Prediction Of Biogas Production Research Articles

Assessing microbial stability and predicting biogas production in full-scale thermophilic dry methane fermentation of municipal solid waste

Compared to typical anaerobic digestion processes, little is known about both sludge microbial compositions and biogas production models for full-scale dry methane fermentation treating municipal solid waste (MSW). The anaerobic sludge composed of one major hydrogenotrophic methanogen (Methanoculleus) and syntrophic acetate oxidizing bacteria (e.g., Caldicoprobacter), besides enrichment of MSW degraders such as Clostridia. The core population remained phylogenetically unchanged during the fermentation process, regardless of amounts of MSW supplied (∼35 ton/d) or biogas produced (∼12000 Nm3/d). Based on the correlations observed between feed amounts of MSW from 6 days in advance to the current day and biogas output (the strongest correlation: r = 0.77), the best multiple linear regression (MLR) model incorporating the temperature factor was developed with a good prediction for validation data (R2 = 0.975). The proposed simple MLR method with only data on the feedstock amounts will help decision-making processes to prevent low-efficient biogas production.

Comparative evaluation of Artificial intelligence based models and kinetic studies in the prediction of biogas from anaerobic digestion of MSW

The generation of biogas from the decomposition of MSW increases greenhouse gas emissions, contributing to global warming. However, the produced biogas can be effectively captured for conversion into a renewable energy resource. This study demonstrates the utility of artificial neural networks (ANN), adaptive network-fuzzy inference systems (ANFIS), and kinetic models in predicting biogas production from the anaerobic digestion of MSW. The digestion time, volatile solids, pH, temperature, and moisture content were selected as the independent variables. Furthermore, kinetic studies were conducted to predict the biogas yield using First-order, modified Gompertz, Logistic, and Transference models. To assess the efficacy of these models, their performance was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). Upon comparing the results, it was evident that for set IX under 100 % field capacity (FC), the ANFIS network exhibited superior performance with RMSE and R2 values of 0.670 and 0.999, respectively. In comparison, the ANN and modified Gompertz models yielded RMSE values of 0.863 and 21.705, and R2 values of 0.999 and 0.998, respectively. While the coefficient of determination (R2 ≥ 0.99) suggested satisfactory agreement between all the models and experimental data, the ANFIS and ANN models achieved notably lower RMSE values, demonstrating their competitive performance.

Influences of straw alkaline pretreatment on biogas production and digestate characteristics: artificial neural network and multivariate statistical techniques.

Anaerobic digestion is one of the best options for producing valuable end products (biogas and biofertilizer). The aim of this study was to investigate the influences of thermoalkaline pretreatment of wheat straw on biogas production and digestate characteristics from codigestion with waste-activated sludge. Different alkaline conditions (NaOH, KOH and Na2CO3) and pretreatment durations (1, 3 and 5 h) were used for straw pretreatment. Batch anaerobic codigestion of sludge and pretreated straw was conducted under different pretreatment conditions. A feedforward neural network (FFNN) model, logistic model and statistical analysis were applied to the experimental data to predict biogas and investigate the significance and relationships among the variables. NaOH pretreatment for 5 h showed the best treatment conditions: biogas yield was 6.59 times higher than that without treatment. Moreover, the proportions of total solids, total volatile solids, chemical oxygen demand and microbial count removed reached 63.52%, 74.60%, 78.15% and 82.22%, respectively. The methane content was 67.50%, indicating that the biogas had a high quality. The thermoalkaline pretreatment significantly affected biogas production and digestate characteristics, allowing it to be used as a biofertilizer. Experimental data were successfully modelled for predicting biogas production using the applied models. The R2 values reached 0.985 and 0.999 for the logistic and FFNN models, respectively.

Biogas Production Prediction Based on Feature Selection and Ensemble Learning

The allocation of biogas between power generation and heat supply in traditional kitchen waste power generation system is unreasonable; for this reason, a biogas prediction method based on feature selection and heterogeneous model integration learning is proposed for biogas production predictions. Firstly, the working principle of the biogas generation system based on kitchen waste is analyzed, the relationship between system features and biogas production is mined, and the important features are extracted. Secondly, the prediction performance of different individual learner models is comprehensively analyzed, and the training set is divided to reduce the risk of overfitting by combining K-fold cross-validation. Finally, different primary learners and meta learners are selected according to the prediction error and diversity index, and different learners are fused to construct the stacking ensemble learning model with a two-layer structure. The experimental results show that the research method has a higher prediction accuracy in predicting biogas production, which provides supporting data for the economic planning of kitchen waste power generation systems.

Biogas production prediction model of food waste anaerobic digestion for energy optimization using mixup data augmentation-based global attention mechanism.

Achieving rapid, efficient, and cost-effective anaerobic digestion (AD) of food waste is a key means to improve the efficiency of food waste treatment. However, in view of the shortage of historical anaerobic digestion data, the limitation of general neural networks in predicting biogas production, and its sensitivity to abnormal variation points, achieving accurate prediction of biogas production is not easy. This paper proposes a novel biogas production prediction model of food waste AD for energy optimization based on the mixup data augmentation integrating an improved global attention mechanism long short-term memory (LSTM). Taking the AD data of the actual factory as samples, the mixup data augmentation is introduced to generate virtual samples with the similar distribution as original samples. Then original samples and generated virtual samples are used as the input of the global attention mechanism LSTM to establish the food waste AD biogas production prediction model. Finally, the proposed method is applied in the biogas production prediction of actual food waste treatment plants. Compared with other industrial modeling models, the experimental results show that the proposed method has the highest prediction accuracy of 0.988, which performs well in predicting biogas production and can effectively guide and timely adjust feed configuration of AD plants.

Feature Engineering and Supervised Machine Learning to Forecast Biogas Production during Municipal Anaerobic Co-Digestion.

Municipalities with excess anaerobic digestion capacity accept offsite wastes for co-digestion to meet sustainability goals and create more biogas. Despite the benefits inherent to co-digestion, the temporal and compositional heterogeneity of external waste streams creates operational challenges that lead to upsets or conservative co-digestion. Given the complex microbial bioprocesses occurring during anaerobic digestion, prediction and modeling of the outcomes can be challenging, and machine learning has the potential to improve understanding and control of co-digestion processes. Biogas flows are a surrogate for process health, and here, we predicted biogas production from historical data collected by a water resource recovery facility (WRRF) during normal operation. We tested a daily lab and operational data set (n = 1089 after cleaning) and a minute-by-minute supervisory control and data acquisition (SCADA) operational data set (n = 491,761 after cleaning) to determine if forecasting biogas flow for a 24 h time horizon is feasible without collecting additional data. We found that a multilayer perceptron (MLP) neural network model outperformed tree-based and multiple linear regression models. Using a high-resolution SCADA data set for the first time, we showed that MLP neural networks could predict biogas production with an adjusted coefficient of determination (R2) of 0.78 and a mean absolute percentage error of 13.4% on a holdout test set. Adding daily laboratory analyses to the model did not appreciably improve the prediction of biogas flows. Feature engineering was essential to an accurate prediction, and 11 of the 15 most important features in the SCADA model were calculated from raw SCADA outputs. In summary, this paper demonstrates that minute-scale SCADA information collected at a municipal co-digestion facility can forecast biogas production, as a first step toward a digital twin model, without additional data collection.

Innovative approach for predicting biogas production from large-scale anaerobic digester using long-short term memory (LSTM) coupled with genetic algorithm (GA)

An artificial neural network (ANN) model called long-short term memory (LSTM), coupled with a genetic algorithm (GA) for feature selection, was used to predict biogas production of large-scale anaerobic digesters (ADs) of Tehran South Wastewater Treatment Plant (Iran), with a biogas production of approximately 30,000 Nm3/d. In order to employ the real conditions, the hydraulic retention time (HRT) of the ADs (21 days) was considered as the LSTM look-back window. To evaluate the model predictions, three different scenarios were defined. In the first scenario, the model predicted the produced biogas by using raw wastewater characteristics and reached the coefficient of determination of R2 = 0.84. The GA selected four out of eleven parameters of raw wastewater, including loads of BOD5, COD, TSS, and TN (kg/d), as the most informative data for the model. In the second scenario, the model predicted the produced biogas by employing the data of the thickened sludge streams entering the ADs and yielded a higher accuracy (R2 = 0.89). In this scenario, GA selected two out of six parameters of the sludge streams, including total flow rate (m3/d) and average solids content (w/w%). Finally, in the third scenario, by putting the parameters of the two previous scenarios together, the model's prediction accuracy increased slightly (R2 = 0.90). The results demonstrated that the GA-LSTM modeling technique could achieve reliable performance in predicting biogas production of large-scale ADs by including HRT in modeling procedure. It was also found that the raw wastewater characteristics severely affect AD behavior and can be successfully used as the input data of the AD models.

Predicting Biogas Production by Anaerobic Digestion of Organic Wastes through Kinetic Modeling

Predicting Biogas Production by Anaerobic Digestion of Organic Wastes through Kinetic Modeling

Using automated machine learning techniques to explore key factors in anaerobic digestion: At the environmental factor, microorganisms and system levels

Exploring key factors has important guidance for understanding complex anaerobic digestion (AD) systems. This study proposed a multi-layer automated machine learning framework to understand the complex interactions in AD systems and explore key factors at the environmental factor, microorganisms and system levels. The first layer of the framework identified hydraulic residence time (HRT) as the most important environmental factor, with an optimal range of 33–45 d. In the second layer of the framework, Methanocelleus (optimal relative abundance (ORA) = 3.0%) and Candidatus_Caldatribacterium (ORA = 1.7%) were found to be the key archaea and bacteria, respectively. Furthermore, the prediction of key microorganisms based on environmental factors and remaining microbial data showed the essential roles of Methanothermobacter and Acetomicrobium. The third layer for finding the optimal combination of data variables for predicting biogas production demonstrated that combined Archaea genera and environmental factors should be achieved for the most accurate prediction (root mean square error (RMSE) = 84.21). GBM had the best model performance and prediction accuracy among all the built-in models. Based on the optimal GBM model, the analysis at the system level showed that HRT was the most important variable. However the most important microorganism, Methanocelleus, within the appropriate survival range is also essential to achieve optimal biogas production. This research explores key parameters at various levels through automated machine learning techniques, which are expected to provide guidance in understanding the complex architecture of industrial and laboratory AD systems.

Restructuring anaerobic hydrolysis kinetics in plant-wide models for accurate prediction of biogas production

In this study, the effect of anaerobic hydrolysis rate on biogas production was investigated with mesophilic digesters in seven large-scale wastewater treatment plants. A linear correlation was determined between the percentage of primary sludge mass in the total sludge fed to the digester and the overall anaerobic hydrolysis rate. The anaerobic hydrolysis rate of primary sludge was determined to be three times higher than that of biological sludge. The reduction factors for anaerobic hydrolysis (ηHYD,ana) were identified in the range of 0.11–0.30 which is lower compared to the recommended range (0.30–0.50) given in the literature. This study proposes a new model approach where anaerobic degradation kinetics of influent originated (XB) and decay originated (XB,E) particulate biodegradable organics are separated. Current plant-wide models with a single kinetic expression required recalibration of the model for calculating biogas flowrate for each treatment facility with different primary and secondary sludge ratios fed to the digesters. The new model structure is able to predict biogas production of all wastewater treatment plants without any recalibration effort by segregating degradation kinetics of two particulate biodegradable organic fractions (XB, XB,E).

DNN model development of biogas production from an anaerobic wastewater treatment plant using Bayesian hyperparameter optimization

Deep neural networks have been regarded as accurate models to predict complex fermentation processes due to their capacity to learn from a high number of data sets via artificial intelligence. To enhance the performance of these models the main challenge is to select the appropriate hyperparameters, such as neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and others.This study aims to use a hybrid Bayesian optimization with tree-structured Parzen estimator (BO-TPE) to predict biogas production from real wastewater treatment plant data using deep neural network machine learning (DNN) with optimized hyperparameters. Due to the high number of missing sample measurement records, the data preprocessing process has been performed in three sequential steps: the first step is to remove columns with a high percentage of missing values. The second step concerns removing rows with a high number of missing values. The remaining missing values in the dataset were removed in the third step using the dropna function from Pandas' library. Then, on the remaining data, three normalization techniques (MinMaxScaler, RobustScaler, and StandardScaler) were used for 16 relevant features of the anaerobic digestion process (AD) and compared with Non-Normalized data. The RobustScaler technique demonstrated good prediction capabilities of biogas volume produced. The maximum predicted volume was 2236.105 Nm3/d, with the coefficient of determination (R2), the mean absolute error (MAE), and the root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively. This value remains slightly higher than the actual biogas volume produced in the wastewater treatment plant, which was 2131 Nm3/d. Adopting StandardScaler, MinMaxScaler, and Non-Normalized data provided statistical performance indicator values of (0.690; 170.518; 231.519), (0.679; 180.575; 235.648), and (0.647; 183.403; 247.203), respectively. These findings offer an autonomous strategy to monitor the effective operational variables of a large-scale digester, ensuring the stability of the complex fermentation process as well as the long-term sustainability and economic viability of the renewable energy approach in the sector of waste treatment.

Non-linear Regression Models for Predicting Biogas Yields from Selected Bio-wastes

The benefits of biogas as alternative energy to other fossil fuel sources, due to its renewability, environmentally friendly nature, health benefits, etc., cannot be overemphasized. There are numerous models for predicting biogas production rate from bio-materials, including the modified Gompertz equation. These models are primarily dependent on specific biomass parameters. When any of these parameters, like the slurry volume, changes, another round of experiments must be conducted and curve fitted before biogas yield predictions can be made. This could be time-consuming and costly. Using experimentally published data, simple empirical models can be developed for predicting biogas yields over a range of input parameters. This will eliminate the need for always performing experiments before biogas yield predictions can be made. In light of this, scarce literature provides explicit models for predicting biogas yield over a range of parameters based on published data. This study developed non-linear regression models using published data on parameters that affect biogas yields, like the slurry volume, carbon-to-nitrogen ratio, temperature, total solids, volatile solids, hydraulic retention time, and pH. The data covered seven readily available bio-wastes, including cow dung, cow dung with plant waste, cow dung with poultry dung, poultry dung with grass, pig dung, and plant wastes. On validation of the models, the results showed that the models had a relatively low standard error of estimates, Akaike information criterion, Schwarz criterion, and Hannan-Quinn information criterion. Furthermore, the coefficients of determination, R2, were between 94.62 and 98.93%. The percentage average absolute deviation (% AAD) for each model was less than 7 %. The non-linear models were found to adequately predict the biogas yields within the limits of the available data set.

Comparing the effect of mesophilic and thermophilic anaerobic co-digestion for sustainable biogas production: An experimental and recurrent neural network model study

Anaerobic digestion is a promising technology for treating bio wastes from energetic and environmental point of views. Co-digestion of wastes and process temperature are essential parameters that affect biogas production. In this study, comparing the effect of mesophilic and thermophilic anaerobic co-digestion of waste activated sludge and wheat straw at different mixing ratios is applied for sustainable biogas production based on energetic, environmental, and economic perspectives. Moreover, modeling and optimizing the process by using a time-series model and a partially connected recurrent neural network (RNN) based a slime mold algorithm (SMA) is established to calculate the optimal structure of the RNN model and the optimal values of its parameters such as the optimal number of neurons in the hidden layers, number of feedback connections, activation functions, and connection weights. The results show that the co-digestion of sludge and straw improves the carbon to nitrogen (C/N) ratio and enhances biogas production. The highest biogas production is recorded at C/N ratio of 33.15 and is approximately 30% higher in thermophilic digesters compared to mesophilic ones. Moreover, thermophilic digesters show higher chemical oxygen demand (COD) (75.38%) and total volatile solids (TVS) (72.37%) elimination than mesophilic digesters. The thermophilic digester increases the produced energy by 25.67% and decreases the production cost by 20.43% compared to the mesophilic digester in case using evacuated tube solar collectors. Furthermore, the RNN model could effectively predict biogas production, and the SMA could determine the optimal structure of the RNN model.

Optimisation and performance evaluation of response surface methodology (RSM), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) in the prediction of biogas production from palm oil mill effluent (POME)

In recent years, machine learning (ML) techniques have been developed to predict the performance of anaerobic digestion (AD) processes including methane potential and reactor stability. However, their practical applications to industrial-scale palm oil mill effluent (POME) treatment plant are limited. In this study, ML algorithms such as response surface methodology (RSM), adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) are employed to model the biogas production and methane yield from the AD of POME in a local industry-scale anaerobic covered lagoon. Results demonstrated that these models were well aligned with two years of operational data with high coefficient of determination (R2) of up to 0.98. ANFIS yields the highest prediction accuracy, with R2 of 0.9791 along with the lowest mean absolute error (MAE) of 0.0730 and root mean squared error (RMSE) of 0.1438. Subsequently, ANFIS is used in the multi-objective optimisation to maximise the biogas production and methane yield. Optimal conditions for the temperature of the anaerobic digester, pH and recirculation ratio are 38.9 °C, 7.03 and 1.89 respectively which could enhance the biogas production and methane yield by 19.4% and 12.2% respectively. Confirmatory experiments were carried out in the biogas plant under this set of optimised variables for a period of two months. The predicted biogas production and methane yield are highly correlated to the actual data with small percentage difference of 1.25% and 5.09% respectively, indicating that ANFIS model was accurate and reliable. Sensitivity analysis shows that pH has the most dominant effect on the methane yield.

Integration of anaerobic digestion with heat Pump: Machine learning-based technical and environmental assessment

Anaerobic digestion (AD)-based biogas production mitigates the environmental footprint of organic wastes (e.g., food waste and sewage sludge) and facilitates a circular economy. The work proposed an integrated system where the thermal energy demand of an AD is supplied using an air source heat pump (ASHP). The proposed system is compared to a baseline system, where the thermal energy is supplied by a natural gas-based heating system. Several machine learning models are developed for predicting biogas production, among which the Gaussian Process Regression (GPR) showed a superior performance (R2 = 0.84 and RMSE = 0.0755 L gVS−1 day−1). The GPR model further informed a thermodynamic model of the ASHP, which revealed the maximum biogas yield to be approximately 0.585 L.gVS−1.day−1 at an optimal temperature of 55 °C (thermophilic). Subsequently, life cycle assessment showed that ASHP-based AD heating systems achieved 28.1 % (thermophilic) and 36.8 % (mesophilic) carbon abatement than the baseline system.

Design of Biogas Production Prediction Model Based on Improved BP Neural Network and Genetic Algorithm

This paper presents a model for predicting biogas production. Most biogas production models are only suitable for laboratories due to their high complexity and are not suitable for practical production applications and promotion. The existing biogas stations have a low degree of automation, and biogas production is often manually estimated based on experience. In view of these problems, the BP neural network was studied and the biogas production prediction model was established. Genetic algorithm (GA) is introduced to optimize the model parameters to make the experimental results more accurate. The data show that the prediction effect based on GA-BP model is very ideal.

Exploring available input variables for machine learning models to predict biogas production in industrial-scale biogas plants treating food waste

Anaerobic digestion (AD) of food waste (FW) has been widely used in China and shows great potential in both recovering renewable energy and reducing carbon emissions. Unfortunately, many digesters suffer from unexpected perturbations and low biogas production due to the specific characteristics of food waste. Modeling of AD is crucial to better understand the process and improve efficiency. In this study, five machine learning (ML) algorithms were used to build models to predict biogas production in an industrial-scale biogas plant treating FW. Three categories of routine monitoring indicators (feed amount, feedstock properties, and digester properties), individually or collectively, were used as the input variables. The results showed that the random forest (RF) model achieved the best performance with an average R2 of 0.74 when all the indicators were contained in the dataset. Feature importance analysis revealed that the significance descended in the order of feed amount (45.9%), digester properties (38.6%), and feedstock properties (15.4%). The performance of the predictive models degraded with lag time except for the RF model, which showed the potential to predict biogas production of the next day (R2 = 0.73). The study verified the feasibility of ML models in predicting biogas yield using routine monitoring data from industrial-scale biogas plants treating FW and suggested that the monitoring indicators and frequency be redesigned to build smarter ML predictive models and improve system efficiency.

Process simulation of anaerobic digestion for methane production using aspen plus

A process simulation model was developed for biogas production via an anaerobic digestion process using Advanced System for Process Engineering (Aspen) Plus software. A total of 46 reactions were included in the model and were simulated with appropriate kinetics. For anaerobic digestion of Palm Oil Mill Effluent (POME), few studies have been reported with regards to simulation, and this biogas model has not been validated for use with POME. These works validate the ability of the developed model to predict biogas production using established data on biogas production from literature namely (O-thong et al.,2016; Mamimin et al., 2015). Average Absolute Deviation (AAD) was computed, and a deviation calculated less than 5% was obtained for both case studies of biogas production from POME with the model. The developed model was also used to study the effects of adding an external supply of H2 and CO2 at different ratios (2:1, 1:1). The results showed that the ratio of H2 and CO2, 2:1, has higher methane production compared to an equal ratio of H2 and CO2, 1:1. The developed model is flexible and able to estimate the enhancement of methanation via the input of an external supply of H2 and CO2 quantitatively.

Influence of the Construction Materials Properties of the Biodigester on the Biogas Production and Electricity Generated by the Slaughterhouse Waste

The objective of this study was to carry out a comparative analysis of the influence of the properties of the construction materials of the biodigester based on three different materials (steel, plastic PVC, and concrete) to predict the rate of biogas production from the anaerobic digestion of slaughterhouse waste. The input parameters were substrate temperature, ambient temperature, biogas temperature, biodigester temperature, specific biogas production rate, and material properties. A thermal model was developed using MATLAB® software to predict biogas production, with readily available input data for an unheated, uninsulated, and partially buried biodigester. The results obtained showed that the temperatures and the average daily biogas productions were higher for the steel biodigester (1.5 ± 0.12 m3/day at 36 ± 2℃) than those produced from the PVC (1.3 ± 0.1 m3/day at 31 ± 1.5℃) and concrete (1.2 ± 0.05 m3/day at 27 ± 2℃) biodigesters. Moreover, the production of electricity for a steel biodigester (14.64 kWh) was found to be greater than that produced from the PVC (12.81 kWh) and concrete (10.98 kWh) biodigesters. The results showed that the properties of the construction materials of the digester had a significant influence on the temperature and production of biogas, and therefore on the production of electricity. On the other hand, among the three materials studied, steel was the material, which yielded the best results. The proposed model gave rRMSE values between 7.4 and 8.3% and R2 between 0.92 and 0.96.

Understanding of the interrelationship between methane production and microorganisms in high-solid anaerobic co-digestion using microbial analysis and machine learning

Co-digestion of lignocellulosic biomass and animal manure is a common approach to increase the efficiency of methane production, but the niche differentiation and microbial metabolism of the anaerobic digestion (AD) process remain to be determined. To further explore the effect of the interaction between species and their compositional niches, the methane yield and resulting microbial community were determined by machine learning (ML) and 16S rRNA gene sequencing in mixed high-solid anaerobic digestion (HS-AD) with spray-enhanced conditions to explore the internal relationship between physical and chemical parameters and microorganisms and to speculate on the enhancement mechanism of co-digestion. In this study, three ML models (extreme learning machine (ELM), artificial neural network (ANN), and random forest (RF)) were applied to analyse and model AD of dry fermentation. The results showed that the best prediction model, based on ELM, could best predict the material biogas production in this experiment with a mean absolute error (MAE/10) of 0.678 and a coefficient of determination (R2) of 0.9574, whereas the characteristic percentage analysis of the RF model showed that butyric acid, acetic acid, and pH had three important influences on the biogas production values. Meanwhile, the results of high-throughput 16S rRNA gene sequencing and PICRUSt showed that the addition of manure containing ammonia nitrogen improved the metabolism of amino acids, enriched species capable of Clostridiales and Methanosarcinales, promoted the electronic transfer of nutrient metabolism, and thus enhanced AD. Moreover, the co-occurrence network showed that seven niches were differentiated within the HS-AD system to reduce the shock of ammonia nitrogen for methanogens. Overall, microbial analysis and ML can help understand the dynamic processes of methanogenic microorganisms and predict biogas production for the efficient operation of AD.