AI for Earth Lab

Use remote sensing and AI to protect the Earth and fight against climate change




Challenges per year


AI for EARTH Engineers


hrs of Engineering

Multiplying Engineering Skills and Effort for Biodiversity

Combining the powers of remote sensing, GIS and AI to protect life on Earth

The AI for Earth Lab pools resources and knowledge of our partners, together with the work of our AI for Good Engineers to fight climate change and preserve life on Earth. We use remote sensing and GIS methods and apply machine learning to solve real life problems of our home planet and our life on it. AI for Earth Lab generates a constant stream of AI for Good Challenges for the FruitPunch AI community of data scientists and AI engineers.


The need for climate action and protecting the environment has never been more acute

To fight for the preservation of our planet, we need a better and more timely insight into what’s happening on its surface. Satellites, drones and other remote sensing sensors are our eyes in the air detecting, monitoring, and measuring human impact on nature. Thanks to their data we are able to train machine learning models to help detect fires, predict floods, and measure tree growth. 

Remote sensing has an incredibly passionate community of researchers, engineers and aficionados rooting for satellites and drones. They see their immense potential to enable geospatial research and turn it into action. For us, for the climate and for all life on earth.   Just like them, we are in awe of this technology and its impact. That’s why we are bundling our remote sensing knowledge and resources to address the UN Sustainable Development Goals 15: Life on Land and Goal 13: Climate Action.

Left image: Offshore oil spill off the coast of Peru taken by the SkySat satellite. Courtesy of Planet

Right image: Aerial image of water bunds (a landscape restoration technique) in Tanzania from a drone. Courtesy of Justdiggit

UN Sustainable Development Goal 13: Climate Action

Take urgent action to combat climate change and its impacts.









Find out more about Goal 13
Goal 13 infographic
Goal 13 infographic, source:

Fight against climate change by applying AI to geospatial data

Predict events dangerous to life on Earth like floods and wildfires

Protect our waters by early detection of threats like pollution

Monitor the success of carbon capture projects

Preserving habitats essential for life of earth


Remote Sensing

Remote sensing is the process of detecting and monitoring an object or a phenomenon without making physical contact with it. It usually refers to the use of satellite, drone and other sensor technologies to detect and classify objects on Earth. To develop our machine learning models, we use open source and commercial satellite data, drone images and various camera & lidar sensor data collected by our challenge partners.

Remote Sensing


Another part of the geospatial field is the geographic information system (GIS). GIS is a system of databases, software tools, procedures and body of knowledge around location relevant data. We apply these technologies in combination with machine learning to understand the geographic context of data and patterns in our Challenges.


Computer Vision

Using satellites & drones to capture what’s going on is useless if we can’t analyze what’s in those images. That’s why in almost every remote sensing challenge we apply a multitude of computer vision techniques that derive meaningful information from images, videos and other visual inputs. We’ve applied it to open source satellite data, commercial hi-res imagery, cam footage from drones and even hydrological sensors distributed along a french river.

Computer Vision
July 17, 2023

AI against Toxic Clouds

Use Computer Vision to detect toxic clouds emitted by large factories and report the authorities on the sightings
June 26, 2023

AI for Air Quality

Automated detection of atmospheric NO2 and CH4 plumes over Greater Kampala metropolitan area using high-resolution satellite observations from TROPOMI and Deep learning methods
March 10, 2023

AI against Carbon Impact

Classify bank transactions and estimate their carbon impact to help people live more sustainably
August 14, 2022

AI against Oil Spills Challenge

Use drone & satellite imagery to develop a machine learning model to detect oil spills on open seas, in ports and in inland waterways.
July 8, 2022

AI for Trees Challenge

Monitor tree growth on drone and satellite imagery from reforestation projects in Africa. Create an ML model for automated tree detection and segmentation.
June 19, 2022

AI for Earth 2 - Inland Floods Prediction

Combine hydrological sensor data with satellite images to predict flood propagation with machine learning.
June 19, 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.
June 12, 2022

AI for Greener Cities Challenge

Harvest driving video data from urban areas to get 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.
November 15, 2021

AI for Wind Energy Challenge

Extend the lifetime of wind turbine blades by identifying the damage based on ambient vibration data.
September 30, 2021

AI for Coral Reefs Challenge

Automating coral analysis - detecting and classifying coral reef to aid conservation and research of life under water.
August 31, 2021

AI for Earth Challenge

Using European Space Agency Earth observation data to show humanity’s impact on planet Earth.
June 10, 2021

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.

We use satellite, drone and sensor data to get some machine learning done

  • Use GIS to map water levels in forests, highlighting flooding risk areas
  • Create prediction models for floods based on data from hydrological sensors measuring water level, volume and surface speed
  • Build ML models to estimate propagation speed of flood events
  • Develop a model to map rivers & its tributaries based on satellite data
  • Develop a satellite data detection system of human impact sites of -
  • Illegal deforestation
  • Wildfires
  • Coral bleaching
  • Use GIS and multispectral data to identify and detect oil in satellite and drone imagery, apply U-net architectures to generate masks for the oil spills
  • Use semi-supervised learning to try to classify the type of leaked oil
  • Monitor tree coverage and growth from satellite and drone data
SPOTS Robi Beninca launching the flying ranger UAV (unmanned aerial vehicle) & Poacher detection running on the thermal video camera footage on edge hardware of the UAV
Results: Watch and read

From our YouTube channel

How can you participate?

Become a certified AI for Earth Engineer

Individual engineers who collaborate in the AI for Earth Challenges are trained in working with remote sensing, GIS, computer vision and other skills essential for the applied AI projects.

FruitPunch AI for Earth Community

Sign-up at the platform for free and fill your profile. Pick your interests and join corresponding communities. Create a skill tree you’ll be developing with every AI for Good activity.

Start my journey
Upgrade your skills with AI bootcamps & masterclasses

Learn how to apply your acquired AI knowledge in the real world. Join AI for Good challenges and collaborate in teams all over the globe.

Upgrade my skills
AI for Earth Certificate

Every activity adds to your development. You’ll be accredited with badges for specific hard and soft skills and certifications after an accomplished challenge.

Build my skill tree
AI for Earth Skills
Remote Sensing
Geospatial Data
Anomaly Detection
Semantic Segmentation
Data Engineering
Vision Transformers
Deep Learning
ML Pipelines
Hyperspectral data
Object Detection
Supervised Methods
How can you participate?

Become a certified AI for Wildlife Engineer

Individual engineers who collaborate in the AI for Wildlife Challenges are trained in edge computing, computer vision, model pruning and other skills essential for the applied AI  projects.

Join the community

Sign-up at the platform for free and fill your profile. Pick your interests and join corresponding communities. Create a skill tree you’ll be developing with every AI for Good activity.
Start my journey
Start your personalized learning journey

Participate in a challenge

Join our machine learning focused learning events led by experts collaborating with the AI for Good community. Learn with the pros and from one another.
Join the community platform
FruitPunch AI challenge and skilltree

Get certified

Every activity adds to your development. You’ll be accredited with badges for specific hard and soft skills and certifications after an accomplished challenge.
Get certified
Get your badges and certificates
For Organizations
Solve your challenges!

Challenge Partners

Impact organizations and experts applying the results of the AI for Earth Challenges. Do you have a climate change problem that can be solved with AI? Submit your challenge


Contributing Partners

Use their teams, expertise and resources to advance AI for Earth Lab & Challenges. Can your experts or technology contribute to solving an AI for Earth Challenge? Partner up! 👇

Get your community involved!

Community Partners

Use their reach to spread the AI for Good news, advocate for AI for Good Lab & Challenges. Do you have a network we could reach out to with environmental or climate action AI topics? Connect on Linkedin, Twitter or drop us a note 👇

Come on board the AI for Earth Lab!

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.