Database underlying the research for the development of machine learning models for predicting the physicochemical properties of hydrochar

This dataset was developed as part of research aimed at building machine learning models to predict the physicochemical properties of hydrochar produced via hydrothermal carbonization (HTC) of biomass. The study focuses on understanding how various process parameters and feedstock properties influence hydrochar characteristics. Data were collected through experimental HTC processes under controlled laboratory conditions, using a variety of biomass types and process settings. The dataset includes both input variables (such as reaction temperature, residence time, stirring rate, and feedstock composition) and output variables describing the elemental composition and yield of the resulting hydrochar. The data type is quantitative, comprising variables representing chemical and process parameters.

本数据集是为构建机器学习模型以预测生物质经水热碳化（hydrothermal carbonization, HTC）制备的水热炭理化性质相关研究的一部分。本研究旨在厘清各类工艺参数与原料特性对水热炭特性的影响规律。研究团队通过受控实验室条件下的HTC实验流程采集数据，采用了多种生物质原料与工艺设置方案。本数据集涵盖输入变量与输出变量两大类别：输入变量包含反应温度、停留时间、搅拌速率及原料组成等，输出变量则用于表征所得水热炭的元素组成与产率。本数据集为定量型数据，涵盖表征化学参数与工艺参数的各类变量。