Machine learning techniques for cross-section measurements for the vector-boson-fusion production of the Higgs boson in the $H\rightarrow WW^\ast\rightarrow e\nu\mu\nu$ decay channel with the ATLAS detector.

This talk reports on the measurements of the fiducial and differential production cross section of Higgs bosons with an electron, a muon, and two energetic neutrinos from the decay of W bosons in the final state. The understanding of the fundamental properties of the Higgs boson is one of the main goals of the physics programme of the Large Hadron Collider. The analysis of 139 fb$^{-1}$ of proton–proton collision data at a centre-of-mass energy of $\sqrt(s)$ = 13 TeV recorded by the ATLAS experiment unlocks the study of the Higgs boson’s properties with unprecedented precision. While the first differential and fiducial production cross section measurements had been reported in the di-photon and four-lepton final states, the exploration of secondary production mechanisms in extreme kinematic regions has been heavily anticipated. Cutting-edge machine-learning-based methodologies are exploited for maximising the signal sensitivity while minimising the model-dependency of the results. The results are compared with state-of-the-art theoretical predictions. Furthermore, the measurements are used to constrain the presence of new phenomena in the framework of Effective Field Theories.