Machine learning-aided inverse design for biogas upgrading through biological CO2 conversion.

The biogas upgrading process through bioconversion of CO2 to CH4 by hydrogenotrophic methanogens is an attractive strategy for energy decarbonation. Many studies have optimized operational parameters to improve key performance indicators such as CH4% and H2 utilization efficiency. However, inconsistent laboratory conditions make it challenging to compare results. Existing models for analyzing operating conditions can only assess the impact of individual conditions and lack the ability to simultaneously optimize multiple conditions. To address this, two XGBoost models were built with R2 of 0.779 and 0.903 with data collected from literatures and were embedded into multi-objective partitive swarm optimization algorithm to optimal operating conditions. Predictions were compared with experimental validations under optimized conditions, revealing an 8.50% and 2.95% relative error in CH4% and H2 conversion rate, respectively. This approach streamlines biogas upgrading processes, offering a data-driven solution to enhance efficiency and consistency in the pursuit of sustainable methane production.

Machine learning facilitated the conceptual design of an alum dosing system for phosphorus removal in a wastewater treatment plant.

Wastewater treatment plants (WWTPs) face challenges in controlling total phosphorus (TP), given more stringent regulations on TP discharging. In particular, WWTPs that operate at a small scale lack resources for real-time monitoring of effluent quality. This study aimed to develop a conceptual alum dosing system for reducing TP concentration, leveraging machine learning (ML) techniques and data from a full-scale WWTP containing incomplete TP information. The proposed system comprises two ML models in series: an Alert model based on LightGBM with an accuracy of 0.92, and a Dosage model employing a voting algorithm through combining three ML algorithms (LightGBM, SGD, and SVC) with an accuracy of 0.76. The proposed system has demonstrated the potential to ensure that 88.1% of the effluent remains below the TP discharge limit, which outperforms traditional dosing methods and could reduce overdosing from 61.3 to 12.1%. Furthermore, the SHapley Additive exPlanations (SHAP) analysis revealed that incorporating the output features from the previous cycle and utilizing the results of the Alert model as the input features for dosage prediction could be an effective method for data with limited information. The findings of this study have practical applications in improving the efficiency and effectiveness of TP control in small-scale WWTPs, providing a valuable solution for complying with stringent regulations and enhancing environmental sustainability.

Prediction of biogas production in anaerobic digestion of a full-scale wastewater treatment plant using ensembled machine learning models.

Anaerobic digestion (AD) of sludge is a key approach to recover useful bioenergy from wastewater treatment and its stable operation is important to a wastewater treatment plant (WWTP). Because of various biochemical processes that are not fully understood, AD operation can be affected by many parameters and thus modeling AD processes becomes a useful tool for monitoring and controlling their operation. In this case study, a robust AD model for predicting biogas production was developed using ensembled machine learning (ML) model based on the data from a full-scale WWTP. Eight ML models were examined for predicting biogas production and three of them were selected as metamodels to create a voting model. This voting model had a coefficient of determination (R2 ) at 0.778 and a root mean square error (RMSE) of 0.306, outperformed individual ML models. The Shapley additive explanation (SHAP) analysis revealed that returning activated sludge and temperature of wastewater influent were important features, although they affected biogas production in different ways. The results of this study have demonstrated the feasibility of using ML models for predicting biogas production in the absence of high-quality data input and improving model prediction through assembling a voting model. PRACTITIONER POINTS: Machine learning is applied to model biogas production from anaerobic digesters at a full-scale wastewater treatment plant. A voting model is created from selected individual models and exhibits better performance of predication. In the absence of high quality data, indirect features are identified to be important to predicting biogas production.

Metabolic Mechanism of Sulfadimethoxine Biodegradation by Chlorella sp. L38 and Phaeodactylum tricornutum MASCC-0025.

Antibiotic resistance is one of the most important environmental challenges. Microalgae has been considered as a promising green media for environmental purification. In this work, sulfadimethoxine (SDM) biodegradation potential of Chlorella sp. L38 and Phaeodactylum tricornutum MASCC-0025 is investigated. Experimental results indicated that the tested freshwater and marine microalgae strains presented stress response to SDM addition. For Chlorella sp. L38, it has a good adaptability to SDM condition via antioxidant enzyme secretion (SOD, MDA, and CAT up to 23.27 U/mg, 21.99 µmol/g, and 0.31 nmol/min/mg) with removal rate around 88%. P. tricornutum MASCC-0025 exhibited 100% removal of 0.5 mg/L SDM. With increasing salinity (adding a certain amount of NaCl) of cultivation media, the removal rate of SDM by microalgae increased. Although its adaptive process was slower than Chlorella sp. L38, the salinity advantage would facilitate enzyme accumulation. It indicated that microalgae could be used to remove SDM from freshwater and marine environment via suitable microalgae strain screening.

Biodegradation and metabolic fate of thiamphenicol via Chlorella sp. UTEX1602 and L38.

Thiamphenicol (TAP) is a typical medicament in animal husbandry and aquaculture for treating diverse infections. In this work, thiamphenicol biodegradation performance via microalgae was tested. The cultivation results showed that TAP could be biodegraded via the target algae. Chlorella sp. L38 presented strong adaptive ability to high concentration TAP. Biodegradation, biosorption and bioaccumulation were the dominant metabolic fates. Biodegradation contributed around 97% of the total removal efficiency at the TAP concentration of 46.2 mg·L-1. The removal of TAP by Chlorella L38 and UTEX1602 agreed with the kinetic range of zero-order reaction, and the shortest half-lives were 3.2 d and 5.0 d. Based on the identification of metabolites, the metabolic pathway of TAP by microalgae was proposed, including chlorination, chlorine substitution, dehydration and hydroxylation. Therefore, biological treatment via microalgae has the potential for TAP purification.

Bio-regeneration of different rich CO2 absorption solvent via microalgae cultivation.

As one of the most mature carbon capture technologies, thermal regeneration of rich CO2 absorption solvent is a crucial challenge due to its high energy consumption (typically in the range of 3-6 MJ/kg CO2). In this work, a concept of bio-regeneration was proposed using microalgae to convert bicarbonate (which is one of the dominant components in rich solution) into value-added biomass. To evaluate the performance of bio-regeneration, different rich solution (including NH4HCO3, KHCO3 and NaHCO3) were investigated. Experimental results indicated that NH4HCO3 could be a promising bicarbonate carrier for the proposed absorption-microalgae hybrid process, which had a higher biomass productivity (55.36 mg·L-1·d-1) compared to KHCO3 and NaHCO3 and carbon sequestration capacity could be up to 158.3 mg·L-1·d-1. Meanwhile, pH adjustment was an effective approach to further intensify the performance of hybrid process. As a result, bio-regeneration of solvents could be a promising alternative to the conventional thermal regeneration.

Real-time ultrasound elastography for differentiation of benign and malignant thyroid nodules: a meta-analysis.

OBJECTIVES: The clinical challenge of managing thyroid nodules nowadays is to diagnose the minority of malignant disease. Real-time ultrasound elastography, which can measure tissue elasticity, is used as a complement to conventional sonography for improving the diagnosis of thyroid tumors. There are 2 common criteria for evaluating an elastogram: the elasticity score and strain ratio. This meta-analysis was performed to expand on a previous meta-analysis to assess the diagnostic power of ultrasound elastography in differentiating benign and malignant thyroid nodules for elasticity score and strain ratio assessment. METHODS: The MEDLINE, EMBASE, PubMed, and Cochrane Library databases up to January 31, 2013, were searched. The pooled sensitivity, specificity, and summary receiver operating characteristic curve were obtained from individual studies with a random-effects model. The extent and sources of heterogeneity were explored. RESULTS: A total of 5481 nodules in 4468 patients for elasticity score studies and 1063 nodules in 983 patients for strain ratio studies were analyzed. The overall mean sensitivity and specificity of ultrasound elastography for differentiation of thyroid nodules were 0.79 (95% confidence interval [CI], 0.77-0.81) and 0.77 (95% CI, 0.76-0.79) for elasticity score assessment and 0.85 (95% CI, 0.81-0.89) and 0.80 (95% CI, 0.77-0.83) for strain ratio assessment, respectively. The areas under the curve for the elasticity score and strain ratio were 0.8941 and 0.9285. CONCLUSIONS: These results confirmed those obtained in the previous meta-analysis. Ultrasound elastography has high sensitivity and specificity for identification of thyroid nodules. It is a promising tool for reducing unnecessary fine-needle-aspiration biopsy.

Macroporous polypyrrole-TiO2 composites with improved photoactivity and electrochemical sensitivity.

Macroporous polypyrrole (PPy)-TiO2 composites were prepared by in situ oxidative polymerization of pyrrole in the macropores of TiO2. The formation mechanism of the PPy nanoparticles, including nucleation and further growth, was proposed by studying the particle growth process with increasing reaction time. The special growth process favors the formation of good cohesion and stabilized interface between the inorganic and organic phases. The conversion ratio of pyrrole monomer is in the range of 65.3-97.5%, and PPy content in the composites can reach as high as 21.04% with well preservation of the macroporous framework. Furthermore, dispersed PPy particles of ~100 nm in size can be obtained by etching the composites in HF acid, which is smaller than the PPy particles synthesized in the absence of the TiO2 template due to the pore-confinement effect. The composites show improved photoactivity on degradation of dye under simulated sunlight irradiation and electrocatalytic activity toward the detection of H2O2 in 0.1M phosphate buffer solution. Synergetic interaction between the two components and the porous structure is considered to be responsible for the enhanced properties of the new composites.