MapYog

The MapYog project aims to simplify exploratory data analysis of complex spatiotemporal phenomena such as air pollution, urban heat islands, weather conditions, and other variables. The primary challenge lies in the lack of tools that can seamlessly fuse data from diverse sources and types for visual analysis, especially for users without coding skills. This project addresses this gap by building a tool that facilitates exploratory visual analysis. The tool preprocesses and combines data from various resolutions and modalities, harmonizing them to a uniform resolution suitable for neighborhood or building-level visualization. A backend machine learning model will generate fine-scale predictions based on sparsely distributed observations of particulate matter, heat levels, and relevant environmental factors. Additionally, the system will enable the integration of datasets like socio-economic indicators in map-based visualizations, offering a comprehensive understanding of critical urban phenomena.

Data Abstraction

  • Streamlined Data Curation: Supports heterogeneous multi-granular data by abstracting datasets into tables/objects, accessible via a backend API.
  • Flexible Data Handling: Accommodates various data types (actual, predicted, simulated) and attributes (source type, metric, span, granularity).

Decoupled Architecture

  • Dataset-Driven Communication: Uses dataset abstraction for consistent data management across various sources and types.
  • API-Driven Microservices: Keeps preprocessing and model training behind APIs, ensuring flexibility and modularity.

Powerful UI Interface

  • Map UI: Built on deck.gl and kepler.gl libraries, supports layer-based visualization of multi-granular and heterogeneous data on maps with robust data analytics capabilities
  • Data UI: Facilitates listing, loading, and curating datasets, including actual, predicted, and simulated data with customizable spatial and temporal granularity.

Data Curation and Integration

Dataset-Driven Data Curation: Handles data collection and model-based predictions with backend job scheduling for integration and aggregation.

Dataset cataloging and viewing: Well organised list of all the available datasets which can be loaded from there.

Advanced Visualization Features

Auto-Granularity Zooming: Uses H3-based spatial indexing for dynamic visualization based on zoom levels.

Temporal Data Visualization: Supports real-time and historical data visualization with interactive pop-ups for area and point-level information.

Data Analytics Capabilities

Powerful Filtering: Includes spatial, spatio-temporal, and layer-based filtering.

Joint Analysis: Supports joint visualization and filtering of multiple layers, and layer blending.

To experience all the above mentioned capabilities live click the button given below.

Dr. Ankit Sharma

Dr. Ankit Sharma is the PI of the MapYog project and is also the founder of YogLabs. He is an accomplished AI and data science expert with a diverse range of academic and industry experiences. He completed his MS and Ph.D. in Computer Science at the University of Minnesota.

Madhur Gupta

Contributions in mapyog include design and implementaion of backend Api's for data dashboard and task schedulars.

Mohd Junaid

Worked on both frontend and backend technologies. Major contributions include working on the MapUI frontend, deck.gl layers, and the backend of the project.

Anuj Nandwana

Major works include setting up tileserver for base maps, handling deployment of frontend and tileserver along with creation Data UI dashboard.

Get in touch