.png)
July 15, 2024
FruitPunch AI 2.0: Community Driven
The next step in our mission to build a community of 1M people willing & able to solve humanity’s greatest Challenges by 2030.
AI for Good Articles
May 14, 2024
The Bear Necessity of AI in Conservation
The AI for Bears Challenge results which aims to improve the monitoring and identification of bears using advanced computer vision techniques.
AI for Good
AI for Wildlife
Artificial Intelligence
Computer vision
Deep Learning
April 12, 2024
Looking inland to clean up oil spills with AI
Case study of calculating the volume of oil spills with models like SAM and Mask-RCNN to create segmentation masks.
Computer vision
Segmentation
Challenge results
May 13, 2024
AI and Visualisations: A Data Driven All-Rounded Approach for Road Safety
Unveiling accident triggers: how we uncovered patterns and signals through Exploratory Data Analysis and Machine learning from a collision avoidance dataset.
Artificial Intelligence
Deep Learning
Explainable AI
GIS
LLMs
October 18, 2023
Leveraging Large Language Models to make businesses around the world more sustainable
How we managed to build NLP models to classify customer product descriptions to estimate their impact on the environment.
NLP
LLMs
Deep Learning
Challenge results
August 25, 2023
Flying High with AI: Counting Pelican Breeding Pairs in the Danube Delta
Learn how we build computer vision models to detect and classify the pelican population in Romania as well as automate the evaluation of the breeding population based on aerial photographs.
AI for Wildlife
Computer vision
Object detection
Challenge results
October 14, 2022
How to use vehicle sensors to make cities more sustainable
A case study on making cities greener by vegetation monitoring and detecting traffic density; differentiating between heavy vehicles, buses and private transport.
Segmentation
Object detection
Challenge results
October 3, 2022
Can AI detect the risk of heart failure from ECGs?
Electrocardiogram data was subjected to a sweeping array of machine learning and deep learning models. Is it as good a predictor of heart failure risk as blood tests?
Deep Learning
AI for Health
Challenge results
September 21, 2022
The pains of classifying flooded forests in satellite data
A tricky detection use case - from weeks of data pre-processing to training 2 CNNs; and why the answer might be in infrared band data.
AI for Earth
Remote Sensing
GIS
Challenge results
September 6, 2022
How we applied AI to prevent sepsis in preterm babies
A case study on using XGBoost for time series forecasting to predict the onset of sepsis in preterm infants within a 12-hour prediction horizon.
AI for Health
Time Series Forecasting
Explainable AI
Challenge results
August 27, 2022
User-friendly, Wilderness-proof MLOps
Developing a CI/CD pipeline that automatically retrains the existing poacher-detecting model, which can be deployed to the drone with improved performance.
Edge Computing
AI for Wildlife
MLOps
Challenge results
August 29, 2022
AI-powered Wildlife Conservation in Africa
Developing multiple machine learning and hardware pipelines to bring production-ready AI to edge hardware on flying rangers.
Edge Computing
AI for Wildlife
TinyML
Challenge results
August 26, 2022
Autonomous Flight and the Landing of a Fixed-Wing UAV
Developing a model for autonomous landing using a ‘traditional’ technique using GPS beacons a more experimental method of Reinforcement Learning.
Edge Computing
Autonomous
AI for Wildlife
Challenge results
November 24, 2022
Can AI track reforestation projects using drone and satellite data?
We used satellite and drone data to monitor tree coverage of Justdiggit re-greening projects in Tanzania and Kenya to measure the efficiency of carbon capture!
AI for Earth
Remote Sensing
Object detection
Deep Learning
Challenge results
February 1, 2024
Tracking Turtles: How AI helps conservationists to re-identify sea turtles
Our collaboration with Sea Turtle Conservation Bonaire uses cutting-edge AI to match turtle photos with a database, aiding preservation efforts by understanding their migratory patterns.
AI for Good
AI for Wildlife
Artificial Intelligence
Computer vision
Deep Learning
August 28, 2022
Model Optimization and Pruning of Poacher-detecting YOLOv5
Optimizing a YOLOv5 model for NVIDIA Jetson Nano to increase the inference speed and reduce memory footprint, focusing on inference speed not the absolute mAP.
Edge Computing
AI for Wildlife
Challenge results
August 10, 2023
Solving automated wildlife taxonomy with AI
Camera traps are vital for researching European wildlife. FruitPunch developed an AI solution for the European Wildlife Challenge to help analyze the significant data generated.
AI for Wildlife
Computer vision
Deep Learning
MLOps
Object detection
November 20, 2023
From Pixels to Preservation: How AI Gives Rise to a Birdwatching Revolution
FruitPunch AI and SLU collaborated to explore the interface of ecology and AI. The AI for Eagles Challenge aimed to develop a machine-learning pipeline to assess bird behavior, species, and age
AI for Wildlife
Computer vision
Explainable AI
Object detection
Challenge results
September 14, 2022
AI-based early warning system for river floods
Forecasting flash floods with LSTM, ARIMA and Prophet using time series data from hydrological sensors monitoring French rivers.
AI for Earth
Time Series Forecasting
Challenge results
March 23, 2023
Understanding seals with AI
AI for Seals aimed to improve the SealNet facial recognition model for studying and monitoring marine mammals, enhancing the model's accuracy and streamlining data processing and development workflows
AI for Wildlife
Computer vision
Challenge results
February 21, 2024
Saving Marine Ecosystems with Artificial Intelligence
Discover how the AI for Coral Reefs Challenge enhances coral reef monitoring through advanced technology, offering hope for marine ecosystem preservation.
AI for Wildlife
Artificial Intelligence
Challenge results
Computer vision
Deep Learning
July 27, 2023
Listening to the Giants: Protecting Forest Elephants Through Audio Monitoring
How we managed to create a model that process raw audio and detect gunshots and rumbles with high accuracy.
AI for Wildlife
Deep Learning
Edge Computing
Challenge results
February 10, 2023
How we detect oil spills on open sea and support response teams
By using computer vision and segmentation we aim to assist drones of the Rijkswaterstaat response team in a quicker oil clean-up that needs fewer chemicals. See all results 🚀
AI for Earth
GIS
Remote Sensing
Segmentation
Deep Learning