The ISRC received two final reports on projects completed in fall of 2023. Following are outcome summaries from those projects.

Lie Tang, professor of agricultural and biosystems engineering, reported on his “In-Field Soybean Seed Pod Analysis on Harvest Stocks Using 3D Imaging and Machine Learning” project.  The last paragraph in Lie’s report summarized the project results. 

“In this project, we proposed an automated soybean seed and pod counting system consisting of a robotic platform and a set of deep learning based 3D point cloud processing algorithms for high throughput operations using images captured from two sides of the soybean plant. The results demonstrate that the proposed soybean pod and seed counting methods produced better accuracies than counting them using images captured from only one side of soybean rows. The proposed system can greatly reduce human effort. In the future, the counting and classification accuracies of the proposed system can be further improved by using more image samples to train the deep learning model as some highly overlapping pods were not detected. Besides, the accuracy of pod identification could be improved by combining multiple features like distance and inclination angle. Also, when there were overexposures, the quality of images was decreased, causing degraded 3D reconstruction. Improving the illumination uniformity of the strobe lights will alleviate this problem.” Full report

Prashant Jha, professor of agronomy (now at Louisiana State University), reported on his project “Enhancing Implementation and Adoption of Non-Chemical Tactics for Integrated Weed Management in Soybean.” He reported the following results.

“A cereal rye cover crop (3-4 feet tall, with biomass of at least 4000 lbs/acre), when terminated at soybean planting, was very effective in reducing waterhemp density (by 35-40%) and seed production (up to 90%) compared with the no cover crop treatment. Waterhemp plants retained greater than 70% of seeds at the typical harvest dates of soybean in Iowa. Header loss accounted for 30% of waterhemp seed losses at soybean harvest and additional 10-15% losses occurred at the grain tank and from seeds escaping through the combine thresher (chopper). 

The Redekop™ Seed Destructor unit physically destroyed greater than 90% of waterhemp seeds that entered the combine at soybean harvest. Those seeds were mostly non-viable and failed to germinate. Thus, cover crops and weed seed destruction are effective integrated weed management tactics to mitigate herbicide-resistant waterhemp seedbanks in Iowa soybean production systems. These non-chemical tactics can reduce reliance on herbicides and preserve the utility of existing herbicide tools in soybean. In addition, my program successfully implemented the seed destructor technology at corn harvest in Iowa in 2022, indicating that growers can use this harvest weed seed control method in both corn and soybean phases of the rotation for a faster decline in weed seed banks.” This project went on to receive additional funding from the USDA-National Institute of Food and Agriculture Crop Protection and Pest Management program and was leveraged with multi-state (IA, AR, KS, IL) collaborations. Full Report