Source: MADAIN CORP. submitted to NRP
REVOLUTIONIZING CROP MANAGEMENT: HARNESSING AI AND EDGE COMPUTING FOR ENHANCED PLANT HEALTH
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
COMPLETE
Funding Source
Reporting Frequency
Annual
Accession No.
1031820
Grant No.
2024-33530-41934
Cumulative Award Amt.
$174,923.00
Proposal No.
2024-00321
Multistate No.
(N/A)
Project Start Date
Jul 1, 2024
Project End Date
Apr 11, 2025
Grant Year
2024
Program Code
[8.13]- Plant Production and Protection-Engineering
Recipient Organization
MADAIN CORP.
1958 MOSS LANDING AVE
CHULA VISTA,CA 91913
Performing Department
(N/A)
Non Technical Summary
1. Addressing the Current Issue: The Edgebot.ai project is designed to tackle a pressing problem in modern agriculture: the challenge of efficiently managing crop health and production using the latest technology. In an age where technology is rapidly advancing, many farmers and agricultural professionals find themselves unable to fully utilize AI and data-driven methods due to a lack of technical expertise. This gap not only affects crop yields and farm efficiency but also has broader economic and environmental implications. By improving agricultural practices, we can enhance food security, reduce environmental strain, and support community development. In simpler terms, Edgebot.ai is about helping farmers make the most of modern technology to grow more food, more sustainably.2. Basic Methods and Approaches: The approach of Edgebot.ai is user-friendly and inclusive, designed for those without a technical background. Essentially, we're building a platform that allows farmers and agricultural workers to easily create and use AI tools for better crop management. These tools will help them analyze data like soil conditions and crop health, without needing to be tech experts. Think of it as a simple app on a phone or computer that can give powerful insights into how to grow crops more effectively. We'll be working closely with people in the agricultural field, using their feedback to make sure our platform is easy to use and genuinely helpful.3. Ultimate Goals and Societal Benefits: The ultimate goal of Edgebot.ai is to empower farmers and agricultural professionals with AI tools that are easy to use and understand. By doing so, we aim to improve crop yields, reduce waste, and make farming more efficient and environmentally friendly. If successful, this project will not only benefit farmers by making their work easier and more productive but also have wider societal benefits. Better farming methods mean more food production, which can lead to lower food prices and increased food security. Environmentally, efficient farming reduces the strain on resources like water and land. In summary, Edgebot.ai aims to bring the benefits of AI to agriculture in a way that's accessible to everyone, leading to healthier crops, a better environment, and a stronger community.
Animal Health Component
30%
Research Effort Categories
Basic
10%
Applied
30%
Developmental
60%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
2052499202080%
2040110303020%
Goals / Objectives
Major Goals and Objectives of the Edgebot.ai ProjectThe overarching goal of the Edgebot.ai project is to revolutionize agricultural practices by empowering farmers and agricultural professionals with an accessible, AI-driven platform for efficient farm management. This goal encompasses the vision of enhancing crop productivity, optimizing resource utilization, and facilitating sustainable agricultural practices through advanced technological solutions. By bridging the gap between complex AI technology and practical agricultural applications, Edgebot.ai aims to catalyze a significant shift towards data-driven, eco-friendly, and economically viable farming.Objectives:1. Development of Edgebot.ai Infrastructure: - Integrate cutting-edge AI and ML tools for automated data preprocessing, model generation, and analysis, tailored to agricultural needs. - Implement cloud-based and edge computing technologies to ensure efficient, real-time data processing and decision-making. - Achieve high accuracy and efficiency in data handling and model training, with specific targets such as 95% Lambda-RPA accuracy and 90% Glue-ETL success rate.2. User-Friendly Interface Creation: - Develop a no-code/low-code interface that is intuitive and accessible to non-technical users, particularly focusing on the agricultural community. - Ensure that the platform can be easily navigated and utilized by farmers and agricultural workers with minimal technical background.3. Comprehensive Data Analysis and Model Training: - Collect and analyze diverse agricultural data sets to inform and enhance AI model accuracy and applicability. - Attain a high success rate in AI model training and data annotation, aiming for at least an 85% success rate in model training and a 90% success rate in data labeling.4. Educational Outreach and Capacity Building: - Conduct workshops, seminars, and training programs for farmers, agricultural workers, and students to familiarize them with Edgebot.ai and its applications. - Collaborate with agricultural educational institutions to integrate Edgebot.ai into their curriculum and research activities.5. Usability Testing and Feedback Integration: - Perform rigorous usability testing in real-world agricultural settings, in collaboration with institutions like Prairie View A&M University. - Continuously refine and adapt the platform based on user feedback and testing results, targeting a prediction precision of over 90%.6. Environmental Impact and Sustainability Focus: - Monitor and assess the environmental impact of implementing AI-driven agricultural practices, aiming to demonstrate improvements in resource utilization and sustainability. - Promote practices that contribute to environmental conservation and reduced ecological footprints through the use of Edgebot.ai.7. Market Penetration and User Adoption: - Strategically market and promote Edgebot.ai within the agricultural sector to maximize its adoption and use. - Aim for significant user adoption metrics, focusing on small and medium-sized farms and underserved agricultural communities.8. Continuous Innovation and Technological Advancement: - Stay abreast of technological advancements in AI and ML, continuously integrating these innovations into the Edgebot.ai platform. - Foster a culture of innovation and continuous improvement within the project team to ensure Edgebot.ai remains at the forefront of AI-driven agricultural solutions.9. Impact Assessment and Evaluation: - Develop and implement a comprehensive evaluation framework to measure the impact of Edgebot.ai on agricultural practices, productivity, and sustainability. - Utilize both qualitative and quantitative methods to assess the effectiveness and reach of the platform.10. Long-Term Sustainability and Scalability: - Establish a model for the long-term financial and operational sustainability of the Edgebot.ai platform. - Plan for scalability, ensuring that Edgebot.ai can adapt and grow to meet the evolving needs of the agricultural sector.These objectives, while specific and measurable, contribute collectively towards the realization of the major goal of transforming agricultural practices through AI technology. By achieving these objectives, Edgebot.ai will not only enhance the efficiency and productivity of farming but also promote environmental sustainability and economic viability in the agricultural sector.
Project Methods
The methods of the Edgebot.ai project are structured to ensure the effective delivery and evaluation of its objectives. The project will be conducted using a blend of scientific methods, innovative technologies, and educational efforts. The methodology is divided into various components:1. Project Development and Implementation: - Utilizing a no-code/low-code platform approach to facilitate ease of use for non-technical users. - Integrating advanced AI/ML tools for data processing, model training, and analysis. - Implementing cloud-based technologies like AWS services for efficient data handling and model generation. - Emphasizing edge computing to enable real-time data processing and decision-making.2. Data Collection and Analysis: - Gathering diverse datasets relevant to agricultural practices, including soil conditions, crop health, and environmental factors. - Employing statistical and machine learning techniques to analyze the data. - Utilizing TensorFlow and other AI/ML frameworks for model creation and training. - Continuous monitoring and refinement of AI models based on data input and feedback.3. Educational and Outreach Efforts: - Developing and implementing educational programs and workshops for agricultural professionals, students, and other target audiences. - Creating online resources and tutorials for self-learning and practical application of Edgebot.ai. - Collaborating with agricultural universities and extension services for knowledge dissemination and practical demonstrations. - Providing hands-on experiences through internships, practicum experiences, and experiential learning opportunities.4. Evaluation and Impact Assessment: - Implementing a Test-Driven Development (TDD) approach to evaluate the functionality and efficiency of Edgebot.ai. - Conducting usability testing in collaboration with agricultural institutions, focusing on precision and reliability of predictions. - Analyzing the impact of Edgebot.ai on crop management efficiency, decision-making processes, and overall farm productivity. - Collecting qualitative and quantitative data from users to assess the change in knowledge, actions, and conditions.5. Evaluation Methods: - Utilizing surveys and feedback forms post-implementation to gauge user satisfaction and areas of improvement. - Analyzing usage statistics and success rates of model predictions to evaluate the technical performance of the platform. - Comparing pre-and post-implementation data to measure the improvement in agricultural practices and crop yields. - Documenting case studies and success stories as qualitative evidence of the project's impact.6. Key Milestones and Indicators of Success: - Achievement of a 95% accuracy rate in Lambda-RPA functions and a 90% success rate in Glue-ETL services. - Reduction in average data transformation time to under 5 minutes per dataset. - Attainment of a model training success rate of at least 85% and a data labeling success rate of 90%. - Realizing a prediction precision of over 90% in feasibility studies with agricultural crops. - Significant user adoption and application of Edgebot.ai in agricultural practices.7. Continuous Improvement and Adaptation: - Regularly updating the Edgebot.ai platform based on user feedback and technological advancements. - Adapting the platform to accommodate new agricultural challenges and environmental conditions. - Ensuring the platform remains accessible and user-friendly for its diverse target audience.The Edgebot.ai project, through its innovative approach and comprehensive methodology, aims to revolutionize agricultural practices. By combining advanced AI technologies with educational efforts, the project seeks to empower its target audience with the knowledge and tools needed for efficient and sustainable agriculture. The evaluation and impact assessment will ensure that the project remains aligned with its objectives and continues to make a meaningful impact on the agricultural community.

Progress 07/01/24 to 04/11/25

Outputs
Target Audience:Small to Medium-Sized Farms: These farms face significant challenges in resource management and productivity optimization. Our tools aimed to provide accessible AI solutions that can easily integrate into their existing workflows. Engagement Strategy: We offered targeted workshops and demonstrations showcasing the practical benefits of adopting AI for crop management, resource allocation, and yield prediction. Agricultural Cooperatives: Cooperatives, which often pool resources for better access to technology and markets, were identified as key beneficiaries due to their collective approach to innovation adoption. Engagement Strategy: We engaged with cooperatives through tailored seminars and training programs focused on showcasing collaborative data use and shared AI model benefits for member farms. Agronomy Consultants and Advisors: These professionals provide expert guidance to farmers on crop production and management. By equipping them with cutting-edge AI tools, we amplify their capability to advise efficiently. Engagement Strategy: Our direct engagement included specialized training sessions and access to pilot programs that demonstrated Edgebot.ai's value in enhancing decision-making processes based on AI insights. Educational and Training Institutions: Schools and vocational institutions involved in agricultural education are pivotal in preparing the generation of ag-tech professionals. Engagement Strategy: We collaborated with these entities to incorporate Edgebot.ai into curricula and provide early exposure to AI technologies through hands-on workshops and supplemented learning materials. Tech-Savvy Farmers and Early Adopters: This group of progressive farmers is eager to embrace new technologies to boost efficiency and sustainability on their farms. - Engagement Strategy: We reached this audience through digital marketing campaigns, webinars, and interactive online platforms demonstrating the tangible benefits and ease of use of our AI solutions. Changes/Problems:Had to adampt to many changes in the underlying AI models as the changes in the AI industry have exploded. However, while there was much rework that was needed. We were able to produce a working platform https://edgebot.ai/ that is in production now. We also faces some issues when coordinating with the university around timing of testing. What opportunities for training and professional development has the project provided?Trained all participants on how to prepare their data. import it into the system and create thier own AI Mobile App in under **2 hours** to produce a workable prototype. How have the results been disseminated to communities of interest? Nothing Reported What do you plan to do during the next reporting period to accomplish the goals? Nothing Reported

Impacts
What was accomplished under these goals? 1. Development of Edgebot.ai Infrastructure: 100% Completed. 2. User-Friendly Interface Creation:100% Completed. 3. Comprehensive Data Analysis and Model Training:100% Completed. 4. Educational Outreach and Capacity Building:100% Completed. 5. Usability Testing and Feedback Integration:100% Completed. 6. Environmental Impact and Sustainability Focus:100% Completedwith 90% confidence on high imact. 7. Market Penetration and User Adoption:100% Completed was able to strike a deal to whole sale and whitelabel the product. 8. Continuous Innovation and Technological Advancement: Continuous 9. Impact Assessment and Evaluation: Experts provides a 93% confidencefor those farmers that adobt the technology witht he proper data sets will achieve higher yeilds. 10. Long-Term Sustainability and Scalability:100% Completed.

Publications