Morphological changes in canals are greatly influenced by sediment load dynamics, whose estimation is a challenging task because of the non-linear behavior of the sediment concentration variables. This study aims to compare different techniques including Artificial Intelligence Models (AIM) and empirical equations for estimating sediment load in Upper Chenab Canal based on 10 years of sediment data from 2012 to 2022. The methodology involves utilization of a newly developed empirical equation, the Ackers and White formula and AIM including 20 neural networks with 10 training functions for both Double and Triple Layers, two Artificial Neuro-Fuzzy Inference System (ANFIS), Particle Swarm Optimization, and Ensemble Learning Random Forest models. Sensitivity analysis of sediment concentration variables has also been performed using various scenarios of input combinations in AIM. A state-of-the-art optimization technique has been used to identify the parameters of the empirical equation, and its performance is tested against AIM and the Ackers and White equation. To compare the performance of various models, four types of errors—correlation coefficient (R), T-Test, Analysis of Variance (ANOVA), and Taylor’s Diagram—have been used. The results of the study show successful application of Artificial Intelligence (AI) and empirical equations to capture the non-linear behavior of sediment concentration variables and indicate that, among all models, the ANFIS outperformed in simulating the total sediment load with a high R-value of 0.958. The performance of various models in simulating sediment concentration was assessed, with notable accuracy achieved by models AIM11 and AIM21. Moreover, the newly developed equation performed better (R = 0.92) compared to the Ackers and White formula (R = 0.88). In conclusion, the study provides valuable insights into sediment concentration dynamics in canals, highlighting the effectiveness of AI models and optimization techniques. It is suggested to incorporate other AI techniques and use multiple canals data in modeling for the future.