in 10 weeks.
Submit a challenge

How do crowdsourced AI challenges work

Do you have data and a problem that can be solved by applying machine learning technology? Let us organize a group of up to 50 AI engineers to address the issue and come up with a production-ready AI in 10-weeks time. We’ll use our platform to facilitate a productive exchange of AI expertise.

We’ll work with you to define deliverables for the challenge based on your problems and data available.

Start a challenge
Recruiting the project team

Once we’re ready to go, we recruit the AI for Good Engineer team, the project manager, product owner, scrum master, work group coordinators and a storyteller. An open call for participants is launched via our community and marketing channels. The best AI engineers with skills relevant to your cause are selected from the pool of applicants.

Start a challenge
AI for Good engineers working over 10 weeks to create an MVP solution for a challenge

From kick-off, through mid-term presentation to final presentation in 10 weeks, a group of 50 participants spends 4,000 hours on the project to find a usable solution to the problem. The work group managers present their progress to you on a weekly basis. At the end, the final MVP is implemented on your systems.

Start a challenge
AI for Good participants discussing their challenge results and accreditations

After the final presentation the results are shared with the public and open source communities. Participants are accredited and outcomes are shared within and beyond the AI for Good Community.

Start a challenge

How do crowdsourced AI challenges work

Do you have data and a problem that can be solved by applying machine learning technology? Let us organize a group of up to 50 AI engineers to address the issue and come up with a production-ready AI in 10 weeks time. We’ll use our platform to facilitate a productive exchange of AI expertise.

Challenge definition

We’ll work with you to define deliverables for the challenge based on your problems and data available.
Start a challengeA globe representing FruitPunch AI's global community and challenges

Recruiting the project team

Once we’re ready to go, we recruit the AI for Good Engineer team, the project manager, product owner, scrum master, work group coordinators and a storyteller. An open call for participants is launched via our community and marketing channels. The best AI engineers with skills relevant to your cause are selected from the pool of applicants.
Start a challengeA globe representing FruitPunch AI's global community and challenges

The 10-week crunch

From kick-off, through mid-term presentation to final presentation in 10 weeks, a group of 50 participants spends 4,000 hours on the project to find a usable solution to the problem. The work group managers present their progress to you on a weekly basis. At the end, the final MVP is implemented on your systems.
Start a challengeA globe representing FruitPunch AI's global community and challenges

Evaluation & sharing actionable results

After the final presentation the results are shared with the public and open source communities. Participants are accredited and outcomes are shared within and beyond the AI for Good Community.
Start a challengeA globe representing FruitPunch AI's global community and challenges

Why should you join the AI for Good Community

Robi Beninca

Company
Challenge Participant

I’ve learned how to apply my theoretical AI knowledge to a real-world problem

Yohan Runhaar

Challenge Partner

As a startup we lacked the capacity to develop our AI project. Thanks to the AI for Good community, we were blessed with an enthusiastic team of AI experts that helped us develop a working solution.

Reef Support

Jesse van Kempen

Challenge Partner

We came into contact with the AI for Good Community through their appealing challenge based learning approach. They helped us turning an idea into a solution that is actually applicable!

Tarucca

Kamal Eldin

Challenge Participant

I’m industry oriented and know how difficult it is to make AI work in the real world. Seeing the technology in practical use for a good cause is incredibly rewarding.

AI for Good Engineer

Joppe Massant

Teambuilding & Upskilling Partner

Our team was very energized to take on a project which could have an actual positive impact on the planet!

ML6

Bram Volbeda

Project Manager

FruitPunch AI enabled me to engage with renowned organisations and actually start making a real-world impact. I am incredibly proud of what we were able to achieve together with our team!

AI for Good Engineer

Jayesh Kenaudekar

Challenge Participant

The Challenge gave me a fantastic opportunity to use my AI skills for good to solve a real world problem.

AI for Good Engineer

Micha van den Herik

Ambassador

Applying AI for Good is the key for a more sustainable world.

AI for Good Ambassador

Jenna Hurlow

Chapter Member

FruitPunch AI provides the opportunity to learn fascinating hands on machine learning while also helping the community I care about. Being a part of the SA chapter is so exciting!

FruitPunch AI - South Africa Chapter

Jullieta Millán

Challenge Participant

I learned a lot and had a great time mixing two of my biggest passions - biology and AI for Good.

AI for Good Engineer

Aisha Kala

Challenge Participant

Each challenge provides me with the opportunity to learn & grow as well as apply my mind to solve complex problems, gain confidence in my abilities and interact with incredible people from around the globe.

AI for Good Engineer

Yasemin Yasarol

Project Manager

It was the perfect opportunity to see the real life applications of AI with people who are passionate to make an innovative impact on healthcare!

FruitPunch AI - Eindhoven Chapter

Martijn Beeks

Teambuilding & Upskilling Partner

Participating in the AI for Good Challenges helped our team members acquire new skills and help the green energy transition.

Xomnia

What is needed to start an AI for Good Challenge?

We work with impact organizations to solve their problems. If you have a problem and data, we would love to learn all about it and see if we can help you. The challenge has to meet the AI for Good criteria - address one of the UN 17 Sustainable Development Goals. Apply your challenge below and we'll get in touch.

Start a new challenge
A lady on her phone with the United Nations Sustainable Development goals floating around her

Who can join a challenge?

We are always in need of AI engineers, but the list of essential professions for the success of a challenge is long. We also need challenge-specific domain experts (wind energy, predictive maintenance, remote sensing, etc.), great communicators and storytellers, coordinators and project & product managers. A challenge participant should be available approximately 8-12 hours a week over 10 weeks. Participants are accredited after every challenge.

Join a challenge now
FruitPunch AI community members from different domains joining a challenge

AI for Good Challenges

A flooded forest
📣 starting soon 📣
Challenge
Application Deadline: 19 June 2022

AI for Earth 2 - Forest Health

Detect excess water in European forests endangering the fragile balance of one of the largest woodland ecosystems via open satellite data.
People in a flooded city wearing plastic around their legs to keep themselves dry
📣 starting soon 📣
Challenge
Application deadline: 19 June 2022

AI for Earth 2 - Inland Floods Prediction

Combine hydrological sensor data with satellite images to predict flood propagation with machine learning.
AI for Health - Heart Failure Detection
📣 starting soon 📣
Challenge
Application deadline: 25 May 2022

AI for Health - Heart Failure Detection

Developing a machine learning model to predict blood values from electrocardiograms as an indication of heart failure.
AI for Greener Cities Challenge
📣 starting soon 📣
Challenge
Application Deadline: 12 June 2022

AI for Greener Cities Challenge

Harvest driving video data from urban areas to gain insight into the state of the environment of our cities. Use this data to come up with solutions to improve the sustainability of a city.
An image of elephants bathing with their babies
🔴 IN PROGRESS 🔴
Challenge
Final presentations: 30 May 2022

AI for Wildlife Challenge 3

AI for Wildlife 3 is bringing poacher-detecting ML models into production on a wildlife protection drone. In the third challenge of the AI for Wildlife series we’ll be focusing on the elusive concept of MLOps.
doctor doing a scan of a pregnant ladies stomach
🔴 IN PROGRESS 🔴
Challenge
Final Presentations: 12 May 2022

AI for Health - Preventing Sepsis

Early prediction of the risk of a preterm born baby developing sepsis by extending an existing classification model with more features, exploring more advanced models and developing a new explainable time-series model.
AI for Wildlife Challenge 2
✅ completed ✅
Challenge
Completed

AI for Wildlife Challenge 2

Creating a machine learning model for an on-edge detection of poachers on thermal video feed of a wildlife protection drone.
AI for Wildlife Challenge 1
✅ completed ✅
Challenge
Completed

AI for Wildlife Challenge 1

Using AI to help protect wildlife in South Africa. Developing an edge-ready computer vision model to detect poachers on thermal video streams on a fixed wing drone.
AI for Health - Predicting Deterioration
✅ completed ✅
Challenge
Completed

AI for Health - Predicting Deterioration

Adapting and evaluating the deterioration index (DI) model to better predict the risk of deterioration of patients in the hospital beds.
AI for Health - Hernia Detection
✅ completed ✅
Challenge
Completed

AI for Health - Hernia Detection

Detecting hernia on X-ray images in collaboration with hospital radiologists.
off-shore wind turbine
✅ completed ✅
Challenge
Completed

AI for Wind Energy Challenge

Extend the lifetime of wind turbine blades by identifying the damage based on ambient vibration data.
AI for Earth Challenge
✅ completed ✅
Challenge
Completed

AI for Earth Challenge

Using European Space Agency Earth observation data to show humanity’s impact on planet Earth.
divers swimming next to large coral
✅ completed ✅
Challenge
Completed

AI for Coral Reefs Challenge

Automating coral analysis - detecting and classifying coral reef to aid conservation and research of life under water.
AI for Food Challenge
✅ completed ✅
Challenge
Completed

AI for Food Challenge

Developing high-precision agricultural robots that will increase land yield while reducing resources, with use of digital twins and reinforcement learning.
AI for Health - Covid Detection
✅ completed ✅
Challenge
Completed

AI for Health - Covid Detection

Create an ML model for color correction and image segmentation of coral rImprove the workflow of radiologists by automating lung segmentation in thorax X-rays to detect Covid.
AI against Covid-19 Challenge
✅ completed ✅
Challenge
Completed

AI against Covid-19 Challenge

How can we predict the growth of new infections? How do we know if our measures against COVID-19 are working? What are the implications for how the virus is spreading?