Human neuroscience research remains largely preoccupied with mapping distinct brain areas to complex psychological processes and features of mental health disorders. While this reductionist and localizationist perspective has resulted in a number of substantive contributions to the field, it has long been viewed as only a piece of the puzzle. Emerging evidence now empirically demonstrates how a historical reliance on localizationist techniques may underlie recent challenges to reproducibility and translation in human neuroscience. To advance discovery, we must collectively think more seriously about complex systems and machine learning approaches that better capture the multidimensional, dynamic, and interacting nature of the brain. Moreover, we must begin to contend with how to best integrate complementary modalities beyond the brain to better understand complex mental processes.