Applications of artificial intelligence in anaerobic co-digestion: Recent advances and prospects.

Anaerobic co-digestion (AcoD) offers several merits such as better digestibility and process stability while enhancing methane yield due to synergistic effects. Operation of an efficient AcoD system, however, requires full comprehension of important operational parameters, such as co-substrates ratio, their composition, volatile fatty acids/alkalinity ratio, organic loading rate, and solids/hydraulic retention time. AcoD process optimization, prediction and control, and early detection of system instability are often difficult to achieve through tedious manual monitoring processes. Recently, artificial intelligence (AI) has emerged as an innovative approach to computational modeling and optimization of the AcoD process. This review discusses AI applications in AcoD process optimization, control, prediction of unknown input/output parameters, and real-time monitoring. Furthermore, the review also compares standalone and hybrid AI algorithms as applied to AcoD. The review highlights future research directions for data preprocessing, model interpretation and validation, and grey-box modeling in AcoD process.

Application of machine learning in anaerobic digestion: Perspectives and challenges.

Anaerobic digestion (AD) is widely adopted for remediating diverse organic wastes with simultaneous production of renewable energy and nutrient-rich digestate. AD process, however, suffers from instability, thereby adversely affecting biogas production. There have been significant efforts in developing strategies to control the AD process to maintain process stability and predict AD performance. Among these strategies, machine learning (ML) has gained significant interest in recent years in AD process optimization, prediction of uncertain parameters, detection of perturbations, and real-time monitoring. ML uses inductive inference to generalize correlations between input and output data, subsequently used to make informed decisions in new circumstances. This review aims to critically examine ML as applied to the AD process and provides an in-depth assessment of important algorithms (ANN, ANFIS, SVM, RF, GA, and PSO) and their applications in AD modeling. The review also outlines some challenges and perspectives of ML, and highlights future research directions.

Anaerobic co-digestion of various organic wastes: Kinetic modeling and synergistic impact evaluation.

Anaerobic mono- and co-digestion of coffee pulp (CP), cattle manure (CM), food waste (FW) and dewatered sewage sludge (DSS), were assessed using biochemical methane potential tests. The effects of two different inocula, anaerobically digested cattle manure (ADCM) and anaerobically digested waste activated sludge (ADWAS), and five different co-feedstock ratios for CP:CM and FW:DSS (1:0, 4:1, 2:1, 4:3, and 0:1) on specific methane yields were also evaluated. Mono-digestions of both CP and FW yielded the highest methane yield compared to the co-digestion ratios examined. Furthermore, no synergistic or antagonistic effect was observed for any of the co-digestion ratios tested. Nine different kinetic models (five conventional mono-digestion models and four co-digestion models) were compared and evaluated for both mono- and co-digestion studies. For CP:CM, cone and modified Gompertz with second order equation models were the best-fit for mono- and co-digestion systems, respectively, while for FW:DSS, superimposed model showed the best-fit for all systems.

Anaerobic co-digestion: Current status and perspectives.

Anaerobic digestion is a long-established technology for the valorization of diverse organic wastes with concomitant generation of valuable resources. However, mono-digestion (i.e., anaerobic digestion using one feedstock) suffers from challenges associated with feedstock characteristics. Co-digestion using multiple feedstocks provides the potential to overcome these limitations. Significant research and development efforts have highlighted several inherent merits of co-digestion, including enhanced digestibility due to synergistic effects of co-substrates, better process stability, and higher nutrient value of the produced co-digestate. However, studies focused on the underlying effects of diverse co-feedstocks on digester performance and stability have not been synthesized so far. This review fills this gap by highlighting the limitations of mono-digestion and critically examining the benefits of co-digestion. Furthermore, this review discusses synergistic effect of co-substrates, characterization of microbial communities, the prediction of biogas production via different kinetic models, and highlights future research directions for the development of a sustainable biorefinery.

Nanobubble technology in anaerobic digestion: A review.

Nanobubble technology has significant potential to improve the anaerobic digestion (AD) process by ameliorating the rate-limiting steps of hydrolysis and methanogenesis, as well as providing process stability by reducing sulfide and volatile fatty acid (VFA) levels. Nanobubbles (NB) can enhance substrate accessibility, digestibility, and enzymatic activity due to their minuscule size, high electrostatic interaction, and ability to generate reactive oxygen species. Air- and O2-NB can create a microaerobic environment for higher efficiency of the electron transport system, thereby reducing VFAs through enhanced facultative bacterial activity. Additionally, H2- and CO2-NB can improve hydrogenotrophic methanogenesis. Recently, several studies have employed NB technology in the AD process. There is, however, a lack of concise, synthesized information on NB applications to the AD process. This review provides an in-depth discussion on the NB-integrated AD process and the putative mechanisms involved. General discussions on other potential applications and future research directions are also provided.