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

TL;DR

This study explores using vis-NIRS spectral data combined with machine learning to rapidly and non-invasively estimate and classify key chemical soil properties in sugarcane cultivation, aiming to improve crop management.

Contribution

It introduces a machine learning framework applied to vis-NIRS data for soil property prediction and classification, demonstrating comparable performance to existing methods.

Findings

Achieved high accuracy in pH prediction (R^2=0.8)

Successfully classified soil organic matter and mineral contents

Validated machine learning approach as effective alternative to traditional methods

Abstract

Knowing chemical soil properties might be determinant in crop management and total yield production. Traditional soil properties estimation approaches are time-consuming and require complex lab setups, refraining farmers from promptly taking steps towards optimal practices in their crops. Soil properties estimation from its 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 frameworks. This proposal uses vis-NIRS in sugarcane soils and machine learning techniques such as three regression and six classification methods. The scope is to assess performance in predicting and inferring categories of common soil properties (pH, soil organic matter OM, Ca, Na, K, and Mg), evaluated by the most common metrics. We use regression to estimate properties and classification to assess soil property status. In both cases, we achieved comparable performance on similar setups reported in the literature for property estimation for pH($R^2$=0.8, $\rho$=0.89), OM($R^2$=0.37, $\rho$=0.63), Ca($R^2$=0.54, $\rho$=0.74), Mg($R^2$=0.44, $\rho$=0.66) in the validation set.