Artificial intelligence applications in precision agriculture to predict the effect of Root-Knot nematodes and grafting on vegetable crop health from proximal remote sensing machines

Abstract

In precision agriculture, the Normalized Difference Vegetative Index (NDVI) considers the spectral characteristics of healthy green vegetation. This index is an effective way of detecting the green state of plants. This is why we choose to use NDVI as a reference index to predict the effect of Root-Knot nematodes and grafting on vegetable crop health from proximal remote sensing machines. These machines were used to estimate different physiological, biochemical, and agronomic parameters as indicators of stress (GA, GGA, SPAD, and canopy temperature). Leaf level pigments were measured using a handheld sensor (SPAD). Canopy vigor and biomass were assessed using vegetation indices derived from RGB images and the NDVI was measured with a portable spectroradiometer (Greenseeker). The plant level water stress was assessed indirectly by plant temperature using an infrared thermometer. We conclude that the grafted plants were less stressed and more protected against nematode attack. The comparison of NDVI index predicted by AI models showed that artificial neural network MLP demonstrated the best prediction performance than the linear regression method. However, their R-squared decreased from 0.820 to 0.772, and NRMSE increased from 12.3% to 12.4%, respectively.

Keywords

• Artificial intelligence
• precision agriculture
• crop health indicator
• grafting
• remote sensing machines