EthnoHack

🌿 EthnoHack 2026
Data Hackathon on Ethnopharmacology & Health
2–8 November 2026 · 100% Online · Discord + Devpost
Unlocking traditional knowledge with data, AI, and digital innovation
EthnoHack 2026 is a week-long online hackathon bringing together
data scientists, AI researchers, computer scientists, bioinformaticians, pharmacognocists, botanists, historians, anthropologists, pharmacologists, ecologists, clinicians, and students
to explore how computational methods can unlock the potential of traditional medicine and ethnopharmacology.
Across four challenge tracks, participants will work with open datasets, scientific literature, biodiversity data, chemical information, and digital health technologies to build innovative solutions addressing real-world challenges in:
🌿 Traditional knowledge
Use NLP and AI to extract medicinal knowledge from historical, folklore texts and ethnobotanical studies. Map plant names across eras, identify therapeutic uses, and connect ancient knowledge to modern pharmacology.
🧪 Natural products and drug discovery
Apply machine learning and cheminformatics to identify promising plant-derived compounds for specific disease targets. Build predictive models, knowledge graphs, and screening pipelines.
🌍 Biodiversity and sustainability
Leverage geospatial and ecological datasets to map medicinal plant diversity, identify conservation risks, and develop tools for sustainable harvesting.
🩺 Digital health and phytotherapy
Design apps, decision-support tools

Requirements
What to Build
Build a
working prototype, computational pipeline, model, application, analysis, or digital tool
addressing a challenge within one of the four EthnoHack tracks.
Your project should demonstrate how data, computation, AI, or digital technologies can generate useful insights or capabilities related to ethnopharmacology, natural products, biodiversity, sustainability, or health.
Your project may be:
A web application
A mobile application
An AI/NLP system
A machine-learning model
A knowledge graph
A data-analysis pipeline
A cheminformatics workflow
A geospatial application
A visualisation or dashboard
A decision-support prototype
A research tool
An interactive database
A computational research project
Another digital solution relevant to one of the four tracks
Your project should demonstrate
A clearly defined problem
A computational or data-driven approach
A working prototype or demonstrable result
Evidence supporting your approach
Clear documentation
Potential real-world relevance
Projects do not need to be production-ready. Hackathon prototypes, research prototypes, proof-of-concepts, and experimental systems are welcome.
What to Submit
Each team must submit the following through Devpost by the final submission deadline:
1. Devpost Project Page
Your project page should include:
Project title
Selected challenge track
Short project description
Problem statement
Solution/approach
Technologies used
Data sources
Results or prototype demonstration
Team members
Impact and future development
2. Source Code
Provide a link to a
public GitHub repository
containing:
Source code
Data-processing scripts
Model code/notebooks where applicable
Installation instructions
README
Dataset references and licences
Instructions for reproducing the results where reasonably possible
3. Pitch Video
Submit a
maximum 10-minute video
explaining:
The problem
Your motivation
Your approach
Your technology
Your data
Your results
A demonstration of the project
Potential impact
Future development
4. Slide Deck
Submit a presentation of
maximum 10 slides
.
The slides should communicate the problem, methodology, results, demonstration, and potential impact clearly.
Recommended Project Structure
A strong submission will make it easy for judges to understand:
Problem → Data → Method → Prototype → Results → Impact
Teams should clearly identify assumptions, limitations, uncertainty, and any important data-quality issues.
Responsible Research
Projects should respect:
Dataset licences and attribution requirements
Intellectual property rights
Privacy and personal-data protections
Indigenous and traditional knowledge considerations
Scientific integrity
Appropriate interpretation of computational predictions
Responsible use of AI
Projects must not present unvalidated computational findings as established medical facts.

Judging Criteria
Scientific Relevance
Does the project address a genuine ethnopharmacology or health challenge?
Innovation
Is the approach novel? Does it use data in a creative way?
Technical Implementation
Quality of code, model or tool — reproducibility and documentation
Data Science Quality
Appropriate methods, validation, handling of uncertainty
Feasibility
Is the solution realistic and scalable beyond the hackathon?
Impact
Potential benefit to conservation, sustainability, drug discovery or public health
Presentation
Clarity of the pitch, slides and demo