Deep learning prediction and experimental investigation of specific capacitance of nitrogen-doped porous biochar

• Published in: Bioresource technology 2024-07, Vol.403, p.130865-130865, Article 130865
• Main Authors: Xiaorui, Liu, Haiping, Yang, Yuanjun, Tang, Chao, Ye, Hui, Jin, Peixuan, Xue
• Format: Article
• Language: English
• Subjects: Charcoal - chemistry; Convolutional neural network (CNN); Deep Learning; Electric Capacitance; Electrodes; Nitrogen - chemistry; Nitrogen-doping; Porosity; Porous carbon material; Pyrolysis; Supercapacitor
• ISSN: 0960-8524; 1873-2976
• DOI: 10.1016/j.biortech.2024.130865

•A Convolutional Neural Network model was developed for capacitance prediction.•Weight Analysis Feature Importance was firstly employed for model interpretation.•The most important feature affecting capacitance was specific surface area.•The model exhibited strong generalization ability by experimental validation. N-doped porous biochar is a promising carbon material for supercapacitor electrodes due to its developed pore structure and high chemical activity which greatly affect the capacitive performance. Predicting the capacitance and exploring the most influential factors are of great significance because it can not only avoid the trial-and-error experiments but also provide guidance for the synthesis of biochar with the aim of capacitance enhancement. In this study, a CNN model with ReLU activation function was established using DenseNet architecture for specific capacitance prediction. The importance and impacts of the physiochemical properties of N-doped porous biochar to the capacitance were revealed. With the guidance of the model, N-doped porous biochar samples with high capacitance were synthesized, the data of which were further used for model validation. This study provides not only a deep learning model which can be used in practice for capacitance prediction but also directions for the synthesis of N-doped porous biochar with high capacitive performance.