[M-IS23] Developments and applications of non-destructive analyses in natural archives

[MIS23-P08] A novel multi-model estimation of phosphorus in coal and its ash using FTIR spectroscopy

*Arya Vinod¹, Anup Krishna Prasad^1,4, Sameeksha Mishra¹, Bitan Purkait¹, Shailayee Mukherjee^1,4, Anubhav Shukla^1,2, Nirasindhu Desinayak³, Bhabesh Chandra Sarkar⁴, Atul Kumar Varma ² (1.Photogeology and Image Processing Laboratory, Department of Applied Geology, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, 826004, India, 2.Coal Geology and Organic Petrology Laboratory, Department of Applied Geology, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, 826004, India, 3.Department of Geology, Ravenshaw University, Cuttack, Odisha, 753003, India, 4.Geocomputational and GIS Laboratory, Department of Applied Geology, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, 826004, India)

Keywords:Coal, Coal ash, FTIR, Phosphorus

Phosphorus is a deleterious element that occurs in all coals in minor or trace amounts. The phosphorus content in coal needs to be assessed to optimize combustion efficiency, and maintenance cost, ensure quality, and minimize environmental impact. Coal ash from power plants was seen as a pollutant earlier but is now used in many industries. The low concentration and complex chemical composition of coal make phosphorus detection in coal and coal ash difficult. In this study, Fourier transform infrared spectroscopy (FTIR) along with machine learning models (piecewise linear regression (PLR), partial least square regression (PLSR), random forest regression (RFR), and support vector regression (SVR)) is used to quantify the phosphorus content in coal and coal ash. For this, the mid-infrared absorption peak intensity levels, of phosphorus-specific functional groups and anionic groups of phosphate minerals at various working concentration ranges of coal and coal ash were utilized. A multi-model approach using the average of the best-performing models (PLR, PLSR, and RFR) resulted in an R² of 0.836, RMSE of 0.735 ppm, RMSE (%) of 34.801, MBE of -0.077 ppm, MBE (%) of 5.499, and MAE of 0.528 ppm in coal samples and R² of 0.803, RMSE of 0.676 ppm, RMSE (%) of 38.050, MBE of -0.118 ppm, MBE (%) of 4.501, and MAE of 0.474 ppm in coal ash samples. FTIR combined with the multi-model approach combining PLR, PLSR, and RFR regression models is a reliable tool for rapid and near-real-time measurement of low levels of phosphorus in coal and its ash.