Spatio-Temporal Malaria Incidence Analysis Pipeline

This visualization displays the workflow for analyzing spatio-temporal malaria incidence data using both statistical and machine learning approaches.

Features

• Interactive Graph: Drag nodes to explore relationships between different analysis components
• Statistical Models: Bayesian, CAR, and Gaussian approaches for parameter estimation
• Machine Learning Models: Random Forest, XGBoost, and CNN/LSTM for pattern learning
• Unified Evaluation: Comprehensive assessment framework considering accuracy, uncertainty, and interpretability

Components

• Input: Spatio-Temporal malaria incidence data
• Processing: Two parallel pipelines (statistical and ML-based)
• Output: Unified evaluation framework combining insights from both approaches

How to Use

The graph is interactive - you can drag nodes around to better understand the flow of data and analysis through different stages of the pipeline.