Remote sensing has proven to be an effective tool to collect and analyze spatial data for crop growth analytics. The thermal infrared (TIR) and color infrared (CIR) imaging using multi-spectral (MS) sensors can provide valuation data based knowledge to draw inferences on crop growth parameters especially when conducting breeding experiments for disease and drought resistance varieties. Typically, multiple remote sensing missions are conducted throughout the crop growing season to analyze crop growth parameters. Although the raw images can be stitched to develop an geo-referenced orthomosaic, extracting data from target crop rows from hundreds of breeding plots could be tedious, time consuming and prone to errors. Therefore the goals if this is to develop develop data analytic technique to map row by row RTK GPS quality planting map to rapidly extract plot level soybean canopy reflectance and emittance response to compare and contrast its advantages with manual techniques.

1. Record in-season real-time kinematic (RTK) GPS planting; and canopy thermal and multi-spectral profiles using thermal infrared and multi-spectral imaging system
2. Develop data analytic technique to map row by row RTK GPS quality planting map.
3. Evaluate the effectiveness of rapid row by row data extraction using RTK GPS row-by-row planted maps for high-throughput phenotyping and precision agriculture applications

The proposed project will develop a functional rapid data analytic procedure which will involve RTK-GPS surveyed information on test plots, high spatial and RTK-GPS as-planted data, novel techniques to utilize as-planted data to develop row-by-row planted maps. The high resolution row-by-row planted knowledge will provide ability to develop methodology for rapid extraction of plot-by-plot canopy response to quickly analyze large field datasets. It is expected that the newer data analytic technique would provide rapid data analysis but with results equivalent or better results compared to manual analysis. UAS TIRIS will accurately measure canopy temperatures under varying ambient conditions. This data analytic technique can provide critical knowledge for high throughput phenotyping and can be utilized in breeding and precision agriculture programs to develop more resilient soybean programs for the Kansas growers.

Update:
Soybean planting data from a 16-row planter was collected during the 2021 season. The planter was equipped with the custom data acquisition system to collect high frequency GPS, speed and other machine parameters. The data was utilized to develop a methodology to develop row-by-row planted maps to have high resolution information in planted row. This row-by-row data will be utilized to generate buffers and polygons for each pass as next steps for rapid analytics.

Update:

View uploaded report

On-farm planter application data was utilized to create row-by-row way point. The 10 Hz data provided high resolution RTK-GPS information required to develop row-by-row planted data for ArcGIS analysis and mapping. Way points from each row unit were converted from point data to line data (representing row unit pass), and finally buffers were created around each line. The planter row unit passes with buffers was overlaid on low altitude high-resolution data to extract crop response data.
The individual steps needed to go from planter as-applied point data to creating buffers for each row unit pass was accomplished. In year-2 the process as indicated for 2021 work will be completely automated including automatically naming each plot for plot-by-plot analysis.

Rapid data analytics of soybean breeding varietal data, particularly drought and disease resistant varieties, could support robust and timely development of soybean varieties for producers to adopt in a timely manner. With current weather uncertainties and particularly SDS disease impact on crop acres, resistant varieties could augment greater productivity and profits for soybean producers.
In addition to variety development, remote sensing data is getting more and more relevant both for researchers and producers interested in generating and utilizing data. These rapid analytic techniques would help them to extract and analyze these datasets easily and draw inferences.