RIM2D is an existing, highly efficient 2D hydraulic simulation model for fluvial, pluvial, and urban flooding. As part of a strategic partnership, we supported the extension of the research code with a web application and a cloud-based GPU simulation environment, enabling its transition into a market-ready product.
Client/Company/Industry
GFZ Helmholtz Centre for Geosciences
Duration
24 months
Product
Service
Expertise
Software Development
The goal of the project was to make the existing RIM2D simulation model accessible to a broader range of users in a simpler way. For this purpose, a web application was to be developed that simplifies model creation, model control, and the visualization of simulation results while also enabling the use of cloud-based GPU environments. As part of a strategic partnership, the research code was to be further developed toward a market-ready product.
A key challenge was transforming an existing scientific research codebase into a usable web platform for cloud-based GPU simulations. At the same time, geodata processing, map integration, model control, security logic, and backend services had to be brought together within a consistent and maintainable architecture. In addition, the domain-specific requirements of the research context had to be translated into a form suitable for later product use.
Programming Languages
Python, JavaScript/TypeScript
Technologies
Black, DnD Kit, Flask, GDAL, Gunicorn, Material UI, Next.js, OpenLayers, Proj4, React, React Hook Form, REST, SQLAlchemy, TypeScript
Visualization of the flood event in the Ahr Valley at a spatial resolution of 10 meters, simulated accurately within a few minutes.
Client website: www.rim2d.eu
Similar problem?
The result was a web platform for running cloud-based GPU simulations with RIM2D. The solution met the defined requirements and became a core component of the client’s SaaS product. Through the strategic partnership, we actively supported the transfer from research to practice and helped pave the way for RIM2D to move from a scientific context toward market entry.
We developed an Open-Source S3-based data lake solution for the centralized ingestion, categorization, and searchability of data. The goal was to automate and improve manual data management through an integrated architecture with workflow orchestration, data cataloging, and access control.
We developed computer vision and AI components for a wound detection system. The result was a service that segments wound areas in patient images and calculates their size based on reference markers.