Machine Learning–Driven Insights into Sustainability Trends in the United States: Examining Financial and Economic Influences

This research investigates the quantitative associations between gross domestic product (GDP) and GDP squared while integrating energy consumption, financial accessibility (FA), and urbanization, to analyze their joint effects on the load capacity factor (LCF) in the United States using an autoregressive distributive lag model (ARDL) bound testing technique within the load capacity curve (LCC) hypothesis framework. The examination utilizes time series data from 1996 to 2022 to test variable stationarity using several unit root assessments. The results from ARDL demonstrate that economic growth and FA create positive influences on LCF, thus supporting environmental sustainability over longer periods. Moreover, environmental quality becomes worse, as economies grow, energy usage increases, and rapid urbanization occurs during short-term periods. Multiple confirmation tests including fully modified ordinary least squares (FMOLS), dynamic ordinary least squares (DOLS), and canonical cointegrating regression (CCR) techniques together with various diagnostic evaluations enhance the research validity. This study confirms that environmental degradation occurs due to urban expansion alongside temporary economic growth and increased electricity needs based on carbon-intensive fuels which generate pollutants while speeding up world temperature increases. Furthermore, this study utilized the AutoRegressive Integrated Moving Average (ARIMA) method to estimate LCF economic trend between 2023 and 2040. These outcomes emphasize the necessity of exploring the simultaneous relationships between economic advancement, energy usage, and urban growth patterns in environmental governance in the United States.