The human brain is an unimaginably complicated system of interconnected neurons that is capable of complex thought, emotion and behavior. Macroscale white matter connections quantified via the structural connectome (SC) act as the backbone for the flow of functional activation, which can be represented via the functional con- nectome (FC). Our group and others have shown that quantifying properties of the brain’s structural and func- tional connectomes and their relationship can inform understanding of brain-behavior associations and disease mechanisms4-9. However, models that describe SC-FC relationships have only achieved moderate agreement with observations and have not been used to fully explore the heritability and cognitive implications of structure- function coupling in adult and developing populations. If we do not accurately understand how the brain’s anat- omy and physiology are linked across the human lifespan, then we will not be able to quantify the impact of disease or pathological developmental trajectories. Our long-term goal is to create computational tools for stud- ying the brain’s structure and function, particularly in the context of disease. The overarching objective of this project is to create a model that accurately {and interpretably} quantifies the coupling between the structural and functional connectomes in both sexes, which will in turn allow us to investigate the heritability and cognitive implications of SC-FC coupling across developing and adult populations. Our central hypothesis is that a {hybrid approach to predicting FC from SC, combining both biophysical modeling and deep learning,} will be more ac- curate than existing techniques. Based on the prior literature and our preliminary data, we hypothesize that SC- FC coupling will vary with sex, be heritable, associated with development, and explain inter-subject variability in cognition. Our hypothesis is supported by preliminary data from our group and others that show SC-FC relation- ships are heritable and vary with sex and cognition in patients7,18. The rationale for this work is that having an accurate model of the SC-FC relationship in healthy populations, which currently does not exist, will further our understanding of the complex relationship between anatomy, physiology, sex, genetics and cognition. We will test the central hypothesis via three specific aims: 1) identify the most accurate model for predicting FC from SC, 2) quantify the heritability of SC-FC coupling and its association with cognitive performance and 3) characterize the SC-FC coupling trajectory and its cognitive implications throughout development. We will use neuroimaging, genetic and cognitive data from the Human Connectome Project, including young adult (~1000 individuals, 22- 37 years) and developing populations (~650 individuals, 5-21 years). The approach is innovative, as it proposes to use model-driven, data-driven and hybrid approaches to model SC-FC relationships and that it p...