A novel intelligent system based on machine learning for hydrochar multi-target prediction from the hydrothermal carbonization of biomass

Weijin Zhang; Junhui Zhou; Qian Liu; Zhengyong Xu; Haoyi Peng; Lijian Leng; Hailong Li

doi:10.1007/s42773-024-00303-8

Biochar > 2024 > 6(1): 19-19. > DOI: 10.1007/s42773-024-00303-8

Weijin Zhang, Junhui Zhou, Qian Liu, Zhengyong Xu, Haoyi Peng, Lijian Leng, Hailong Li. A novel intelligent system based on machine learning for hydrochar multi-target prediction from the hydrothermal carbonization of biomass[J]. Biochar, 2024, 6(1): 19-19. DOI: 10.1007/s42773-024-00303-8

Citation:

PDF (4093 KB)

A novel intelligent system based on machine learning for hydrochar multi-target prediction from the hydrothermal carbonization of biomass

1. School of Energy Science and Engineering, Central South University, Changsha, 410083, China;
2. Xiangjiang Laboratory, Changsha, 410205, China;
3. Hunan Modern Environmental Technology Co., LTD., Changsha, 410000, China

Funds:

This work was supported by the National Key Research and Development Program of China (2021YFE0104900), the Open Project of Xiangjiang Laboratory (22xj03003), and the Science and Technology Innovation Program of Hunan Province (2021RC4005, 2021GK1210).

More Information

Received Date: September 17, 2023
Revised Date: January 03, 2024
Accepted Date: January 10, 2024
Published Date: February 29, 2024

Graphical Abstract

Abstract

Abstract

Hydrothermal carbonization (HTC) is a thermochemical conversion technology to produce hydrochar from wet biomass without drying, but it is time-consuming and expensive to experimentally determine the optimal HTC operational conditions of specific biomass to produce desired hydrochar. Therefore, a machine learning (ML) approach was used to predict and optimize hydrochar properties. Specifically, biochemical components (proteins, lipids, and carbohydrates) of biomass were predicted and analyzed first via elementary composition. Then, accurate single-biomass (no mixture) based ML multi-target models (average R² = 0.93 and RMSE = 2.36) were built to predict and optimize the hydrochar properties (yield, elemental composition, elemental atomic ratio, and higher heating value). Biomass composition (elemental and biochemical), proximate analyses, and HTC conditions were inputs herein. Interpretation of the model results showed that ash, temperature, and the N and C content of biomass were the most critical factors affecting the hydrochar properties, and that the relative importance of biochemical composition (25%) for the hydrochar was higher than that of operating conditions (19%). Finally, an intelligent system was constructed based on a multi-target model, verified by applying it to predict the atomic ratios (N/C, O/C, and H/C). It could also be extended to optimize hydrochar production from the HTC of single-biomass samples with experimental validation and to predict hydrochar from the co-HTC of mixed biomass samples reported in the literature. This study advances the field by integrating predictive modeling, intelligent systems, and mechanistic insights, offering a holistic approach to the precise control and optimization of hydrochar production through HTC.
- Biomass,
- Hydrothermal carbonization,
- Hydrochar,
- Machine learning,
- Intelligent prediction system

FullText(HTML)

References (53)

References

[1]	Buss W, Jansson S, Wurzer C, Mašek O (2019) Synergies between BECCS and biochar—maximizing carbon sequestration potential by recycling wood ash. ACS Sustain Chem Eng 7:4204–4209. https://doi.org/10.1021/acssuschemeng.8b05871
[2]	Deng Q, Lin B (2022) Automated machine learning structure-composition-property relationships of perovskite materials for energy conversion and storage. Energy Mater 1:100006. https://doi.org/10.20517/energymater.2021.10
[3]	Duan P, Chang Z, Xu Y et al (2013) Hydrothermal processing of duckweed: effect of reaction conditions on product distribution and composition. Bioresour Technol 135:710–719. https://doi.org/10.1016/j.biortech.2012.08.106
[4]	Duan PG, Yang SK, Xu YP et al (2018) Integration of hydrothermal liquefaction and supercritical water gasification for improvement of energy recovery from algal biomass. Energy 155:734–745. https://doi.org/10.1016/j.energy.2018.05.044
[5]	DuBois M, Gilles KA, Hamilton JK et al (1956) Colorimetric method for determination of sugars and related substances. Anal Chem 28:350–356. https://doi.org/10.1021/ac60111a017
[6]	Fang Y, Ma L, Yao Z et al (2022) Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm. Energy Convers Manag 264:115734. https://doi.org/10.1016/j.enconman.2022.115734
[7]	Gao F, Shen Y, Brett Sallach J et al (2022) Predicting crop root concentration factors of organic contaminants with machine learning models. J Hazard Mater 424:127437. https://doi.org/10.1016/j.jhazmat.2021.127437
[8]	He M, Cao Y, Xu Z et al (2022a) Process water recirculation for catalytic hydrothermal carbonization of anaerobic digestate: water-energy-nutrient nexus. Bioresour Technol 361:127694. https://doi.org/10.1016/j.biortech.2022.127694
[9]	He M, Zhu X, Dutta S et al (2022b) Catalytic co-hydrothermal carbonization of food waste digestate and yard waste for energy application and nutrient recovery. Bioresour Technol 344:126395. https://doi.org/10.1016/j.biortech.2021.126395
[10]	Hoekman SK, Broch A, Robbins C (2011) Hydrothermal carbonization (HTC) of lignocellulosic biomass. Energy Fuels 25:1802–1810. https://doi.org/10.1021/ef101745n
[11]	Kim JY, Shin UH, Kim K (2023) Predicting biomass composition and operating conditions in fluidized bed biomass gasifiers: an automated machine learning approach combined with cooperative game theory. Energy 280:128138. https://doi.org/10.1016/j.energy.2023.128138
[12]	Kirchner K, Zec J, Delibašić B (2016) Facilitating data preprocessing by a generic framework: a proposal for clustering. Artif Intell Rev 45:271–297. https://doi.org/10.1007/s10462-015-9446-6
[13]	Leng L, Zhang W, Peng H et al (2020) Nitrogen in bio-oil produced from hydrothermal liquefaction of biomass: a review. Chem Eng J 401:126030. https://doi.org/10.1016/j.cej.2020.126030
[14]	Leng L, Zhang W, Chen Q et al (2022a) Machine learning prediction of nitrogen heterocycles in bio-oil produced from hydrothermal liquefaction of biomass. Bioresour Technol 362:127791. https://doi.org/10.1016/j.biortech.2022.127791
[15]	Leng L, Zhang W, Liu T et al (2022b) Machine learning predicting wastewater properties of the aqueous phase derived from hydrothermal treatment of biomass. Bioresour Technol 358:127348. https://doi.org/10.1016/j.biortech.2022.127348
[16]	Leng S, Jiao H, Liu T et al (2022c) Co-liquefaction of Chlorella and soybean straw for production of bio-crude: effects of reusing aqueous phase as the reaction medium. Sci Total Environ 820:153348. https://doi.org/10.1016/j.scitotenv.2022.153348
[17]	Leng L, Li T, Zhan H et al (2023) Machine learning-aided prediction of nitrogen heterocycles in bio-oil from the pyrolysis of biomass. Energy 278:127967. https://doi.org/10.1016/j.energy.2023.127967
[18]	Li Y, Liu H, Xiao K et al (2019) Correlations between the physicochemical properties of hydrochar and specific components of waste lettuce: influence of moisture, carbohydrates, proteins and lipids. Bioresour Technol 272:482–488. https://doi.org/10.1016/j.biortech.2018.10.066
[19]	Li J, Pan L, Suvarna M et al (2020a) Fuel properties of hydrochar and pyrochar: prediction and exploration with machine learning. Appl Energy 269:115166. https://doi.org/10.1016/j.apenergy.2020.115166
[20]	Li L, Flora JRV, Berge ND (2020b) Predictions of energy recovery from hydrochar generated from the hydrothermal carbonization of organic wastes. Renew Energy 145:1883–1889. https://doi.org/10.1016/j.renene.2019.07.103
[21]	Li J, Zhang W, Liu T et al (2021a) Machine learning aided bio-oil production with high energy recovery and low nitrogen content from hydrothermal liquefaction of biomass with experiment verification. Chem Eng J 425:130649. https://doi.org/10.1016/j.cej.2021.130649
[22]	Li J, Zhu X, Li Y et al (2021b) Multi-task prediction and optimization of hydrochar properties from high-moisture municipal solid waste: application of machine learning on waste-to-resource. J Clean Prod 278:123928. https://doi.org/10.1016/j.jclepro.2020.123928
[23]	Li H, Chen J, Zhang W et al (2023) Machine-learning-aided thermochemical treatment of biomass: a review. Biofuel Res J. 10:1786–1809. https://doi.org/10.18331/BRJ2023.10.1.4
[24]	Liu A, Su Y, Nie W, Kankanhalli M (2017) Hierarchical clustering multi-task learning for joint human action grouping and recognition. IEEE Trans Pattern Anal Mach Intell 39:102–114. https://doi.org/10.1109/TPAMI.2016.2537337
[25]	Liu H, Basar IA, Nzihou A, Eskicioglu C (2021) Hydrochar derived from municipal sludge through hydrothermal processing: a critical review on its formation, characterization, and valorization. Water Res 199:117186. https://doi.org/10.1016/j.watres.2021.117186
[26]	Liu Z, Cui Y, Wang J et al (2022) Multi-objective optimization of multi-energy complementary integrated energy systems considering load prediction and renewable energy production uncertainties. Energy 254:124399. https://doi.org/10.1016/j.energy.2022.124399
[27]	Marzbali MH, Kundu S, Halder P et al (2021) Wet organic waste treatment via hydrothermal processing: a critical review. Chemosphere 279:130557. https://doi.org/10.1016/j.chemosphere.2021.130557
[28]	Mu L, Wang Z, Wu D et al (2022) Prediction and evaluation of fuel properties of hydrochar from waste solid biomass: machine learning algorithm based on proposed PSO–NN model. Fuel 318:123644. https://doi.org/10.1016/j.fuel.2022.123644
[29]	Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobot. https://doi.org/10.3389/fnbot.2013.00021
[30]	Palansooriya KN, Li J, Dissanayake PD et al (2022) Prediction of soil heavy metal immobilization by biochar using machine learning. Environ Sci Technol 56:4187–4198. https://doi.org/10.1021/acs.est.1c08302
[31]	Putatunda S, Rama K (2018) A Comparative Analysis of Hyperopt as Against Other Approaches for Hyper-Parameter Optimization of XGBoost. In: Proceedings of the 2018 International Conference on Signal Processing and Machine Learning. ACM press, New York, USA, pp 6–10
[32]	Qureshi AS, Khan A, Zameer A, Usman A (2017) Wind power prediction using deep neural network based meta regression and transfer learning. Appl Soft Comput 58:742–755. https://doi.org/10.1016/j.asoc.2017.05.031
[33]	Ribeiro MT, Singh S, Guestrin C (2016) “Why Should I Trust You?” Explaining the Predictions of Any Classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM press, New York, USA, pp 1135–1144
[34]	Rodrigues R, Souza D, Toebe M, Chuquel A (2023) Sample size and Shapiro-Wilk test: AN analysis for soybean grain yield. Eur J Agron 142:126666. https://doi.org/10.1016/j.eja.2022.126666
[35]	Seo MW, Lee SH, Nam H et al (2022) Recent advances of thermochemical conversion processes for biorefinery. Bioresour Technol 343:126109. https://doi.org/10.1016/j.biortech.2021.126109
[36]	Shafizadeh A, Shahbeik H, Rafiee S et al (2023) Machine learning-based characterization of hydrochar from biomass: implications for sustainable energy and material production. Fuel 347:128467. https://doi.org/10.1016/j.fuel.2023.128467
[37]	Shapiro SS, Wilk MB (1965) An analysis of variance test for normality (complete samples). Biometrika 52:591–611. https://doi.org/10.2307/2333709
[38]	Sheng L, Wang X, Yang X (2018) Prediction model of biocrude yield and nitrogen heterocyclic compounds analysis by hydrothermal liquefaction of microalgae with model compounds. Bioresour Technol 247:14–20. https://doi.org/10.1016/j.biortech.2017.08.011
[39]	Shi N, Liu Q, He X et al (2019) Molecular structure and formation mechanism of hydrochar from hydrothermal carbonization of carbohydrates. Energy Fuels 33:9904–9915. https://doi.org/10.1021/acs.energyfuels.9b02174
[40]	Toptas Tag A, Duman G, Yanik J (2018) Influences of feedstock type and process variables on hydrochar properties. Bioresour Technol 250:337–344. https://doi.org/10.1016/j.biortech.2017.11.058
[41]	Xiong T, Cui J, Hou Z et al (2023) Prediction of arsenic adsorption onto metal organic frameworks and adsorption mechanisms interpretation by machine learning. J Environ Manage 347:119065. https://doi.org/10.1016/j.jenvman.2023.119065
[42]	Xu D, Lin G, Liu L et al (2018) Comprehensive evaluation on product characteristics of fast hydrothermal liquefaction of sewage sludge at different temperatures. Energy 159:686–695. https://doi.org/10.1016/j.energy.2018.06.191
[43]	Xu Z, Ma X, Zhou J et al (2022) The influence of key reactions during hydrothermal carbonization of sewage sludge on aqueous phase properties: a review. J Anal Appl Pyrolysis 167:105678. https://doi.org/10.1016/j.jaap.2022.105678
[44]	Yap BW, Sim CH (2011) Comparisons of various types of normality tests. J Stat Comput Simul 81:2141–2155. https://doi.org/10.1080/00949655.2010.520163
[45]	Yu J, Zhong X, Huang Z et al (2023) Mining the synergistic effect in hydrothermal co-liquefaction of real feedstocks through machine learning approaches. Fuel 334:126715. https://doi.org/10.1016/j.fuel.2022.126715
[46]	Yuan T-Q, Sun S-N, Xu F, Sun R-C (2011) Characterization of lignin structures and lignin-carbohydrate complex (LCC) linkages by quantitative 13 C and 2D HSQC NMR spectroscopy. J Agric Food Chem 59:10604–10614. https://doi.org/10.1021/jf2031549
[47]	Yuan X, Suvarna M, Low S et al (2021) Applied machine learning for prediction of CO 2 adsorption on biomass waste-derived porous carbons. Environ Sci Technol 55:11925–11936. https://doi.org/10.1021/acs.est.1c01849
[48]	Zhang W, Li J, Liu T et al (2021) Machine learning prediction and optimization of bio-oil production from hydrothermal liquefaction of algae. Bioresour Technol 342:126011. https://doi.org/10.1016/j.biortech.2021.126011
[49]	Zhang B, Biswal BK, Zhang J, Balasubramanian R (2023a) Hydrothermal treatment of biomass feedstocks for sustainable production of chemicals, fuels, and materials: progress and perspectives. Chem Rev. https://doi.org/10.1021/acs.chemrev.2c00673
[50]	Zhang W, Chen Q, Chen J et al (2023b) Machine learning for hydrothermal treatment of biomass: a review. Bioresour Technol 370:128547. https://doi.org/10.1016/j.biortech.2022.128547
[51]	Zhang X, Liu H, Yang G et al (2023c) Comprehensive insights into the application strategy of kitchen waste derived hydrochar: Random forest-based modelling. Chem Eng J 469:143840. https://doi.org/10.1016/j.cej.2023.143840
[52]	Zhang S, Luo X, Mai B (2024) Multi-task machine learning models for simultaneous prediction of tissue-to-blood partition coefficients of chemicals in mammals. Environ Res 241:117603. https://doi.org/10.1016/j.envres.2023.117603
[53]	Zhu X, Liu B, Sun L et al (2023) Machine learning-assisted exploration for carbon neutrality potential of municipal sludge recycling via hydrothermal carbonization. Bioresour Technol 369:128454. https://doi.org/10.1016/j.biortech.2022.128454