In our latest Performance Report, we analyze BWI’s discharge forecast model’s performance for the L’Arly – Pont des Mollières 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’Arly’ river, with its outlet located at Pont des Mollières, in the French Alps.
The L’Arly River, flowing elegantly through the towering landscapes of the French Alps, is a picturesque basin known for its natural beauty, diverse ecosystems, and cultural significance for it’s inhabitants. Originating from the synergy of the rivers Aravis and Borne from the Savoie region, the L’Arly flows through the stunning valleys, alpine meadows, and charming villages of Haute-Savoie, eventually joining the Isère River near the town of Albertville. Floods are quite significant in the region, owing to the presence of numerous mountains and it’s abundant water flow.
The gorges of Arly, on the other hand, are known for dangerous landslides and accidents. Moreover, the waterflow into the rivershed is over 1000 mm, which is rather high. The river is 32km long, with a basin area of over 600 square kilometers.
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 Pont des Mollières outlet, the model achieves an NNSE of 0.836. 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.
