2017
Detecting Chlorosis Regions and Predicting Yield of Soybean by Large Scale UAV
Contributor/Checkoff:
Category:
Sustainable Production
Keywords:
Field management Nutrient managementSoil healthTillageYield trials
Parent Project:
This is the first year of this project.
Lead Principal Investigator:
John Nowatzki, North Dakota State University
Co-Principal Investigators:
Sreekala Bajwa, North Dakota State University
R Jay Goos, North Dakota State University
Oveis Hassanijalilian, North Dakota State University
+2 More
Project Code:
Contributing Organization (Checkoff):
Institution Funded:
Brief Project Summary:

Farmers could benefit from an early season estimation of the final yield since they could contract their product at more competitive prices. One of the reasons that can reduce yield in soybean is chlorosis which can be caused by lack of usable iron, nitrogen, potassium or rooting restriction. Unmanned Aircraft Vehicles (UAV) can fly over the fields and give lots of information in such a short time. By using Near Infrared (NIR) and normal camera we can monitor different characteristics of the fields like plants growth and plants health status by calculation of different Vegetation Indices (VIS). The method proposed in this study will make use of aerial imagery of the large scale UAV...

Unique Keywords:
#crop management systems
Information And Results
Project Deliverables

Upon completion of this research, we expect to have lots of VI maps for soybean fields in Hillsboro, ND and relate several of them to soil properties to find out the reason of chlorosis in those fields. VI maps will also be related to yield maps to find a method to predict yield before harvest. We also determine the best spatial resolution for the images, so they need less storage capacity as well as time to process. After finding the chlorosis regions, farmers can apply different management practices to their fields to avoid chlorosis and increase yield. They also can apply variable rate application fertilizer to use the proper amount of fertilizer according to the chlorosis regions based on VI maps. Results of this work will be presented at conferences, grower meetings, field day tours and NDSU websites. The work will also be submitted to peer reviewed journals for publication.

Final Project Results

Update:

View uploaded report Word file

Executive Summary: Detecting Chlorosis Regions and Predicting Yield of Soybean by Large Scale UAV

Principle Investigator: John Nowatzki, Agricultural and Biosystems Engineering, NDSU

This project used imagery collected with unmanned aircraft systems (UAS) to identify iron deficiency chlorosis (IDC) in soybeans fields and predict soybean yields.

The objectives included: 1) to evaluate the use of various spatial resolution and imagery types at various each crop growth stages to predict soybean yield; and 2) to evaluate types of imagery and vegetative indices to detect chlorosis regions in soybean fields.

This study was conducted on Dr. Ted Helms IDC yield trials. The trial were located in Galesburg, Leonard, Colfax, and Amenia. There were 40 soybean varieties, with four replications in three locations. We used Dark Green Color Index (DGCI) to assess the greenness of the soybean plots. The higher the DGCI, the greener the plots are. Similarly low values of DGCI indicates chlorosis in soybean plots.

Project personnel used ArcGIS software to identify spots in the fields with low vegetative indices to identify areas of chlorosis in soybean fields. Project personnel walked fields to identify chlorosis areas in these fields.

The project was able to determine the best spatial resolution for the images to identify areas of chlorosis in soybean fields.

The United Soybean Research Retention policy will display final reports with the project once completed but working files will be purged after three years. And financial information after seven years. All pertinent information is in the final report or if you want more information, please contact the project lead at your state soybean organization or principal investigator listed on the project.