Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties

Knowing chemical soil properties might be determinant in crop management and total yield production. Traditional property estimation approaches are time-consuming and require complex lab setups, refraining farmers from taking steps towards optimal practices in their crops promptly. Property estimation from spectral signals(vis-NIRS), emerged as a low-cost, non-invasive, and non-destructive alternative. Current approaches use mathematical and statistical techniques, avoiding machine learning framework. Here we propose both regression and classification with machine learning techniques to assess performance in the prediction and infer categories of common soil properties (pH, soil organic matter, Ca, Na, K, and Mg), evaluated by the most common metrics. In sugarcane soils, we use regression to estimate properties and classification to assess soil's property status and report the direct relation between spectra bands and direct measure of certain properties. In both cases, we achieved similar performance on similar setups reported in the literature.