Quantile regression with a metal oxide sensors array for methane prediction over a municipal solid waste treatment plant

Methane leakage is a crucial issue regarding its potential Green House effect. This study developed a quantile regression model for methane estimation over a municipal solid waste treatment plant (MSW) subject to biogas leakages and monitored with MOS gas sensors. Experimental data from 6 MOS gas sensors and a methane FID analyser taken during fourth months have been used for that purpose. The data processing consisted of (i) a drift correction, (ii) the addition of interactions, (iii) a principal component analysis (PCA) to extract new uncorrelated predictors, and (iv) a log transform of the methane data distribution. The forecast ability of the derived field calibrated model, compared with results from PLS regression, indicates well how helpful has been the data processing methods. Moreover, it highlighted, with some caution, the interest in using the quantile regression and interactions for models with MOS gas sensors considering the cross-sensitivity.

Automated summary

The study developed a quantile regression model for methane estimation using MOS gas sensors over a municipal solid waste treatment plant subject to biogas leakages. Data processing involved drift correction, interaction addition, PCA analysis, and log transformation. The field-calibrated model demonstrated the effectiveness of data processing methods and highlighted the caution needed when using models with MOS gas sensors.