Meet Thomas Aghavnian, R&D Engineer at BWI. With a PhD in physics and ten years in data engineering, Thomas works on the REVALTO satellite project – helping turn scientific ideas into usable code. Discover his journey and what drew him to BWI.

Meet Kartik Gera, Lead Data Engineer at BWI. From India to Melbourne to Paris, Kartik brings eight years of data and cloud expertise to building the scalable platforms that keep BWI’s forecasts reliable and accessible. Discover his journey and what drew him to BWI.

BWI release v2.17 brings a new Data Origins Viewer to the portal, an important API update, and a series of improvements to clarity, navigation, and usability. Here’s everything that’s new.

Meet Hugo Tricou, Junior Business Analyst at BWI. Based in Paris with a background in international relations and hydro-diplomacy, Hugo supports BWI’s response to tenders and helps secure the projects that bring hydrological forecasting to institutions worldwide. Discover his journey and what drew him to BWI.

Meet Gavriel Langer, DevOps Engineer Intern at BWI. Based in Paris and specializing in cybersecurity, Gavriel builds and secures the cloud infrastructure behind BWI’s hydrological forecasting platform. Discover his journey and what drew him to BWI.

Meet Mohamed Fadel Thiam, Finance & Accounting Intern at BWI. Based in Paris and currently studying accounting, control and audit, Fadel supports the company’s day-to-day financial activities — from financial reporting and bank reconciliation to treasury operations. Discover his journey and what drew him to BWI.

We’re pleased to welcome Issam El Kadiri, Research & Development Engineer at BWI. With a strong background in data science and applied mathematics, Issam contributes to improving BWI’s hydrological forecasting models and developing new approaches – a key element for delivering reliable river flow forecasts to our clients.

We’re pleased to announce the release of BWI service v2.16.00, bringing meaningful improvements to forecast horizon and data transparency.

BWI’s hydrological model for the La Mayenne and Le Vicoin catchment in western France achieves NNSE 0.75 on the testing dataset (April 2024 – April 2026), consistent with training performance (NNSE 0.76). Across 16 validated stations, 15 exceed the deployment threshold of NNSE 0.65. The model reliably simulates baseflow dynamics and seasonal flow variability on a slow-response, dam-regulated river system where oscillation control and low-flow accuracy are the primary operational challenges.

BWI’s hydrological model for the La Dyle catchment in central Belgium achieves a catchment-area-weighted mean NNSE of 0.76 on the testing dataset (January 2025 – March 2026), with 9 of 10 validated stations exceeding the deployment threshold of NNSE 0.65. The model demonstrates reliable performance across a mixed agricultural and urban catchment with no dam regulation, where seasonal variability and land-use influence on runoff are the primary hydrological challenges.