Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Digital Agriculture Sandbox for Collaborative Research

Osama Zafar, Rosemarie Santa González, Alfonso Morales, Erman Ayday

TL;DR

The paper addresses privacy barriers to agricultural data sharing that impede data-driven research and innovation. It introduces the Digital Agriculture Sandbox, a privacy-preserving, web-based platform that enables secure collaboration through federated learning, local differential privacy, and Principal Component Analysis. Key contributions include a modular, containerized architecture with identity management via TACC, privacy-preserving data operations (upload, similarity discovery, and distributed model training), and risk-aware model governance via a repository and analytics tools. The framework demonstrates practical use cases for farmers and researchers and outlines future work to expand models, explanations, risk analyses, safeguards, and a data-sharing component that preserves privacy.

Abstract

Digital agriculture is transforming the way we grow food by utilizing technology to make farming more efficient, sustainable, and productive. This modern approach to agriculture generates a wealth of valuable data that could help address global food challenges, but farmers are hesitant to share it due to privacy concerns. This limits the extent to which researchers can learn from this data to inform improvements in farming. This paper presents the Digital Agriculture Sandbox, a secure online platform that solves this problem. The platform enables farmers (with limited technical resources) and researchers to collaborate on analyzing farm data without exposing private information. We employ specialized techniques such as federated learning, differential privacy, and data analysis methods to safeguard the data while maintaining its utility for research purposes. The system enables farmers to identify similar farmers in a simplified manner without needing extensive technical knowledge or access to computational resources. Similarly, it enables researchers to learn from the data and build helpful tools without the sensitive information ever leaving the farmer's system. This creates a safe space where farmers feel comfortable sharing data, allowing researchers to make important discoveries. Our platform helps bridge the gap between maintaining farm data privacy and utilizing that data to address critical food and farming challenges worldwide.

Digital Agriculture Sandbox for Collaborative Research

TL;DR

The paper addresses privacy barriers to agricultural data sharing that impede data-driven research and innovation. It introduces the Digital Agriculture Sandbox, a privacy-preserving, web-based platform that enables secure collaboration through federated learning, local differential privacy, and Principal Component Analysis. Key contributions include a modular, containerized architecture with identity management via TACC, privacy-preserving data operations (upload, similarity discovery, and distributed model training), and risk-aware model governance via a repository and analytics tools. The framework demonstrates practical use cases for farmers and researchers and outlines future work to expand models, explanations, risk analyses, safeguards, and a data-sharing component that preserves privacy.

Abstract

Digital agriculture is transforming the way we grow food by utilizing technology to make farming more efficient, sustainable, and productive. This modern approach to agriculture generates a wealth of valuable data that could help address global food challenges, but farmers are hesitant to share it due to privacy concerns. This limits the extent to which researchers can learn from this data to inform improvements in farming. This paper presents the Digital Agriculture Sandbox, a secure online platform that solves this problem. The platform enables farmers (with limited technical resources) and researchers to collaborate on analyzing farm data without exposing private information. We employ specialized techniques such as federated learning, differential privacy, and data analysis methods to safeguard the data while maintaining its utility for research purposes. The system enables farmers to identify similar farmers in a simplified manner without needing extensive technical knowledge or access to computational resources. Similarly, it enables researchers to learn from the data and build helpful tools without the sensitive information ever leaving the farmer's system. This creates a safe space where farmers feel comfortable sharing data, allowing researchers to make important discoveries. Our platform helps bridge the gap between maintaining farm data privacy and utilizing that data to address critical food and farming challenges worldwide.

Paper Structure

This paper contains 9 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Background
  3. Digital Agriculture Framework
  4. Sandbox's underlying architecture
  5. Key features
  6. Deployment
  7. Use Cases
  8. Future Work
  9. Conclusion

Figures (3)

  • Figure 1: Illustrate the farm dataset upload user interface: users can input a dataset name and upload their farm data via the designated upload area, then confirm with 'Upload Dataset'.
  • Figure 2: Illustrate the model training user interface: users can input a model name, define parameters like model type and visibility, add an optional readme, select collaborators, and then confirm with 'Start Training'.
  • Figure 3: Illustrates the deployment of the sandbox within a containerized environment and the interaction among the containers.