Speaker
Description
Transverse Momentum Dependent Parton Distribution Functions (TMDPDFs) provide crucial insights into the three-dimensional structure of hadrons and can be extracted from processes involving multiple kinematic scales, including Drell-Yan (DY), Semi-Inclusive Deep Inelastic Scattering (SIDIS), and $e^+e^-$ annihilation. Deep Neural Networks (DNNs) have emerged as powerful tools for information extraction and modeling based on data with multi-dimensional kinematics and offer new possibilities for TMDPDFs extractions. This talk will detail our flavor-dependent extraction of Sivers functions within the $SU(3)_{\text{flavor}}$ framework through fits to SIDIS data and projections to DY kinematics. I will also present preliminary results for unpolarized TMDPDFs.
