Tests of Autoencoder Compression of Trigger Jets in the ATLAS Experiment

Abstract: Limited data storage capability is a large obstacle for saving data in high energy particle physics. One method of partially circumventing these limitations, is trigger level analysis (TLA) as used by the ATLAS experiment. The efficiency of TLA can be further increased by doing effective data compression. One class of artificial neural networks are called autoencoders, which may be used for data compression. This thesis further tests the use of autoencoders for compression of TLA data, while showing that it may however be difficult to generalize between different datasets. The processing resources needed to compress TLA data in real time is shown to fit well within the computing constraints available, and that the memory usage is predictable. The use of different compression techniques used sequentially, by so called float truncation then followed by autoencoder compression is evaluated. It is shown that autoencoders show that same potential to be used on both uncompressed and float truncated data. Compression artifacts from float truncation, called double quantization, are also explained and analytically predicted.