Articles
Ramezaninia, Mohammad,
Shams, M.,
Zoofaghari, Mohammad Electronics Letters (00135194)(21)
Characterizing soil moisture around drip irrigation pipes is crucial for precise and optimized farming. Machine learning (ML) approaches are particularly suitable for this task as they can reduce uncertainties caused by soil conditions and the drip pipe positions, using features extracted from relevant datasets. This letter addresses local moisture detection in the vicinity of dripping pipes using a portable microwave imaging system. The employed ML approach is fed with two dimensional images generated using back projection as a radar-based algorithm and the Born approximation as an inverse scattering method, based on spatio-temporal (collected data at various positions over the soil surface and at different time points.) measurements at various frequencies. The study investigates the performance of K-nearest neighbour (KNN) and convolutional neural networks (CNN) algorithms for moisture classification based on these imaging techniques. We also explore the potential of KNN and CNN for moisture estimation around the plant roots and in the presence of pebbles. In general, CNN outperforms KNN in moisture content detection from microwave data, especially after applying imaging algorithms. A combination of CNN as the ML approach and the back projection algorithm to provide training data, yielded (Formula presented.) accuracy more than other models for moisture content estimation. Also, the practical results demonstrate that our method can detect soil moisture with an estimation error of less than 10%. © 2024 The Author(s). Electronics Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
Mohammadi, F.,
Bina, B.,
Amin, M.M.,
Pourzamani, H.R.,
Yavari, Z.,
Shams, M. Canadian Journal of Chemical Engineering (00084034)96(8)pp. 1762-1769
Alkylphenols (APs) received great attention in the past decade because they were on the priority hazardous substances list. The kinetics of a lab-scale moving bed biofilm reactor (MBBR) that was fed with synthetic wastewater containing 4-NonylPhenol (4-NP) and 4-tert-OctylPhenol (4-t-OP) was investigated in this paper. The MBBR reactor was evaluated under different APs, organic loading rates, and hydraulic retention times (HRT). The substrate removal rate was predicted with the first-order, second-order, Stover-Kincannon, and Monod substrate removal models. 4-NP and 4-t-OP pollutants were removed in the different percentages of 87.1 to 99.9 % and 83.2 to 99.9 %, respectively. Biokinetic parameters, like Y, KS, k, μmax, and kd, that would be favourable to design an MBBR were evaluated. Based on the results, the second-order (Grau), Stover-Kincannon, and Monod models were observed to be the most suitable for this reactor. These models showed high correlation coefficients of about 99.6, 99.1, and 92.9 %, respectively. Consequently, these models could be utilized in anticipating the performance and design of MBBR reactors. © 2017 Canadian Society for Chemical Engineering
