Thermochemical treatment is a promising technique for biomass disposal and valorization. Recently, machine learning (ML) has been extensively used to predict yields, compositions, and properties of ...biochar, bio-oil, syngas, and aqueous phases produced by the thermochemical treatment of biomass. ML demonstrates great potential to aid the development of thermochemical processes. The present review aims to 1) introduce the ML schemes and strategies as well as descriptors of the input and output features in thermochemical processes; 2) summarize and compare the up-to-date research in both ML-aided wet (hydrothermal carbonization/liquefaction/gasification) and dry (torrefaction/pyrolysis/gasification) thermochemical treatment of biomass (i.e., predicting the yields, compositions, and properties of oil/char/gas/aqueous phases as well as thermal conversion behavior or kinetics); and 3) identify the gaps and provide guidance for future studies concerning how to improve predictive performance, increase generalizability, aid mechanistic and application studies, and effectively share data and models in the community. The development of biomass thermochemical treatment processes is envisaged to be greatly accelerated by ML in the near future.
Biochar produced from pyrolysis of biomass has been developed as a platform carbonaceous material that can be used in various applications. The specific surface area (SSA) and functionalities such as ...N-containing functional groups of biochar are the most significant properties determining the application performance of biochar as a carbon material in various areas, such as removal of pollutants, adsorption of CO
2
and H
2
, catalysis, and energy storage. Producing biochar with preferable SSA and N functional groups is among the frontiers to engineer biochar materials. This study attempted to build machine learning models to predict and optimize specific surface area of biochar (SSA-char), N content of biochar (N-char), and yield of biochar (Yield-char) individually or simultaneously, by using elemental, proximate, and biochemical compositions of biomass and pyrolysis conditions as input variables. The predictions of Yield-char, N-char, and SSA-char were compared by using random forest (RF) and gradient boosting regression (GBR) models. GBR outperformed RF for most predictions. When input parameters included elemental and proximate compositions as well as pyrolysis conditions, the test R
2
values for the single-target and multi-target GBR models were 0.90–0.95 except for the two-target prediction of Yield-char and SSA-char which had a test R
2
of 0.84 and the three-target prediction model which had a test R
2
of 0.81. As indicated by the Pearson correlation coefficient between variables and the feature importance of these GBR models, the top influencing factors toward predicting three targets were specified as follows: pyrolysis temperature, residence time, and fixed carbon for Yield-char; N and ash for N-char; ash and pyrolysis temperature for SSA-char. The effects of these parameters on three targets were different, but the trade-offs of these three were balanced during multi-target ML prediction and optimization. The optimum solutions were then experimentally verified, which opens a new way for designing smart biochar with target properties and oriented application potential.
Graphical Abstract
Highlights
Yield, N content, and specific surface area of biochar predicted by machine learning
Gradient boosting regression outperformed random forest, with test R
2
of 0.81–0.95
Temperature, nitrogen, and ash were top features for predicting the three targets
The yield and properties of biochar were engineered and experimentally verified
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
R
2
= 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.
Graphical Abstract
Highlights
Biochemical components of biomass were first predicted by elemental composition.
The multi-target ML model accurately predicted hydrochar with
R
2
= 0.93.
The ash,
T
, N, and C were the most critical factors affecting hydrochar properties.
An online intelligent system based on optimal models was posted and verified.
Display omitted
•20–40% of the N in biomass feedstock would distribute into bio-oil during the HTL.•Effects of biomass and HTL processing parameters on bio-oil N were overviewed.•Pretreatment and ...co-HTL of biomass are effective to mediate bio-oil N.•High bio-oil yield is accompanied by high bio-oil N content.•Bio-oil extraction solvent & procedure are decisive to bio-oil N.
Hydrothermal liquefaction (HTL) of biomass, especially that of high moisture such as microalgae, macroalgae, sludge, manure, and food waste, for the production of bio-oil has been widely concerned worldwide. However, the contents of nitrogen (N) in these biomasses are commonly high, and 20–40% of the N in the raw biomasses would distribute into bio-oil during the HTL process, resulting in a high content of N in bio-oil, sometimes up to 10 wt%. The combustion of N-rich bio-oil will probably induce massive emission of nitrogen oxides. The transformation behavior of N has not yet been fully understood, and the denitrogenation is a critical issue during bio-oil production and upgrading. This review comprehensively summarized the effects of the type, composition, and pretreatment of biomass and HTL processing parameters, such as temperature, residence time, solid loading, reaction solvent, extraction solvent/procedure, and catalyst, on the N content of bio-oil. The N conversion mechanisms in the HTL process were also clarified. Research gaps were identified, and future research directions were finally proposed to achieve the production of bio-oil with low N content.
Biomass is a type of renewable and sustainable resource that can be used to produce various fuels, chemicals, and materials. Nitrogen (N) in biomass such as microalgae should be reduced if it is used ...to produce fuels, while the retention of N is favorable if the biomass is processed to yield chemicals or materials with N-containing functional groups. The engineering of the removal and retention of N in hydrochar during hydrothermal carbonization (HTC) of biomass rich in protein is a research hot spot in the past decade. However, the N transformation during HTC has not yet been fully understood. In order to mediate the migration and transformation of N in hydrochar, the present review overviewed i) the characteristics of hydrochar and the original feedstock, ii) the possible N transformation behavior and mechanisms, and iii) the effect of factors such as feedstock and pyrolysis parameters such as temperature on hydrochar N. The high temperature and high protein content promote the dehydration, decarboxylation, and deamination of biomass to produce hydrochar solid fuel with reduced N content, while the Millard and Mannich reactions for lignocellulosic biomass rich in carbohydrate (cellulose, hemicellulose, and lignin) at medium temperatures (e.g., 180–240 °C) significantly promote the enrichment of N in hydrochar. The prediction models can be built based on properties of biomass and the processing parameters for the estimation of the yield and the content of N in hydrochar.
Display omitted
•Feedstock type and HTC reaction severity affect hydrochar nitrogen significantly.•Carbohydrates increase hydrochar nitrogen by Millard and Millard-like reactions.•Models with feedstock and process parameters predict hydrochar yield and nitrogen.
Display omitted
•Machine learning predict specific surface area, total pore volume, yield of biochar.•Gradient boosting regression with test R2 of 0.90–0.94 outperformed random forest.•Pyrolysis ...temperature, biomass ash, volatile matter are key factors to biochar.•Machine learning models were experimentally verified with acceptable results.•Machine-learning-optimized biomass mixtures produced designer biochar.
Biochar produced from pyrolysis of biomass is a platform porous carbon material that have been widely used in many areas. Specific surface area (SSA) and total pore volume (TPV) are decisive to biochar application in hydrogen uptake, CO2 adsorption, and organic pollutant removal, etc. Engineering biochar by traditional experimental methods is time-consuming and laborious. Machine learning (ML) was used to effectively aid the prediction and engineering of biochar properties. The prediction of biochar yield, SSA, and TPV was achieved via random forest (RF) and gradient boosting regression (GBR) with test R2 of 0.89–0.94. ML model interpretation indicates pyrolysis temperature, biomass ash, and volatile matter were the most important features to the three targets. Pyrolysis parameters and biomass mixing ratios for biochar production were optimized via three-target GBR model, and the optimum schemes to obtain high SSA and TPV were experimentally verified, indicating the great potential of ML for biochar engineering.
Display omitted
•Machine learning (ML) approach was used for predicting algae bio-oil characteristics.•Two ML models, GBR and RF were developed (train R2 > 0.90, test R2 > 0.85).•ML-based reverse and ...forward optimizations were carried out.•The experimental verifications were accept compared to optimal predictive results.
Hydrothermal liquefaction (HTL) of algae is a promising biofuel production technology. However, it is always difficult and time-consuming to identify the best optimal conditions of HTL for different algae by the conventional experimental study. Therefore, machine learning (ML) algorithms were applied to predict and optimize bio-oil production with algae compositions and HTL conditions as inputs, and bio-oil yield (Yield_oil), and the contents of oxygen (O_oil) and nitrogen (N_oil) in bio-oil as outputs. Results indicated that gradient boosting regression (GBR, average test R2 ∼ 0.90) exhibited better performance than random forest (RF) for both single and multi-target tasks prediction. Furthermore, the model-based interpretation suggested that the relative importance of operating conditions (temperature and residence time) was higher than algae characteristics for the three targets. Moreover, ML-based reverse and forward optimizations were implemented with experimental verifications. The verifications were acceptable, showing great potential of ML-aided HTL for producing desirable bio-oil.
Display omitted
•Dataset about HTL of biomass for bio-oil production was systematically complied.•Multi-task ML models were successfully developed for bio-oil prediction.•ML-based reverse ...optimization was achieved to guide high-quality bio-oil production.•Optimal solutions from reverse optimization were experimentally verified.
Hydrothermal liquefaction (HTL) of biomass with high moisture (e.g., algae, sludge, manure, and food waste) is a promising and sustainable approach to produce renewable energy (bio-oil) and protect the environment. However, the production of bio-oil with high yield and preferable properties such as low nitrogen content (N_oil) is time/labor-consuming using the traditional HTL experimental method. To this context, machine learning (ML) algorithms were employed to aid the bio-oil production with the consideration of related factors in HTL, including biochemical and elemental compositions of biomass, process parameters, and solvents. Results showed that the random forest (RF) algorithm was the best one (average R2 = 0.80) for the multi-task prediction of bio-oil yield (Yield_oil), N_oil, and energy recovery (ER_oil), hence employed for post feature interpretation and optimization. Feature importance indicates that both Yield_oil and ER_oil follow the trend of lipid content in biomass > temperature > retention time, while N_oil follows the trend of N content in biomass > temperature > retention time. Then ML-based optimization was conducted to guide the experimental research to produce bio-oil with high yield and low N content. The HTL experiment verification based on the optimal solutions from the ML-based Particle Swarm Optimization achieved the maximum Yield_oil (54.30%) and minimal N_oil (2.60%) from model biomass (composed of protein content 28%, lipid 48%, and carbohydrates 21%) at 300 °C and 30 min. The experiment verification was successful as the results were comparable to the modeling results, with errors of less than 7% for Yield_oil and ER_oil, and 23% for N_oil, and the N_oil of the experiment N_oil (2.60%) was interestingly lower than the modeled one (3.37%). This work provides new insight and strategy to accelerate the engineered HTL for desired bio-oil production.
Display omitted
•Microalgae can be effectively harvested by co-pelletization with fungi.•Fungi-microalgae consortium has a complementary effect on pollutant removal.•Fungi-microalgae biomass ...facilitated the production of biofuel and lipid.•Fungi-microalgae consortium may outperform bacteria-microalgae in some areas.
The treatment of wastewater by microalgae has been studied and proved to be effective through previous studies. Due to the small size of microalgae, how to efficiently harvest microalgae from wastewater is a crucial factor restricting the development of algal technologies. Fungi-assisted microalgae bio-flocculation for microalgae harvesting and wastewater treatment simultaneously, which was overlooked previously, has attracted increasing attention in the recent decade due to its low cost and high efficiency. This review found that fungal hyphae and microalgae can stick together due to electrostatic neutralization, surface protein interaction, and exopolysaccharide adhesion in the co-culture process, realizing co-pelletization of microalgae and fungi, which is conducive to microalgae harvesting. Besides, the combination of fungi and microalgae has a complementary effect on pollutant removal from wastewaters. The co-culture of fungi-microalgae has excellent development prospects with both environmental and economic benefits, and it is expected to be applied on an industrial scale.
Display omitted
•Biomass compositions and hydrothermal treatment (HTT) parameters predict products.•Machine learning (ML) models and procedure were introduced and compared.•ML can predict yield, ...compositions, and properties of products from HTT accurately.•ML-aided prediction, optimization, and application are promising in HTT field.
Hydrothermal treatment (HTT) (i.e., hydrothermal carbonization, liquefaction, and gasification) is a promising technology for biomass valorization. However, diverse variables, including biomass compositions and hydrothermal processes parameters, have impeded in-depth mechanistic understanding on the reaction and engineering in HTT. Recently, machine learning (ML) has been widely employed to predict and optimize the production of biofuels, chemicals, and materials from HTT by feeding experimental data. This review comprehensively analyzed the application of ML for HTT of biomass and systematically illustrated basic ML procedure and descriptors for inputs and outputs of ML models (e.g., biomass compositions, operation conditions, yield and physicochemical properties of derived products) that could be applied in HTT. Moreover, this review summarized ML-aided HTT prediction of yield, compositions, and physicochemical properties of HTT hydrochar or biochar, bio-oil, syngas, and aqueous phase. Ultimately, future prospects were proposed to enhance predictive performance, mechanistic interpretation, process optimization, data sharing, and model application during ML-aided HTT.
