The building and transportation sectors account for approximately 75% of CO2 emissions. Accurate forecasts of future energy usage are an important step towards reaching carbon mitigation commitments for city policymakers. Beyond identifying sources of emission intensity for a region, the forecast mechanism must be capable of compensating for gaps in available data and of accounting for the uncertainties behind the dynamics of an urban system. By considering a range of possible scenarios, the prediction model can identify recurring sources of high energy consumption and fine-tune areas of priority with incoming data. Although there are many studies dedicated to modeling techniques for predicting household building energy consumption, very few focus on household transportation energy consumption using household variables. Buildings connect different networks of transportation and influence transit patterns. Developing a robust and integrated residential, commercial, and transportation energy use model is useful for multiple planning purposes. This is crucial for future urban development; there is a critical need to analyze the integrated impacts of transportation infrastructure and building construction on the environment. Machine learning techniques in artificial intelligence (AI) predictive modeling have become popular in energy prediction due to their ability to capture nonlinear and complex relationships. Nevertheless, developing a comprehensive understanding of the inference mechanisms in AI models and ensuring trust in their predictions is challenging. This is because AI models are mostly of high complexity and low interpretability. There is a need to analyze the insights of energy models to interpret local and global features and to demonstrate how existing bottom-up approaches can augment scenario planning forecasts. This dissertation will address the abovementioned integration needs and interpretability challenges in the following four steps: (1) Examine four machine learning approaches for predicting household transportation energy consumption. These are decision trees, random forest, neural networks, and elastic net regularization analyses. These models will be compared in terms of both accuracy and interpretability. This step aims to determine the best ML application for transportation energy models. (2) Predict residential and commercial building energy demand by generating bottom-up models using datasets commonly available in the United States. (a) The residential model applies machine learning methods to match records in the Residential Energy Consumption Survey (RECS) with Public Use Microdata samples. This produces a synthetic household energy distribution at the neighborhood scale. (b) The commercial building energy model is generated by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Commercial building energy consumption is predicted at the building and household level in order to aggregate it with the residential (step 2a) and transportation models (step 1). (3) Evaluate model transparency and explainability for the residential, commercial, and transportation models produced in steps 1 and 2. The application of Local Interpretable Model-Agnostic Explanation (LIME) and SHAP (SHapley Additive exPlanations) will support advanced machine learning techniques in the transportation and building energy research. (4) Analyze the impact of alternative policy scenarios on urban energy consumption. Sustainability scenarios will be constructed from available projections of demographic and socioeconomic data for Philadelphia County. The goal of this step is to apply urban planning priorities to our models to inform our understanding of their predicted environmental outcomes. This project extends urban energy analysis by developing AI and XAI techniques for the three most energy intensive sectors of urban development. The integrated assessment of the transportation, residential and commercial sectors is critical to assessing and prioritizing urban planning scenarios for sustainable urban growth. These results are essential in decision-making among urban planners and building and transportation engineers.