oNe hEalth SusTainabiLity partnership between
EU-AFRICA for food sEcuRity
Fostering One-Health Sustainability through
Advanced Technology
NESTLER is a joint EU-African initiative dedicated to promoting a One-Health sustainable partnership.
This pioneering project integrates interdisciplinary technological advances to holistically monitor the well-being of animals, plants, and humans, building upon the foundations of existing FARM2FORK strategies.
Project Consortium
Key Highlights
-
Advanced Monitoring Platform: The core of NESTLER is a sophisticated platform that ingests and processes large volumes of data from cutting-edge sources. This includes satellite imagery, video streams from Unmanned Aerial Vehicles (UAVs), and IoT devices.
-
AI-Driven Insights: Machine Learning (ML) and Artificial Intelligence (AI) algorithms analyze this data, coupled with Remote Sensing and GIS systems, to extract intuitive insights, conduct large-scale environmental surveillance, and develop predictive models for One-Health sustainability.
-
Circular Economy Research: NESTLER drives research into key areas of the circular economy, focusing on the use of insect protein for farmed animal feed and investigating the sustainable impact of animal waste in crop-based farming.
-
EU-Africa Collaboration: The project establishes a joint task force to evaluate the economic sustainability of these innovative farming practices, supporting the transition from a linear to a circular economy for sustained growth across both continents.
From Multimedia Streams to Anomaly Deciders:
Full-Stack AI Monitoring for Chicken Flocks, Aquaculture,
and Wild Predator Detection
Within the NESTLER project, Rinisoft developed and implemented a set of AI-powered monitoring systems for domestic animals (poultry), aquaculture (fish) and wild animals (predators).
The goal was to enable early detection of risks, improve animal welfare, and support farm operators with reliable, automated insights based on video and audio data.
Resilient Last-Mile Connectivity for Smart Agriculture
In remote agricultural landscapes, limited communication infrastructure often hinders the real-time collection of critical data.
To bridge this gap, the NESTLER project implements a robust "Mesh-in-the-Sky" architecture, utilizing RapidNet mesh topology to ensure reliable last-mile wireless communication. This innovative work was delivered by Rinisoft to enhance data-driven decision-making in smart farming.
Project Results
01.
Deliverables
Deliverable 3.1 - Remote Sensing technologies and multi-modal data aggregation protocols
Deliverable 3.2 - NESTLER implementation of data aggregation protocols and AI algorithms
02.
Datasets
Wild Animal Recognition Video Dataset
This Data set contains videos of four animal classes, namely Foxes, Jackals, Ravens and Vultures, captured at RAKOVO, Silven region, Bulgaria. The dataset also contains videos of 12 classes of wild animals that can be found in Africa. Namely, the 12 classes are Baboons, Buffaloes, Elephant, Giraffes, Gorillas, Hippopotamus, Impala, Lions, Rhinocerus, Topi, Warthog, Zebra, captured at Rwanda and Uganda. The folder “Elephants-Gorillas-Kobs_Detection_Dataset” contains the extracted frames which are accompanied by their respective bounding box annotations making this part of the dataset suitable for detection tasks. The videos were captured in Uganda at different periods of 2025 (January, February, June) using a HD camera (1920×1080) from CTPH.
The dataset contains several videos of poultry while eating, drinking water and moving around into their hen house. The videos were captured using RGB cameras which were fixed and mounted in a way to stand over the poultry.
03.
Publications
Multimodal Neural Network for Detecting and Classifying Deviations in Poultry Behavior
The paper introduces a multimodal neural network for optical and acoustic data analysis, developed under the Horizon 2020 NESTLER project to advance sustainable agriculture. The research establishes the Poultry Quality of Life (PQL) Index, a diagnostic framework for forecasting flock health. By integrating this index into a real-time monitoring system, the solution enables early detection of distress and proactive interventions, minimizing productivity loss while enhancing animal welfare.
Utilisation of Mesh-in-the-Sky and Advanced IoT Sensors in Agriculture, December 2024
Deploying IoT sensors in remote agriculture is difficult due to a lack of cellular or Long-Range (LoRa) infrastructure. The paper proposes 'Mesh-in-the-Sky,' a system using Unmanned Aerial Vehicles (UAVs) as mobile signal nodes to create communication networks in off-grid areas.
This project has received funding from the EU Horizon Europe research and innovation Programme under Grant Agreement No. 101060762