An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

The hemispherical temperature (HT) is the most important indicator representing ash fusion temperatures (AFTs) in the Polish industry to assess the suitability of coal for combustion as well as gasification purposes. It is important, for safe operation and energy saving, to know or to be able to pre...

Full description

Bibliographic Details
Main Authors:	Maciej Rzychoń, Alina Żogała, Leokadia Róg
Format:	Article
Language:	English
Published:	MDPI AG 2020-05-01
Series:	Minerals
Subjects:	ash fusion temperature XGBoost feature importance partial dependence plots chemical ash composition
Online Access:	https://www.mdpi.com/2075-163X/10/6/487

id	doaj-4e8898360a44426db8bbd327f60d2fba
record_format	Article
spelling	doaj-4e8898360a44426db8bbd327f60d2fba2020-11-25T02:48:59ZengMDPI AGMinerals2075-163X2020-05-011048748710.3390/min10060487An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion TemperaturesMaciej Rzychoń0Alina Żogała1Leokadia Róg2Department of Acoustics, Electronics and IT Solutions, Central Mining Institute, Plac Gwarków 1, 40-166 Katowice, PolandDepartment of Acoustics, Electronics and IT Solutions, Central Mining Institute, Plac Gwarków 1, 40-166 Katowice, PolandDepartment of Solid Fuel Quality Assessment, Central Mining Institute, Plac Gwarków 1, 40-166 Katowice, PolandThe hemispherical temperature (HT) is the most important indicator representing ash fusion temperatures (AFTs) in the Polish industry to assess the suitability of coal for combustion as well as gasification purposes. It is important, for safe operation and energy saving, to know or to be able to predict value of this parameter. In this study a non-linear model predicting the HT value, based on ash oxides content for 360 coal samples from the Upper Silesian Coal Basin, was developed. The proposed model was established using the machine learning method—extreme gradient boosting (XGBoost) regressor. An important feature of models based on the XGBoost algorithm is the ability to determine the impact of individual input parameters on the predicted value using the feature importance (FI) technique. This method allowed the determination of ash oxides having the greatest impact on the projected HT. Then, the partial dependence plots (PDP) technique was used to visualize the effect of individual oxides on the predicted value. The results indicate that proposed model could estimate value of HT with high accuracy. The coefficient of determination (R<sup>2</sup>) of the prediction has reached satisfactory value of 0.88.https://www.mdpi.com/2075-163X/10/6/487ash fusion temperatureXGBoostfeature importancepartial dependence plotschemical ash composition
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Maciej Rzychoń Alina Żogała Leokadia Róg
spellingShingle	Maciej Rzychoń Alina Żogała Leokadia Róg An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures Minerals ash fusion temperature XGBoost feature importance partial dependence plots chemical ash composition
author_facet	Maciej Rzychoń Alina Żogała Leokadia Róg
author_sort	Maciej Rzychoń
title	An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures
title_short	An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures
title_full	An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures
title_fullStr	An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures
title_full_unstemmed	An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures
title_sort	interpretable extreme gradient boosting model to predict ash fusion temperatures
publisher	MDPI AG
series	Minerals
issn	2075-163X
publishDate	2020-05-01
description	The hemispherical temperature (HT) is the most important indicator representing ash fusion temperatures (AFTs) in the Polish industry to assess the suitability of coal for combustion as well as gasification purposes. It is important, for safe operation and energy saving, to know or to be able to predict value of this parameter. In this study a non-linear model predicting the HT value, based on ash oxides content for 360 coal samples from the Upper Silesian Coal Basin, was developed. The proposed model was established using the machine learning method—extreme gradient boosting (XGBoost) regressor. An important feature of models based on the XGBoost algorithm is the ability to determine the impact of individual input parameters on the predicted value using the feature importance (FI) technique. This method allowed the determination of ash oxides having the greatest impact on the projected HT. Then, the partial dependence plots (PDP) technique was used to visualize the effect of individual oxides on the predicted value. The results indicate that proposed model could estimate value of HT with high accuracy. The coefficient of determination (R<sup>2</sup>) of the prediction has reached satisfactory value of 0.88.
topic	ash fusion temperature XGBoost feature importance partial dependence plots chemical ash composition
url	https://www.mdpi.com/2075-163X/10/6/487
work_keys_str_mv	AT maciejrzychon aninterpretableextremegradientboostingmodeltopredictashfusiontemperatures AT alinazogała aninterpretableextremegradientboostingmodeltopredictashfusiontemperatures AT leokadiarog aninterpretableextremegradientboostingmodeltopredictashfusiontemperatures AT maciejrzychon interpretableextremegradientboostingmodeltopredictashfusiontemperatures AT alinazogała interpretableextremegradientboostingmodeltopredictashfusiontemperatures AT leokadiarog interpretableextremegradientboostingmodeltopredictashfusiontemperatures
_version_	1724745455034695680

An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

Similar Items