Source: TEXAS TECH UNIVERSITY submitted to NRP
CAPACITY BUILDING FOR AI-DRIVEN RESEARCH AND EDUCATION ON UAS APPLICATIONS IN PRECISION AGRICULTURE
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
ACTIVE
Funding Source
OTHER GRANTS
Reporting Frequency
Annual
Accession No.
1031297
Grant No.
2023-70001-40993
Cumulative Award Amt.
$749,999.00
Proposal No.
2023-01530
Multistate No.
(N/A)
Project Start Date
Sep 1, 2023
Project End Date
Aug 31, 2026
Grant Year
2023
Program Code
[NLGCA]- Capacity Building Grants for Non Land Grant Colleges of Agriculture
Recipient Organization
TEXAS TECH UNIVERSITY
(N/A)
LUBBOCK,TX 79409
Performing Department
(N/A)
Non Technical Summary
Our project is dedicated to advancing precision agriculture in the Southern Great Plains region, addressing the crucial issue of sustainable farming. Precision agriculture, which incorporates cutting-edge technologies like Unmanned Aerial Systems (UAS) and Artificial Intelligence, allows for the collection and analysis of high-resolution data on soil properties, crop characteristics, and environmental factors. By implementing precision agriculture practices, farmers can make data-driven decisions to optimize resource allocation, increase crop yields, and minimize environmental impact.The significance of this research extends beyond the agricultural community, as it directly impacts economic stability, environmental conservation, and food security in the broader community. As we work towards these goals, our project goes beyond simple research. We are committed to sharing knowledge through education and training, playing a key role in promoting the adoption of precision agriculture practices.In line with our mission, we will develop a comprehensive new course that focuses on UAS applications in precision agriculture. This course will equip the next generation of agricultural professionals with the necessary knowledge and skills to drive innovation and sustainability in the field. Additionally, we will provide cohort training activities, offering hands-on experiences and practical applications to enhance understanding and proficiency in precision agriculture techniques.Through these educational and training efforts, we aim to empower farmers with actionable insights, fostering productivity while minimizing resource waste. Emphasizing the adoption of precision agriculture techniques will lead to improved water use efficiency, better preservation of natural resources, and ultimately, a more resilient and sustainable agricultural sector. We hope to create a positive impact not only for farmers but for the broader community as well, contributing to economic growth, environmental protection, and ensuring a steady and reliable food supply for generations to come.
Animal Health Component
40%
Research Effort Categories
Basic
30%
Applied
40%
Developmental
30%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
1020199106030%
2050210208030%
9030199302020%
6010199301020%
Knowledge Area
601 - Economics of Agricultural Production and Farm Management; 102 - Soil, Plant, Water, Nutrient Relationships; 205 - Plant Management Systems; 903 - Communication, Education, and Information Delivery;

Subject Of Investigation
0210 - Water resources; 0199 - Soil and land, general;

Field Of Science
1060 - Biology (whole systems); 3020 - Education; 2080 - Mathematics and computer sciences; 3010 - Economics;
Goals / Objectives
The long-term goals of the Large-scale Comprehensive Initiatives (LCI) project are multifold. First, we would like to establish an Artificial Intelligence (AI) based precision agriculture program at Texas Tech University to address crucial agricultural production challenges in the Southern Great Plains region. Second, we would like to develop a collaborative on-farm research program to support precision agriculture training that would sustain beyond the project period and continue to benefit researchers, students, and the farming community in the long term. The Southern Great Plains region is one of the most intensively farmed regions in the world. Cotton, corn, and grain sorghum are the major crops contributing billions of dollars in agricultural revenue to the local economy. Major production challenges include declining irrigation water, deterioration of soil health, wind erosion, and maintenance of profitable production. The application of AI-based precision agriculture and unmanned aerial system (UAS) technologies would be critical in addressing these challenges. To enable this, we will develop an on-farm research and teaching program with involvement from local producers and agricultural industries in the region. This will provide students with opportunities to experience real-world agricultural production challenges first-hand. We also envision our project to improve interactions between educators, farming communities, service providers, and other related industries to enhance awareness of AI and digital technologies and to identify challenges and opportunities in technology development and adoption.Our proposed project is cross-disciplinary and mainly aligns with two disciplines: Agricultural and Biological Engineering (E) and Plant Sciences and Horticulture (P). With a solid background and extensive experience in precision agriculture, UAS technologies, computer science, and agricultural economics, our interdisciplinary team proposes the following specific objectives to achieve our long-term goals.1) Establish on-farm research in collaboration with local producers to foster the development of UAS-based precision agriculture technologies to address critical production issues in the region;2) Create a collaborative course to improve undergraduate and graduate learning in UAS application in precision agriculture;3) Build a cohort training and on-farm demonstration program to connect education, farming communities, and the industry to train students, identify challenges and opportunities in UAS application in crop production, and strengthen the agricultural technology workforce.
Project Methods
The project will be conducted through a combination of research, education, and outreach efforts. The general scientific methods will include data collection through ground-based and UAS-based methods, data analysis using statistical techniques and AI-driven algorithms, and interpretation of results for practical applications in precision agriculture. A unique aspect of this project is the integration of UAS technology with AI-driven data analysis to develop innovative solutions for yield prediction, crop monitoring, and resource management.Research Methods:Data Collection: Ground-based data collection will involve gathering soil physical and chemical properties, apparent soil electrical conductivity, elevation, and crop characteristics, including plant growth and development and yield. UAS will be used for aerial data acquisition, capturing multispectral and thermal imagery to assess crop health and stress levels.Data Analysis: The collected data will be processed and analyzed using AI-based algorithms to derive meaningful insights and correlations between crop characteristics, soil properties, and environmental factors. Statistical analysis will be used to validate the accuracy of the predictive models.Experimental Design: On-farm research trials will be leveraged to enable the comparison of different treatments and practices to identify the most effective precision agriculture strategies.Education and Outreach Efforts:Curriculum Development: The project will develop a new course focused on UAS applications in precision agriculture. This course will incorporate cutting-edge research findings and hands-on training using UAS technology.Workshops and Trainings: Outreach activities will include workshops and trainings for local producers, extension agents, and educators. These events will cover the latest advancements in precision agriculture and UAS applications, fostering knowledge transfer and adoption.Outreach: outreach services will assist farmers, crop consultants, and companies in implementing precision agriculture practices, leveraging the data collected and analyzed during the research phase.Evaluation Plan:The team will work with Dr. Susan O'Shaughnessy, a Research Agricultural Engineer with the Conservation and Production Research Laboratory of USDA-ARS in Bushland, Texas.Impact Assessment: The project's success will be evaluated based on key milestones and measurable indicators of success. These indicators will include the number of students enrolled in the new course, the participation and adoption and of precision agriculture practices by local producers, and the level of engagement and satisfaction of the target audience with the trainings.Data Collection: Data will be collected through surveys, questionnaires, and feedback forms to assess the knowledge gained and behavioral changes among the target audience. Additionally, the number of farmers adopting precision agriculture practices and the extent of their technology integration will be quantified.Publication and Dissemination: The impact of the project will also be measured through the dissemination of research findings in scientific journals, conference proceedings, and extension materials. The reach and citation of these publications will provide an additional measure of success and knowledge dissemination.

Progress 09/01/23 to 08/31/24

Outputs
Target Audience:During this reporting period, the project engaged a diverse array of target audiences through educational, research, and outreach activities. Our efforts focused on reaching stakeholders within the precision agriculture sector, including students, researchers, producers, and industry professionals. The research and educational efforts of this project focused on providing theoretical and hands-on training in UAS and precision agriculture technologies to both graduate and undergraduate students through coursework and research activities. Two courses were central to this effort. New Graduate Course (PSS 6001-006): This problem course, launched in Fall 2024 at Texas Tech University, enrolled five graduate students and introduced them to UAS applications in agriculture. Topics include UAS safety and policies, UAS image acquisition and processing, UAS applications in water stress assessment, breeding, precision chemical analysis, machine learning, etc. It provided a strong foundation in UAS systems, data analytics, and software relevant to image analysis and precision agriculture. Students participated in practical exercises and workshops, gaining hands-on experience with real-world precision agriculture applications. Ongoing Graduate Course (PSS 5329-001 and PSS 5329-D01: Precision Agriculture): This course offered at Texas Tech University, with 17 enrolled students, provided comprehensive training in precision agriculture concepts and technologies. Topics included GPS, GIS, remote sensing, variable rate technologies, management zone delineation, profitability, and environmental impact. Students engaged in hands-on training on data analysis to apply these concepts, enhancing their ability to integrate precision technologies into agricultural management practices. In addition, graduate students conducted research projects addressing various aspects of precision agriculture. Their work included economic analysis, UAS image analysis, and/or machine learning applications. Five undergraduate students actively participated in UAS image acquisition and performed preliminary data analysis. Additionally, one undergraduate student conducted a dedicated research project leveraging UAS imagery to predict sorghum biomass and leaf area index, demonstrating the integration of remote sensing technologies in crop monitoring and analysis. Our on-farm research directly engaged three regional crop producers in Lubbock, Lynn, and Garza Counties. Through collaboration, we conducted on-farm research on precision nitrogen application and precision cover crop (winter wheat) management. Cotton yield monitor and associated management data were collected from over 30 fields across these counties in 2023. Preliminary analysis has been shown to participating producers to demonstrate the significance of precision agriculture technologies. We collaborated with researchers from Texas Tech University, Texas A&M University, West Texas A&M University, and USDA-ARS to foster innovation and knowledge exchange in precision agriculture. Through a collaborative workshop and research meetings, we created opportunities for scientists to share insights on the latest advancements in precision agriculture technologies, including soil mapping, UAS image acquisition, and image processing. Preliminary findings from these collaborations were also presented at the 16th International Conference on Precision Agriculture in Manhattan, Kansas, further disseminating key outcomes to the broader scientific community. An undergraduate student affiliated with a seed company participated in research evaluating sorghum growth parameters using UAS imagery, highlighting opportunities for larger-scale industry collaborations. Additionally, we integrated soil water sensors from ForeFront Agronomy into our research efforts to enhance data collection and analysis. These collaborations strengthen ties between academia and industry to advance precision agriculture practices. Through the cohort training and workshop in Summer 2024, we engaged with faculty from Texas Tech University, Texas A&M AgriLife Research and Extension, and USDA ARS scientists. This effort fosters potential collaborations, expands the project's impact on local communities, and establishes a strong foundation for future outreach and knowledge-sharing activities. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?The project has provided numerous training and professional development opportunities. The principal investigators collaborated to implement the project across institutions. We developed a training plan for students and organized cohort training and a workshop. Graduate and undergraduate students were trained in UAS and satellite imagery for precision agriculture, gaining hands-on experience in data collection and analysis. During the workshop, students also learned to present preliminary results, develop image analysis skills, and enhance their understanding of precision agriculture technologies. Through interdisciplinary collaboration, machine learning models were developed to predict cotton yield using satellite and UAS imagery, improving students' skills in both agriculture and data science. Additionally, four graduate students attended the 16th International Conference on Precision Agriculture, where they shared research findings and learned about precision agriculture from a broader perspective. How have the results been disseminated to communities of interest?The results have been disseminated to communities of interest through several channels. First, the project team presented preliminary results at conferences, both orally and via posters, allowing for broader academic and industry engagement. Second, a workshop was organized, where participants shared findings and discussed applications of precision agriculture technologies, fostering collaboration among researchers, students, and industry professionals. Additionally, the team maintained direct communication with collaborating producers, keeping them informed of the project's progress and findings. Through these efforts, the project successfully engaged key stakeholders and facilitated the exchange of knowledge and insights within the agricultural community.? What do you plan to do during the next reporting period to accomplish the goals?During the next reporting period, the project will focus on several key initiatives to accomplish its goals. First, we expect approval for the new course and plan to offer it at Texas Tech University in 2025/26, enhancing the curriculum to provide students with comprehensive training in UAS technologies and precision agriculture applications. In collaboration with Dr. Victor Sheng from the Department of Computer Science at Texas Tech University, we will refine the machine learning algorithms by incorporating additional data to improve model accuracy and prediction capabilities. Outreach efforts will include additional workshops and on-farm demonstrations aimed at reaching a broader audience, sharing progress, and gathering stakeholder feedback to improve the program continuously. These initiatives will facilitate knowledge exchange and foster collaboration between industry and academic partners. Furthermore, in collaboration with Dr. Chenggang Wang from the Department of Agricultural and Applied Economics at Texas Tech University, we will perform economic analyses to evaluate the impact of precision agriculture technologies on farm profitability.

Impacts
What was accomplished under these goals? Through our project's initiatives, we have successfully established research and educational programs, strengthened collaboration with local producers and industry partners, and provided hands-on training on precision agriculture and UAV technologies to graduate and undergraduate students. In collaboration with local producers, we have collected crop yield, soil mapping, and soil testing. Objective 1: We successfully initiated collaborative on-farm research with local producers, focusing on the practical application of UAS and satellite imagery in precision agriculture. Multispectral and thermal UAS imagery, along with cotton ground data such as plant height, biomass, and leaf area, were collected from commercial fields. Soil samples were analyzed for texture, organic matter, and pH, while a Veris mapping system integrated with a guidance system was used to map apparent soil electrical conductivity, pH, and sensor-derived organic matter. Additionally, yield monitor data were gathered from over 30 fields. These datasets establish a strong foundation for developing AI-based crop yield prediction models and decision-support tools to enhance precision water and nitrogen application and cover crop management. In addition, on-station research experiments were also established at all three locations with cotton as the main crop and soil, plant, and UAS data were collected from these studies. Objective 2: A graduate-level course, Precision Agriculture (PSS 6001-006), was introduced at Texas Tech University to provide hands-on training in UAS technologies and AI-based applications in agriculture. Currently offered as a problem course while awaiting approval as a regular course, it covers a wide range of topics, including UAV components, licensing, flight safety, data collection methods, remote sensing, image processing, vegetation indices, and their applications in high-throughput crop phenotyping. A graduate-level course, Agricultural Remote Sensing, is submitted for approval at Texas A&M University. Objective 3: In the summer of 2024, a cohort training program at Texas Tech University provided hands-on UAS image acquisition and processing training for five graduate and four undergraduate students. The program focused on collecting, analyzing, and interpreting UAS data to assess crop health, water stress, and growth status. This training also fostered collaboration among students, enabling them to work together on real-world image analysis in precision agriculture applications. On August 9, 2024, Texas Tech University hosted a workshop with 36 attendees from USDA-ARS, Texas A&M University, West Texas A&M University, Texas A&M AgriLife Research and Extension, and Texas Tech University. Participants included faculty, students, research and extension agents, and scientists. The event featured live demonstrations of precision agriculture technologies, such as drones, sensors, RTK guidance systems, and EC mapping, at the Texas Tech Quaker Research Farm, providing hands-on experience with equipment operation, data collection, and field applications. The workshop also included presentations on UAS operation, image analysis, and machine learning in precision agriculture, offering insights into processing and interpreting geospatial datasets. This event facilitated knowledge exchange and fostered collaboration among academic institutions, government agencies, and industry professionals.

Publications

  • Type: Conference Papers and Presentations Status: Published Year Published: 2024 Citation: Karn, R., Guo, W. (2024). Temporal and Spatial Variability of Nitrogen Use Efficiency across Landscape Positions in Southern High Plains. Great Plains Soil Fertility Conference, Lubbock, Texas, March 4-5, 2024.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2024 Citation: Guo, W., Karn, R., Lewis, K. 2024. Advancing Precision Nitrogen Management in Agriculture: A Multifaceted Approach. Great Plains Soil Fertility Conference, Lubbock, Texas, March 4-5, 2024.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2024 Citation: Wieber, E., Adedeji, O., Karn, R., Ghimire, B., & Guo, W. (2024). Using UAV remote sensing to assess cotton cultivars for water stress resistance in West Texas. 16th International Conference on Precision Agriculture, Manhattan, KS, July 2124, 2024.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2024 Citation: Karn, R., Adedeji, O., Ghimire, B., Abdalla, A., Sheng, V., Ritchie, G., & Guo, W. (2024). Within-field cotton yield prediction using temporal satellite imagery combined with deep learning. 16th International Conference on Precision Agriculture, Manhattan, KS, July 2124, 2024.