Predicting organic acid concentration from UV/vis spectrometry measurements - A comparison of machine learning techniques

Christian Wolf*, Daniel Gaida, André Stuhlsatz, Thomas Ludwig, Seán McLoone, Michael Bongards

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)


The concentration of organic acids in anaerobic digesters is one of the most critical parameters for monitoring and advanced control of anaerobic digestion processes. Thus, a reliable online-measurement system is absolutely necessary. A novel approach to obtaining these measurements indirectly and online using UV/vis spectroscopic probes, in conjunction with powerful pattern recognition methods, is presented in this paper. An UV/vis spectroscopic probe from S::CAN is used in combination with a custom-built dilution system to monitor the absorption of fully fermented sludge at a spectrum from 200 to 750 nm. Advanced pattern recognition methods are then used to map the non-linear relationship between measured absorption spectra to laboratory measurements of organic acid concentrations. Linear discriminant analysis, generalized discriminant analysis (GerDA), support vector machines (SVM), relevance vector machines, random forest and neural networks are investigated for this purpose and their performance compared. To validate the approach, online measurements have been taken at a full-scale 1.3-MW industrial biogas plant. Results show that whereas some of the methods considered do not yield satisfactory results, accurate prediction of organic acid concentration ranges can be obtained with both GerDA and SVM-based classifiers, with classification rates in excess of 87% achieved on test data.
Original languageEnglish
Pages (from-to)5-15
JournalTransactions of the Institute of Measurement and Control
Issue number1
Publication statusPublished - Feb 2013


  • Anaerobic digestion
  • classification
  • feature extraction
  • GerDA
  • LDA
  • neural networks
  • online measurement
  • organic acids
  • random forest
  • RVM
  • SVM
  • UV/vis spectroscopy

ASJC Scopus subject areas

  • Instrumentation


Dive into the research topics of 'Predicting organic acid concentration from UV/vis spectrometry measurements - A comparison of machine learning techniques'. Together they form a unique fingerprint.

Cite this