In our latest Performance Report, we analyze BWI’s discharge forecast model’s performance for the L’Arve – Bonneville catchment.
As climate change amplifies hydrological extremes, such as droughts and floods, regular monitoring of water resources is becoming increasingly important for optimal water resource management.
BWI employs a semi-distributed hydrological model. With the integration of machine learning techniques, it monitors and forecasts river discharges. This blog post delves into a detailed performance evaluation of BWI’s discharge prediction model. We specifically focus on the ‘L’Arve’ river, with its outlet located in Bonneville, in the French alps.
The L’Arve River is a significant tributary of the Rhône River. Originating from the Mont Blanc glaciers, the Arve makes its way through the valleys, giving rise to various streams and waterfalls along its course. The river’s waters provide essential habitat for a wide variety of creatures including aquatic life and an array of plant species.
The catchment area is defined by its rugged terrain, with high peaks, steep cliffs, and lush forests dominating the landscape. The most eye-catching characteristic of this region is the Mont Blanc, one of the highest mountains in the world. The river’s length is 108km, and the basin extends well over 2000 square kilometers. It’s upper course, between the region of Passy and it’s source of origin, has a steepy descent all the way to Argentière and it enters into the Chamonix valley.
BWI utilizes a robust model performance evaluation framework that considers a range of metrics. Some of these include Nash-Sutcliffe model efficiency scores (NSE), normalized NSE (NNSE), Kling-Gupta Efficiency (KGE), and their respective modified and normalized versions. The preferred metric within this framework is NNSE, which ranges between 0 and 1. A higher NNSE score indicates superior model performance. This metric is particularly useful for tracking the model’s performance over time and effectively communicating the results.
At the Bonneville outlet, the model achieves an NNSE of 0.928. This is a score that scientific publications classify as indicative of good model performance (NNSE > 0.65). The optimal parameter sets and the final state of the basin at the end of the training are recorded and utilized to initialize the subsequent training batch.
