Research Article Feasibility Study on the Use of a Portable NIR Spectrometer and Multivariate Data Analysis to Discriminate and Quantify Adulteration in Fertilizer Ernest Teye , 1 Charles L. Y. Amuah , 2 Kofi Atiah , 3 Ransford Opoku Darko , 1 Kwadwo Kusi Amoah , 4 Emmanuel Afutu , 4 and Rebecca Owusu 5 1 University of Cape Coast, College of Agriculture and Natural Sciences, School of Agriculture, Department of Agricultural Engineering, Cape Coast, Ghana 2 University of Cape Coast, College of Agriculture and Natural Sciences, School of Physical Sciences, Department of Physics, LAFOC, Cape Coast, Ghana 3 University of Cape Coast, College of Agriculture and Natural Sciences, School of Agriculture, Department of Soil Science, Cape Coast, Ghana 4 University of Cape Coast, College of Agriculture and Natural Sciences, School of Agriculture, Department of Crop Science, Cape Coast, Ghana 5 University of Cape Coast, College of Agriculture and Natural Sciences, School of Agriculture, Department of Agricultural Economics and Extension, Cape Coast, Ghana CorrespondenceshouldbeaddressedtoErnestTeye;ernest.teye@ucc.edu.gh Received 22 July 2022; Revised 22 October 2022; Accepted 10 November 2022; Published 29 November 2022 AcademicEditor:MassimoLucarini Copyright©2022ErnestTeyeetal. TisisanopenaccessarticledistributedundertheCreativeCommonsAttributionLicense, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Teriseinpopulationgrowthworldwiderequiresefcientmanagementofagriculturallandsthroughthecorrectdeterminationof authenticfertilizers.Inthiscurrentstudy,arapidon•sitedetectiontechniquewasdevelopedbyusingportableNIRspectroscopy inthewavelengthrangeof740–1070nmtogetherwithoptimummultivariatealgorithmstoidentifyfertilizerintegrity(unexpired, expired,andadulterated)aswellasquantifythelevels(10–50%)ofadulteration.NIRmodelswerebuiltbasedonsupportvector machine(SVM)andrandomforest(RF)foridentifcation,whilediferenttypesofpartialleastsquareregression(PLS,iPLS,Si• PLS, and GaPLS) were used for quantifcation purposes. Te models were evaluated according to identifcation rate (Rt), co• efcient of correlation in prediction (Rpre 2 ), and root mean square error of prediction (RMSEP). For the identifcation ofthe integrity of the fertilizer, among the mathematical pretreatments used, the frst derivative (FD) together with SVM gave above 99.20%identifcationrateinbothcalibrationandpredictionsets.Forthequantifcationoftheadulterants,Si•PLSwasfoundtobe superior and showed an excellent predictive potential of Rpre 2 =0.95–0.98andRMSEP=0.069–0.11forthetwofertilizertypes used.TeoverallresultsindicatedthatahandheldNIRspectrometertogetherwithappropriatealgorithmscouldbeemployedfor fast and on•site determination of fertilizer integrity. 1. Introduction Te rise in population growth worldwide puts a lot of pressure on agricultural resources. Tis rapid growth has called for agricultural intensifcation to supply the neces• sities of life, which include healthy food. To address the demand for food to support the rising population growth, agro•inputs such as fertilizers are rigorously used in agriculture to increase productivity [1]. Recent studies in• dicatedthatfertilizeruseinagriculturehasresultedin[1,2]. Nevertheless, the proliferation of fertilizer has created an opportunity for fraudsters to cheat by either selling fake, adulterated,orexpiredfertilizer,andoftenthismischiefgoes unnoticedandthefarmersareatthereceivingend.Farmers intendtoalsopassontheirassociatedburdentoconsumers. therefore, time for policymakers and major players in the Hindawi Journal of Spectroscopy Volume 2022, Article ID 1412526, 12 pages https://doi.org/10.1155/2022/1412526