International Journal of Multidisciplinary Research and Growth Evaluation  |  ISSN (Online): 2582-7138  |  Double-Blind Peer Review  |  Open Access  |  CC BY 4.0

Current Issues
     2026:7/3

International Journal of Multidisciplinary Research and Growth Evaluation

ISSN (Online): 2582-7138 | Open Access

Evaluating Machine Learning Ensemble Methods for Cotton Mapping in Pakistan Using MODIS NDVI & EVI Data

Author(s):

Published:

Volume: 7 | Issue: 1 | Pages: 854-865

Subject: Artificial Intelligence

Country: China

DOI: https://doi.org/10.54660/IJMRGE.2026.7.1.854-865

License: CC BY 4.0

Full Text (PDF)

Open Access - Free to Download

Download Full Article (PDF)

Alternative download link

Abstract

Accurate crop classification is crucial for agricultural management, food security assessment, and environmental monitoring. In Pakistan, where agriculture is a key economic sector, precise mapping of crops like cotton is essential for effective resource management and policy-making. Remote sensing technologies provide cost-effective and efficient alternatives to traditional field surveys. This study leverages machine learning techniques, particularly ensemble methods to classify cotton using time-series Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) data from MODIS satellite imagery. The year 2014 was selected for analysis due to the availability of high-quality FAO-SPOT reference data and representative climatic conditions during that growing season. The research compares the performance of various machine learning algorithms and evaluates the effectiveness of an ensemble approach in improving classification accuracy within Pakistan's agricultural landscape. Machine learning models, including Random Forest, Support Vector Machine (SVM), Gradient Boosting, XGBoost, and an Ensemble Voting classifier, were applied to EVI and NDVI time-series data. Performance was assessed using a 5-fold cross-validation approach to ensure robust evaluation. The models demonstrated strong predictive capabilities, with Gradient Boosting achieving the highest overall accuracy (OA) of 93.02%, followed closely by the Ensemble Voting model at 92.53%. Other models, including Random Forest, SVM, and XGBoost, also performed well, with OA of 92.46%, 92.17%, and 92.24%, respectively. The inherent limitations of MODIS 250 m spatial resolution, including mixed-pixel effects in fragmented agricultural landscapes, are acknowledged. These results highlight the potential of machine learning for large-scale cotton classification and agricultural monitoring in Pakistan.

How to Cite This Article

Zakria Zaheen, Wilson Kalisa, Muhammad Awais, Khandakar Md Bappy, Abdul Basit, Hidayat Ullah, Shawkat Ali, Jiahua Zhang (2026). Evaluating Machine Learning Ensemble Methods for Cotton Mapping in Pakistan Using MODIS NDVI & EVI Data . International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE), 7(1), 854-865. DOI: https://doi.org/10.54660/IJMRGE.2026.7.1.854-865

Export Citation:

BibTeX RIS EndNote

References

  1. 1. Khurshid N, Sharif H, Tabash MI, El Refae GA. Anassessmentofasymmetricimpactoffinancialstabilityandagriculturalsubsidiesonagriculturalproductionin Pakistan. JAgribus Dev Emerg Econ.2024. doi:10.1108/JADEE-10-2023-0248.
  2. 2. Asma, Illyas M, Zeb N, Javed A, Shabbir I, Bibi A. Arecentreviewoncottonandclimatechangein Pakistan: impacts, mitigation, andadaptation. Insights JHealth Rehabil.2025;3(2\:631-638. doi:10.71000/J14PEN89.
  3. 3. Pereirade Sousa S, Nunesda Silva M, Braga C, Vasconcelos MW. Weavingthefuture: theroleofnovelfibresandmoleculartraceabilityincirculartextiles. Appl Sci.2026;16(1\. doi:10.3390/APP16010497.
  4. 4. Javed K, Smagghe G, Kang YQ, Wang Q, Wang Y. Artificialintelligenceinthemassproductionofnaturalenemiesforbiologicalcontrolinmodernagriculture. Pest Manag Sci.2025;81(12\:7577-7592. doi:10.1002/PS.70116.
  5. 5. Latif RMA, He J, Umer M. Mappingcroplandextentin Pakistanusingmachinelearningalgorithmson Google Earth Enginecloudcomputingframework. ISPRSInt JGeo-Inf.2023;12(2\. doi:10.3390/IJGI12020081.
  6. 6. Batkalova A, Hao P. Trainingsamplemigrationfortemporalcroplandmappingin Central Asia. Land.2026;15(1\:156. doi:10.3390/LAND15010156.
  7. 7. Srikar R, Singh M, Sinha B, Bisaria J. Exploringtheprospectsofclimate-forestnexusforsustainablelandscapes. In: Eco-Resilience Biology.2025. p.249-276. doi:10.1201/9781003588580-14.
  8. 8. Massey R, etal. MODISphenology-derived, multi-yeardistributionofconterminous U. S. croptypes. Remote Sens Environ.2017;198:490-503. doi:10.1016/J. RSE.2017.06.033.
  9. 9. Wenxin Z, Misbari S, Doh SI. Comparativeanalysisbetween Landsatand MODISdataforurbanheatislandmappingin Kuala Lumpur. CONSTRUCTION.2025;5(2\:139-145. doi:10.15282/CONSTRUCTION. V5I2.12436.
  10. 10. Salehin SMU, Poudyal C, Rajan N, Bagavathiannan M. Covercroptypesinfluencebiomassestimationusingunmannedaerialvehicle-mountedmultispectralsensors. Remote Sens(Basel\.2025;17(8\. doi:10.3390/RS17081471.
  11. 11. Be MC, etal. Comparativeanalysisofmachinelearningalgorithmsforobject-basedcropclassificationusingmultispectralimagery. Drones.2025;9(11\. doi:10.3390/DRONES9110763.
  12. 12. Okolie C, etal. Assessmentofexplainabletree-basedensemblealgorithmsfortheenhancementof Copernicusdigitalelevationmodelinagriculturallands. Int JImage Data Fusion.2024;15(4\:430-460. doi:10.1080/19479832.2024.2329563.
  13. 13. Khan R, Goyal A, Kanyal HS, Parashar D, Sharma SK, Iqbal M. Improvedmachinelearningframeworkwithfeatureengineeringand SHAPanalysisforpredictingwinequality. Discov Appl Sci.2026;8(1\:27. doi:10.1007/S42452-025-07999-8.
  14. 14. Sakib M, Mustajab S, Alam M. Ensembledeeplearningtechniquesfortimeseriesanalysis: acomprehensivereview, applications, openissues, challenges, andfuturedirections. Cluster Comput.2024;28(1\:73. doi:10.1007/S10586-024-04684-0.
  15. 15. Ahmed K, Dubey MK, Kajal, Pandey DK. Ensemblemethodsfordata-drivenmodelinginagricultureandapplications. In: Data-Driven Modeling.[Place-164. doi:10.1002/
  16. 9781394287925. CH6.
  17. 16. Sagi O, Rokach L. Ensemblelearning: asurvey. Wiley Interdiscip Rev Data Min Knowl Discov.2018;8(4\: e1249. doi:10.1002/WIDM.1249.
  18. 17. Shahzad MU, etal. Machinelearning-basedcottonyieldforecastingunderclimatechangeforprecision International Journalof Multidisciplinary Researchand Growth Evaluationwww. allmultidisciplinaryjournal. com864|Pageagriculture. Smart Agric Technol.2025;12:101117. doi:10.1016/J. ATECH.2025.101117.
  19. 18. Shahzad S, Wang B. Geographicalindicationsandsustainabledevelopment: bridgingpolicygapsin-economicgrowth. Sustainability(Basel\.2025;17(11\. doi:10.3390/SU17115114.
  20. 19. Cohen-Manrique CS, Rodr?guez-Manrique JA, Burbano-Bustos AF, Castro-Rodr?guez JA. Analysisofseasonalchangesinvegetationcoverinthe La Caimaneramarsh(Colombia\usingremotesensingandsatellitesensorimagery. F1000 Res.2026;14:748. doi:10.12688/f1000research.164770.2.
  21. 20. Liu D, Yu C, Jiang L, Feng R. Multiscalesynergyofsolar-inducedchlorophyllfluorescenceandnormalizeddifferencevegetationindexenhancesmaizechillinginjurymonitoring: aremotesensingverificationin Northeast China. JAppl Remote Sens.2025;19(4\:044503. doi:10.1117/
  22. 1. JRS.19.044503.
  23. 21. Handbookonremotesensingforagriculturalstatistics. Publicationpreparedintheframeworkofthe Global Strategytoimprove Agriculturaland Rural Statistics.[Placeunkndate
  24. 22. Zhao LQ, Lan, Zhao Q. Examiningthepotentialofintegratingmachinelearninginspatialmulticriteriaevaluationforurbansuitabilityanalysis.2024 Aug2.
  25. 23. Jaloliddinov J, etal. Large-scalecottonclassificationunderinsufficientsampleconditionsusinganadaptivefeaturenetworkand Sentinel-2imageryin Uzbekistan. Agronomy(Basel\.2023;14(1\. doi:10.3390/AGRONOMY14010075.
  26. 24. Zhang J, Zheng Y, Shi Y. Asoftlabelmethodformedicalimagesegmentationwithmultiraterannotations. Comput Intell Neurosci.2023;2023:1883597. doi:10.1155/2023/1883597.
  27. 25. Zhao T, etal. Assessingtheaccuracyandconsistencyofsixfine-resolutiongloballandcoverproductsusinganovelstratifiedrandomsamplingvalidationdataset. Remote Sens(Basel\.2023;15(9\. doi:10.3390/RS15092285.
  28. 26. Zhang X, etal. Mappingsoilavailablenitrogenusingcrop-specificgrowthinformationandremotesensing. Agriculture(Basel\.2025;15(14\. doi:10.3390/AGRICULTURE15141531.
  29. 27. Standard Scalerscikit-learn1.8.0documentation.. Availablefrom: https://scikit-learn. org/stable/modules/generated/sklearn. preprocessing. Standard Scaler. html.
  30. 28. Li Y, Yang Y, Song P, Duan L, Ren R. Animproved SMOTEalgorithmforenhancedimbalanceddataclassificationbyexpandingsamplegenerationspace. Sci Rep.2025;15(1\:23521. doi:10.1038/s41598-025-09506-w.
  31. 29. Netayawijit P, Chansanam W, Sorn-In K. Interpretablemachinelearningframeworkfordiabetesprediction: integrating SMOTEbalancingwith SHAPexplainabilityforclinicaldecisionsupport. Healthcare(Basel\.2025;13(20\. doi:10.3390/HEALTHCARE13202588.
  32. 30. Du Q, Zhai J. Applicationofartificialintelligencesensorsbasedonrandomforestalgorithminfinancialrecognitionmodels. Meas Sens.2024;33:101245. doi:10.1016/J. MEASEN.2024.101245.
  33. 31. Researchontheapplicationofsupportvectormachinesinhigh-dimensionaldatamining. IEEEXplore. Availablefrom: https://ieeexplore. ieee. org/abstract/document/
  34. 1102008032. Acomparativestudyofmachinelearningmodelsforidentificationofantiviralpeptidesusingvariousencodedfeatures. IEEEXplore. Availablefrom: https://ieeexplore. ieee. org/abstract/document/1135295733. v?M, Armanuos AM. Hydraulicperformancemodelingofinclineddoublecutoffwallsbeneathhydraulicstructuresusingoptimizedensemblemachinelearning. Sci Rep.2025;15(1\:27592. doi:10.1038/s41598-025-10990-3.
  35. 34. Jackson M, Marvin G, Chakrabarty A. Robustensemblemachinelearningforprecisionagriculture. In:2022 International Conferenceon Innovationsin Science, Engineeringand Technology(ICISET\;2022. p.492-497. doi:10.1109/ICISET54810.2022.9775879.
  36. 35. Niu Q, Lei J, Fang Q, Zhang L. Dynamicmonitoringandanalysisofmountainexcavationandlandcreationprojectsin Lanzhouusingmulti-sourceremotesensingandmachinelearning. Remote Sens(Basel\.2026;18(2\:273. doi:10.3390/RS18020273.
  37. 36. Feng F, Gao M, Gao R, Jin Y, Yang Y. Anovelframeworkforwintercropmappingusingsamplegenerationautomaticallyand Bayesian-optimizedmachinelearning. Agronomy(Basel\.2025;15(9\. doi:10.3390/AGRONOMY15092034.
  38. 37. Sher M, Remyes D, Sharma R, Toma M. Learningdynamicsanalysis: assessinggeneralizationofmachinelearningmodelsforopticalcoherencetomographymulticlassclassification. Informatics(Basel\.2025;12(4\:128. doi:10.3390/INFORMATICS12040128.
  39. 38. Chi J, Bu X, Zhang X, Wang L, Zhang N. Insightsintocottonseedcultivaridentificationusing Ramanspectroscopyandexplainablemachinelearning. Agriculture(Basel\.2023;13(4\. doi:10.3390/AGRICULTURE13040768.
  40. 39. Wang X, etal. Evaluatingtheeffectivenessofmachinelearninganddeeplearningmodelscombinedtime-seriessatellitedataformultiplecroptypesclassificationoveralarge-scaleregion. Remote Sens(Basel\.2022;14(10\. doi:10.3390/RS14102341.
  41. 40. Rezk NG, Attia AF, El-Rashidy MA, El-Sayed A, Hemdan EED. Anefficient Io T-basedcropdamagepredictionframeworkinsmartagriculturalsystems. Sci Rep.2025;15(1\:27742. doi:10.1038/s41598-025-12921-8.
  42. 41. Shafique R, Khan SH, Ryu J, Lee SW. Weather-drivenpredictivemodelsforjassidandthripsinfestationincottoncrop. Sustainability(Basel\.2025;17(7\. doi:10.3390/SU17072803.
  43. 42. Dou S, etal. Whatiswrongwithyourcodegeneratedbylargelanguagemodels?Anextensivestudy. Sci China Inf Sci.2026;69(1\:112107. doi:10.1007/S11432-025-4632-8.
  44. 43. Elmotawakkil A, etal. Hydro Predictorahybridmachinelearningmodelforaddressingdatascarcityingroundwaterprediction. Sci Rep.2025;15(1\:44069. doi:10.1038/s41598-025-24960-2.
  45. 44. Wen L, Ryan S, Powell M, Ling JE. Fromclusterstocommunities: enhancingwetlandvegetationmappingusingunsupervisedandsupervisedsynergy. Remote Sens(Basel\.2025;17(13\. doi:10.3390/RS
  46. 17132279. International Journalof Multidisciplinary Researchand Growth Evaluationwww. allmultidisciplinaryjournal. com865|Page
  47. 45. Chaiyana A, Kumari A, Jagadish SVK. Evaluatingtrade-offsamongcottonyield, groundwaterextraction, andfutureprojectionsforsustainablewatermanagementinthe Texas High Plains. Agric Water Manag.2025;322:110045. doi:10.1016/J. AGWAT.2025.110045.
  48. 46. Gunda SK. Softwaredefectpredictionusingadvancedensembletechniques: afocusonboostingandvotingmethod. In: IEEEInternational Conferenceon Electronic Systemsand Intelligent Computing, ICESIC2024;2024. p.157-161. doi:10.1109/ICESIC61777.2024.10846550.
  49. 47. Zuhairi AH, etal. Performanceanalysisoftree-basedensemblemachinelearningmodelforfloodforecastingintropicalregions. IEEEAccess.2025. doi:10.1109/ACCESS.2025.3632033.
  50. 48. Manokhin V, Vovk V, Sancetta A. Machinelearningforprobabilisticprediction;2022.
  51. 49. Sang H, Zhang L, Chen T, Guo W, Zhang Z. Onboarddeploymentofremotesensingfoundationmodels: acomprehensivereviewofarchitecture, optimization, andhardware. Remote Sens(Basel\.2026;18(2\:298. doi:10.3390/RS18020298.
  52. 50. Uddin M, Samiappan S, Drewry JL. Automatedyieldmonitordatapost-processingpipelineviaexplainablemodelbenchmarkingandstackedensemble. Comput Electron Agric.2026;241:111278. doi:10.1016/J. COMPAG.2025.111278.
  53. 51. Singh A, etal. Multi-modelmachinelearningforpredictingtractoroperatordiscomfortcausedbywhole-bodyvibration. Comput Electron Agric.2026;243:111375. doi:10.1016/J. COMPAG.2025.111375.
  54. 52. Rana SS, etal. Predictingandidentifyinglandfeaturesutilisingremotesensingsatelliteimageryandmachinelearningtechniques. Kashf JMultidiscip Res.2024;1(12\:17-35. doi:10.71146/KJMR141.
  55. 53. Yadav CS, etal. Multi-classpixelcertaintyactivelearningmodelforclassificationoflandcoverclassesusinghyperspectralimagery. Electronics(Basel\.2022;11(17\. doi:10.3390/ELECTRONICS11172799.
  56. 54. Naveed M, etal. Cottoncultivatedareadetectionandyieldmonitoringcombiningremotesensingwithfielddatainlower Indus Riverbasin, Pakistan. Environ Monit Assess.2023;195(3\:401. doi:10.1007/S10661-023-11004-3.
  57. 55. Rathore UBPS, Sajan B, Singh SK, Kanga S. Cropacreageandyieldestimationusingremotesensing;2025. p.325-351. doi:10.1007/978-3-032-02118-2_13.
  58. 56. Ejigu D, Pushpalatha R, Kumar S. Assessinglandproductivityusing NDVIandenvironmentaldriversforprecisionfarmplanning: insightsfrom Dewgain, Rural India.2026. doi:10.2139/SSRN.6057120.
  59. 57. Zhang X, Liu Z, Li X, Bao H, Zhang N, Bai T. High-accuracycottonfieldmappingandspatiotemporalevolutionanalysisofcontinuouscroppingusingmulti-sourceremotesensingfeaturefusionandadvanceddeeplearning. Agriculture(Basel\.2025;15(17\. doi:10.3390/AGRICULTURE15171814.
  60. 58. Xu J, Luo Y, Wu G, Wang W, Zhang Z, Kanapathipillai A. Multi-sourcedata-driven CNNTransformerhybridmodelingforwindenergydatabasereconstructioninthetropical Indian Ocean. Remote Sens(Basel\.2026;18(2\:226. doi:10.3390/RS18020226.
  61. 59. Chen L, Fan X. Financialriskforecastingwith RGCT-prerisk: arelationalgraphandcross-temporalcontrastivepretrainingframework. JKing Saud Univ Comput Inf Sci.2025;37(6\:143. doi:10.1007/S44443-025-00166-4.
  62. 60. Pagliaro A. Artificialintelligencevs. efficientmarkets: acriticalreassessmentofpredictivemodelsinthebigdataera. Electronics(Basel\.2025;14(9\. doi:10.3390/ELECTRONICS14091721.
  63. 61. Baker MR, Buyrregressionstrategiesforconcretestrengthestimation: acomparativeensembleapproach. In: Studiesin Systems,-122. doi:10.1007/978-3-032-07738-7_6.
  64. 62. Hou Z, etal. Highresolutioncroptypeandrotationmappinginfarmingpastoralecotonein Chinausingmulti-satelliteimageryand Google Earth Engine. Remote Sens(Basel\.2025;17(10\. doi:10.3390/RS17101707.
  65. 63. Saravana MK, Roopa MS, Arunalatha JS, Venugopal KR. Transformersformultivariatetimeseriesforecasting: comprehensiveanalysis, challenges, researchopportunitiesandfutureprospects. IEEEAccess.2026. doi:10.1109/ACCESS.2026.3654408.
  66. 64. H?hl A, Ofori-Ampofo S, Fern?ndez-Torres M?, Kuzu RS, Zhu XX. Alarge-scale, multitask, multisensorydatasetforclimate-awarecropmonitoringinthe USfrom
  67. 20182022. Sci Data.2026;13(1\:72. doi:10.1038/s41597-026-06611-x.
  68. 65. Mahmood GG, Sacco P, Carabin G, Mazzetto F. Farm-leveloperationalmonitoringinsmartagriculture: reviewandclassificationframework. Sustainability(Basel\.2026;18(1\. doi:10.3390/SU18010419.

Publication Information

Journal: International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE)

Publisher: Anfo Publication House

ISSN: 2582-7138 (Online)

Frequency: Bimonthly

Language: English

Open Access: Yes - This article is distributed under the terms of the Creative Commons Attribution 4.0 International License

Share This Article: