TY  - JOUR
EP  - 1064
ID  - scholars19984
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85170710612&doi=10.1016%2fj.ijhydene.2023.08.290&partnerID=40&md5=e35e47fa3f5281ed297728e0c1d91d09
N1  - cited By 1
A1  - Lim, C.E.
A1  - Chew, C.L.
A1  - Pan, G.-T.
A1  - Chong, S.
A1  - Arumugasamy, S.K.
A1  - Lim, J.W.
A1  - Al-Kahtani, A.A.
A1  - Ng, H.-S.
A1  - Abdurrahman, M.
KW  - Bacteria; Bacteriology; Biofilms; Forecasting; Machine learning; Microbial fuel cells; Physicochemical properties; Wastewater treatment
KW  -  Artificial neural network modeling; Cell-based; Community generation; Conducting Complexes; Geobacter; Literature studies; Machine-learning; Physicochemical property; Power- generations; Sludge inoculums
KW  -  Neural networks
TI  - Predicting microbial fuel cell biofilm communities and power generation from wastewaters with artificial neural network
Y1  - 2024///
N2  - Artificial neural network (ANN) was used to predict the biofilm communities present in the microbial fuel cells (MFCs), as well as the power generation from wastewater treatment. The ANN model was able to predict the total abundances of seven exoelectrogenic bacteria-associated genera, viz. Anaeromyxobacter, Bacillus, Clostridium, Comamonas, Desulfuromonas, Geobacter, and Pseudomonas for the MFCs based on the physicochemical properties of the sludge inocula, with accuracies in the range of 62�92. An additional ANN model was developed to integrate the biofilm results and predict the power generation from wastewater, with an accuracy of 84 when validating with literature studies. The results show that ANN is a useful tool for predicting the biofilm communities and power generation from MFCs, thus avoiding the necessity of conducting complex biofilm metagenome analysis, and greatly aiding future parametric investigation and scale-up studies. © 2023 Hydrogen Energy Publications LLC
VL  - 52
JF  - International Journal of Hydrogen Energy
AV  - none
SP  - 1052
ER  -