Progress 09/01/23 to 08/31/24
Outputs
Target Audience:During this reporting period, our efforts were totargetaudiences that are pivotal to deveop and expand our D-RAP team; and also towards initiate outreach in tghe community targeted towards resilientforage production under limited water resources, specifically in the context of precision agriculture. The target audiences included - The primary audience reached through our outreach efforts consisted of alfalfa producers in Kansas and South Texas, who are directly impacted by drought conditions and the depletion of the Ogallala Aquifer. These producers are seeking innovative solutions to optimize water use for maintaining or improving forage yield and quality. Our research is targeted towards this group as it addresses the pressing need for effective water management strategies, particularly through the application of UAV-based thermal imaging and modeling. A significant portion of our efforts was directed towards students, both at the undergraduate and graduate levels. These students were engaged through formal educational programs, internships, and hands-on training opportunities related to digital agriculture and machine learning. For example, at Texas A&M University, two undergraduate female students were trained in UAV data collection and processing, which are critical skills for future agricultural professionals. Additionally, students at Kansas State University were involved in collecting and analyzing data from field experiments, providing them with experiential learning opportunities that bridge classroom theory with real-world agricultural challenges. Sourajit Dey, Ph.D. student on this project was recognized for his presentation at International Conference on Precision Agriculture-2024, where he received first place in student competition. Another important audience included agricultural researchers and academics who are focused on improving crop resilience and sustainability through innovative research. Our project reached this group through collaborations, conference presentations, and publications. For example, manuscripts were prepared and presented on topics such as detecting climate factors affecting alfalfa production using machine learning, contributing to the scientific discourse on sustainable agriculture. Community stakeholders, including representatives from industry, government agencies, and producer organizations, were engaged through our outreach activities. This group is important for as our research is aligned with the needs of the agricultural industry and that the results are effectively implemented on the ground. Efforts such as the South Texas Beef and Forage Field Day and the Digital Agriculture Symposium provided platforms to share insights and gather feedback from these stakeholders. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?Undergraduate students at Texas A&M University Kingsville received hands-on training in UAV data collection and processing, learning to operate drones and analyze multispectral imagery for alfalfa research. Graduate students and visiting scholar at Kansas State University were trained in usingsensors like GreenSeeker, multispectral, thermaland hyperspectral spectroradiometers, gaining experience in measuring NDVI, chlorophyll content, NDVI, thermal maps and hyperspectral data. Students also participated in writing grant proposals and submitted to regional funding ageny, enhancing their skills in research funding applications. Additionally, they presented their work at the 16th International Conference on Precision Agriculture, where they developed public speaking and networking skills. Participation in field days and workshops, such as the South Texas Beef and Forage Field Day, allowed students and faculty members to engage with local producers and demonstrate the practical applications of digital agriculture technologies, further enriching their educational experiences. How have the results been disseminated to communities of interest?We focused on alfalfa producers, extension professionals, researchers, and students in the Southern Great Plains. We participated in field days, like the South Texas Beef and Forage Field Day, to show how UAVs and sensors can monitor alfalfa growth and water stress. This helped producers learn about and adopt precision agriculture technologies. We also presented our research at the 16th International Conference on Precision Agriculture, where our work on machine learning in alfalfa production received top recognition. Additionally, we published an article in "Crops & Soils" magazine about precision irrigation. We began developing web-based tools to help producers make better decisions about water use in real-time. Students were involved in the project, gaining valuable experience and helping to share our findings through research and presentations. These efforts have helped spread our research to a wide audience and encouraged collaboration and innovation in agriculture. What do you plan to do during the next reporting period to accomplish the goals?1. We will continue collecting detailed data from our field experiments at the North Agronomy Farm in Manhattan, Kansas, and the Southwest Research-Extension Center in Garden City, Kansas, as well as from our sites in South Texas. The data will include measurements of alfalfa biomass, plant height, canopy cover, soil moisture, and evapotranspiration under various irrigation treatments. In Texas, we will specifically focus on the rainfed and limited irrigation plots to assess how these practices impact alfalfa growth under local climatic conditions. The collected data will be analyzed using machine learning algorithms to identify the most critical factors influencing water use efficiency in each region. 2.We will initiate the development of web-based decision support tools that provide real-time irrigation recommendations. These tools will integrate data from our Texas and Kansas sites, offering region-specific advice to help alfalfa producers optimize water use. 3.We will establish advisory groups for both Texas and Kansas, including industry representatives, government agencies, and alfalfa producers. These groups will review our findings and provide feedback to ensure that our research addresses the practical needs of producers in both regions. We will also explore opportunities to expand these advisory groups to include more local stakeholders from each state. 4.We plan to submit manuscripts detailing our research findings for two publications in peer-reviewed journals, focusing on the results from both Kansas and Texas sites.In Kansas, we will involve undergraduate and graduate students from Kansas State University in ongoing research activities, providing them with hands-on experience in field data collection, sensor technology, and data analysis. In Texas, we will continue to engage students from Texas A&M University Kingsville in similar activities, with a focus on data processing and analysis related to local conditions. 5. Wewill refine our research methodologies based on the insights gained from our ongoing experiments. This includes exploring new technologies, such as advanced sensors and data integration platforms, to further enhance water management practices in alfalfa production.
Impacts
What was accomplished under these goals?
Accomplishments under Goal 1 - Spatiotemporal Quantification and Management of Water Budget Development of UAV-Based Data Collection Pipeline -Theproject team developed a UAV-based data processing pipeline to standardize the collection and analysis of RGB and multispectral imagery, along with ground-based measurements. This will aim to advance research for developing models that predict water stress and quantify the water budget in alfalfa production systems. Field Experimentation and Data Collection -At the North Agronomy Farm, Kansas State University, plots were established under different irrigation treatments, including 100% ETc, 60% ETc, limited irrigation, and rainfed conditions. Data collected included canopy height, dry weight, and canopy cover, which are useful for understanding the water use efficiency of alfalfa under various water regimes. Machine Learning Algorithm Development-The team utilized machine learning algorithms to analyze the data collected from the UAVs and ground sensors. This allowed for the identification of key variables driving water use efficiency and drought resilience in alfalfa. A manuscript focusing on the detection of climate factors affecting alfalfa production through machine learning was prepared, contributing to the understanding of spatiotemporal water management in the region. Accomplishments under Goal 2 - Social and Economic Data Collection Economic Analysis of Precision Water Management-The project included the collection of social and economic data related to the use of wireless sensor networks and machine learning techniques in alfalfa production. This analysis is for understanding the cost-benefits of implementing D-RAP systems in real-world farming scenarios. Student Training and Grant Writing-The project provided opportunities for students to engage in research that blends economic analysis with precision agriculture. A graduate student grant proposal was written (by Sourajit Dey) focusing on precision water management, although it was not funded, the process provided valuable insights into the economic dimensions of implementing advanced technologies in agriculture. Accomplishments under Goal 3 - Social and Economic Data Collection Field Days and Workshops-The project team actively participated in South Texas Beef and Forage Field Day, where digital agriculture applications and alfalfa production systems were presented to the community. Conference Presentations-Research findings were disseminated at the International Society of Precision Agriculture-2024, where a poster presentation by Sourajit Dey on machine learning algorithms in alfalfa production was awarded first place. Student Involvement in Knowledge Dissemination-Training was provided to undergraduate students at Texas A&M University Kingsville in UAV data collection and processing.
Publications
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Nazrul, F., Kim, J., Dey, S., Palla, S. P., Sihi, D., Whitaker, B., Min, D., and Jha, G. (2024). Machine learning algorithm in detecting long-term effect of climatic factors for alfalfa production in Kansas. Poster presented at International Society of Precision Agriculture, Kansas State University, Manhattan, KS. (July 21-24, 2024). (First Place: Big Data, Data Mining, and Deep Learning section in the 16th International Conference on Precision Agriculture (ICPA))
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Dey, S., Jha, G., & Min, D. (2024). Precision Irrigation Technologies for Water?Wise and Climate Resilient Alfalfa Production. Crops & Soils. doi.org/10.1002/crso.20383
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Calil, Y. C. D., Oliveira, A. M. B., Ribera, L., Landivar, J. (2024). Digital Twin Models: Financial Strategies for Farm Management. Agricultural & Applied Economics Association (AAEA) Annual Meeting. New Orleans, LA.
|