Affiliations: [a] School of Computer and Software, Nanjing University of Information Science and Technology, Jiangsu, China
| [b] State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University, Wuhan, Hubei, China
| [c] Department of Environmental Sciences, University of California, Riverside, CA, USA
Correspondence:
[*]
Corresponding author. Sunil Kr. Jha, School of Computer and Software, Nanjing University of Information Science and Technology, Nan-Jing 210044, China. E-mail: 002891@nuist.edu.cn.
Abstract: Microbial activities are the indicators of soil strength. The present study explores the development of efficient predictive modeling systems for the estimation of specific soil microbial dynamics, phosphate solubilization (PS), bacterial population (BP), and 1-aminocyclopropane-1-carboxylate ACC-deaminase activity. More specifically, fuzzy c-means clustering (FCM)-FIS, Wang and Mendel’s (WM) fuzzy inference systems (FIS), adaptive neuro-fuzzy inference system (ANFIS), and subtractive clustering (SC) and have been implemented with the objective to achieve the best estimation accuracy of microbial dynamics. Experimental measurements were performed using controlled pot experiment using minimal salt media. Three experimental parameters, including temperature, pH, and incubation period have been used as inputs of FCM-FIS, SC-FIS, ANFIS, and WM-FIS methods. The SC-FIS method has the best estimation accuracy for the PS (R2 of 0.99) and BP (R2 of 0.94) than the rest three FIS methods.
