Transformer Versus LSTM
A Comparison of Deep Learning Models for Karst Spring Discharge Forecasting
Recent publication
As part of a joint ICC Water & Health project, scientists analysed different AI models for predicting water runoff. They compared the performance of two different applications using three karst sources as examples. Their work will be used for the management of drinking water flows in the future. The ‘Transformer’ application was tested in comparison to a neural network with ‘long short-term memory’ (LSTM). The study and the results obtained have been published in the scientific journal ‘Water Resources Research’.
Pölz, A, Blaschke, AP, Komma, J, Farnleitner, AH & Derx, J 2024, 'Transformer Versus LSTM: A Comparison of Deep Learning Models for Karst Spring Discharge Forecasting', Water Resources Research, vol. 60, no. 4, e2022WR032602. https://doi.org/10.1029/2022WR032602
Univ.-Prof. PD Dr. Andreas Farnleitner MSc
Head of
Division of Water Quality and Health
