Hyperparameter tuning is crucial in the development of machine learning models. This study introduces the nonlinear shrinking factor and the Cauchy mutation mechanism to improve the Dujiangyan Irrigation System Optimization (DISO), proposing the improved Dujiangyan Irrigation System Optimization algorithm (IDISO) for hyperparameter tuning in machine learning. The optimization capabilities and convergence performance of IDISO were validated on 87 CEC2017 benchmark functions of varying dimensions and nine real-world engineering problems, demonstrating that it significantly outperforms DISO in terms of convergence speed and accuracy, and ranks first in overall performance among the seventeen advanced metaheuristic algorithms being compared. To construct a robust and generalizable prediction model for hydrochar element characteristics, this study utilized IDISO and DISO algorithms to fine-tune the parameters of the XGBoost model. The experimental results show that the IDISO-XGBoost model achieved an average prediction performance of 0.95, which represents a 4% improvement over the DISO-XGBoost model. These results indicate that the IDISO algorithm has significant potential and value in practical applications.
KOH-activated hydrochar (HC) prepared using biomass straw serves as a promising carbon dioxide (CO 2 ) adsorbent. However, numerous factors influence its preparation process, leading to significant variability in the adsorption performance of the resulting products. However, thoroughly understanding and optimizing this process remains challenging. In this study, a response surface method (RSM) and machine learning model were applied to predict the CO 2 adsorption capacity of potato straw active HC and analyze the influence of multiple factors on the CO 2 adsorption capacity. The results showed that the random forest (RF) model had a good predictive effect on the CO 2 adsorption effect of active HC, compared with the RSM model, based on the central composite design experimental dataset and additional experimental data. In addition, the hydrothermal carbonization temperature had the most significant influence on the CO 2 adsorption performance among various preparation factors, based on analysis of the RSM and RF models. Through experimental characterization and analysis, we found that with an increase in hydrothermal carbonization temperature, more biomass components would be decomposed, with the degree of carbonization increasing accordingly, forming a stable aromatic structure. Subsequently, more micropores would be generated following KOH activation, thus increasing the CO 2 adsorption performance of active HC.