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.
KarlenD.L., DitzlerC.A. and AndrewsS.S., Soil quality: Why andhow?Geoderma114(2003), 145–156.
2.
GhoshP.K., PalsaniyaD.R., KumarT.K., Resource conservation technologies for sustainable soil health management, In: A. Rakshit, Abhilash, H. Singh and S. Ghosh (Eds.), Adaptive Soil Management: From Theory to Practices, Springer, Singapore (2017), 161–187.
3.
PazC.G., RodríguezT.T., Behan-PelletierV.M., HillS.B., Vidal-TorradoP. and CooperM.Encyclopedia of soil science, (2016).
4.
AdnanM., ShahZ., FahadS., ArifM., AlamM., KhanI.A., MianI.A., BasirA., UllahH., ArshadM. and SaudS., Phosphate-solubilizing bacteria nullify the antagonistic effect of soil calcification onbioavailability of phosphorus in alkaline soils, Scientific Reports7(2017), 16131.
5.
BarriosE., Soil biota, Ecosystem services and land productivity, Ecological Economics64, 269–285.
6.
LangeM., EisenhauerN., SierraC.A., BesslerH. and EngelsC., R.I.Griffiths, P.G. Mellado-Vázquez, A.A. Malik, J. Roy, S. Scheuand S. Steinbeiss, Plant diversity increases soil microbial activity and soil carbon storage, Nature Communications6(2015), 6707.
7.
ZifčákováL., VětrovskýT., HoweA., and BaldrianP., Microbial activity in forest soil reflects the changes inecosystem properties between summer and winter, Environmental Microbiology18(2016), 288–301.
8.
LiuZ.F., FuB.J., LiuG.H. and ZhuY.G., Soil quality: Concept, indicators and its assessment, Acta Ecologica Sinica3(2006), 901–913.
9.
ArmeniseE., Redmile-GordonM.A., StellacciA.M., CiccareseA. and RubinoP., Developing a soil quality index to compare soil fitness for agricultural use under different managements in the Mediterranean environment, Soil and Tillage Research130(2013), 91–98.
10.
MukhlisinM., El-ShafieA. and TahaM.R., Regularized versusnon-regularized neural network model for prediction of saturatedsoil-water content on weathered granite soil formation, Neural Computing and Applications21(2012), 543–553.
11.
TaghavifarH. and MardaniA., Use of artificial neural networks forestimation of agricultural wheel traction force in soil bin, Neural Computing and Applications24(2014), 1249–1258.
12.
ShiriJ., KeshavarziA., KisiO., Iturraran-ViverosU.,
BagherzadehA.,
MousaviR. and KarimiS., Modeling soil cation exchangecapacity using soil parameters: Assessing the heuristic models, Computers and Electronics in Agriculture135(2017), 242–251.
13.
ShiriJ., KeshavarziA., KisiO. and KarimiS., Using soil easily measured parameters for estimating soil water capacity: Soft computing approaches, Computers and Electronics in Agriculture141(2017), 327–339.
14.
HughesJ.B., HellmannJ.J., RickettsT.H. and BohannanCountingB.J., The uncountable: Statistical approaches to estimating microbial diversity, Applied and Environmental Microbiology67(2001), 4399–4406.
15.
HaiderM.A., PakshirajanK., SinghA. and ChaudhryS., Artificial neural network-genetic algorithm approach to optimize media constituents for enhancing lipase production by a soilmicroorganism, Applied Biochemistry and Biotechnology144(2008), 225–235.
16.
TajikS., AyoubiS. and NourbakhshF., Prediction of soil enzymes activity by digital terrain analysis: Comparing artificial neural network and multiple linear regression models, Environmental Engineering Science29(2012), 798–806.
17.
AhmadZ., CrowleyD., MarinaN. and JhaS.K., Estimation ofbiosurfnt yield produced by Klebseilla sp. FKOD36 bacteria using artificial neural network approach, Measurement81(2016), 163–173acta.
18.
EbrahimiM.,
SineganiA.A.S,
SarikhaniM.R. and MohammadiS.A., Comparison of artificial neural network and multivariate regression models for prediction of Azotobacteria population in soil underdifferent land uses, Computers and Electronics in Agriculture140(2017), 409–421.
19.
DaleziosI. and SiebertK.J., Comparison of pattern recognition techniques for the identification of lactic acid bacteria, Journal of Applied Microbiology91(2001), 225–236.
20.
DudekG., GrzywnaZ.J. and WillcoxM.L., Classification of antituberculosis herbs for remedial purposes by using fuzzy sets, Biosystems94(2008), 285–289.
21.
FernandesF.C., RigdenD.J. and FrancoO.L., Prediction of antimicrobial peptides based on the adaptive neuro-fuzzy inference system application, Peptide Science98(2012), 280–287.
22.
HeddamS., BermadA. and DechemiN., ANFIS-based modelling forcoagulant dosage in drinking water treatment plant: A case study, Environmental monitoring and assessment184(2012), 1953–1971.
23.
LeonardN., BlanchetonJ.P. and GuiraudJ.P., Populations of heterotrophic bacteria in an experimental recirculating aquaculture system, Aquacultural Engineering22(2000), 109–120.
OlsenS.R., Phosphorus, Methods of Soil Analysis (1982), 403–430.
26.
PenroseD.M. and GlickB.R., Methods for isolating and characterizing ACC deaminase-containing plant growth-promoting rhizobacterial, Physiologia Plantarum118(2003), 10–15.
27.
KlirG., YuanB., Fuzzy sets and Fuzzy Logic, Prentice Hall, New Jersey, USA, (1995).
28.
BezdekJ.C., Pattern recognition with fuzzy objective function algorithms, Springer Science & Business Media, (2013).
29.
WangL.X. and MendelJ.M., Generating fuzzy rules by learning from examples, IEEE Transactions on Systems, Man, and Cybernetics22(1992), 1414–1427.
30.
R Core Team, R: A language and environment for statistical computing, R Foundation for Statistical Computing, Austria, Vienna, (2017) https://www.R-project.org.
31.
RizaL.S., BergmeirC., HerreraF. and Ben’itezJ.M., frbs: Fuzzy Rule-Based Systems for Classification and Regression in R, Journal of Statistical Software65(2015), 1–30.
32.
JangJ.S.R. and SunC.T., Neuro-fuzzy and soft computing: Acomputational approach to learning and machine intelligence, Prentice Hall, USA, (1997).
33.
ChiuS., Fuzzy model identification based on cluster estimation, Journal of Intelligent and Fuzzy Systems2(1994), 267–278.
34.
SteelR.G., TorrieJ., Principles and Procedures of Statistics, McGraw-Hill Book Company, New York, (1960).
35.
KeshavarziA., SarmadianF., RahmaniA., AhmadiA., LabbafiR. and IqbalM.A., Fuzzy clustering analysis for modeling of soil cation exchange capacity, Australian Journal of AgriculturalEngineering3(2012), 27–33.
