EarthObservation

The Atlantic Multidecadal Oscillation is a slow-moving climate pattern with outsized influence on river systems. By shaping atmospheric circulation, precipitation, and groundwater recharge over decades, AMO can alter river flow regimes, drought persistence, and flood risk across continental basins.

Hydropower is entering a more demanding phase. For executives, the central issue is no longer whether hydropower can deliver energy but whether hydropower assets can be managed as basin infrastructure that strengthens grid resilience, water security, and downstream system performance.

A new feature brings more context to hydrological forecasts by revealing the data origins behind virtual stations.

Iraq just lived through its driest year since 1933. It also buried people killed by flash floods in the space of a single week. These look like opposite problems. They are the same problem wearing two faces, and it is one Iraq can solve without waiting for a drop of rain.

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.

Water scarcity threatens 45 percent of global GDP by 2050. Forty-one utilities across 24 countries reveal their top struggles: non-revenue water, service reliability, and climate vulnerability. This article exposes the urgent water crisis and why operational decision support-not just data-is the gap utilities desperately need filled.

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.

On 4-5 June 2026, BWI attended Forum by Aerospace Valley 2026 in Biarritz to discuss Earth observation, hydrological forecasting and the future of water intelligence.

BWI’s hydrological model for the La Dordogne catchment at Domme achieves a catchment-area-weighted mean NNSE of 0.88 on the testing dataset (May 2025 – May 2026) — the highest area-weighted score across BWI’s published performance reports to date. Of 27 validated stations, 25 exceed the deployment threshold of NNSE 0.65, and 19 exceed NNSE 0.80. Performance at station level is highly variable however, with a standard deviation of 0.17 and one station recording a minimum NNSE of 0.07 — a localised outlier discussed below.

At GeoField 2026 in Rome, BWI explores how river basin digitization and river flow forecasting can improve irrigation dispatch, strengthen water efficiency, and help basin managers balance agriculture with energy, industry, drinking water, and ecosystem needs.