In this paper, we aim to detect crop injury from glyphosate, a herbicide, by both traditionally used spectral indices and newly extracted features with leaf hyperspectral reflectance data for non-Glyphosate-Resistant (non-GR) soybean and non-GR cotton. The new features were extracted by canonical analysis technique, which could provide the largest separability to distinguish the injured leaves from the healthy ones. Spectral bands used for constructing these new features were selected based on the sensitivity analysis results of a physically-based leaf radiation transfer model (leaf optical PROperty SPECTra model, PROSPECT), which could help extend the effectiveness of these features to a wide range of leaf structures and growing conditions. This approach has been validated with greenhouse measured data acquired in glyphosate treatment experiments. Results indicated that glyphosate injury could be detected by NDVI (Normalized Difference Vegetation Index), RVI (Ratio Vegetation Index), SAVI (Soil Adjusted Vegetation Index), and DVI (Difference Vegetation Index) in 48 h After the Treatment (HAT) for soybean and in 72 HAT for cotton, but the other spectral indices either showed little use for separation, or did not show consistent separation for healthy and injured soybean and cotton. Compared with the traditional spectral indices, the new features were more feasible for the early detection of glyphosate injury, with leaves sprayed with a higher rate of glyphosate solution having larger feature values. This trend became more and more pronounced with time. Leaves sprayed with different glyphosate rates showed some separability 24 HAT using the new features and could be totally distinguished at and beyond 48 HAT for both soybean and cotton. These findings demonstrated the feasibility of applying leaf hyperspectral reflectance measurements for the early detection of glyphosate injury using these newly proposed features.

Remote sensing technology has been developed and applied to provide spatiotemporal information on crop stress for precision management. A series of multispectral images over a field planted cotton, corn and soybean were obtained by a Geospatial Systems MS4100 camera mounted on an Air Tractor 402B airplane equipped with Camera Link in a Magma converter box triggered by Terraverde Dragonfly® flight navigation and imaging control software. The field crops were intentionally stressed by applying glyphosate herbicide via aircraft and allowing it to drift near-field. Aerial multispectral images in the visible and near-infrared bands were manipulated to produce vegetation indices, which were used to quantify the onset of herbicide induced crop stress. The vegetation indices normalized difference vegetation index (NDVI) and soil adjusted vegetation index (SAVI) showed the ability to monitor crop response to herbicide-induced injury by revealing stress at different phenological stages. Two other fields were managed with irrigated versus nonirrigated treatments, and those fields were imaged with both the multispectral system and an Electrophysics PV-320T thermal imaging camera on board an Air Tractor 402B aircraft. Thermal imagery indicated water stress due to deficits in soil moisture, and a proposed method of determining crop cover percentage using thermal imagery was compared with a multispectral imaging method. Development of an image fusion scheme may be necessary to provide synergy and improve overall water stress detection ability.

Experiments were conducted to evaluate the Accu-Flo multiple orifice nozzle for penetration of spray into a soybean (Glycine max L.) canopy by comparing results to those from a popular straight stream nozzle and rotary atomizer. A mixture of water + Induce® adjuvant was applied at three different spray release heights in a random sequence, using an Air Tractor 402-B agricultural aircraft. Sampler stands were placed at twenty-four locations in the field. Water sensitive paper (WSP) cards were clipped onto rigid stands just above the canopy and 30 cm off the ground within the canopy. Weather data were recorded using two different stations on-site. Wind was predominantly from the west and parallel to the direction of the spray runs. The spray delivery systems compared were the Accu-Flo nozzles, (64 needle 0.020 opening), CP®-09 straight stream with 5 degree deflection, and Micronair® AU5000 atomisers (14 mesh screen) at a low volume spray rate of 18.7 l/ha. A total of 54 spray runs were made over three days, and heights were varied at 3.7 m, 4.9 m and 6.1 m. Water sensitive papers were scanned and analysed for coverage per unit card area using an image analysis system. Altitude and [Nozzle X Altitude] interaction were significant effects on coverage at the 0.01 and 0.07 significance levels, respectively, for the top cards. Nozzle type was not a significant effect on coverage for the top cards, but was significant at the 0.01 level for the bottom cards. Altitude alone had no obvious effect on coverage for the bottom cards, although it had an effect for the top cards. The highest percentage area of spray coverage was observed from the Accu-Flo nozzles, especially for the bottom cards. Average spray coverage from the Accu-Flo nozzles was 1.7 times higher than coverage from the CP® nozzles or Micronair® atomisers in the lower portion of the canopy.