ClimAID - Climate Change impact using AI on Diseases
ClimAID is an integrated toolkit for modeling, forecasting, and projecting climate-sensitive diseases such as dengue and malaria using machine learning and climate model ensembles.
-
ClimAID has inbuilt climate data for South Asian countries, namely India, Nepal, Bhutan, Sri Lanka, Myanmar, Afghanistan, Pakistan and Bangladesh.
-
ClimAID support data from other countries through the global mode on the browser interface.
What you can do
- Analyze historical disease patterns
- Integrate climate variables (temperature, rainfall, humidity)
- Automatically detect optimal lag effects using AutoML
- Train hybrid ML models
- Generate CMIP6-based future projections
- Identify outbreak risk under climate change scenarios
- Generate automated policy reports using the integrated C-DSI or local LLM models.
Quick Example using Codes
from climaid.climaid_model import DiseaseModel
dm = DiseaseModel(
district='IND_Mumbai_MAHARASHTRA',
disease_file="dengue_data.xlsx",
disease_name="Dengue"
)
dm.optimize_lags()
dm.train_final_model()
Workflow
ClimAID has two interfaces,
-
ClimAID Browser Interface (For both South Asian + Global countries)
For initialisation through terminal, use
climaid browse
-
ClimAID Wizard Interface (For South Asian countries)
For initialisation through terminal, use
climaid wizard
Documentation
The full documentation is available here: https://sam-as.github.io/ClimAID/
Designed for
- Epidemiologists
- Climate scientists
- Public health analysts
- Data scientists
Dependencies & License
Dependencies
-
Core Requirements
pandas numpy geopandas matplotlib scikit-learn xarray regionmask plotly xgboost optuna
-
Additional Utilities
These packages support extended functionality and will be auto-installed.
requests joblib fastapi uvicorn typer markdown fastparquet python-multipart seaborn openpyxl
-
Optional (LLM Support)
To enable local LLM-based report generation:
pip install climaid[full]
Includes:
ollama
License
Designed by Avik Kumar Sam & Harish C. Phuleria as an open-access software.
-
MIT License Summary
- Free to use, modify, and distribute
- Suitable for research and commercial use
- No warranty is provided
- Attribution is required
-
Full License Text
- See the complete license here: https://github.com/sam-as/ClimAID/blob/main/LICENSE
Release files for climaid 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| climaid-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Release files / climaid-0.1.2-py3-none-any.whl
| Download URL | climaid-0.1.2-py3-none-any.whl |
|---|---|
| Size | 10.7 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
648477e1eaccfe47d959aba7cbf819ebb26d383fdc896266f5c76be6347f73ae
|
|
BLAKE2b-256 checksum How to use checksums |
af49ff7b22a0498e64c28a3c2d9752c54491edd46e0f8595d22bd71eedba4c13
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.6
|