Uncovering The Secret Masks Behind Algae Growth In The South-to-north Water

A cross-national team of researchers from China, Germany and The Netherlands developed a deep learning-based Transformer model, Bloomformer-1, designed for end-to-end identification of algal growth driving factors. Bloomformer-1 was compared to four widely used traditional machine learning models and demonstrated superior performance in terms of R2 and RMSE when tested on the Middle Route of the South-to-North Water Diversion Project in China. The development of Bloomformer-1 aims to create a win-win situation in terms of interpretability and performance, enabling the driving factors of algal growth to be identified transparently and accurately.