Update:

View uploaded report

Small Unmanned Aircraft Thermal Infrared Imaging System to Identify Soybean Drought Tolerant Varieties (1879)
Introduction: During the course of the project two major projects were undertaken 1) Assessment of sudden death syndrome in soybean through multispectral broadband remote sensing aboard small unmanned aerial systems; and 2) Remote thermal infrared imaging for rapid screening of sudden death syndrome in soybean.
M.S. Student Graduated: Nicholle Hatton
Publications:
1. Hatton, N.,* E. Menkeb, A. Sharda, D. Merwe and W. Schapaugh. 2019. Assessment of sudden death syndrome in soybean through multispectral broadband remote sensing aboard small unmanned aerial systems. Computers and Electronics in Agriculture. https://doi.org/10.1016/j.compag.2019.105094
2. Hatton, N.,* A. Sharda, W. Schapaugh and D. Merwe. 2020. Remote thermal infrared imaging for rapid screening of sudden death syndrome in soybean. Computers and Electronics in Agriculture. (Under 2nd Review)
Project 1: Assessment of sudden death syndrome in soybean through multispectral broadband remote sensing aboard small unmanned aerial systems
Sudden Death Syndrome (SDS) has spread from the US to other countries which are causing yield loss of 10% to 15% and 70% in extreme cases from infected plants. Currently, SDS impacts are scored by visual assessment of infection severity and percent of crop diseased. The quality of manually collected row-based coarse data collected over several hours can be impacted by assessment errors and changes in diurnal environmental conditions. Small unmanned aerial systems (sUAS) offer an alternative method to provide a more accurate and reliable measurement of crop disease. A platform designed to collect high throughput aerial imagery data to quantify SDS is proposed. A comparative evaluation of ground-based and aerial remote sensing methods for the scoring of SDS is proposed to evaluate efficacy. The purpose of this research was to (1) compare accuracy and benefits of ground-based and aerial remote sensing methods for the scoring of SDS, (2) determine if pigment index (PI) can be used for the assessment and quantification of SDS, and (3) assess if PI can be utilized for determination of maturity. A seven-acre field was selected as test plots to collect reflectance using both a ground-based spectrometer and sUAS aerial imagery using a broadband modified color infrared sensor over a two-year period. Aerial imagery was collected once in 2016 (FD1) and twice in 2017 (FD2 and FD3) using an sUAS late in the growing season and at maturity each year. PI values were compared to manual collected ground-based data. Results from check plots indicated that the PI derived using aerial imagery and the ground-based spectrometer data explained 80 and 78% of the variation in SDS scores, respectively. When analyzing only high instances of SDS (SDS score >25) in the check plots aerial data and ground-based data explained 84 and 71% of the variation in SDS scores, respectively. Correlations between SDS scores and different indices analyzed showed that only PI and Blue Normalized Difference Vegetation Index (BNDVI) were significantly correlated with SDS score, with PI showing significantly greater correlations (-0.79 (FD2) and -0.72 (FD3)) to SDS on field-scale than BNDVI (-0.36 (FD2) and -0.35 (FD3)). The PI derived from aerial imagery data showed strong correlations with SDS score, SDS severity, and plant maturity, indicating that PI can be used in field studies to quantify critical growth indicators in soybean plots.

Project 2: Assessment of sudden death syndrome in soybean through multispectral broadband remote sensing aboard small unmanned aerial systems
Sudden death syndrome (SDS), a fungal infection in soybean caused by Fusarium virguliforme, greatly affects the plant health and in some cases, can cause yield losses of more than 70%. Infected plants are scored by visual assessment based on the severity and extent of infection. This manual process is time-intensive and not practical for large acreages. Diseased and stress in plants show elevated canopy temperatures that can potentially lead to the identification of unhealthy plants without manual scoring. The infection decreases nutrient distribution causing stress that results in internal plant temperature to increase. Thermal infrared (TIR) sensors have the ability to measure the emitted radiation of an object in the infrared region of the electromagnetic spectrum to estimate canopy temperatures. However, TIR sensors have not yet been utilized to capture changes in canopy temperatures to detect SDS in soybean. Therefore, the goal of this study was to 1) use a TIR sensor to assess plant health and vitality, and 2) evaluate canopy temperatures over the growing season to quantify disease development. A thermal infrared camera was mounted on a small unmanned aerial system to capture aerial imagery over the growing season. The first flight was achieved once SDS foliar symptoms began initial development. The remaining three flights occurred before, during, and after full pod fill when symptoms had reached their apex. Results show increasing correlations over the four days. Elevated canopy temperature changes were observed on canopies at early SDS symptom development. Symptoms at the end of the growing season displayed strong correlations to the canopy temperature with ?= 0.7404. Disease severity showed the strongest correlation throughout the four flights with the last at ?= 0.7245. The four flights exhibit a decreasing trend with Spearman's rho (R2=0.86 for disease severity). Therefore, thermal imaging can be utilized to detect diseased plots. Future studies will be conducted to understand how to mitigate for SDS using thermal detection.

Future Vision
Previous studies showed that thermal assessment of disease was possible through aerial platforms. This case study demonstrated that an infield assessment of soybean SDS using a TIR camera and sUAS system was possible. Correlations with temperature difference and SDS score increased throughout the growing season. Correlations with disease incidence and severity also increased through the growing season with the largest correlations toward the end of the seed fill period Overall assessment of incidence displayed the highest relationship in correlation over the days flown while severity maintained a similar relationship. The severity of SDS infection is the most practical predictor of SDS for large application use because of its high correlation and easy application. This case study exhibits the potential use of TIR remote sensing for the detection of SDS in soybean. While correlations at the beginning of the flight period were moderate, they have the potential to act as predictors to SDS within a field and give preliminary indications of the disease before visual symptoms appear. Future studies will expand this research to assess disease over an entire field and determine when the earliest that definable SDS symptoms are present.