Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models

• Published in: Sustainability 2022-06, Vol.14 (12), p.7125
• Main Authors: Gava, Ricardo, Santana, Dthenifer Cordeiro, Cotrim, Mayara Favero, Rossi, Fernando Saragosa, Teodoro, Larissa Pereira Ribeiro, da Silva Junior, Carlos Antonio, Teodoro, Paulo Eduardo
• Format: Article
• Language: English
• Subjects: Agricultural commodities; Algorithms; Band spectra; Classification; Cultivars; Data processing; Decision trees; Error reduction; Image acquisition; Learning algorithms; Machine learning; Neural networks; Radial basis function; Remote sensing; Sensors; Software; Soybeans; Spectral bands; Statistical analysis; Support vector machines; Sustainability; Variance analysis; Vegetation
• ISSN: 2071-1050; 2071-1050
• DOI: 10.3390/su14127125

Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars.