European Physical Journal C: Particles and Fields (Jan 2023)
Identifying hadronic molecular states with a neural network
Abstract
Abstract Neural networks are trained to judge whether or not an exotic state is a hadronic molecule of a given channel according its line-shapes. This method performs well in both trainings and validation tests. As applications, it is applied to study X(3872), X(4260) and $$Z_c(3900)$$ Z c ( 3900 ) . The results show that $$Z_c(3900)$$ Z c ( 3900 ) should be regarded as a $${\bar{D}}^* D$$ D ¯ ∗ D molecular state but X(3872) not. As for X(4260), it can not be a molecular state of $$\chi _{c0}\omega $$ χ c 0 ω . Some discussions on $$X_1(2900)$$ X 1 ( 2900 ) are also provided.