Heuristic Approach to Multivariate Inverse Prediction Problem using Data Reconciliation

Abstract

Some engineering waste management tasks require a complete data sets of its production. However, these sets are not available in most cases. Whether they are not archiving at all or are unavailable for their sensitivity. This article deals with the issue of incomplete datasets at the microregional level. For estimates, the data from higher territorial units and additional information from the micro-region are used. The techniques used in this estimation are illustrated by an example in the field of waste management. In particular, it is an estimate of the amount of waste in individual municipalities. It is based on recorded waste production at district level and total waste management costs, which is available at a municipal level. To estimate the waste production, combinations of linear regression models with random forest models were used, followed by correction by quadratic and nonlinear optimization models. Such task could be seen as a multivariate version of inverse prediction (or calibration) problem, which is not solvable analytically. To test this approach, data for 2010 - 2015 measured in the Czech Republic were used.

Keywords

• Data reconciliation
• Random forest
• Regression
• Waste management
• Optimization
• Multivariate calibration