Research on the removal of heavy metals (HMs) from contaminated waters, aiming at ensuring the safety of water bodies, has shifted from direct experimental tests to machine learning (ML)-aided investigations. This approach offers advantages such as reduced time and labor as well as deeper insights into HM removal behaviors. Recent advancements in ML-aided HM removal from water present an opportunity to optimize physiochemical processes through data-driven approaches, suggesting that biochar-based HM-removal systems can be successfully modeled and predicted by ML algorithms. This review encompasses various implementations of ML algorithms covering different stages of work including data preparation, ML model building, and postanalysis data interpretation of HM removal from contaminated waters. Several major challenges, including limitations in data availability, data formatting inconsistencies, and data collection inefficiencies, are emphasized in this review. To address these challenges, we advocate for both centralized and decentralized data sharing methodologies to streamline data acquisition, which is urgently needed to accelerate ML-guided strategies for the removal of HMs from contaminated waters. Investigations on ML-based predictive models and model-based feature analyses have been primarily performed for HM removal from contaminated waters; however, this review highlights model-guided practices as a powerful goal-oriented reverse engineering approach, which is beneficial to revealing the underlying relationships between biochar properties and HM removal behaviors. This review also discusses potential solutions, including successful demonstrations at the laboratory scale, to address the major limitations, revolutionizing water treatment strategies and providing valuable insights for future ML-based studies. Furthermore, closed-loop ML-based guidelines for HM removal from contaminated waters are beneficial to achieving UN Sustainable Development Goals 6, 14, and 15.