ORIGINAL ARTICLE Optimization of hydrothermal liquefaction process through machine learning approach: process conditions and oil yield Punniyakotti Varadharajan Gopirajan 1 & Kannappan Panchamoorthy Gopinath 2 & Govindarajan Sivaranjani 2 & Jayaseelan Arun 3 Received: 13 September 2020 /Revised: 5 December 2020 /Accepted: 21 December 2020 /Published online: 3 January 2021 # The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature 2021 Abstract This study involves an artificial intelligence approach in the optimization of hydrothermal liquefaction (HTL) of biomass feedstock. A Decision Support System (DSS) was developed using machine learning algorithms. Dataset from published work and unpublished dataset from the authors’ research team were used in this study. The Pearson correlation matrix was generated for a training dataset of 400. Bio-oil yield showed a high positive correlation of %C, %H of biomass and temperature, and catalysts loading in the HTL process. A high negative correlation was seen among %O, %moisture, and %ash with yield. Weighted ranks were assigned to the influential parameters and predictions were made for optimum HTL process parameters for a testing dataset of 20. To validate the DSS output, laboratory experiments were carried out and the results showed more than 94% accuracy with the predicted data. The machine learning-based optimization method is more suitable for a highly parameter- oriented process like HTL of biomass. Keywords Hydrothermal liquefaction . Biomass . Artificial intelligence . Machine learning . Optimization . Bio-oil 1 Introduction An alternative source of energy attracts attention due to the scarcity of energy resources [1]. Energy sources such as wind energy, solar energy, nuclear energy, geothermal energy, hy- drogen gas, tidal energy, biomass energy, and biofuels were considered non-depleting sustainable energy sources. Various studies were being carried out on these energy sources to find the efficient extraction of energy. Computational models using fuzzy and artificial intelligence approach were applied in wind energy generation [2–5]. Among these energy resources, biomass and biofuels are the instantaneous sources of energy compared with other men- tioned sources [6]. Biomass feedstock comprises purpose- grown crops, residues of crops, wood, algae, fatty acids, edi- ble plant oils, and wastes from sewage, and food [ 7]. Choosing appropriate input feedstock and process conditions from the wide range of source of biomass claims a strong knowledge [8]. The thermo-chemical conversion process was the most pre- ferred common technique to derive valuable products from waste biomass. Hydrothermal process, pyrolysis, and hydro- deoxygenation are the most preferred methods used to pro- duce liquid hydrocarbons from waste. The hydrothermal pro- cess has three classifications based on the desire of product such as hydrothermal liquefaction (HTL), hydrothermal gasi- fication (HTG), and hydrothermal carbonization (HTC) [9]. The HTL process was preferred to convert wet biomass into bio-oil under moderate temperature (200–380 °C), pressure (5–20 MPa), and time (15–60 min). Various wet biomasses like microalgae, wood biomass, agriculture waste, sewage sludge, etc. are converted into bio- oil through the HTL process. Biomass undergoes numerous reactions like hydrolysis, oxidation, reduction, depolymeriza- tion, dehydration, deoxygenation, and repolymerization [10]. * Kannappan Panchamoorthy Gopinath gopinathkp@ssn.edu.in 1 Department of Computer Science and Engineering, Saveetha Engineering College, Saveetha Nagar, Thandalam, Chennai, Tamil Nadu 602 105, India 2 Department of Chemical Engineering, Sri Sivasubramaniya Nadar College of Engineering, Rajiv Gandhi Salai (OMR), Kalavakkam, Chennai, Tamil Nadu 603110, India 3 Centre for Waste Management, International Research Centre, Sathyabama Institute of Science and Technology, Jeppiaar Nagar (OMR), Chennai, Tamil Nadu 600119, India Biomass Conversion and Biorefinery (2023) 13:1213–1222 https://doi.org/10.1007/s13399-020-01233-8