Applied machine learning for predicting the properties and carbon and phosphorus fate of pristine and engineered hydrochar

Abstract

Application of advanced techniques and machine learning (ML) for designing and predicting the properties of engineered hydrochar/biochar is of great agro-environmental concern. Carbon (C) stability and phosphorus (P) availability in hydrochar (HC) are among the key limitations as they cannot be accurately predicted by traditional one-factor tests and might be overcome by engineering the pristine HC. Therefore, the aims of this study were (1) to determine the optimal production conditions of engineered swine manure HC with high C stability and P availability, and (2) to develop the best ML models to predict the properties of HC derived from different feedstocks. Pristine- (HC) and FeCl₃ impregnated swine manure-derived HC (HC-Fe) were produced by hydrothermal carbonization under different pH (4, 7, and 10), reaction temperature (180, 220, and 260 ℃), and residence time (60, 120, and 180 min) and characterized using thermo-gravimetric, microscopic, and spectroscopic analyses. Also, different ML algorithms were used to model and predict the hydrochar solid yield, properties, and nutrients content. FeCl₃ impregnation increased Fe-phosphate content, while it reduced H/C and O/C ratios and hydroxyapatite P content, and therefore improved C stability and P availability in the HC-Fe as compared to HC, particularly under lower pH (4), temperature of 220 ℃, and at 120 min. The generalized additive ML model outperformed the other models for predicting the HC properties with a correlation coefficient of 0.86. The ML analysis showed that the most influential features on the hydrochar C stability were the H and O contents in the biomass, while P availability in HC was more dependent on the C, N and O contents in biomass. These results provided optimal production conditions for Fe-engineered manure hydrochar and identified the best performing ML model for predicting hydrochar properties. The main implication of this study is that it offers a high potential to improve the utilization of biowastes and produce biowaste-derived engineered hydrochar with high C stability and P availability on a large scale.

Graphical Abstract

References

[] Chen G, Wang J, Yu F, Wang X, Xiao H, Yan B, Cui X. A review on the production of P-enriched hydro/bio-char from solid waste: transformation of P and applications of hydro/bio-char Chemosphere, 2022, 301: 134646.

[] De Jager M, Rohrdanz M, Giani L. The influence of hydrochar from biogas digestate on soil improvement and plant growth aspects Biochar, 2020, 2: 177-194.

[] Deng Y, Zhang T, Clark J, Aminabhavi T, Kruse A, Tsang D, Sharma B, Zhang F, Ren HQ. Mechanisms and modelling of phosphorus solid-liquid transformation during the hydrothermal processing of swine manure Green Chem, 2020, 22(17): 5628-5638.

[] Djandja OS, Kang S, Huang Z, Li JQ, Feng JQ, Tan ZM, Salami AA, Lougou BG. Machine learning prediction of fuel properties of hydrochar from co-hydrothermal carbonization of sewage sludge and lignocellulosic biomass Energy, 2023, 271: 126968.

[] Fu H, Wang B, Wang H, Liu H, Xie H, Han L, Wang N, Sun X, Feng Y, Xue L. Assessment of livestock manure-derived hydrochar as cleaner products: insights into basic properties, nutrient composition, and heavy metal content J Clean Prod, 2022, 330: 129820.

[] Funke A, Ziegler F. Hydrothermal carbonization of biomass: a summary and discussion of chemical mechanisms for process engineering Biofuels, Bioprod Biorefin, 2010, 4(2): 160-177.

[] Huang R, Fang C, Lu X, Jiang R, Tang Y. Transformation of phosphorus during (hydro)thermal treatments of solid biowastes: reaction mechanisms and implications for P reclamation and recycling Environ Sci Technol, 2017, 51(18): 10284-10298.

[] Huang R, Fang C, Zhang B, Tang Y. Transformations of phosphorus speciation during (hydro)thermal treatments of animal manures Environ Sci Technol, 2018, 52(5): 3016-3026.

[] Ji L, Yu Z, Cao Q, Gui X, Fan X, Wei C, Jiang F, Wang J, Meng F, Li F, Wang J. Effect of hydrothermal temperature on the optical properties of hydrochar-derived dissolved organic matter and their interactions with copper (II) Biochar, 2024, 6: 64.

[] Kardani N, Hedayati Marzbali M, Shah K, Zhou AN. Machine learning prediction of the conversion of lignocellulosic biomass during hydrothermal carbonization Biofuels, 2022, 13(6): 703-715.

[] Khan N, Mohan S, Dinesha P. Regimes of hydrochar yield from hydrothermal degradation of various lignocellulosic biomass: a review J Clean Prod, 2021, 288: 125629.

[] Khosravi A, Zheng H, Liu Q, Hashemi M, Tang Y, Xing BS. Production and characterization of hydrochars and their application in soil improvement and environmental remediation Chem Eng J, 2022, 430: 133142.

[] Lang Q, Zhang B, Liu Z, Jiao W, Xia Y, Chen Z, Li D, Ma J, Gai C. Properties of hydrochars derived from swine manure by CaO assisted hydrothermal carbonization J Environ Manage, 2019, 233: 440-446.

[] Li S, Zeng W, Jia Z, Wu G, Xu H, Peng Y. Phosphorus species transformation and recovery without apatite in FeCl₃-assisted sewage sludge hydrothermal treatment Chem Eng J, 2020, 399: 125735.

[] Liu Y, Gao C, Wang Y, He L, Lu H, Yang S. Vermiculite modification increases carbon retention and stability of rice straw biochar at different carbonization temperatures J Clean Prod, 2020, 254: 120111.

[] Marzban N, Libra JA, Ro KS, Paniagua DM, Rotter VS, Sturm B, Filonenko S. Hydrochar stability: understanding the role of moisture, time and temperature in its physiochemical changes Biochar, 2024, 6: 38.

[] Shafizadeh A, Shahbeig H, Nadian MH, Mobli H, Dowlati M, Gupta VK, Peng W, Lam SS, Tabatabaei M, Aghbashlo M. Machine learning predicts and optimizes hydrothermal liquefaction of biomass Chem Eng J, 2022, 445: 136579.

[] Shafizadeh A, Shahbeik H, Rafiee S, Moradi A, Shahbaz M, Madadi M, Li C, Peng WX, Tabatabaei M, Aghbashlo M. Machine learning-based characterization of hydrochar from biomass: implications for sustainable energy and material production Fuel, 2023, 347: 128467.

[] Tekin K, Karagöz S, Bektaş S. A review of hydrothermal biomass processing Renew Sustain Energy Rev, 2014, 40: 673-687.

[] Wan C, Li H, Zhao L, Li Z, Zhang C, Tan X, Liu X. Mechanism of removal and degradation characteristics of dicamba by biochar prepared from Fe-modified sludge J Environ Manage, 2021, 299: 113602.

[] Wang T, Zhai Y, Zhu Y, Li C, Zeng G. A review of the hydrothermal carbonization of biomass waste for hydrochar formation: process conditions, fundamentals, and physicochemical properties Renew Sustain Energy Rev, 2018, 90: 223-247.

[] Wang F, Guo C, Liu X, Sun H, Zhang C, Sun Y, Zhu H. Revealing carbon-iron interaction characteristics in sludge-derived hydrochars under different hydrothermal conditions Chemosphere, 2022, 300: 134572.

[] Wei X, Liu Y, Shen L, Lu Z, Ai Y, Wang XK. Machine learning insights in predicting heavy metals interaction with biochar Biochar, 2024, 6: 10.

[] Xu Q, Zhang T, Niu YQ, Mukherjee S, Abou-Elwafa SF, et al.. A comprehensive review on agricultural waste utilization through sustainable conversion techniques, with a focus on the additives effect on the fate of phosphorus and toxic elements during composting process Sci Total Environ, 2024, 942: 173567.

[] Zhang T, Wu XS, Shaheen SM, Zhao Q, Liu X, Rinklebe J, Ren HQ. Ammonium nitrogen recovery from digestate by hydrothermal pretreatment followed by activated hydrochar sorption Chem Eng J, 2020, 379: 122254.

[] Zhang T, Pasha AMK, Sajadi SM, Jasim DJ, Nasajpour-Esfahani N, Maleki H, Salahshour S, Baghaei S. Optimization of thermophysical properties of nanofluids using a hybrid procedure based on machine learning, multi-objective optimization, and multi-criteria decision-making Chem Eng J, 2024, 485: 150059.

[] Zhu ZP, Zhang XM, Dong HM, Wang ST, Reis S, Li Y, Gu BJ. Integrated livestock sector nitrogen pollution abatement measures could generate net benefits for human and ecosystem health in China Nat Food, 2022, 3: 161-168.

Funding

the National Key Research and Development Program of China(2023YFE0104700)