This post was co-authored with Etzik Bega from Agmatix. Agmatix is an agtech company pioneering data-driven solutions for the agricultural industry, leveraging advanced AI technologies, including generative AI, to accelerate research and development processes, improve crop yields, and improve sustainability. We will promote possible agriculture. Focused on addressing the challenge of agricultural data standardization, Agmatix has developed unique patented technology that harmonizes and standardizes data to facilitate informed decision-making in agriculture. A suite of data-driven tools enables you to manage agronomic field trials, create digital crop nutrient formulations, and promote sustainable farming practices. Agmatix field testing and analysis solutions are widely adopted by agronomists, scientists, crop input manufacturing and contract research organization research and development teams and are at the forefront of agricultural innovation.
This post describes how Agmatix uses full-featured services from Amazon Bedrock and AWS to enhance its research process and development of high-yield seeds and sustainable molecules for global agriculture.
Amazon Bedrock is a fully managed service that provides a selection of high-performance foundational models (FM) from leading AI companies, including AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon, through a single API. Broad feature set for building generative AI applications with security, privacy, and responsible AI. With Amazon Bedrock, you can experiment and evaluate top FMs for your use case, privately customize them with your data using techniques such as fine-tuning and acquisition augmentation generation (RAG), and develop enterprise systems and data. You can use it to build agents to perform tasks. sauce.
Through this innovative approach, Agmatix is streamlining operations, accelerating the introduction of high-yielding seeds, and developing new and sustainable molecules used in crop protection, including pesticides, herbicides, fungicides, and biologicals. Promote.
Innovation in field trial research and development is complex
Innovation continues to be a key driver for increasing yields and increasing the security of the world’s food supply. Discoveries and improvements across seed genetics, site-specific fertilizers, and molecular development of crop protection products are powered by generative AI, the Internet of Things (IoT), integrated R&D test data, and high-performance computing analytics services. It is happening at the same time as innovation.
Collectively, these systems have significantly reduced the time to market for new genes and molecules, allowing producers to offer new and more effective products. Historical and current research and development on crop varieties and pesticides are essential to improving crop yields, but the process of introducing new crop inputs to farms is expensive and complex. A key step in this process is field testing. After new materials are developed in the laboratory, field trials are conducted to test the effectiveness of new crop varieties and pesticides in real-world settings.
There are a variety of technologies that can help operationalize and optimize the field testing process, including data management and analytics, IoT, remote sensing, robotics, machine learning (ML), and now generative AI.
Generative AI, led by agricultural technology innovators, is the latest AI technology that helps agronomists and researchers have unlimited human-like interactions with computing applications, assisting with a variety of tasks, and Automate processes that used to be done at work. Applications of generative AI in agriculture include predicting yields, improving the accuracy of agronomic recommendations, educating and training agronomic staff, and enabling users to query large datasets using natural language.
Current challenges in analyzing field trial data
Agricultural testing is complex and generates vast amounts of data. Most companies do not have access to field test data based on manual processes and disparate systems. Agmatix’s test management and agricultural data analytics infrastructure allows you to collect, manage, and analyze agricultural field test data. Agronomists use this service to accelerate innovation and turn research and experiment data into meaningful, actionable intelligence.
Agronomists upload or enter field trial data, create and manage tasks to monitor field trials, and analyze and visualize trial data to generate insights. The time-consuming and unwise tasks of cleaning, standardizing, harmonizing, and processing data are automated and handled by Agmatix’s intelligent services.
Without generative AI, the ability to analyze test data and build analytical dashboards to gain meaningful insights from field trials is complex and time-consuming. Two common challenges are:
- Each test can include hundreds of different parameters, making it difficult for agronomists to understand which parameters and data points are meaningful for the particular problem they want to investigate.
- Choose from a wide range of analytical visualization tools and charts, including one-way ANOVA, regression, boxplots, maps, and more. However, choosing the best visualization technique to help you understand patterns and identify anomalies in your data can be a difficult task.
Additionally, after creating an analytical dashboard, it can be complex to draw conclusions and establish relationships between different data points. For example, do the test results support the test hypothesis? Is there a relationship between the fertilizer applied and the weight of grain produced? Which external factors have the greatest impact on the effectiveness of product testing? mosquito?
AWS Generative AI Services Provide Solutions
In addition to other AWS services, Agmatix uses Amazon Bedrock to solve these challenges. Amazon Bedrock is a fully managed serverless generative AI product from AWS that offers a variety of high-performance FMs to support generative AI use cases.
Through the integration of Agmatix’s landscape with Amazon Bedrock, Agmatix has developed a specialized generative AI assistant called Leafy. This provides a significantly improved user experience for agronomists and R&D staff.
Instead of spending hours evaluating data points for research, choosing the right visualization tools, and creating multiple dashboards to analyze R&D and trial information, agronomists can ask questions in natural language. You can write and have Leafy instantly provide you with relevant dashboards and insights (see screenshot of an example of Leafy in action). This helps improve productivity and user experience.
The first step in developing and deploying generative AI use cases is having a clearly defined data strategy. Agmatix’s technology architecture is built on AWS. The data pipeline (as shown in the following architecture diagram) consists of ingest, storage, ETL (extract, transform, load), and data governance layers. Multisource data is first received and stored in an Amazon Simple Storage Service (Amazon S3) data lake. AWS Glue accesses data from Amazon S3 to perform data quality checks and important transformations. Next, use AWS Lambda to further enrich your data. The transformed data serves as input to the AI/ML service. The generated insights are accessed by users through Agmatix’s interface.
Focusing on generative AI, let’s first understand the basics of generative AI chatbot applications.
- prompt – Input questions or tasks that include context information provided by the user
- data – Data needed to answer prompt questions
- agent – Agents that perform task orchestration
For Agmatix, when an agronomist asks Leafy a question, Agmatix’s Insights solution sends a request to Anthropic Claude on Amazon Bedrock through an API.
- prompt – The prompt sent to Anthropic Claude consists of a task and data. Tasks are questions submitted by users.
- data – Data in prompts includes two types of data:
- Directing context data to the model. For example, a list of widget types that can be used for visualization.
- Data from specific field trials.
The following diagram shows the generative AI workflow.
The workflow consists of the following steps:
- Users submit questions to Leafy, Agmatix’s AI assistant.
- The application reads field trial data, business rules, and other required data from the data lake.
- The agent in the Insights application collects questions, tasks, and related data and sends them as prompts to FM via Amazon Bedrock.
- The generative AI model response is sent back to the Insights application.
- The responses are displayed to the user through a widget that visualizes the exam data and the user’s answers to specific questions, as shown in the following screenshot.
The data used in prompt engineering (trial results and rules) is stored in plain text and sent to the model as is. Rapid engineering plays a central role in this generative AI solution. For more information, see the Anthropic Claude Prompt Engineering Guide.
Overall, by using Amazon Bedrock on AWS, Agmatix’s data-driven field trial service can increase efficiency by more than 20%, improve data integrity by more than 25%, and increase potential analytical throughput by 3. A fold increase was observed.
In this way, generative AI technologies are improving the overall experience and productivity of agronomists, allowing them to focus on solving complex challenges and tasks that require human knowledge and intervention.
An example of this solution can be seen in the largest open nutrition database for crop nutrition powered by the Agmatix infrastructure, where researchers can leverage insights gleaned from thousands of field trials. In this practical scenario, users benefit from guided question prompts and responses facilitated by generative AI. This advanced data processing enhances users’ understanding of evolving trends in crop nutrient uptake and removal and simplifies the creation of decision support systems.
conclusion
Seed, chemical and fertilizer manufacturers need innovative, smart agricultural solutions to advance the next generation of genetics and molecules. Ron Baruchi, President and CEO of Agmatix, emphasizes the beneficial synergy between humans and technology.
“AI complements, rather than replaces, human expertise. By integrating Amazon Bedrock’s generative AI into our infrastructure, we are providing self-service analytics tools that simplify complex and time-consuming tasks. We will provide it to our customers.”
This integration will equip agronomists and researchers with advanced AI capabilities for data processing and analysis, allowing them to focus on strategic decision-making and creative problem-solving.
Managing field trials has long required the introduction of new technology. Agmatix’s AI-enabled agriculture services powered by AWS allow input manufacturers to reduce time and costs associated with field testing while improving overall productivity and experience for agronomists and growers. You can. By providing growers with the most successful seeds, crop protection products and fertilizers, their farming operations can thrive. This approach not only maximizes the efficiency of these critical crop inputs, but also minimizes the use of natural resources, resulting in a more sustainable and healthier planet for everyone.
For more information about Agmatix, please contact us.
resource
For more information about AWS and Amazon Bedrock, check out the following resources:
About the author
Etzik Vega Chief Architect at Agmatix, where he revolutionized the company’s data lake architecture using cutting-edge GenAI technology. With over 25 years of experience in cybersecurity, systems architecture, and communications, Etzik has recently focused his efforts on helping organizations securely and efficiently migrate to the public cloud.
Menachem Melamed He is a senior solutions architect at AWS, specializing in big data analytics and AI. With a deep background in software development and cloud architecture, he helps organizations build innovative solutions using the latest cloud technologies.
Prerana Sharma I am a Manager Solutions Architect at AWS, specializing in Manufacturing. With extensive experience in the digital farming space, Prerana helps customers solve business problems by experimenting and innovating with new technologies on AWS.
