Effective amendment of cadmium in water and soil before and after aging of nitrogen-doped biochar: Preparation optimization, removal efficiency and mechanism.

Nitrogen-doped biochar (NBC) is a green material for remediating heavy metal pollution, but it undergoes aging under natural conditions, affecting its interaction with heavy metals. The preparation conditions of NBC were optimized using response surface methodology (RSM), and NBC was subjected to five different aging treatments to analyze the removal efficiency of Cd(II) and soil remediation capability before and after aging. The results indicated that NBC achieved optimal performance with a mass ratio of 5:2.43, an immersion time of 10.66 h, and a pyrolysis temperature of 900 °C. Aging diminished NBC's adsorption capacity for Cd(II) but did not change the main removal mechanism of monolayer chemical adsorption. Freeze-thaw cycles (FT), UV aging (L), and composite aging (U) treatments increased the proportion of bioavailable-Cd, and all aging treatments facilitated the conversion of potentially bioavailable-Cd to non-bioavailable-Cd. The application of NBC and five aged NBCs reduced the proportion of bioavailable-Cd in the soil through precipitation and complexation, increasing the proportion of non-bioavailable-Cd. Aging modifies the physicochemical properties of NBC, thus influencing soil characteristics and ultimately diminishing NBC's ability to passivate Cd in the soil. This study provides reference for the long-term application of biochar in heavy metal-contaminated environments.

Multi-output neural network model for predicting biochar yield and composition.

In biomass pyrolysis for biochar production, existing prediction models face computational challenges and limited accuracy. This study curated a comprehensive dataset, revealing pyrolysis parameters' dominance in biochar yield (54.8 % importance). Pyrolysis temperature emerged as pivotal (PCC = -0.75), influencing yield significantly. Artificial Neural Network (ANN) outperformed Random Forest (RF) in testing set predictions (R2 = 0.95, RMSE = 3.6), making it apt for complex multi-output predictions and software development. The trained ANN model, employed in Partial Dependence Analysis, uncovered nonlinear relationships between biomass characteristics and biochar yield. Findings indicated optimization opportunities, correlating low pyrolysis temperatures, elevated nitrogen content, high fixed carbon, and brief residence times with increased biochar yields. A multi-output ANN model demonstrated optimal fit for biochar yield. A user-friendly Graphical User Interface (GUI) for biochar synthesis prediction was developed, exhibiting robust performance with a mere 0.52 % prediction error for biochar yield. This study showcases practical machine learning application in biochar synthesis, offering valuable insights and predictive tools for optimizing biochar production processes.