Accurate prediction of suspended sediment load (SSL) in rivers is crucial for effective water resource management, ecological conservation, and infrastructure maintenance. Traditional methods, primarily relying on empirical and statistical methods, often fail to address the complex, nonlinear dynamics of sediment transport. Recent advancements in deep learning (DL) offer promising alternatives, leveraging sophisticated algorithms to enhance predictive accuracy and reliability. Although several review articles have been published on machine learning (ML) applications for SSL prediction, none have explicitly focused on deep learning. This chapter focuses on the most recent achievements from 2015 to 2024. Various databases, including Scopus, ScienceDirect, Web of Science, and Google Scholar, were used to identify relevant papers. This chapter begins with an overview of the core ideas of DL. Next, the cutting-edge DL architectures such as artificial neural network (ANN), recurrent neural networks (RNN), long-short-term-memory (LSTM), and gated recurrent unit (GRU) models are discussed. The techniques used for input and hyperparameter optimization play a crucial part in executing DL modeling. Lastly, the challenges in predicting SSL with DL models are discussed, along with suggestions for additional study. This chapter aims to contribute to advancing SSL prediction methodologies, ultimately supporting more precise decision-making in environmental safety and water resource management.