Duration: 10/01/2026 to 09/30/2031

Administrative Advisor(s):

NIFA Reps:

Non-Technical Summary

Agricultural industries have seen rapid recent technological advancements that offer new ways to enhance efficiency, sustainability, and profitability^1-3. Tools like weather stations, wireless-sensor networks, drones, and artificial intelligence are advancing our ability to collect data on farms^2-4. These data can be linked with models to guide management of irrigation, timing of planting and harvest, and pest and fertilizer treatments^5,6. Given advancement of tools to collect data on farms, the need for data standardization and integration into actionable models has never been more important. However, there are challenges that need to be addressed to unlock the full potential of digital agriculture^7,8. These include fragmented development of sensing tools, uneven integration of abiotic data into biotic models, and an underdeveloped understanding of how farmers will adopt digital tools. This proposal addresses these barriers with a vision for a national digital agriculture initiative to coordinate efforts across land-grant institutions, support development of shared tools and digital infrastructure, and produce public stakeholder-centered tools to foster private-sector connections and investment. Our project will achieve three aims: (i) Support the collection, analysis, and forecasting potential of abiotic data; (ii) Promote standardized models of biotic processes on farms and delivery of model outputs, and (iii) Understand human adoption of digital agriculture. Through our coordination network we will produce a database of tools that are used to gather data on farms, deliver time-sensitive information through models, and assess how producers perceive and adopt decision support tools. Overall, this project will provide widespread national benefit.

Statement of Issues and Justification

Agricultural industries across the United States are faced with many challenges, such as variation in weather, supply chain disruptions, and changing pest pressures^9-11. At the same time, agriculture has seen rapid recent technological advancement that offers new ways to enhance efficiency, sustainability, and profitability^1-3. Tools such as weather stations, wireless-sensor networks, UAVs (drones), automated pest traps, and artificial intelligence are advancing our ability to collect real-time data on farms^2,3. These data can then be linked with models to guide management of factors such as soil fertility, irrigation, timing of planting and harvest, and pest and fertilizer treatments^2,5. Given the advancement of tools that collect abiotic and biotic data on farms, the need for data standardization and integration into actionable models has never been more important^5,12.

The term “digital agriculture” describes the use of digital tools such as weather networks, sensors, and drones to collect and process data for agricultural applications, as well as delivery of this information through digital platforms^6,13. However, there are several challenges that need to be addressed to unlock the full potential of digital agriculture. First, there has been fragmented development of sensing tools. For example, public weather networks are often operated by land-grant universities (with various partners) at the state level, and vary in the scope and quality of data collection^14,15. Public weather networks also compete with private networks that sometimes outpace the quality of public data^5,16,17. Similarly, development of sensors with broad applicability, such as soil moisture sensors or automated traps to monitor insect pests, will likely succeed only through coordinated implementation across crops by leveraging public and private partnerships¹⁸. Second, we can improve our ability to integrate abiotic data into predictive forecasts of biotic processes. There are platforms that link abiotic data into models to predict factors related to plant growth or pest management, such as the Washington State Decision Aid System, the Oregon State IPM Center, Michigan State Enviroweather, and Cornell’s Network for Environment & Weather Applications (NEWA) (among others)^19-22. While these systems aid particular industries, great benefit would be achieved by developing scalable and user-centered digital platforms that serve public and private interests nationwide. Third, we need a better understanding of how farmers – and the individuals that influence decisions on farms – adopt and engage with digital tools. Social science research increasingly uses new methods, such as sophisticated games, online models, and digital twins to capture more data than was available through surveys^23-25. As we build digital platforms, we can better support research on best practices for delivering actionable tools for decision-making. This proposal addresses these barriers with a vision for a national digital agriculture initiative that coordinates efforts across research institutions, supports shared tools and digital infrastructure, and produces publicly available, stakeholder-centered tools that also foster private-sector connections and investment.

Prerequisite Criteria

How is the NRSP consistent with the mission?

Digital agriculture is a strong fit with the NRSP Program. Rapid technological advances offer great promise for agriculture, but national coordination is urgently needed. All agriculture is impacted by the complex interplay between abiotic conditions and biotic processes²⁶, and sensing technologies developed in particular systems may be integrated into unrelated crop systems or regions through greater coordination. Similarly, while researchers at universities with established digital platforms have ready-made outlets for their work^19-22, many universities have less advanced capacity in this area and would benefit from a national capacity project. At the same time, individuals developing new technologies would benefit from coordination of social science research to better capture how a new generation of farmers will accept and use digital technologies. Social studies in agriculture are increasingly using tools such as sophisticated video games, online models, or digital twins to collect data^27,28, and these methods may allow researchers to supersede traditional regional or crop-centric boundaries. Our project addresses each of these areas to improve our capacity to build digital agriculture for broad national public benefit.

How does the NRSP pertain to a national issue?

Every farming system in the United States is affected by the interplay between abiotic conditions such as soil type, water availability, and weather and biotic processes such as crop development, pest and pathogen dynamics, and nutrient cycling by microbes^26,29-31. Rapid technological advances have created new opportunities to gather real-time data on farms related to both abiotic and biotic conditions^2-4. However, the development of technology has been fragmented across the United States, and technologies implemented regionally may gain national usage through a capacity project. Linking researchers who are developing new tools for data collection on farms, online and mobile platforms to deliver information, and researchers who study how digital tools are adopted by farmers, would provide widespread national benefits.

Our project also complements other NRSPs without duplicating their efforts. For example, one of the primary features of many effective digital agriculture platforms is the ability to display site-specific recommendations to users based on their local farm conditions^21,22. NRSP-4 is focused on the development and maintenance of new chemistries for crop systems, while NRSP-9 is focused on site-specific fertilizer recommendations. Our project could complement these projects by ensuring that site-specific recommendations are hosted and linked to local weather models. Similarly, NRSP-3 is designed to create a national database of pollution inputs into landscapes of the United States, with a focus on agricultural landscapes. That project will use sensor data and other inputs to build models, and complements our integration of abiotic sensing data and biotic models. Finally, the recently supported NRSP-13 focuses on agricultural automation. While automation is different than decision-support, both projects share a need to integrate abiotic data into management decisions on farms, and our initiative will assist in identifying areas of digital agriculture that can be automated. Our project provides a unique approach to digital agriculture on farms while complementing these and other NRSP projects.

Rationale

Priority Established by agInnovation

Our project primarily addresses two Grand Challenges from the ESCOP Roadmap: (GC1) Enhance the sustainability, competitiveness, and profitability of United States food and agricultural systems and (GC6) Heighten environmental stewardship through the development of sustainable management practices.

To address GC1, our project provides national capacity in weather and abiotic data sensing, environmental forecasting, pest and disease modeling, and human adoption of digital tools. Producers and other agricultural partners can see great benefits from digital agricultural systems where they are implemented, often exceeding $100/acre due to large reductions in inputs^32,33. When implemented across large scales, such systems can save producers tens of millions of dollars. Our project will help to scale up systems that have been developed at particular land-grant universities across the entire country, providing benefits to many crop systems.

To address CG6, our project will provide a set of tools to aid producers in managing inputs such as pesticides and irrigation inputs based on site-specific abiotic data. This will reduce inputs overall and allow for them to be timelier and more effective. Integration with social scientists will help our project team understand the economic and social benefits of digital tools^27,28, and aid in implementing these tools across a wider range of systems.

Relevance to Stakeholders

This project is uniquely positioned to serve a wide array of stakeholders. First, digital agriculture benefits crop producers by capturing and delivering real-time information on farm conditions to guide actions. Producers of crops such as tree fruits, tree nuts, potatoes, grapes, and small berries are using digital platforms at regional scales^19-22, but these and other industries would benefit from national coordination. Second, digital agriculture benefits consultants and extension specialists, providing them data to make effective recommendations^34-36. Third, our project will benefit policy makers. By better understanding digital adoption and barriers, we will inform policies to support rural innovation^34,37. Fourth, our project benefits the private sector, including companies that produce new digital tools and those that provide consulting services on farms. Fifth, our project benefits suppliers of agricultural chemicals that have a vested interest in their products being used correctly and at the right time^38-40. Finally, our project benefits the public. By enabling transparent and efficient tools for digital agriculture, we can create systems that better meet human needs across the United States.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

If given the opportunity to write a full proposal we will more fully detail all of these stakeholders, their involvement in the development of the proposal, and alignment towards shared goals.

Implementation

Objectives

1. Aim 1: Support collection, analysis, and forecasting potential of abiotic data
   Comments: As the volume and variety of agricultural data grows, so too does the challenge of making it usable. Data collected from weather stations, wireless-sensor networks, soil monitors, and drones should ideally be harmonized to create accurate, site-specific forecasts (41). Yet, integrating data is complex, and different groups require better coordination on processing and analysis of abiotic data for integration and accessibility. This aim will focus on developing open-source software libraries and common data schemas for capturing, processing, and analyzing data collected from farms through sensing technologies. We will also support the development of machine learning and AI-based software tools to process and integrate disparate data streams (42,43). Standardized tools will be housed in the project’s nationwide database to aid in improving forecasting for yields, irrigation, pest risk, and more in addition to influencing future sensor and tool development.
2. Aim 2: Promote standardized models of biotic processes on farms and delivery of outputs
   Comments: Many biotic processes on farms are driven by weather, such as the relationship between timing of bloom and temperature, or development of pest populations, allowing producers to time many production-related activities (44-46). However, there is a lack of standardization that limits many biotic models from being developed and deployed. This aim will standardize how models that leverage abiotic data to predict biotic processes are built, validated, and deployed. Collaborations across institutions will produce interoperable model templates and a shared platform for field trials and validation datasets and protocols, and tools for adapting crop-specific models to unique regions.
3. Aim 3: Understanding human adoption of digital agriculture
   Comments: Success of digital agriculture depends not just on technologies developed, but whether they are adopted (34,47). Agricultural industries can often be resistant to change, and coordination between researchers and users of technology is needed to guide development (34,47). Through our coordination network we will produce a database of tools that are used to assess how producers perceive, evaluate, and adopt decision support tools. Coordination will allow us to leverage game-based research, experimental economic models, and human-centered design studies from particular crop systems into shared insight on preferences, barriers to adoption, and differences across demographics and geographies. Our project will also create a framework for research into adoption of digital agriculture as we create technologies (48-50)

Projected Outcomes

Management, Budget and Business Plan

Project Management Plan

Our project will be coordinated by a steering committee composed of academic and industry representatives with rotating three-year terms. The steering committee will have a chair and chair-elect chosen by the members. Each aim will also have a chair, a chair-elect, and an at-large member, for a total of 9 committee members representing the three aims. We will then have four industry members, one who will be considered a co-chair and one representing each aim. The committee size of 15 is similar to other NRSPs and will include at least three representatives from each of the four regions. This committee will meet at least quarterly, with one meeting at a National Digital Agriculture Summit. Our work will be guided by an external advisory board along with program leaders. To ensure national impact, the steering committee will establish regional hubs to adapt tools to local conditions, coordinate outreach, and host demonstration projects. The annual National Digital Agriculture Summit will provide an opportunity to convene all partners to share progress, evaluate challenges, and guide future directions.

Project Business Plan

We have several goals for private sector engagement, including developing partnerships with at-tech, agri-business, and agri-chemical sectors by developing compelling value propositions for deployment of new technologies. The development of many new technologies used in agriculture, such as new weather stations or sensing tools, is largely coming from private sector companies. However, these companies often need to partner with academic institutions to ensure their technologies are implemented by producer communities that know and trust extension advice from land-grant partners. Our project will first provide the national capacity to implement new agricultural technologies throughout the United States. This will allow research and extension scientists at land grant universities to leverage local partnerships to support maintenance of the decision support systems they create. Second, by supporting the development of market-ready decision support tools we can integrate into farmer workflows and establish revenue streams through platform services. Third, by creating a scalable innovation ecosystem we can foster an ongoing cycle of research, development, and product innovation through ongoing academic-industry collaboration.

In the first 2-3 years of the project we will integrate existing digital agricultural tools across a variety agricultural landscapes, while building the framework for a national capacity project. During this period we will seek in-kind contributions (field access, equipment) from agricultural extension services and university partners, while also building relationships with agribusinesses and ag-tech startups through workshops and open innovation challenges. Creation of an external advisory group with farmers, industry leaders, and technology experts will broaden collaboration and investment opportunities. In years 3-5 we will advance models linking abiotic data to biotic processes, focusing on high-impact areas such as pest prediction and crop health. During this period we hope to attract 20-30% of funding from private partners through sponsorships, cost-share pilots, and collaborative research and development projects. We will expand our private sector engagement to more broadly include farm equipment manufacturers, crop protection companies, and precision ag startups. If the project is extended, we hope to achieve 80% private funding after 10 years, with 100% of system maintenance costs provided by private contracts; 20% from research grants will still be key for development of new technologies to integrate into our digital platforms. During this period, and after the conclusion of the project, we expect to have created scalable platforms for digital agriculture nationwide, with funding and private-sector investment expected to come from many sources such as: (i) tiered subscription plans (free/basic/premium), (ii) consulting services for agribusiness clients, (iii) licensing of algorithms and application programming interfaces (APIs), (iv) custom analytics services, like personalized dashboards for cooperatives, consultants, and large-scale farms, and (v) data-as-a-service: access to anonymized user data for research and development. Finally, having a public name and logo for the project will be a way to connect with stakeholders and encourage shared production of marketing materials with the private sector. We propose a public name for the project be FARMWISE: Forecasting And Risk Management with a Web-Based Interactive SystEm. The public title will allow us to simply and effectively communicate the impact of the work, brand the project, and market it for the public good. Two drafts of a logo are provided as attachments.

Integration

Digital agriculture offers a perfect complement between research, extension, and teaching, and our project developed these synergies in several ways. Many research scientists in academics and the private sector work to create new technologies that can benefit agricultural industries. These include weather stations, soil monitoring sensors, automated camera traps for pests, drones for in-field phenotyping, and wireless-sensor networks. Other scientists work on integrating data from these sensors into models that may benefit producers make more timely management decisions. Examples of this include weather-driven phenological models for pests, and process-driven models of disease outbreaks in agricultural systems. However, there is often poor integration of new technologies into platforms used by producers and other agricultural partners. This results in what we term, 'a decision support graveyard', which are tools that could be effective but were never implemented in the systems that could benefit. Most academics, for example, are not effective at creating websites or mobile applications to implement their models or abiotic sensing tools. Yet, the software to implement many of these technologies is scalable, and a coordination network can ensure the most effective new technologies are supported.

Our project will ensure that data available from weather stations and other sensing technologies is available in standard formats for researchers to use. This means that researchers throughout the country will be able to implement models they have created in a standardized way. In turn, our project will ensure that agricultural models and abiotic sensing tools are provided to users in standardized user interfaces. This will allow extension scientists as well as teachers to use the tools we host in the outreach and teaching efforts. Extension scientists are ultimately the individuals who help affect pest management decisions in the field, and our project will ensure they have the tools available to do so effectively. Our project will allow extension scientists to gather information in the field and deliver this to their user bases, while also host models that are regionally-adapted and specific to particular crops and pests. At the same time, our project can be used by teachers to train new students in pest management techniques in their local ecosystems. 

Outreach, Communications and Assessment

(i) Overview

Our outreach plan has been crafted to communicate the goals, accomplishments, impacts, outputs, and outcomes of the project to other scientists as well as the broader public. By creating national libraries of tools to process abiotic data and integrate data into models, our capacity project will provide benefits to scientists who need assistance in delivering their tools to producers. We will communicate to these scientists through a national listserve that reports outputs and updates of our project and contains minutes of our quarterly and annual meetings. We will also provide an up-to-date public and evolving database that researchers can access for their own work. We will ask researchers who use our products to become involved in the capacity project if appropriate.

While our project is designed to enhance research capacity in abiotic sensing and implementation of abiotic data into models, it is also designed to aid outreach specialists. When libraries of locally validated models are created and housed as part of a capacity projecxt, they can be used by other researchers and extension scientists to benefit their local agricultural industries. We anticipate that products curated as part of this NRSP can be used on websites, presentations, field days, workshops, and in the classroom to communicate ways in which digital technology can benefit agricultural production.

Our project is also designed to encourage communication between researchers and the public, and in particular agricultural producers and partners who wish to have access to our research outputs. For example, we can make outputs of forecasting models and biotic models available to a wider range of producers and more crop industries as we expand the scope of the project. In turn, we will generate opportunities for private-sector partnership and investment.

(ii) Intended audiences and stakeholder engagement

Our project is intended to provide capacity to support researchers and scientists who are involved in (i) collection of abiotic data in agroecosystems, (ii) the creation and delivery of biotic models in agricultural ecosystems, and (iii) human decision making in agriculture. Results of our project will be disseminated to these individuals through academic publications, conference presentations, extension bulletins, and creation of online decision support platforms. We will also have a portion of our quarterly meeting of the steering committee available to the public for comment and discussion. Our project will also house software libraries through public GitHub libraries and the Open Access Software Framework.

In addition to the scientific community, the project will engage farmers, agronomic consultants, pesticide representatives, and crop commissions who can gain insight into more effective management practices, while also providing iterative feedback to the project team. Government agencies will also be engaged to help translate the project’s findings into policy recommendations and funding priorities. We will work with local, tribal, state, and national politicians to ensure that the project meets the needs of many partners. The research team will also involve crop industry members on our steering committee and we will have an external advisory board with members of crop industries and government agencies. To ensure that the needs and perspectives of these stakeholders are incorporated into the project, the research team will involve them in all stages of the project. Stakeholders will be invited to participate in focus groups, advisory panels, and team meetings where they can provide input and feedback on the project’s direction and outcomes. 

(iii) Methodology for measuring accomplishments and impacts

The project’s accomplishments and impacts will be assessed with quantitative and qualitative methods. Key performance indicators (KPIs) will be established to track progress toward specific objectives, such as (i) development and dissemination of open-source datasets, (ii) creation of tools for processing weather and abiotic sensing data, (iii) the number of biotic models that have been validated and housed in open-source libraries, (iv) growth in a database of tools for human behavior research, and (v) the number of nationwide collaborators and land-grant universities involved in the project. Surveys will be distributed to involved scientists, stakeholders, and end users to gather feedback on the project’s outputs' effectiveness and applicability to real-world scenarios. We will also work with our industry partners to track how their particular industries are adapting to novel digital agriculture tools. The impact of the project on academic partners will be measured through citation analysis, tracking how frequently the project’s publications are referenced. Furthermore, the project includes an aspect of sociological and behavioral research to assess adoption of our tools. These tools will be used by researchers to assess digital technologies curated by this capacity project.

(iv) Communication strategy

We will use several methods to communicate the project’s activities, accomplishments, and impacts. First, scientists funded by the project will develop a weekly blog to provide informal updates on the project on sites such as LinkedIn; this will also serve as a regular tool to recruit new members into the project. We will also provide minutes of our quarterly meetings with a set of action items that can be accessed by the public, and a FAQ based on the most commonly asked questions. In addition, outputs of our project will include detailed reports on the status and growth of digital agriculture, policy briefs on specific issues, infographics on crop industries and users affected, email newsletters, podcasts, extension articles, and case studies that highlight the key outcomes of the project. These materials will be tailored to different audiences so that we can make impacts across a variety of partners. Policy briefs and case studies will be designed for government agencies and policymakers, and we will engage with these members of the public through targeted extension. In contrast, infographics, newsletters, and extension articles will be more suitable for the general public and agricultural producers. We will ensure that our deliverables are available through a variety of channels, including presentations at stakeholder meetings, seminars/webinars, field days, technology demonstrations, conferences, and workshops. The project will also leverage digital platforms such as websites, social media, and email newsletters to reach a broader audience. Additionally, the research team will work closely with the SAES directors and their organizations, as well as funding sources, to ensure that the project’s results are shared with the appropriate decision-makers and influencers. 

(v) Distribution of results

The results of this research support project will be shared in several ways. First, we attend to create a National Digital Agricultural Symposium that will rotate hosts on an annual basis. At this meeting, we will bring together the steering committee, key external partners, and will invite members of the public (to attend in person or particular sessions via Zoom). At this annual meeting we will review progress on goals and set new action items. The research team will also provide material to relevant SAES/ARD organization committees. Furthermore, the project will create a website to host all materials and up-to-date outputs from the project. This will be updated regularly and linked to regular blog and email posts. Finally, project team members will assist the SAES/ARD organization committees prepare documents that highlight the impacts of the research, ensuring that the results are communicated effectively to a broader audience. By implementing this comprehensive outreach, communications, and assessment plan, the project will not only achieve its research objectives but also ensure that its findings are widely disseminated and used, creating broad benefits for agricultural partners nationwide.

Projected Participation

View Participation Form/Appendix E: Participation

Literature Cited

1. Méndez-Zambrano PV, Tierra Pérez LP, Ureta Valdez RE, Flores Orozco ÁP (2023) Technological innovations for agricultural production from an environmental perspective: a review. Sustainability 15, 16100.
2. Padhiary M, Kumar A, Sethi LN (2025) Emerging technologies for smart and sustainable precision agriculture. Discover Robotics 1, 6.
3. Raj M, Prahadeeswaran M (2025). Revolutionizing agriculture: a review of smart farming technologies for a sustainable future. Discover Applied Sciences 7, 937.
4. Rivera A, Ponce P, Mata O, Molina A, Meier A (2023). Local weather station design and development for cost-effective environmental monitoring and real-time data sharing. Sensors 23, 9060.
5. Mourtzinis S, Edreira JI, Conley SP, Grassini P (2017) From grid to field: assessing quality of gridded weather data for agricultural applications. European Journal of Agronomy 82, 163-72.
6. Khanna M, Atallah SS, Kar S, Sharma B, Wu L, Yu C, Chowdhary G, Soman C, Guan K (2022) Digital transformation for a sustainable agriculture in the United States: opportunities and challenges. Agricultural Economics 53, 924-937.
7. Vijayakumar S, Murugaiyan V, Ilakkiya S, Kumar V, Sundaram RM, Kumar RM (2025) Opportunities, challenges, and interventions for agriculture 4.0 adoption. Discover Food 5, 265.
8. Vinatier F, Lagacherie P, Voltz M, Petit S, Lavigne C, Brunet Y, Lescourret F (2016) An unified framework to integrate biotic, abiotic processes and human activities in spatially explicit models of agricultural landscapes. Frontiers in Environmental Science 4, 6.
9. Skendžić S, Zovko M, Živković IP, Lešić V, Lemić D (2021). The impact of climate change on agricultural insect pests. Insects 12, 440.
10. Ishtiaque A. United States farmers’ adaptations to climate change: a systematic review of adaptation-focused studies in the United States agriculture context (2023). Environmental Research: Climate 2, 022001.
11. Rojas-Reyes JJ, Rivera-Cadavid L, Peña-Orozco DL (2024) Disruptions in the food supply chain: A literature review. Heliyon, 10.
12. Hachimi CE, Belaqziz S, Khabba S, Sebbar B, Dhiba D, Chehbouni A (2022) Smart weather data management based on artificial intelligence and big data analytics for precision agriculture. Agriculture 13, 95.
13. Shen S, Basist A, Howard A (2010) Structure of a digital agriculture system and agricultural risks due to climate changes. Agriculture and Agricultural Science Procedia 1, 42-51.
14. National Research Council, Division on Earth, Life Studies, Computer Science, Telecommunications Board, Board on Atmospheric Sciences, Board on Earth Sciences, Committee on Geophysical, Environmental Data, Committee on Partnerships in Weather, Climate Services (2003) Fair Weather: Effective Partnership in Weather and Climate Services. National Academies Press, Washington, DC.
15. Coop AJ, Hubbard KG, Shulski MD, You J, Marx DB (2014). Spatial accuracy of climate networks: a case study in Nebraska. Journal of Applied Meteorology and Climatology 53, 1932-1942.
16. Mandel R, Noyes E (2013) Beyond the NWS: inside the thriving private weather forecasting industry. Weatherwise 66, 12-19.
17. National Weather Service (2017) Enterprise Analysis Report: Findings on Changes in the Private Weather Industry. National Academies Press, Washington, DC.
18. Preti M, Verheggen F, Angeli S (2021) Insect pest monitoring with camera-equipped traps: strengths and limitations. Journal of Pest Science 94, 203-217.
19. Carroll J, Weigle T, Petzoldt C (2025) The Network for Environment & Weather Applications (NEWA). Cornell University Press, Ithaca, NY.
20. Center OI (2022) Oregon State IPM Coordinating Committee Biennial Report. Oregon State University Press, Corvallis, OR.
21. Chambers U, Petit B, Jones VP (2011) WSU-DAS-the online pest management support system for tree fruits in Washington State. In IX International Symposium on Modelling in Fruit Research and Orchard Management, pp. 27-33.
22. Wohleb CH, Waters TD, Crowder DW (2021) Decision support for potato growers using a pest monitoring network. American Journal of Potato Research 98, 5-11.
23. Olejniczak K, Newcomer KE, Meijer SA (2020) Advancing evaluation practice with serious games. American Journal of Evaluation 41, 339-366.
24. Pérez J, Castro M, López G (2023) Serious games and AI: challenges and opportunities for computational social science. IEEE Access 11, 62051-62061.
25. Wen J, Gabrys B, Musial K (2023) Review and assessment of digital twin–oriented social network simulators. IEEE Access 11, 97503-97521.
26. Shennan C (2008) Biotic interactions, ecological knowledge and agriculture. Philosophical Transactions of the Royal Society B: Biological Sciences 363, 717-739.
27. Dernat S, Grillot M, Andreotti F, Martel G (2025) A sustainable game changer? Systematic review of serious games used for agriculture and research agenda. Agricultural Systems 222, 104178.
28. Riaz S, Ishaq K, Alvi A, Salleh SM, Nawaz NA (2025) Culturally tailored serious game design: a revolutionary model for smart agriculture. Human Behavior and Emerging Technologies 2025, 6564116.
29. Hamel C, Landry C, Elmi A, Liu A, Spedding T (2004) Nutrient dynamics: utilizing biotic-abiotic interactions for improved management of agricultural soils. Journal of Crop Improvement 11, 209-248.
30. Lamichhane JR, Debaeke P, Steinberg C, You MP, Barbetti MJ, Aubertot JN (2018) Abiotic and biotic factors affecting crop seed germination and seedling emergence: a conceptual framework. Plant and Soil 432, 1-28.
31. Velásquez AC, Castroverde CD, He SY (2018) Plant–pathogen warfare under changing climate conditions. Current Biology 28, R619-634.
32. Giles DK, Klassen P, Niederholzer FJ, Downey D (2011) “Smart” sprayer technology provides environmental and economic benefits in California orchards. California Agriculture
33. Signorini G, Ivey ML (2023) Comparative feasibility analysis of mechanized equipment for vineyard operations. HortTechnology 33, 239-246.
34. Drewry JL, Shutske JM, Trechter D, Luck BD, Pitman L (2019) Assessment of digital technology adoption and access barriers among crop, dairy and livestock producers in Wisconsin. Computers and Electronics in Agriculture 165, 104960.
35. Nettle R, Ingram J, Ayre M (2025) Digiwork: how agriculture 4.0 is changing work for farm advisers. Frontiers in Sustainable Food Systems 9, 1542007.
36. Singh NK, Sunitha NH, Tripathi G, Saikanth DR, Sharma A, Jose AE, Mary MV (2023) Impact of digital technologies in agricultural extension. Asian Journal of Agricultural Extension, Economics & Sociology 41, 963-70.
37. Small B (2017) Digital technology and agriculture: Foresight for rural enterprises and rural lives in New Zealand. Journal of Agriculture and Environmental Sciences 6, 7.
38. Gould F, Brown ZS, Kuzma J (2018) Wicked evolution: can we address the sociobiological dilemma of pesticide resistance. Science 360, 728-732.
39. Pedersen AB, Nielsen HO, Christensen T, Orum JE, Martinsen L (2019) Are independent agricultural advisors more oriented towards recommending reduced pesticide use than supplier-affiliated advisors? Journal of Environmental Management 242, 507-514.
40. Utyasheva L, Rother H-A, London L, Eddleston M (2024) Stop blaming the farmer: dispelling the myths of ‘misuse’ and ‘safe’ use of pesticides to protect health and human rights. Journal of Human Rights 23, 231-252.
41. Aarif KO M, Alam A, Hotak Y (2025) Smart sensor technologies shaping the future of precision agriculture: Recent advances and future outlooks. Journal of Sensors 2025, 2460098.
42. Xu ZJ, Liu X, Cao X, Huang CP, Liu EK, Qian S, Liu XC, Wu YJ, Dong FL, Qiu CW, Qui JJ, Hua KQ, Su WT, Wu J, Xu HY, Han Y, Fu CG, Yin ZG, Liu M, Roepman R, Dietmann S, Virta M, Kengara F, Zhang Z, Zhang LF, Zhao TL, Dai J, Yang JL, Lan L, Luo M, Liu ZF, An T, Zhang B, He X, Cong S, Liu XH, Zhang W, Lewis JP, Tiedje JM, Wang Q, An ZL, Wang F, Zhang LB, Huang T, Lu C, Cai ZP, Wang F, Zhang JB (2021) Artificial intelligence: a powerful paradigm for scientific research. Innovation 2, 100179.
43. Xu XB, Zhang XP, Li HH, Zheng HJ, Zhang JA, Olsen MS, Varshney RK, Prasanna BM, Qian Q (2022) Smart breeding driven by big data, artificial intelligence, and integrated genomic-environment prediction. Molecular Plant 15, 1664-1695.
44. Herms DA (2004) Using degree-days and plant phenology to predict pest activity. IPM (Integrated Pest Management) of Midwest Landscapes, Illinois Arborist Press, 12 pp.
45. Sridhar V, Reddy PV (2013) Use of degree days and plant phenology: a reliable tool for predicting insect pest activity under climate change conditions. In: Climate-Resilient Horticulture: Adaptation and Mitigation Strategies, pp. 287-294. India: Springer India.
46. Biswas S, Das R (2024) Organic farming to mitigate biotic stresses under climate change scenario. Bulletin of the National Research Centre 48, 71.
47. McFadden J, Njuki E, Griffin T (2023) Precision agriculture in the digital era: recent adoption on United States farms. United StatesDA Economic Services Agency, Washington, DC.
48. Purcell W, Neubauer T, Mallinger K (2023) Digital twins in agriculture: challenges and opportunities for environmental sustainability. Current Opinion in Environmental Sustainability 61, 101252.
49. Escriba-Gelonch M, Liang S, van Schalwky P, Fisk I, Van Duc Long N, Volker H (2024) Digital twins in agriculture: orchestration and applications. Journal of Agriculture and Food Chemistry 72, 10727-10752.
50. Foureaux S, Daum T (2025) “But don’t think it is a game”: agricultural videogame and “good farming”. Journal of Rural Studies 117, 103686.

Attachments

Land Grant Participating States/Institutions

Non Land Grant Participating States/Institutions