Prediction of Coal Volatile Matter Content Based on Terahertz Spectroscopy and Random Forest Algorithm
Journal Title: Chinese Journal of Inorganic Analytical Chemistry - Year 2025, Vol 15, Issue 6
Abstract
This study investigate the prediction of volatile content in coal samples using the Random Forest (RF) algorithm,based on Terahertz time-domain spectroscopy (THz-TDS) data from 257 coal samples.The volatile content of each sample was experimentally determined.To optimize feature extraction and reduce data dimensionality,Local Max detection and Principal Component Analysis (PCA) were employed to identify key peaks and transform the spectral data. Three distinct Random Forest regression models were developed and compared:the RF-LM model,which relie solely on Local Max features;the RF-PCA model,which use only PCA features;and the RF-LM+PCA model,which integrate both feature sets. The RF-LM+PCA model exhibited the highest prediction accuracy,achieving a coefficient of determination (R²) of 0.989,a root mean square error (RMSE) of 1.493,and a mean absolute error (MAE) of 0.902. This research introduces a novel approach that combines terahertz spectroscopy with machine learning techniques for coal quality analysis.It provides an innovative and practical strategy for the intelligent coal mining sector,potentially advancing both technology and application in this field.
Authors and Affiliations
Limin WANG, Lijiang ZHU, Jin'ge LIU
Determination of Erbium in Soil and Sediment by Inductively Coupled Plasma Optical Emission Spectrometry with Solid Phase Extraction Based on Novel Carbon-Based Materials
Rare earth elements have important application values in many fields. However,there are certain challenges in the separation and quantitative analysis of rare earth elements,especially erbium ions,from complex environ...
Simultaneous Determination of Selenium and Tellurium in Soil and Sediment by Inductively Coupled Plasma Mass Spectrometry with Isopropanol Sensitization
Selenium and tellurium,being rare and scattered elements in the Earth's crust,coexist with one another. Their accurate determination is of great significance for evaluating geological backgrounds,indicating the distri...
Determination of Ag in Geochemical Samples by Graphite Furnace Atomic Absorption Spectrometry with Triacidic Decomposition-Thiourea Complexing
The determination of Ag content in geochemical samples typically involves treatment by aqua regia decomposition-hydrochloric acid or aqua regia extraction. However,aqua regia fails to completely dissolve the samples,an...
Determination of Two Forms of Iodine in Water by High Performance Liquid Chromatography Inductively Coupled Plasma Mass Spectrometry (HPLC-ICP-MS)
To offer a scientific foundation for the classification of disease areas in the prevention and treatment of iodine deficiency disorders,to implement precise iodine supplementation policies,and to supply accurate and de...
Preparation of Dietary Fiber Modified by Taro Peel and Its NO2- Adsorption Capacity Prediction Based on Algorithm Optimization Extreme Learning Machine
Based on the response surface methodology,all experimental data,including process parameters and NO2- adsorption capacities were collected. Following data preprocessing,suitable input variables (solid-to-liquid ratio...