Fall armyworm (FAW) is one of the most detrimental pests in corn crops due to its ability to extensively damage plants and therefore cause significant yield losses. Key components of integrated pest management for FAW include monitoring, cultural, physical, biological, chemical, and biotechnological strategies. However, consistent, and accurate monitoring strategies for FAW populations on corn fields before obvious signs of infestations are challenging and time-consuming. Near-infrared (NIR) spectroscopy is a non-invasive, non-destructive, rapid technique used for determining quality of different food and agricultural products by measuring its physiochemical changes. Nonetheless, insect feeding is a important plant stressor that causes physical and chemical changes/ responses in plants.Therefore, this study focuses on evaluating if FAW infestations can be detected using NIR spectroscopy in combination with Machine Learning algorithims, by identifying spectral signatures caused by larval feeding before obvious symptoms of defoliation are visible. To determine if NIR can be used as a tool for monitoring lepidopteran pest infestations, plants will be treated separately with fall armyworm larvae, and keep plants with no damage/ "pest free". Two days post-infestation, NIR measurement will be taken from each plant. Through this study we aim to understand and identify differences in the spectral profile of the plantm and to determine if insect feeding can be accurately identified compared to healthy, non-stress plants using this technique.