<![CDATA[The rapid growth of experimental and computational data in chemical sciences has created new opportunities and challenges for scientific discovery. Traditional hypothesis-driven approaches often struggle to efficiently explore complex chemical spaces characterized by high dimensionality, uncertainty, and resource constraints. Data-driven discovery, supported by artificial intelligence, offers a transformative paradigm by enabling the integration of experimental observations and computational insights into adaptive and scalable research workflows. This study aims to examine how artificial intelligence can be systematically integrated with experimental and computational chemistry to enhance discovery efficiency, predictive accuracy, and scientific interpretability. A mixed-methods research design was employed, combining curated experimental datasets, computational chemistry simulations, and machine learning models within an iterative feedback framework. Quantitative performance analysis and qualitative case studies were used to evaluate model accuracy, robustness, and practical utility. The results demonstrate that integrated AI models significantly outperform single-source approaches, showing lower prediction errors, improved generalization, and stronger alignment with chemical theory. Case-based evidence further indicates reductions in experimental trials and computational screening costs. The study concludes that data-driven discovery frameworks that tightly integrate artificial intelligence with experimental and computational chemistry represent a robust and sustainable approach for accelerating chemical innovation, supporting more informed decision-making, and advancing next-generation research methodologies in chemical sciences.]]>
