USE OF UAV SENSOR DATA AS A DECISION AID IN TURF MANAGEMENT OPERATIONS

• Sponsoring Institution: National Institute of Food and Agriculture
• Project Status: COMPLETE
• Funding Source: HATCH
• Reporting Frequency: Annual
• Accession No.: 1010749
• Project Start Date: Oct 1, 2016
• Project End Date: Sep 30, 2021
• Program Code: [(N/A)]- (N/A)

Recipient Organization
NORTH CAROLINA STATE UNIV
(N/A)
RALEIGH,NC 27695

Performing Department
Crop Science

Non Technical Summary
The use of unmanned aerial vehicles (UAV) commonly called drones will increase to monitor changes in vegetation due to environmental stress and pest problems. Equiping these UAVs with sensor that can autonomously fly, collect data and relay it back to a central computer system that can analyze the data and inform managers with decision making information to deal with these problems will allow more site specific choices for cultrual or pest management options.

Animal Health Component

100%

Research Effort Categories

Basic

(N/A)

Applied

100%

Developmental

(N/A)

Classification

Knowledge Area (KA)	Subject of Investigation (SOI)	Field of Science (FOS)	Percent
102	1620	1010	25%
102	1621	1010	25%
212	1620	1160	25%
212	1621	1160	25%

Knowledge Area
212 - Pathogens and Nematodes Affecting Plants; 102 - Soil, Plant, Water, Nutrient Relationships;

Subject Of Investigation
1620 - Warm season perennial grasses; 1621 - Cool season perennial grasses;

Field Of Science
1160 - Pathology; 1010 - Nutrition and metabolism;

Keywords

turfgrass

unmanned aerial vehicle

drone

disease and nutrient management

drought stress

Goals / Objectives
Develop an unmanned aerial platform equipped with the most reliable sensors to collect environmental data and spectral reflectance data.Develop analytical models using environmental and spectral measurement data collection from sensors mounted on unmanned aerial vehicles to evaluate turfgrass health based on nutrient and moisture conditions and disease incidence.

Project Methods
This will be a two phase project. Phase I will involve comparing spectral data collected from an UAS with ground-based data. This will allow refinement of vegetative indices most useful in determining abiotic and biotic stress. Emphasis will first be on determining relative water content, nitrogen and chlorophyll content. Subsequent investigations will be spectral detection of disease infection. Phase II will involve using the best-fit models to determine validity. Previous work found that reflectance data collected on leaf spot disease was more accurate than visual estimates in providing a rapid, objective and precise measurement of fungicide efficacy (Nutter et al., 1990). Seth-Carley (2006) found that spectral analysis of peanuts grown under nitrogen deficiency and drought stress could detect differences in crop cover at many different wavelength bandwidth groups. Numerous bandwidths were also useful in detecting early outbreaks of early leaf spot/web blotch and tomato spotted wilt disease.The most commonly used turfgrass species in North Carolina will be subjected to nutrient and drought stress under controlled conditions in small plot areas. Spectral data will be collected using multi-spectral spectrometry from an unmanned aerial vehicle and analyzed utilizing Pix4D software to calculate vegetative indices. These will be compared to data collected from a soil moisture meter, chlorophyll meter and tissue samples collected simultaneously to the flight data collection to validate the models developed.For disease detection work, frequent spectral data collection will be made on plots which have been inoculated with Rhizoctonia solani to document brown patch development in fungicide treated and untreated plots. Visual analysis of disease incidence will also be determined to determine if spectral data can be used for detection of brown patch prior to visual observation.The application of multispectral sensing and aerial imagery has the potential to greatly enhance management efforts in North Carolina.At present, we are limited to ground based sensors.Ground based sensors offer the ability to closely monitor the turf, but have limitations in how much data can be collected in timely manner. The UAV offers an opportunity to resolve many of these issues. By flying at relatively low altitudes, 200 to 400 feet above ground level, the UAV can capture high-resolution imagery. The UAV can be deployed quickly and the data made available within short times of capture. A growing list of available sensors further enhances the utility of the UAV for collecting crop data.

Progress 10/01/16 to 09/30/21

Outputs
Target Audience: Nothing Reported Changes/Problems:Restrictions due to Covid-19 protocols prohibited work to continue as planned. What opportunities for training and professional development has the project provided? Nothing Reported How have the results been disseminated to communities of interest? Nothing Reported What do you plan to do during the next reporting period to accomplish the goals? Nothing Reported

Impacts
What was accomplished under these goals? Work continued in a greenhouse experiment to document disease development using a multi-spectral camera. Work was intended to be taken to the field once experimental procedures were developed. Restrictions due to Covid-19 protocols prohibited the greenhouse work to continue and protocols were never fully developed.

Publications

Progress 10/01/19 to 09/30/20

Outputs
Target Audience: Nothing Reported Changes/Problems:Covid-19 restrictions prohibited the use of the greenhouse for experiments. What opportunities for training and professional development has the project provided? Nothing Reported How have the results been disseminated to communities of interest? Nothing Reported What do you plan to do during the next reporting period to accomplish the goals?Once Covid-19 restrictions are lifted further greenhouse experiments will be initiated.

Impacts
What was accomplished under these goals? A greenhouse experiment was conducted to evaluate the use of multi-spectral digital image analysis for predicting disease development. Data are currently being analyzed and further experiments are planned.

Publications

Progress 10/01/18 to 09/30/19

Outputs
Target Audience: Nothing Reported Changes/Problems:Limited availability of trained technical support has slowed progress until recently. Experiments are now planned for the next 6 months to accomplish the project goals. What opportunities for training and professional development has the project provided?Learning the latest digital image analysis software will be part of the training for laboratory and field technicians. How have the results been disseminated to communities of interest? Nothing Reported What do you plan to do during the next reporting period to accomplish the goals?Continue both the greenhouse and field experiments.

Impacts
What was accomplished under these goals? Greenhouse experiments are under way to develop a procedurefor rapidly processing digital images taken with a multi-spectral camera to document disease development. Next stage will be to utilize this processing technique for images taken from a UAV mounted multi-spectral camera in the field.

Publications

• Type: Conference Papers and Presentations Status: Published Year Published: 2018 Citation: Peacock, C. Edenhart-Pepe, S. Wall, J. Miller, G. 2018. Analysis of Multispectral Reflectance Data from Unmanned Aerial Vehicles to Estimate Quality, Color and Nitrogen Content in Turfgrasses Conference Proceedings European Turfgrass Society Pages 44-45. Publisher: European Turfgrass Society

Progress 10/01/17 to 09/30/18

Outputs
Target Audience:Turfgrass professionals and homeowners. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?Speaking at industry conferences on progress of project. How have the results been disseminated to communities of interest?Yes, two presentations to industry groups were made in 2018. What do you plan to do during the next reporting period to accomplish the goals?Continuing with greenhouse and field experiments on digital image analysis from images collected using multi-spectral camera mounted on a UAV to detect disease presence, nitrogen content and moisture stress on turfgrasses.

Impacts
What was accomplished under these goals? Publication of paper at European Turfgrass Society Conference. Presentations to industry groups on progress of project.

Publications

• Type: Conference Papers and Presentations Status: Published Year Published: 2018 Citation: Conference Proceedings European Turfgrass Society Analysis of Multispectral Reflectance Data from Unmanned Aerial Vehicles to Estimate Quality, Color and Nitrogen Content in Turfgrasses Page Number(s): 44-45 Publisher: European Turfgrass Society

Progress 10/01/16 to 09/30/17

Outputs
Target Audience:Turfgrass esearch personnel, turfgrass professionals. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?Training of graduate students in developiing algorithms for data processing and interpretation. How have the results been disseminated to communities of interest?Results have been presented at a regional symposium and regional conference and another is planned at an international conference for this summer. What do you plan to do during the next reporting period to accomplish the goals?Continue collecting digital image data from surveys to be conducted during spring, summer and fall periods.

Impacts
What was accomplished under these goals? Fifty-seven surverys of turfgrass research plots were conducted and digital images taken for analysis to determine the usefulness of the analysis of the reflectance data in determining turfgrass health.

Publications

• Type: Conference Papers and Presentations Status: Awaiting Publication Year Published: 2018 Citation: Analysis of Multispectral Reflectance Data from Unmanned Aerial Vehicles to Estimate Quality, Color, and Nitrogen Content in Turfgrasses