Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 5;195(9):1018.
doi: 10.1007/s10661-023-11576-0.

Using AI and BES/MFC to decrease the prediction time of BOD5 measurement

Ivan Medvedev  1 , Mariya Kornaukhova  1 , Christoforos Galazis  2 , Bálint Lóránt  3 , Gábor Márk Tardy  3 , Alexander Losev  1 , Igor Goryanin  4   5
Affiliations

Using AI and BES/MFC to decrease the prediction time of BOD5 measurement

Ivan Medvedev et al. Environ Monit Assess. .

Abstract

Biochemical oxygen demand (BOD) is one of the most important water/wastewater quality parameters. BOD5 is the amount of oxygen consumed in 5 days by microorganisms that oxidize biodegradable organic materials in an aerobic biochemical manner. The primary objective of this research is to apply microbial fuel cells (MFCs) to reduce the time requirement of BOD5 measurements. An artificial neural network (ANN) has been created, and the predictions we obtained for BOD5 measurements were carried out within 6-24 h with an average error of 7%. The outcomes demonstrated the viability of our AI MFC/BES BOD5 sensor in real-life scenarios.

Keywords: Biochemical Oxygen demand; Biosensor; Microbial fuel cell; Neural network.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Several typical examples of voltage variation over time, when domestic wastewater was used as a sample for MFC
Fig. 2
Fig. 2
Several typical examples of voltage variation over time, are when brewery wastewater was used as samples for MFC
Fig. 3
Fig. 3
Schematic drawing of neural network architectures for a direct prediction approach. Where the input, dense, dropout, and output values correspond to the values from Table 1. After the hidden layers, the neuron values pass through the Relu activation function
Fig. 4
Fig. 4
Schematic drawing of neural network architectures for an indirect prediction approach. Where the input, dense, dropout, and output values correspond to the values from Table 2. After the hidden layers, the neuron values pass through the Relu activation function
Fig. 5
Fig. 5
Plots comparing actual and predicted BOD5 values (for the direct prediction approach). a When using 24-h voltage data; b. for 16 h; c 12 h before; d. 8 h; e 6 h; f for 2 h
Fig. 6
Fig. 6
A few examples of the ratio of real to predicted voltage when voltage values measured over 12 h were used as input to the ANN. Blue graph—real voltage data; orange—obtained using a neural network
Fig. 7
Fig. 7
A few examples of the ratio of real voltage to predicted voltage, when voltage values measured over 2 h were used as input data for the ANN. Blue graph—real voltage data; orange—obtained using a neural network
Fig. 8
Fig. 8
The ratio of the real and predicted charge, when voltage values measured over 2 h were applied to the ANN input. Blue graph—charge values obtained from real data; orange—charge values obtained from predicted data
Fig. 9
Fig. 9
The ratio of the real and predicted charge, when voltage values measured over 12 h were applied to the ANN input. Blue graph—charge values obtained from real data, orange—charge values obtained from predicted data
Fig. 10
Fig. 10
Plots comparing actual and predicted BOD5 values (for the indirect prediction approach). a When using 24-h voltage data; b for 16 h; c 12 h before; d 8 h; e. 6 h; f for 2 h
See this image and copyright information in PMC

References

    1. Fang F, Zang G, Sun M, Yu H. Optimizing multi-variables of microbial fuel cell for electricity generation with an integrated modeling and experimental approach. Applied Energy. 2013;110:98–103. doi: 10.1016/j.apenergy.2013.04.017. - DOI
    1. Garg A, Vijayaraghavan V, Mahapatra S, Tai K, Wong C. Performance evaluation of microbial fuel cell by artificial intelligence methods. Expert Systems with Applications. 2014;41:1389–1399. doi: 10.1016/j.eswa.2013.08.038. - DOI
    1. Ismail ZZ, Al-wared AI, Jaeel AJ. Recourse recovery of bioenergy from cellulosic material in a microbial fuel cell fed with giant reed-loaded wastewater. Biofuels. 2019;10:737–745. doi: 10.1080/17597269.2017.1409057. - DOI
    1. Kingma, D. P., & Ba, J.L. (2015). Adam: a method for stochastic optimization 3rd international conference on learning representations, ICLR 2015 – conference track proceedings San Diego. 10.48550/arXiv.1412.6980
    1. Li, S., Jin, X., Xuan, Y., Zhou, X., Chen, W., Wang, Y. X., & Yan, X. (2019). Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Advances in Neural Information Processing Systems, 32, 5243-5253.

MeSH terms

LinkOut - more resources