Structural behavior of pavements is assessed using various destructive and nondestructive tests, albeit they are found to be cost-intensive. There is a need to develop cost-effective structural condition evaluation methods that are scientifically sound so appropriate maintenance interventions can be performed at the right time. The objective of this research study was to develop a Deep Neural Network (DNN)–based approach to predict pavement structural condition using functional, traffic, and climatic characteristics. A DNN was developed to calculate the deflection bowl parameters along with peak surface deflections from roughness, traffic, pavement age, pavement temperature, and climatic conditions. Over 26,000 data points covering various geographic locations were used to establish a global model (R² = 82 % for the test data) to evaluate the structural integrity of asphalt pavement layers. It is envisioned that this study would assist roadway agencies in assessing the overall condition of asphalt pavements synergizing functional and structural characteristics.