Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Cheng, Feng; Belden, Elizabeth R.; Li, Wenjing; Shahabuddin, Muntasir; Paffenroth, Randy C.; Timko, Michael T.

doi:10.1016/j.cej.2022.136013

Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Journal Article · Sat Mar 26 00:00:00 EDT 2022 · Chemical Engineering Journal

DOI:https://doi.org/10.1016/j.cej.2022.136013· OSTI ID:1976927

Cheng, Feng ^[1]; Belden, Elizabeth R. ^[2]; Li, Wenjing ^[2]; Shahabuddin, Muntasir ^[2]; Paffenroth, Randy C. ^[2]; Timko, Michael T. ^[2]

Worcester Polytechnic Institute, MA (United States); OSTI
Worcester Polytechnic Institute, MA (United States)

Hydrothermal liquefaction (HTL) has potential for converting abundant wet organic wastes into renewable fuels. Because HTL consists of a complex reaction network, deterministic, physics-based prediction of its biocrude yield is prohibitively difficult. Data-driven methods provide an alternative to the physics-based approach; however, rigorous testing must be performed to ensure the accuracy of predictions made by data-driven methods. To this end, a data set was assembled consisting of 570 data points appearing in the open literature. The data set was divided into training, validation, and test sub-sets and used for evaluating different machine learning regression approaches to predict biocrude yield. Among the tested algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost) predicted biocrude yields in a test set that had not been used for training with the greatest accuracy, with root mean square errors (RMSE) of 8.34 and 8.57, respectively. Further refinement of the Random Forest model reduced its RMSE to 8.07. In comparison, predictions of a series of literature models resulted in RMSE ranging from 9.16 in the most accurate case to 27.6 in the least accurate; most literature models yielded RMSE values > 10. Using biocrude yield predictions from the most accurate Random Forest model and a probabilistic economic analysis found that the model accuracy is sufficient to prioritize allocation of resources based on projected minimum fuel selling price. In our report the models and analysis represent a major advance in the ability to use readily available data to predict biocrude yields on new feedstocks that have not previously been studied.

View Accepted Manuscript (DOE)

Research Organization:: Worcester Polytechnic Institute, MA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE); Massachusetts Clean Energy Center (MassCEC); National Science Foundation (NSF)

Grant/Contract Number:: EE0008513

OSTI ID:: 1976927

Alternate ID(s):: OSTI ID: 2246954

Journal Information:: Chemical Engineering Journal, Journal Name: Chemical Engineering Journal Journal Issue: P1 Vol. 442; ISSN 1385-8947

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (69)

Renewable hydrocarbon fuels from hydrothermal liquefaction: A techno-economic analysis: Renewable hydrocarbon fuels from hydrothermal liquefaction: A techno-economic analysis Pedersen, Thomas Helmer; Hansen, Nick Høy; Pérez, Oscar Miralles Biofuels, Bioproducts and Biorefining, Vol. 12, Issue 2 https://doi.org/10.1002/bbb.1831	journal	November 2017
Advances in industrial biopharmaceutical batch process monitoring: Machine-learning methods for small data problems Tulsyan, Aditya; Garvin, Christopher; Ündey, Cenk Biotechnology and Bioengineering, Vol. 115, Issue 8 https://doi.org/10.1002/bit.26605	journal	April 2018
A Comparative Technoeconomic Analysis of Algal Thermochemical Conversion Technologies for Diluent Production Kumar, Mayank; Oyedun, Adetoyese Olajire; Kumar, Amit Energy Technology, Vol. 8, Issue 11 https://doi.org/10.1002/ente.201900828	journal	October 2019
Key Concepts in Model Selection: Performance and Generalizability Forster, Malcolm R. Journal of Mathematical Psychology, Vol. 44, Issue 1 https://doi.org/10.1006/jmps.1999.1284	journal	March 2000
Cross-Validation Refaeilzadeh, Payam; Tang, Lei; Liu, Huan Encyclopedia of Database Systems https://doi.org/10.1007/978-0-387-39940-9_565	book	January 2009
Induction of decision trees Quinlan, J. R. Machine Learning, Vol. 1, Issue 1, p. 81-106 https://doi.org/10.1007/BF00116251	journal	March 1986
Support-vector networks Cortes, Corinna; Vapnik, Vladimir Machine Learning, Vol. 20, Issue 3 https://doi.org/10.1007/BF00994018	journal	September 1995
Predictive modelling of the higher heating value in biomass torrefaction for the energy treatment process using machine-learning techniques García Nieto, P. J.; García-Gonzalo, E.; Paredes-Sánchez, J. P. Neural Computing and Applications, Vol. 31, Issue 12 https://doi.org/10.1007/s00521-018-3870-x	journal	November 2018
Modelling and Predictive Study of Hydrothermal Liquefaction: Application to Food Processing Residues Déniel, Maxime; Haarlemmer, Geert; Roubaud, Anne Waste and Biomass Valorization, Vol. 8, Issue 6 https://doi.org/10.1007/s12649-016-9726-7	journal	October 2016
Catalytic conversion of a biomass-derived oil to fuels and chemicals I: Model compound studies and reaction pathways Adjaye, J. D.; Bakhshi, N. N. Biomass and Bioenergy, Vol. 8, Issue 3 https://doi.org/10.1016/0961-9534(95)00018-3	journal	January 1995
Effects of sample size on accuracy of species distribution models Stockwell, David R. B.; Peterson, A. Townsend Ecological Modelling, Vol. 148, Issue 1 https://doi.org/10.1016/S0304-3800(01)00388-X	journal	February 2002
Techno-economic uncertainty quantification of algal-derived biocrude via hydrothermal liquefaction Jiang, Yuan; Jones, Susanne B.; Zhu, Yunhua Algal Research, Vol. 39 https://doi.org/10.1016/j.algal.2019.101450	journal	May 2019
Techno-economic analysis of alternative aqueous phase treatment methods for microalgae hydrothermal liquefaction and biocrude upgrading system Zhu, Yunhua; Jones, Susanne B.; Schmidt, Andrew J. Algal Research, Vol. 39 https://doi.org/10.1016/j.algal.2019.101467	journal	May 2019
Predicting algal biochar yield using eXtreme Gradient Boosting (XGB) algorithm of machine learning methods Pathy, Abhijeet; Meher, Saswat; P., Balasubramanian Algal Research, Vol. 50 https://doi.org/10.1016/j.algal.2020.102006	journal	September 2020
Techno-economic analysis of liquid fuel production from woody biomass via hydrothermal liquefaction (HTL) and upgrading Zhu, Yunhua; Biddy, Mary J.; Jones, Susanne B. Applied Energy, Vol. 129 https://doi.org/10.1016/j.apenergy.2014.03.053	journal	September 2014
Co-liquefaction of swine manure and mixed-culture algal biomass from a wastewater treatment system to produce bio-crude oil Chen, Wan-Ting; Zhang, Yuanhui; Zhang, Jixiang Applied Energy, Vol. 128 https://doi.org/10.1016/j.apenergy.2014.04.068	journal	September 2014
Hydrothermal liquefaction of biomass model components for product yield prediction and reaction pathways exploration Yang, Jie; He, Quan (Sophia); Niu, Haibo Applied Energy, Vol. 228 https://doi.org/10.1016/j.apenergy.2018.06.142	journal	October 2018
Renewable diesel via hydrothermal liquefaction of oleaginous yeast and residual lignin from bioconversion of corn stover Collett, James R.; Billing, Justin M.; Meyer, Pimphan A. Applied Energy, Vol. 233-234 https://doi.org/10.1016/j.apenergy.2018.09.115	journal	January 2019
A review on hydrothermal co-liquefaction of biomass Yang, Jie; (Sophia) He, Quan; Yang, Linxi Applied Energy, Vol. 250 https://doi.org/10.1016/j.apenergy.2019.05.033	journal	September 2019
Fuel properties of hydrochar and pyrochar: Prediction and exploration with machine learning Li, Jie; Pan, Lanjia; Suvarna, Manu Applied Energy, Vol. 269 https://doi.org/10.1016/j.apenergy.2020.115166	journal	July 2020
Handling limited datasets with neural networks in medical applications: A small-data approach Shaikhina, Torgyn; Khovanova, Natalia A. Artificial Intelligence in Medicine, Vol. 75 https://doi.org/10.1016/j.artmed.2016.12.003	journal	January 2017
Statistical and machine learning models in credit scoring: A systematic literature survey Dastile, Xolani; Celik, Turgay; Potsane, Moshe Applied Soft Computing, Vol. 91 https://doi.org/10.1016/j.asoc.2020.106263	journal	June 2020
Techno-economic analysis of transportation fuels from defatted microalgae via hydrothermal liquefaction and hydroprocessing Ou, Longwen; Thilakaratne, Rajeeva; Brown, Robert C. Biomass and Bioenergy, Vol. 72 https://doi.org/10.1016/j.biombioe.2014.11.018	journal	January 2015
Potential yields and properties of oil from the hydrothermal liquefaction of microalgae with different biochemical content Biller, P.; Ross, A. B. Bioresource Technology, Vol. 102, Issue 1 https://doi.org/10.1016/j.biortech.2010.06.028	journal	January 2011
Hydrothermal liquefaction of Litsea cubeba seed to produce bio-oils Wang, Feng; Chang, Zhoufan; Duan, Peigao Bioresource Technology, Vol. 149 https://doi.org/10.1016/j.biortech.2013.09.108	journal	December 2013
Techno-economic and Monte Carlo probabilistic analysis of microalgae biofuel production system Batan, Liaw Y.; Graff, Gregory D.; Bradley, Thomas H. Bioresource Technology, Vol. 219 https://doi.org/10.1016/j.biortech.2016.07.085	journal	November 2016
Effect of hydrothermal liquefaction aqueous phase recycling on bio-crude yields and composition Biller, Patrick; Madsen, René B.; Klemmer, Maika Bioresource Technology, Vol. 220 https://doi.org/10.1016/j.biortech.2016.08.053	journal	November 2016
Modeling the effects of microalga biochemical content on the kinetics and biocrude yields from hydrothermal liquefaction Sheehan, James D.; Savage, Phillip E. Bioresource Technology, Vol. 239 https://doi.org/10.1016/j.biortech.2017.05.013	journal	September 2017
Prediction model of biocrude yield and nitrogen heterocyclic compounds analysis by hydrothermal liquefaction of microalgae with model compounds Sheng, Lili; Wang, Xin; Yang, Xiaoyi Bioresource Technology, Vol. 247 https://doi.org/10.1016/j.biortech.2017.08.011	journal	January 2018
Hydrothermal liquefaction of high- and low-lipid algae: Mass and energy balances Cheng, Feng; Cui, Zheng; Mallick, Kwonit Bioresource Technology, Vol. 258 https://doi.org/10.1016/j.biortech.2018.02.100	journal	June 2018
Correlations between the physicochemical properties of hydrochar and specific components of waste lettuce: Influence of moisture, carbohydrates, proteins and lipids Li, Yang; Liu, Huan; Xiao, Kangxin Bioresource Technology, Vol. 272 https://doi.org/10.1016/j.biortech.2018.10.066	journal	January 2019
Experimental and model enhancement of food waste hydrothermal liquefaction with combined effects of biochemical composition and reaction conditions Aierzhati, Aersi; Stablein, Michael J.; Wu, Niki E. Bioresource Technology, Vol. 284 https://doi.org/10.1016/j.biortech.2019.03.076	journal	July 2019
Techno-economic analysis of microalgae-based liquid fuels production from wastewater via hydrothermal liquefaction and hydroprocessing Ranganathan, Panneerselvam; Savithri, Sivaraman Bioresource Technology, Vol. 284 https://doi.org/10.1016/j.biortech.2019.03.087	journal	July 2019
Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions Zhu, Xinzhe; Li, Yinan; Wang, Xiaonan Bioresource Technology, Vol. 288 https://doi.org/10.1016/j.biortech.2019.121527	journal	September 2019
Interactive effects of carbohydrate, lipid, protein composition and carbon/nitrogen ratio on biogas production of different food wastes Xue, Shengrong; Wang, Yanbo; Lyu, Xingang Bioresource Technology, Vol. 312 https://doi.org/10.1016/j.biortech.2020.123566	journal	September 2020
Machine learning prediction of biocrude yields and higher heating values from hydrothermal liquefaction of wet biomass and wastes Katongtung, Tossapon; Onsree, Thossaporn; Tippayawong, Nakorn Bioresource Technology, Vol. 344 https://doi.org/10.1016/j.biortech.2021.126278	journal	January 2022
A molecular, elemental, and multiphase kinetic model for the hydrothermal liquefaction of microalgae Hietala, David C.; Savage, Phillip E. Chemical Engineering Journal, Vol. 407 https://doi.org/10.1016/j.cej.2020.127007	journal	March 2021
Effects of various solvents on the liquefaction of biomass to produce fuels and chemical feedstocks Liu, Zhengang; Zhang, Fu-Shen Energy Conversion and Management, Vol. 49, Issue 12 https://doi.org/10.1016/j.enconman.2008.08.009	journal	December 2008
Is hydrothermal treatment coupled with carbon capture and storage an energy-producing negative emissions technology? Cheng, Fangwei; Porter, Michael D.; Colosi, Lisa M. Energy Conversion and Management, Vol. 203 https://doi.org/10.1016/j.enconman.2019.112252	journal	January 2020
Hydrothermal liquefaction of biomass: A review of subcritical water technologies Toor, Saqib Sohail; Rosendahl, Lasse; Rudolf, Andreas Energy, Vol. 36, Issue 5, p. 2328-2342 https://doi.org/10.1016/j.energy.2011.03.013	journal	May 2011
Techno-economic assessment of transportation biofuels from hydrothermal liquefaction of forest residues in British Columbia Nie, Yuhao; Bi, Xiaotao T. Energy, Vol. 153 https://doi.org/10.1016/j.energy.2018.04.057	journal	June 2018
Hydrothermal liquefaction of fresh lemon-peel and Spirulina platensis blending -operation parameter and biocrude chemistry investigation Zhang, Bo; Chen, Jixiang; Kandasamy, Sabariswaran Energy, Vol. 193 https://doi.org/10.1016/j.energy.2019.116645	journal	February 2020
Techno-economic analysis of biomass fast pyrolysis to transportation fuels Wright, Mark M.; Daugaard, Daren E.; Satrio, Justinus A. Fuel, Vol. 89 https://doi.org/10.1016/j.fuel.2010.07.029	journal	November 2010
Hydrothermal liquefaction of biomass: Influence of temperature and biomass composition on the bio-oil production de Caprariis, Benedetta; De Filippis, Paolo; Petrullo, Antonietta Fuel, Vol. 208 https://doi.org/10.1016/j.fuel.2017.07.054	journal	November 2017
Machine learning prediction of bio-oil characteristics quantitatively relating to biomass compositions and pyrolysis conditions Zhang, Tonghuan; Cao, Danyang; Feng, Xin Fuel, Vol. 312 https://doi.org/10.1016/j.fuel.2021.122812	journal	March 2022
Integration of membrane technology into hydrogen production plants with CO2 capture: An economic performance assessment study Ma, Liang-Chih; Castro-Dominguez, Bernardo; Kazantzis, Nikolaos K. International Journal of Greenhouse Gas Control, Vol. 42 https://doi.org/10.1016/j.ijggc.2015.08.019	journal	November 2015
Co-pyrolysis and co-hydrothermal liquefaction of seaweeds and rice husk: Comparative study towards enhanced biofuel production Hu, Yamin; Wang, Shuang; Li, Jiancheng Journal of Analytical and Applied Pyrolysis, Vol. 129 https://doi.org/10.1016/j.jaap.2017.11.016	journal	January 2018
Synergetic effect and primary reaction network of corn cob and cattle manure in single and mixed hydrothermal liquefaction He, Sirong; Wang, Jinglan; Cheng, Zhanjun Journal of Analytical and Applied Pyrolysis, Vol. 155 https://doi.org/10.1016/j.jaap.2021.105076	journal	May 2021
Machine learning technology in biodiesel research: A review Aghbashlo, Mortaza; Peng, Wanxi; Tabatabaei, Meisam Progress in Energy and Combustion Science, Vol. 85 https://doi.org/10.1016/j.pecs.2021.100904	journal	July 2021
Hydrothermal liquefaction of various biomass and waste feedstocks for biocrude production: A state of the art review Dimitriadis, Athanasios; Bezergianni, Stella Renewable and Sustainable Energy Reviews, Vol. 68 https://doi.org/10.1016/j.rser.2016.09.120	journal	February 2017
A cost assessment study for a large-scale water gas shift catalytic membrane reactor module in the presence of uncertainty Ma, Liang-Chih; Castro-Dominguez, Bernardo; Kazantzis, Nikolaos K. Separation and Purification Technology, Vol. 166 https://doi.org/10.1016/j.seppur.2016.04.019	journal	June 2016
Effects of carbohydrate, protein and lipid content of organic waste on hydrogen production and fermentation products Alibardi, Luca; Cossu, Raffaello Waste Management, Vol. 47 https://doi.org/10.1016/j.wasman.2015.07.049	journal	January 2016
Thermophilic anaerobic digestion of pulp and paper mill primary sludge and co-digestion of primary and secondary sludge Bayr, Suvi; Rintala, Jukka Water Research, Vol. 46, Issue 15 https://doi.org/10.1016/j.watres.2012.06.033	journal	October 2012
Prediction of Bio-oil Yield and Hydrogen Contents Based on Machine Learning Method: Effect of Biomass Compositions and Pyrolysis Conditions Tang, Qinghui; Chen, Yingquan; Yang, Haiping Energy & Fuels, Vol. 34, Issue 9 https://doi.org/10.1021/acs.energyfuels.0c01893	journal	August 2020
Hydrothermal Liquefaction of an Animal Carcass for Biocrude Oil Yang, Chuang; Wang, Shuzhong; Ren, Mengmeng Energy & Fuels, Vol. 33, Issue 11 https://doi.org/10.1021/acs.energyfuels.9b03100	journal	October 2019
Synergistic and Antagonistic Interactions during Hydrothermal Liquefaction of Soybean Oil, Soy Protein, Cellulose, Xylose, and Lignin Lu, Jianwen; Liu, Zhidan; Zhang, Yuanhui ACS Sustainable Chemistry & Engineering, Vol. 6, Issue 11 https://doi.org/10.1021/acssuschemeng.8b03156	journal	September 2018
Hydrothermal Treatment of Protein, Polysaccharide, and Lipids Alone and in Mixtures Teri, Gule; Luo, Ligang; Savage, Phillip E. Energy & Fuels, Vol. 28, Issue 12 https://doi.org/10.1021/ef501760d	journal	November 2014
Optimal division of data for neural network models in water resources applications Bowden, Gavin J.; Maier, Holger R.; Dandy, Graeme C. Water Resources Research, Vol. 38, Issue 2 https://doi.org/10.1029/2001WR000266	journal	February 2002
A strategy to apply machine learning to small datasets in materials science Zhang, Ying; Ling, Chen npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0081-z	journal	May 2018
Prediction of microalgae hydrothermal liquefaction products from feedstock biochemical composition Leow, Shijie; Witter, John R.; Vardon, Derek R. Green Chemistry, Vol. 17, Issue 6 https://doi.org/10.1039/C5GC00574D	journal	January 2015
Quantitative multiphase model for hydrothermal liquefaction of algal biomass Li, Yalin; Leow, Shijie; Fedders, Anna C. Green Chemistry, Vol. 19, Issue 4 https://doi.org/10.1039/C6GC03294J	journal	January 2017
Ridge Regression: Biased Estimation for Nonorthogonal Problems Hoerl, Arthur E.; Kennard, Robert W. Technometrics, Vol. 12, Issue 1 https://doi.org/10.1080/00401706.1970.10488634	journal	February 1970
Sparse identification of nonlinear dynamics for model predictive control in the low-data limit Kaiser, E.; Kutz, J. N.; Brunton, S. L. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 474, Issue 2219 https://doi.org/10.1098/rspa.2018.0335	journal	November 2018
Waste to bioenergy: a review on the recent conversion technologies Lee, Sze Ying; Sankaran, Revathy; Chew, Kit Wayne BMC Energy, Vol. 1, Issue 1 https://doi.org/10.1186/s42500-019-0004-7	journal	May 2019
Machine learning algorithm validation with a limited sample size Vabalas, Andrius; Gowen, Emma; Poliakoff, Ellen PLOS ONE, Vol. 14, Issue 11 https://doi.org/10.1371/journal.pone.0224365	journal	November 2019
Conceptual Biorefinery Design and Research Targeted for 2022: Hydrothermal Liquefacation Processing of Wet Waste to Fuels Snowden-Swan, Lesley J.; Zhu, Yunhua; Bearden, Mark D. https://doi.org/10.2172/1415710	report	December 2017
Bio-Crude Production through Aqueous Phase Recycling of Hydrothermal Liquefaction of Sewage Sludge Shah, Ayaz A.; Toor, Saqib S.; Seehar, Tahir H. Energies, Vol. 13, Issue 2 https://doi.org/10.3390/en13020493	journal	January 2020
Methods to Avoid Over-Fitting and Under-Fitting in Supervised Machine Learning (Comparative Study) Jabbar, Haider Khalaf; Khan, Rafiqul Zaman Computer Science, Communication and Instrumentation Devices https://doi.org/10.3850/978-981-09-5247-1_017	conference	January 2014
Biogas Production from Vietnamese Animal Manure, Plant Residues and Organic Waste: Influence of Biomass Composition on Methane Yield Cu, T. T. T.; Nguyen, T. X.; Triolo, J. M. Asian-Australasian Journal of Animal Sciences, Vol. 28, Issue 2 https://doi.org/10.5713/ajas.14.0312	journal	December 2014

Similar Records

Techno-Economic Uncertainty Quantification of Algal-derived Biocrude via Hydrothermal Liquefaction

Journal Article · Wed May 01 00:00:00 EDT 2019 · Algal Research · OSTI ID:1523393

Techno-Economic Uncertainty Analysis of Wet Waste-to-Biocrude via Hydrothermal Liquefaction

Journal Article · Sun Jan 31 23:00:00 EST 2021 · Applied Energy · OSTI ID:1762699

Related Subjects

42 ENGINEERING
biocrude yield prediction
eXtreme gradient boosting
hydrothermal liquefaction
machine learning
random forest

Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Citation Formats

References (69)

Similar Records

Related Subjects