Remote Sensing to Distinguish Soybean from Weeds After Herbicide Application

Abstract

Two experiments, one focusing on preemergence (PRE) herbicides and the other on postemergence (POST) herbicides, were conducted and repeated in time to examine the utility of hyperspectral remote sensing data for discriminating common cocklebur, hemp sesbania, pitted morningglory, sicklepod, and soybean after PRE and POST herbicide application. Discriminant models were created from combinations of multiple indices. The model created from the second experimental run's data set and validated on the first experimental run's data provided an average of 97% correct classification of soybean and an overall average classification accuracy of 65% for all species. These data suggest that these models are relatively robust and could potentially be used across a wide range of herbicide applications in field scenarios. From the data set pooled across time and experiment types, a single discriminant model was created with multiple indices that discriminated soybean from weeds 88%, on average, regardless of herbicide, rate, or species. Signature amplitudes, an additional classification technique, produced variable results with respect to discriminating soybean from weeds after herbicide application and discriminating between controls and plants to which herbicides were applied; thus, this was not an adequate classification technique.

Phenology affects differentiation of crop and weed species using hyperspectral remote sensing

“…With improvements in sensor technology, data management, storage, and processing power, a resurgence of interest in agricultural remote sensing has occurred in the past 15 years (Hung et al 2014;Hunt et al 2014;López-Granados 2011). Remote sensing has been used to estimate crop yield and biomass (Bandyopadhyay et al 2014;Casanova et al 1998;Diker and Bausch 2003;Hansen and Schjoerring 2003;Ray et al 2006), water stress (Bandyopadhyay et al 2014;Penuelas et al 1993), crop nutrient status (Cohen et al 2010;Goel et al 2003;Jain et al 2007), herbicide injury (Everman et al 2008;Henry et al 2004a), damage caused by plant diseases and insects (Del Fiore et al 2010;Mahlein et al 2013), and the detection and control of weeds (Bolch et al 2020;Burks et al 2002Burks et al , 2005Henry et al 2004b;Huang et al 2016;López-Granados 2011;Medlin et al 2000). Despite a growing body of research in which remote sensing in agriculture was used, additional research is needed to continue to narrow the gap between data collection and practical management decisions.…”

“…Although researchers have successfully been able to discriminate between crop and weed species in field settings using multispectral and hyperspectral remote sensing, these studies have been limited to only a few crops and weed species (Gray et al 2009;Hemming and Rath 2001;Henry et al 2004aHenry et al , 2004bKoger et al 2004). These species include common cocklebur (Xanthium strumarium L.), sicklepod [Senna obtusifolia (L.) Irwin & Barneby], pitted moringglory (Ipomoea lacunosa L.), and horsenettle (Solanum carolinense L.) in soybean [Glycine max (L.) Merr.]…”

“…These species include common cocklebur (Xanthium strumarium L.), sicklepod [Senna obtusifolia (L.) Irwin & Barneby], pitted moringglory (Ipomoea lacunosa L.), and horsenettle (Solanum carolinense L.) in soybean [Glycine max (L.) Merr.] (Henry et al 2004a;Henry et al 2004b;Koger et al 2004;Medlin et al 2000); Palmer amaranth (Amaranthus palmeri S. Watson) in cotton (Gossypium hirsutum L.); climbing milkweed et al 1985). Although these studies address some problematic weed species in crops, the list of these species is not exhaustive and more research is needed.…”

The Effect of Postemergence Herbicides on the Spectral Reflectance of Corn

“…It may be possible to find reflectance response patterns of individual weed species that would create new possibilities in site-specific weed management. Classification of weeds in crop and rangeland areas by remote sensing techniques has been accomplished (Chang et al 2004;Everitt et al 1995;Gibson et al 2004;Henry et al 2004b;Lass et al 1996;Lass and Callihan 1997;Leon et al 2003;Menges et al 1985;Smith and Blackshaw 2003;Vrindts et al 2002;Williams and Hunt 2002). found that simulated sitespecific herbicide management in nontransgenic and transgenic soybean production systems resulted in higher estimated net gains than broadcast herbicide management.…”

The Use of Early Season Multispectral Images for Weed Detection in Corn

“…Because the spectral characteristics of a pixel are determined by averaging the reflectance of all objects located within the pixel, high spatial resolution is requisite for detecting small weed seedlings early in crop growth (Bajwa and Tian 2001). However, the detection of individual weeds or lightly populated patches when weeds are small is a difficult task (Brown and Noble 2005;Henry et al 2004;Lamb and Brown 2001). In a study to test image resolution for detecting wild oat (Avena fatua L.) in seedling triticale (3 Triticosecale), Lamb et al (1999) were unable to differentiate weed-free and weedy areas at weed densities below 17 plants/m 2 , using a pixel resolution of 0.5 m 2 .…”