Item No. 1 of 1

INVESTIGATOR: Scudiero, E.; McGiffen, MI, E..; Vellidis, GE, .; Khosla, RA, .; Bali, KH, .; Sanchez, CH, AN.; Chief, KA, .; Cahn, MI, .; Schwabe, KU, A..; Putman, AL, I.; Anderson, RA, G.; Rivera, MO, .; Ajami, HO, .; Chaney, NA, W..; Eldawy, AH, .; French, AN, NI.; Nugent, CO, I..; Papalexakis, EV, .; Skaggs, TO, H.

PERFORMING INSTITUTION:
UNIVERSITY OF CALIFORNIA, RIVERSIDE
RIVERSIDE, CALIFORNIA 92521

ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE WATER, NUTRIENT, SALINITY, AND PEST MANAGEMENT IN THE WESTERN U.S.

NON-TECHNICAL SUMMARY: Vital to local rural communities and the national economy, agriculture in the western U.S. faces challenges including degradation of natural resources, climate variability, and pest outbreaks. Artificial Intelligence (AI) and Digital Agriculture (DA), the transdisciplinary application of high-performance computing and hyperdimensional data, can improve farming resilience. Short- and medium-term, this project applies DA to optimize current practices, maximizing efficiency, and minimizing waste. Long-term, the project develops a foundation of tools and knowledge for a shift to highly-automated mechanized systems for irrigation, nutrient, salinity, and pest management. Applied research supporting objectives (SO) are SO1 -- a decision-support tool for Agricultural Input Management with AI (AIM-AI) -- and SO2 -- a tool for Early Pest Detection with AI (EPD-AI). Tools integrate physical and statistical models, big-geodata (e.g., daily remote sensing), and AI. SO1 will merge recommendations for evapotranspiration-based soil-water balance irrigation scheduling, salinity leaching, and fertilization into a single framework. In SO2, an AI classifier will estimate pest emergence in organic and conventional crops for timely response. AIM-AI and EPD-AI will be evaluated using extensive field data. Cooperative extension SOs will inform stakeholders of current research-based tools, knowledge, and on-farm practices (SO3), and disseminate knowledge from research SOs (SO4) through training (face-to-face and electronic), field days, publications, and smartphone and web apps. SO5 includes an undergraduate DA Fellowship to educate future farmers, and DA professionals and academics via student research, mentorship, and industry externships. Project success in fostering rural prosperity and environmental sustainability will be evaluated by stakeholders, scientists, and professional evaluators.

OBJECTIVES: This project will lay the foundation for a long-term shift (10-20 years after the project) to highly-automated mechanized farm management systems (irrigation, nutrient, salinity, pest), while improving currently used technology in the short-term (during the project) and medium-term (5-10 years after the project). Colorado River Basin and Salinas River Valley farmland will be used as study areas. The project comprises four supporting objectives (SO):SO1 (Applied Research). Develop and evaluate algorithms for Agricultural Input Management with Artificial Intelligence (AIM-AI) that will merge available and novel models for evapotranspiration-based soil-water balance irrigation, nutrient application, and soil salinity management under a single Artificial Intelligence (AI) framework. Short-term: i) evaluate and integrate available decision-support models into a single AI platform; ii) test AIM-AI with current irrigation systems (typically delivering uniform prescriptions across a field) and on variable rate (VR) fertigation systems for its ability to save water, reduce environmental impacts, and sustain yields; and iii) employ hydrological modeling to evaluate the feasibility and benefits of large-scale adoption of automated VR management. Medium-term, the tool will be used to enable growers to shift, where suitable, to automated VR systems. Long-term, with refinements, AIM-AI offers to transform system-wide agricultural resource management over the entire western U.S.SO2 (Applied Research). For this objective, algorithms for early pest detection with AI (EPD-AI), will use very high-resolution remote sensing and other geodata, including spatial weather data. The EPD-AI offers a hierarchical, probabilistic alert for emergence of a generalized disease, pest, or weed problem, as well as targeted pests. Short term, EPD-AI will serve as a supplement to current scouting practices for pest detection. Long term, EPD-AI will be integrated with (semi-) automated pest management systems.SO3 (Cooperative Extension [CE]). Establish a multi-state CE network based on current and new collaborations between project investigators and local extension personnel to develop training programs that will reduce the gaps between state-of-the-art tools and knowledge and ongoing on-farm practices.SO4 (Cooperative Extension). Propagate the developed knowledge from SO1 and SO2. Translate AIM-AI and EPD-AI into user friendly web interfaces, including a novel smartphone app called FutureFarmNow, engage with private companies so that they can incorporate our open-access codes into their own tools. Establish a training program to educate growers and other relevant stakeholders on the Digital Agriculture (DA, i.e., the transdisciplinary application of high-performance computing and hyper-dimensional data in agricultural sciences) tools and knowledge generated from the project. Short-term, stakeholders will be trained to use FutureFarmNow and other developed tools. Medium- and long-term, training will continue to consolidate stakeholder knowledge on DA, to introduce new tools and innovations, and to aid the shift from traditional to DA management.SO5 (Education). Create highly skilled future leaders in the fields of DA, irrigation engineering, and agro-environmental management through Education, mostly of undergraduate students. The USDA and state agencies have highlighted the need to recruit more young people into the agricultural workforce. The US agricultural workforce has been aging for decades. In California, for example, where most farms are family-run, the average farmer age went from 56.8 (2002) to 60.1 (2012). This research project presents an opportunity to recruit a new generation of students, including data science-oriented undergraduate students, into careers in agriculture. To accomplish this, we will establish a Digital Agriculture Fellowship program for undergraduate students from UCR and our partnering institutions (University of Arizona, Colorado State University, Duke University, and University of Georgia).

APPROACH: Research methods for the development of algorithms for Agricultural Input Management with AI (AIM-AI) and for early pest detection with AI (EPD-AI). The project will create and maintain a geodatabase to integrate field collected ground-truth vector data with raster data (e.g., satellite imagery, digital elevation models, spatial weather grids). Ground data will include: legacy data (e.g., soil, soil-water, water, weather) and project measurements (e.g., soil, soil-water, plant leaf/canopy sensor and laboratory analyses, eddy-covariance data, crop yield data, pest incidence). Satellite data will include ECOSTRESS, Landsat 8, Sentinel, Venµs, and the 0.8 to 5-m resolution daily Planet Labs. The artificial intelligent framework will include the following research thrusts: 1. Integration of multimodal data with tensor-based methods; 2. Deep learning models; 3. Incorporation of physical models; 4. Real-time streaming adaptation. Development of AIM-AI, project years (Y) 1 and 2 will integrate established techniques and models for: i) land use, crop classification and phenotyping; ii) rootzone soil texture, hydraulic properties, salinity, and topsoil water content mapping; iii) crop water requirement estimation; iv) salinity leaching estimation; v) nutrient estimation; vi) rootzone soil-water-solute balance; and vii) irrigation and fertilization scheduling optimization. For i), algorithms to estimate land-use, field boundaries, crop type, growth stage, and irrigation methods will be used. For ii), mapping algorithms that integrate geodata and soil databases with new soil data collected at thousands of locations. Networks of soil moisture sensors will calibrate topsoil water content models using remote sensing data and produced soil texture maps. For iii), the project will use the Simplified Surface Energy Balance operational algorithm using satellite thermal data and data from weather station networks. The ECOSTRESS evapotranspiration product will be fused with higher resolution multispectral imagery. For iv) hierarchical set of process-based mechanistic models that describe root-zone water flow, salt transport, and their combined effect on crop water uptake will be used. For v), plant growth status - from (i) and crop-specific N demand curves will inform a remote sensing-directed N budget. Remote sensing model calibration and evaluation will be informed by using N-rich strips and other ground-truth. For vi) Kalman filtering-type scheme will assimilate sensor-derived near-surface soil moisture data into the models' soil profile boundary conditions in (iv) and (v). Hundreds of soil moisture sensors (down to 1.5 m) will be used to train and evaluate the soil-water balance. For vii), the project will improve available formulations for irrigation and fertigation scheduling for field-wide and site-specific management on several irrigation delivery systems. Field experiments will evaluate and refine the AIM-AI algorithms. The project will investigate the potential benefits of mechanized automated long-term site-specific management using the Soil and Water Assessment Tool at selected watersheds in the Colorado River Basin. Model calibration and evaluation will use historic streamflow and groundwater and soil moisture observations. High resolution AIM-AI products will also be used to model calibration and evaluation, then linked to a stochastic dynamic programming model of irrigated agriculture which will build upon previous models developed by the project investigators. Thirty-year climate change projections will guide what-if analyses and upscaling the impacts of agriculture management practices identified at field scale to watershed scale. EPD-AI calibration will use both ground data from controlled field experiments and on-farm surveys. The experiments will be carried at one research station each in the Coachella and Imperial Valleys and in Orange County (CA). Plots will be grown organically (to ensure pest pressure), with rotations of selected crops. Plots surveys will log pests, and pest damage. Pest locations will be tagged with a hand-held GPS, classified by name in a scouting smartphone app, and photographed. Concurrently with the surveys, UAV will record aerial hyper (i.e., <5cm) resolution visible, near-infrared, and thermal reflectance. On-farm surveys will be carried out the project team and by collaborators. The surveys will identify pests and pest damage in vegetable, tree, and field crops at 50 or more organic and conventional sites. Location, name, and photo of any observed pest will be recorded. EPD-AI will use the AIM-AI geodata and analytical framework. Weekly Planet's SkySat imagery (0.72-m resolution) will also be acquired for the EPD-AI controlled field experiments. Remote sensing data time-series, National Weather Service data, and the soil maps and soil-water balance from AIM-AI will train the EPD-AI classifier to identify spatial anomalies that correspond to damage from pests and calculate a probability that the anomaly is caused by a specific (or unidentified) pest, while accounting for known weather-based pest models. Spatiotemporal imagery anomalies may also reveal a soil-related issue, irrigation or other human-related management malfunctions, or localized nutrient stress, and the probability of anomalies being non-pest will rely on soil maps and other spatial covariates in moving neighborhood analyses. UAV and smartphone photography data will be tested to improve EPD-AI predictions. Spatial cross validation will test EPD-AI algorithms. Validation of EPD-AI will be carried out at the sites previously used for calibration and new sites.Cooperative extension (CE) methods include: Training will consist of interactive classes with Q and A sessions. Events will be live-streamed and made widely available on the project's YouTube account. Participants will receive business-card sized handouts with key messages and a QR code to the presentation materials on the project's website and mirrored by participating institution CE services. The developed app(s) will be based on an interactive WebGIS system consisting of two parts: a server-side back end and a client-side front end. The back-end runs on our servers and has access to AIM-AI and EPD-AI outputs. The front end will be an iOS app. Design criteria will always emphasize keeping the app(s) engaging, dynamic, and easy-to-use. Users will receive automatic notifications and will need to open the app only to enter certain information. App(s)training material will be delivered through a series of YouTube video tutorials and online instructions. Field days will be live-streamed with video stored on the project's YouTube channel (to be determined). An independent evaluator will evaluate CE methods by tracking the number of events and attendees, collecting post-survey data about the quality, usefulness, and relevance of the information presented, and measuring web-site use by stakeholders. If applicable, the evaluation will also monitor the how the app is used in the decision-making process, and the longer-term agricultural outcomes of those who utilize the app.Education methods will include a new fellowship program for undergraduate students with the following efforts: 1) Summer research program including professional development activities and a symposium; 2) Academic year research and activities (e.g., student-led research, annual symposium); 3) Externships at the project's industry partners; 4) International conference participation with mentor. An independent evaluator will evaluate education methods through online surveys, interviews, and focus groups with participating students. The evaluation design will be an explanatory mixed methods design, where quantitative survey data collected from students will be analyzed, with quantitative patterns then used to inform the development of interview or focus group protocols that aim to explain these patterns.

PROGRESS: 2022/09 TO 2023/08
Target Audience:The audience of this project continues to be, but is not limited to, growers, farm advisors, extension specialists, and scientists with expertise in soil, crop, irrigation, and pest management, commodity groups, non-profit organizations, water districts, agricultural technology companies, and young scientists and students interested in agricultural data science careers. Audiences such as agricultural consultants, growers, and scientists were reached through conference presentations, scientific (technical and non-technical) publications, and internet media (e.g., https://ai4sa.ucr.edu/; https://twitter.com/ucr ai4sa), and some press coverage. The education portion of the project aims to reach undergraduate students who major in environmental science, engineering, or related fields, and who are interested in learning more about digital agronomy as well as in gaining hands-on experience in the field. Students recruited have had majors in: statistics, mathematics, data science, environmental science, mathematics, and other. The education team utilizes campus communications to reach additional students and faculty, campus events to participate in, and creates or identifies networking opportunities to participate in. Project Co-PIs work with postdoctoral scholars funded by this grant. The extension portion of this project worked with American growers in the Southwest and regional extension personnel. Co-PI Bali and Co-PI Cahn conducted demonstrations for growers in California, demonstrating the technology, research, and resources like CropManage. Workshops reached growers, extension personnel, crop advisors, industry personnel, government officials, and journalists for agriculture-related publications. Changes/Problems:The project was set back by delays resulting from the COVID-19 pandemic during year one, which has resulted in an overall pushed-back timeline. The theft of research equipment during year three, shared by the PD Scudiero and Co-PD Anderson groups, resulted in fieldwork delays that will be rescheduled moving into year four. The postdoctoral scholar hiring process has also resulted in research delays. There have been challenges with the recruitment of undergraduate students to participate in the summer Digital Agriculture Fellowship program located at UC Riverside. Project members will determine the possibility of reallocating educational funds and restructuring the fellowship program to reflect this unforeseen difficulty. The Digital Agriculture Fellowship program continues to adjust based on feedback expressed by the participating students and faculty. Post-survey results showed a decrease in plans of pursuing a career in digital agriculture following completion of the program, with a reported increase in understanding of digital agriculture. The education team will focus on identifying additional qualitative factors that might contribute to this, beginning with the recruitment process of the students for the next Cohort, in collaboration with the evaluation/assessment team. Planned opportunities for hands-on research and networking will continue to be included, since these are areas reported to be of interest. The DAF also has had changes in the program itself due to delays in the student recruitment process; this resulted in Cohort II students concluding their fellowship experience with the summer research program, which was a change in the anticipated schedule. Extension project members will consider the feedback from the first two multi-state event survey evaluation/assessment reports when planning the next regional or multi-state events. Considerations include the possibility of adding smaller-scale farming topics, applied artificial intelligence topics, additional demonstrations, and specific topic areas depending on region. Additionally, to keep track of the stakeholders who are participating at multi-state outreach events, a streamlined method of collecting audience reach and audience participation information will need to be developed. What opportunities for training and professional development has the project provided?The education component of the project includes the Digital Agriculture Fellowship, which is intended to support the education and career paths of each participating undergraduate student. Digital Agriculture Fellowship Coordinator Noel Salunga organizes the DAF program in collaboration with the PD and Co-PD Connie Nugent, organizes the UC Riverside Research in Science and Engineering (RISE) summer program, and serves as the primary contact person for feedback from students, faculty, and the evaluation/assessment team. Organized activities during year three included three faculty/facility lab tours, Western Plant Health Networking night, College of Natural Agricultural Sciences Research and Engagement fair (table event with 250 peer guests); UC Santa Barbara Evaluation Presentation; Entrepreneurial Workshop; Industry Panel Workshop; poster presentations at the campus Precision Agriculture Workshop, Wonderful Company Talk (three students were selected to share their research with the CEO Wonderful Company Citrus), and the RISE summer hands-on research experience which includes 10 weeks of instructional activities and a final symposium. Postdoctoral scholars and student researchers supported by the project have conducted research, presented findings, attended workshops, attended meetings and conferences, co-authored papers, and have been encouraged to collaborate with other research groups on the project. Postdoctoral scholars have supported the Digital Agriculture Fellowship students and supported their work as well, acting as additional mentors. How have the results been disseminated to communities of interest?Results have been disseminated to communities of interest by using Twitter for updates regarding recently published papers and by participating in events/workshops. Multiple Co-PIs maintain updated personal web pages with a bibliography of their work. Through Twitter, affiliated websites (e.g., campus or department), and workshops the goal is to reach growers, academics, scientists, students, advisors, and technical personnel. Press coverage ideally supports the research reaching a local public audience. Student-led research has been disseminated through participation in the College of Natural and Agricultural Sciences RISE Symposium event, which was promoted using campus communications; about 300 guests attended, with about 111 of the guests being student peers. Additionally, the project's research groups participated in conferences to present their research findings, including attending the 2023 February California Plant and Soil Conference. The extension workshops hosted by Co-PI Bali utilize surveys developed by the UC Santa Barbara Evaluation and Assessment group led by Tarek Azzam and Natalie Jones. These surveys collect feedback from audience members to better determine what research topics would be most useful for the presentations to focus on. Project CropManage, Irrigation, and Nitrogen Management outreach activities include 28 workshops and presentations since 10/18/2022. These events took place regionally in California, as well as one event in Arizona and one in Colorado. 22 events were in person, while six events were conducted via Zoom. In total, over 700 participants have attended these events. Outreach Activities highlights by date include: 9/9/22 - Annual Alfalfa and Forage Field Day in Parlier, California - Co-PD Bali presented a talk called "Winter Flooding and Summer Deficit Irrigation of Alfalfa." 11/14/22 - World Alfalfa Congress in San Diego, California - Co-PD Bali moderated as well as presented the talk "Advances in Surface Irrigation Management in Alfalfa." 12/13/22 - Salinity Management in Pistachio in Kearney, California - Co-PD Bali presented "Effects of Soil Texture on Irrigating Pistachios in Saline Conditions" and Co-PI Cahn presented "Calculating Leaching Fractions and Requirements" along with a hands-on portion. 1/18/2023 - CropManage Hands-On Workshop - Co-PD Cahn organized a hands-on training workshop in Watsonville, California with 32 attendees. 2/15/2023 - CropManage Hands-On Workshop - Co-PD Cahn organized a hands-on training workshop in Modesto, California with 25 attendees. 2/21/23 - 2/24/23 - Visits to Agricultural Water Conservation Projects in Imperial Valley and other California portions of the Colorado River Basin - Co-PD Khaled Bali, Co-PD Charles Sanchez, and PD Elia Scudiero met with stakeholder groups, irrigation districts, and staffers from the offices of Senator Dianne Fienstein and Senator Mark Kelly, and the Bureau of Reclamation, DC. 2/23/23 - Using Planet Satellite Imagery in ArcGIS Workshop in Riverside, California - This UC Riverside campus event was organized by Co-PD Hoori Ajami, UCR Library, ESRI, and Planet. PD Elia Scudiero and Co-PD Ahmed Eldawy also supported the event. 13 guests attended including students and one faculty member. Participants received hands-on training with Planet imagery and a suite of ArcGIS products. 3/29/2023 - CropManage Hands-On Workshop - Co-PD Cahn organized a hands-on training workshop in San Martin, California with 33 attendees. 4/4/23 - Sustainable Agriculture with Artificial Intelligence Extension workshop in Maricopa, Arizona - This event was a project-organized event, led by Co-PD Khaled Bali and Co-PD Charles Sanchez. Speakers included multiple project Co-PDs, and this was the first multi-state workshop organized as part of Supporting Objective Three (SO3). 4/5/23 - Extension Public Seminar Sustainable Agriculture with Artificial Intelligence in Loma, Colorado - This event was a project-organized event, led by Co-PD Khlaed Bali and Co-PD Raj Khosla's group. Speakers included multiple project Co-PDs, and this was part of the multi-state workshops organized as part of SO3. 4/19/2023 - CropManage Hands-On Workshop - Co-PD Cahn organized a hands-on training workshop in Parlier, California with 30 attendees. 5/22/23 - Precision Agriculture Workshop in Riverside, California - This UC Riverside campus event was co-organized by PD Elia Scudiero, with the goal of promoting networking between campus precision agriculture researchers. Faculty, students, and industry partners participated. The event reached UC Riverside faculty, administrators, and students primarily in the College of Natural and Agricultural Sciences, School of Policy and Business, and the College of Engineering. There were about 60-70 guests throughout this all-day event. NEWS & PRESS 11/10/22 - "2022 FREP/WPH Nutrient Management Conference Recap" located on CA.gov's Fertilizer Research and Education Program blog - Emad Jahanzad provides a summary of the conference held in October, including a Kearney Ag. Research and Extension Center facility tour led by Co-PI Khaled Bali. 5/17/23 - "Efforts to Recharge California's Underground Aquifers Shows Mixed Results" located on npr.org - Nathan Rott transcribes an interview with Co-PD Khaled Bali, describing the effects of rainfall on aquifers. 6/12/23 - "Digital Ag. Fellowship Opens Doors to the Future" located on UC Riverside's online College of Natural and Agricultural Sciences blog - PD Elia Scudiero describes the Digital Ag. Fellowship opportunity and how UCR students can participate. Products (models, instruments, audio/visual, curricula, data, databases, collab): https://cropmanage.ucanr.edu/ CropManage is a free online crop management decision support tool managed by Co-PI Michael Cahn as part of the University of California Cooperative Extension. https://ai4sa.ucr.edu The AI4SA project-based website was created using the management system maintained by UC Riverside. Planet Labs, Inc. collaboration: AI4SA has collaborated with Planet Labs, Inc. to extend the use of the product license to all UCR personnel with a UCR email address through the year 2025. 77 total campus personnel have accessed the license to create a general user Planet account since year one, with 21 participants joining in year three. Of the 21 newly added participants in year three, three total are affiliated with the AI4SA project and four total are campus faculty members. What do you plan to do during the next reporting period to accomplish the goals?During year three, internal management adjusted to streamline communication chains and improve collaboration. Moving into year four, this process will continue in order to align with the increased communication needs required for completing supporting objectives. The extension groups will work towards continuing planning outreach workshops and events, with continued effort in establishing a multi-state network. Using the feedback from survey data and the evaluation/assessment reports, topics will be adjusted to match regional interests. Project members will increase specific stakeholder attendance tracking with a goal of streamlining this process for the project's needs. Co-PD Cahn will investigate interfacing OpenET with CropManage (ETo, ETz), improving user experience, adding a model to estimate N mineralization from organic amendments and fertilizers, and add leaching calculator for salinity management in collaboration with project members Co-PD Eldawy and Co-PD Vellidis' group will add new states as the data becomes available, they will increase the maximum area to get the soil statistics data, and they will use beta testers' feedback for bug fixes and improvements. The education portion of the project will continue as a fellowship program that supports each student's education and career paths. The education group will continue in the recruitment of eligible students to participate in the Digital Agriculture Fellowship program, with an updated emphasis on recruiting students with expressed interest in precision agriculture. The outcomes of this will be tracked with surveys in collaboration with the Evaluation and Assessment team. The program itself will continue to be adjusted based on student feedback described in the project's evaluation/assessment reports. Students will participate in planned tours, conferences, hands-on research, and networking events; students indicate via survey that networking with peers and faculty is an area of interest.

IMPACT: 2022/09 TO 2023/08
What was accomplished under these goals? In its third year, the project has demonstrated remarkable progress in the use of AI-driven agricultural management and precision farming. Breakthroughs in remotely sensed imagery and AI have enabled more precise irrigation and pest detection strategies, particularly in specialty crops. The implementation of advanced models like BAITSSS and the integration with novel data streams such as Hydrosat and Planet have significantly enhanced early season irrigation detection and soil moisture analysis. Field experiments have shown the efficacy of multispectral drones in disease and weed detection in crops like cantaloupe. Collaborative efforts have led to the improvement of soil class maps through Polaris Version 2, aiding in the more accurate prediction of surface temperatures. The project's extension efforts have substantially influenced water management in California, while educational initiatives under the Digital Agriculture Fellowship have fostered a new cadre of data-savvy agricultural professionals. Overall, Year 3 has consolidated the project's foundation in integrating AI and remote sensing with practical agricultural applications, paving the way for more efficient and sustainable farming practices in the U.S. Southwest. Research Research activities in Year 3 faced challenges, including equipment theft, but made notable progress in AI and remote sensing for agriculture. Co-PDs Anderson and French (SO1) continued satellite remote sensing work, focusing on the BAITSSS model for specialty crops and collaborating with Hydrosat for high-resolution imagery. This work enhanced early season irrigation detection using daily Planet data for vegetable crops, a significant advancement over traditional multispectral satellite sources. The team is processing evaporative fraction data for validating the evapotranspiration model and plans to integrate BAITSSS with improved data streams, including POLARIS and PLANET, and Hydrosat for irrigation assessment. Co-PD Chaney advanced Polaris to Version 2, improving soil class maps and surface temperature predictiveness. The team plans to merge Polaris v2 properties with in-situ soil data. Chaney works with PhD student Emma Xu on this aspect. The Khosla group's fieldwork in Colorado involved extensive data collection, including leaf tissue nitrogen and soil readings. They used Planet satellite data to estimate plant traits and applied different nitrogen treatments to enhance algorithm training. The group is also focusing on soil moisture data collection and plans to expand test sites. Co-PD Papalexakis's group tackled AI challenges in crop data layer prediction and self-supervised learning, grappling with issues like class imbalance and lack of deep learning datasets. They are investigating the application of the Segment Everything (SAM) model for crop region segmentation and preparing research papers in collaboration with Co-PI Eldawy's lab. Sanchez and French expanded a salt and water-tracking database, addressing nitrogen usage efficiency and the lack of variable rate application technology among stakeholders. Co-PD McGiffen's group experimented with multispectral drones for disease and weed detection in cantaloupe, achieving high accuracy. PD Scudiero and Co-PD Skaggs contributed to soil surveys and moisture sensing for precision input management. They investigated soil-plant relationships using Planet scoping and developed models for mapping available water capacity, using comprehensive soil moisture data from sensors. Overall, Year 3 saw significant advancements in integrating AI and remote sensing with practical agricultural practices, overcoming challenges and setting the stage for future innovations in sustainable farming. Extension In SO3, Co-PI Bali focused on groundwater management in California's Central Valley, working on reducing demand, enhancing irrigation efficiency, and promoting groundwater recharge. His work extended to deficit irrigation in the Lower Colorado River Basin and improving irrigation and nitrogen management in diverse regions. Bali also engaged in subsurface drip irrigation on alfalfa, incorporating new technologies and collaborating with growers to optimize irrigation and crop management. He continues collecting survey data to refine workshop content, with the surveys designed by UC Santa Barbara. Co-PI Cahn leads digital agriculture training for the CropManage tool, which tracks water, fertilizer, and soil samples, and supports weather-based irrigation scheduling. Efforts include integrating open ET and expanding service areas in the Western U.S. Recent updates to CropManage include incorporating the Arizona weather station network and enhancing algorithms for crop stress and deficit irrigation. Cahn's demonstrations and support in commercial fields have contributed to a 36% increase in CropManage usage. In SO4, Co-PD Eldawy's team, along with Co-PD Vellidis and developer José Andreis, are developing FutureFarmNow, a tailored recommendation app for growers. Hosted at UC Riverside, its backend supports data access via an API, and the iOS frontend is in beta testing. The app includes data on farmlands, regions, and soil products, allowing for detailed visualization and analysis. Education SO5: During year three, eight students participated in Cohort II of the Digital Agriculture Fellowship (DAF). Student majors included statistics, mathematics for teachers, data science, environmental science, mathematics, and other. Students conducted research with faculty mentors, participated in Digital Agronomy Club activities, networked, toured faculty labs, traveled to a state conference, participated in workshops, and kept in contact with DAF peers through monthly check-ins. Students recently either interned off campus or continued their research in the UC Riverside RISE summer program and symposium. One student interned at Aquaspy, one student interned at Farmsense, four students continued in the UCR RISE program, and one student transferred to another program. Five students have been recruited for Cohort III, with three more students planned to be recruited in September of 2023. Majors include: data science, bioengineering, and electrical engineering. Students from Cohort III have participated in the RISE summer program and symposium and will continue with their student-led research. DAF students are all registered as Digital Agronomy Club members, which is an affiliated chapter of the Students of Agronomy, Soils, and Environmental Sciences (SASES). Plans include sending DAF students to the annual SASES meeting. Three DAF scholars have been recognized for their work: V. Gajjewar was awarded the "2023 National Student Recognition Award" by ASA, CSSA, and SSSA; H. Dingilian was awarded third place at the 2023 California Plant and Soil Conference poster competition, and M. Nolasco was awarded the 2023 ASA, CSSA, and SSSA Golden Opportunity Scholar. The Evaluation and Assessment continued to develop surveys in collaboration with the education coordinator and project director to gather feedback from the DAF undergraduate students. The results are used to develop the program with the student's input and plan professional development activities moving forward.

PUBLICATIONS (not previously reported): 2022/09 TO 2023/08
1. Type: Journal Articles Status: Published Year Published: 2023 Citation: Dhungel, R., Anderson, R.G., French, A.N. et al. Assessing evapotranspiration in a lettuce crop with a two-source energy balance model. Irrig Sci 41, 183â196 (2023). https://doi.org/10.1007/s00271-022-00814
2. Type: Journal Articles Status: Published Year Published: 2023 Citation: Dhungel, R., Anderson, R.G., French, A.N. et al. Remote sensing-based energy balance for lettuce in an arid environment: influence of management scenarios on irrigation and evapotranspiration modeling. Irrig Sci 41, 197â214 (2023). https://doi.org/10.1007/s00271-023-00848-9
3. Type: Journal Articles Status: Published Year Published: 2023 Citation: Dhungel, R., Anderson, R.G., French, A.N. et al. Early season irrigation detection and evapotranspiration modeling of winter vegetables based on Planet satellite using water and energy balance algorithm in lower Colorado basin. Irrig Sci (2023). https://doi.org/10.1007/s00271-023-00874-7
4. Type: Journal Articles Status: Published Year Published: 2023 Citation: Xu, C., Torres-Rojas, L., Vergopolan, N., & Chaney, N. W. (2023). The benefits of using state-of-the-art digital soil properties maps to improve the modeling of soil moisture in land surface models. Water Resources Research, 59, e2022WR032336. https://doi.org/10.1029/2022WR032336
5. Type: Journal Articles Status: Published Year Published: 2023 Citation: Cahn, Michael, et al. Field evaluations of the cropmanage decision support tool for improving irrigation and nutrient use of cool season vegetables in California. Agricultural Water Management, vol. 287, 2023, p. 108401, https://doi.org/10.1016/j.agwat.2023.108401.
6. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Xu, C., & Chaney, N. W. (2022) Towards Polaris 2.0: Revisiting the Prediction of Soil Classes [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/144328
7. Type: Conference Papers and Presentations Status: Awaiting Publication Year Published: 2022 Citation: Dhungel, R., Anderson, R. G., French, A. N., and Scudiero, E., âHigh-resolution Planet Multispectral Images for Evapotranspiration Estimation of Lettuce Using a Two-Source Water and Energy Balance Modelâ, AGU Fall Meeting 2022, held in Chicago, IL, 12-16 December 2022, id. H54C-03.
8. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Scudiero, E., Singh, A., Huang, J., Ellegaard, P., Skaggs, T. H. (2022) Soil Moisture Estimation of Agricultural Fields Using Remote Sensing and Machine Learning [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/143481
9. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Scudiero, E., Singh, A., Mahajan, G., Chatziparaschis, D., Karydis, K., Houtz, D., & Skaggs, T. H. (2022) On-the-Go Microwave Radiometry for High-Resolution Soil Moisture Mapping in Micro-Irrigated Orchards [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/143485
10. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Scudiero, E., Burgess, W., Ahmed, S., Dingilian, H., Gajjewar, V., Ho, C., Lincoln, K., Morales, I., Urrutia, K., Guillory, J., Jimenez, N., Singh, S. (2022) The University of California, Riverside's Digital Agriculture and Agronomy Club [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/145470
11. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Kayad, A., Putman, A., Scudiero, E., Dingilian, H., & McGiffen, M. (2022) A Simple Weed Detection Technique through Drone Images for Transplanted Vegetables [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/143059
12. Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Mahajan, G., Singh, A., Montazar, A., Corwin, D. L., & Scudiero, E. (2022) Investigating Soil-Plant Relationship in Salt-Affected Farmland Using Soil Apparent Electrical Conductivity -Directed Soil Sampling and Planetscope Time-Series Analysis. [Abstract]. ASA, CSSA, SSSA International Annual Meeting, Baltimore, MD. https://scisoc.confex.com/scisoc/2022am/meetingapp.cgi/Paper/142084
13. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Nolasco et al. Creating a Rapid GIS Workflow to Correct On-the-go Gamma Ray Soil Spectrometry Data According to Survey Speed. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA
14. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Attride et al. Investigating the Relationship of Maize Yield with Sentinel 2 Time Series Data Over Hundreds of Fields in the Conterminous United States. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA
15. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Banik et al. Investigating the Relationship of Maize Yield with Sentinel 2 Time Series Data Over Hundreds of Fields in the Conterminous United States. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA
16. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Dingilian et al. Using Drone Multispectral Imaging for Weed Discrimination: A Case Study from Riverside, CA. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA
17. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Guillory et al. Machine Learning with Landsat Satellite Data for Crop Mapping in the Yuma Valley Region of the Lower Colorado River Basin . California Plant and Soil Conference. February 7-8, 2023. Fresno, CA. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA
18. Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Jimenez et al. Using Gamma-ray Surveys to Predict Soil Properties in Perennial Cropping Systems. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA. California Plant and Soil Conference. February 7-8, 2023. Fresno, CA