<p>Emerging contaminants (ECs) like pharmaceuticals, endocrine disruptors, PFAS, microplastics, and antibiotic resistance genes are increasingly detected in waste and wastewater systems. However, their low concentrations, chemical diversity, and transformation during treatment limit reliable monitoring using conventional target-based analytical methods. Wastewater treatment plants, landfill leachates, and sludge processing units act as critical accumulation and redistribution points for these contaminants, highlighting the need for more sensitive and adaptive monitoring approaches. This review examines recent advances in artificial intelligence (AI) for the detection and analysis of ECs in waste and wastewater matrices. The study focuses on the application of machine learning and deep learning techniques integrated with spectroscopic, chromatographic, sensor-based, imaging, and molecular analytical platforms. AI-driven methods are shown to improve signal extraction from complex datasets, enable non-target and suspect screening, and support pattern recognition and anomaly detection in multivariate environmental data. These capabilities enhance detection sensitivity, reduce analytical time, and allow early identification of contamination trends that are often missed by conventional workflows. Despite these advantages, practical implementation remains constrained by limited high-quality datasets, poor model robustness across sites, lack of standardized validation protocols, and challenges related to model interpretability and regulatory acceptance. This study highlights AI as a powerful analytical support tool that can shift monitoring of emerging contaminants from reactive, compound-specific analyses toward proactive, data-driven surveillance, thereby strengthening environmental risk assessment and management in waste and wastewater systems.</p>