Selected agronomic traits are the conventional approach to evaluating corn plantings. However, this approach is only some-encompassing for planting plots; hence, needing a more precise method for the evaluation. Unmanned aerial vehicles (UAVs) or drones are precision technologies that provide detailed information regarding cropping status through image analysis to make the assessment and prediction process more efficient. Therefore, using agronomic traits and drones together is a necessary approach to take. Presented research aimed to develop a productivity prediction model based on selective and precision secondary characters. The experiment happened from September to December 2021 in Tarowang Village, Takalar Regency, South Sulawesi, Indonesia. Eight maize cultivars, i.e., ADV1, Pioneer 1, Pioneer 2, NK, Bisi 18, Sinhas 1, NASA 29, and ADV2, grown and evaluated in a randomized completely block design with three replications, served as the main factor. Based on the results, the weight of 1000 grains, was a recommended agronomic trait in the evaluation and prediction of corn planting. In addition, normalized difference vegetation index (NDVI)-UAV, as part of ‘Technology 4.0’, considerably showed effectiveness in predicting maize productivity. Meanwhile, combining two variables notably have the highest accuracy in predicting corn productivity compared with their independent predictions. However, the advanced research still needs optimizing by using more maize genotypes and locations to increase the accuracy and forecast of the model.

Keywords: Agronomic traits, multivariate regression, NDVI, Technology 4.0, Zea mays

Key findings: Combining a selective agronomic trait (weight of 1000 grain) and NDVI-UAV revealed more effectiveness in evaluating the maize genotypes. This combined strategy can enhance the accuracy and precision of corn yield prediction. The multiple regression formulation from combining the two characters was 17.0486 NDVI + 0.038 weight of 1000 grain – 20.244. Moreover, the maize cultivar NK-7328 proved to be the best for cultivation in Takalar Region, Indonesia.