[{
  "type": "article-journal",
  "title": "IMPACT OF POST EMERGENCE HERBICIDES ON WEED DYNAMICS, YIELD AND NUTRIENT UPTAKE OF MAIZE: A COMPARATIVE EVALUATION OF LINEAR AND MACHINE LEARNING APPROACH",
  "author": [
    {
      "family": "Rao",
      "given": ""
    },
    {
      "family": "Jambamma",
      "given": ""
    },
    {
      "family": "B.",
      "given": ""
    },
    {
      "family": "Sravanthi",
      "given": ""
    },
    {
      "family": "Reddy",
      "given": ""
    },
    {
      "family": "I.V.",
      "given": ""
    }
  ],
  "issued": {
    "date-parts": [[2027]]
  },
  "container-title": "Journal of Animal and Plant Sciences",
  "ISSN": "1018-7081",
  "volume": "37",
  "issue": "1",
  "DOI": "https://doi.org/10.36899/JAPS.2027.1.0005",
  "abstract": "<p style=\"text-align: justify;\">Effective weed management is essential for improving maize (<em>Zea mays</em> L.) productivity through the identification of selective and efficient post-emergence herbicides. Field experiments were conducted during 2019&ndash;2021 at the farmer field to evaluate weed control efficacy, weed dynamics, and maize yield under four herbicide treatments i.e. T<sub>1</sub>: Weedy check, T<sub>2</sub>: Tembotrione (42% S.C.) 287.5 mL ha<sup>-1</sup> [25 DAS (days after sowing)], T<sub>3</sub>: Topramezone (33.6% S.C.)&nbsp; 100 mL ha<sup>-1</sup> (25 DAS) and T<sub>4</sub>: Halosulfuron Methyl (75% WG) 90 g ha<sup>-1 </sup>(25 DAS) with data averaged across five locations for four treatments each year. The resulting dataset comprised 12<strong> </strong>treatments-year observations with 11 agronomic variables. The machine-learning analyses were conducted as an initial exploratory assessment. Using chronological validation, 2019&ndash;2020 observations were used for training and 2021 observations for independent testing (66:34 split). Among the evaluated treatments, application of tembotrione proved the greatest broad-spectrum weed suppression and produced the highest grain yield<strong> (</strong>8,936 kg ha⁻&sup1;), compared with the untreated control <strong>(</strong>3,897&ndash;4,324 kg ha⁻&sup1;). Spearman correlation analysis revealed strong positive associations between grain yield and nutrient uptake of maize (&rho; = 0.916) and strong negative associations with the weed index (&rho; = &minus;0.909) and broadleaf weed density (&rho; = &minus;0.825). These predictive modeling using linear regression (LR), random forest (RF), and XGBoost was evaluated using the coefficient of determination (R&sup2;), root mean square error (RMSE), and mean absolute error (MAE). Within the constraints of the small dataset, LR achieved the best predictive performance (R&sup2; = 0.949, RMSE = 379.58, MAE = 327.96). Ridge Regression with SHAP analysis identified total nutrient input (total NPK; +408.95) as the strongest predictor of maize yield while year had the lowest contribution (+192.78). These findings demonstrate that effective broad-spectrum weed management enhances maize productivity, while the modelling provides preliminary insights into weed control, soil fertility and yield relationships.</p>",
  "publisher": "Pakistan Agricultural Scientists Forum",
  "URL": "https://thejaps.org.pk/AbstractView.aspx?mid=2026-JAPS-568"
}]