E-Bio Reactivomics-Based AI Monitoring Service for Crop Stress Environments

Overview

The frequency and intensity of weather disasters and adverse environmental conditions are increasing. However, due to inadequate proactive monitoring and response systems, crop damage is rising. The reality is that relying solely on simple external phenotypic analysis and response based on visual inspection makes early detection and timely intervention impossible. Furthermore, overcoming agricultural environmental changes caused by climate change and securing stable agricultural productivity urgently require the introduction of biotechnology and AI-based big data prediction technologies. Preemptive response technology development utilizing biosensing technology and artificial signals is necessary.

The project aims to develop an AI-based damage prediction system that enables more precise analysis of disease and pest damage, as well as drought damage, by analyzing biomarker (specific gene) expression data rather than relying solely on visible damage symptoms in crops. This system will detect damage within 1 to 3 days, compared to the current 1 week required for visual detection, and provide public services such as AI diagnosis and prescription for diseases and pests.

Project description

Establish big data on crop growth-cycle biometric information, including biometric variation data from local agricultural institutions and universities, and AI training datasets for drought / heat / pest / disease responses.

This project will collect and analyze biological information for rice and soybean crops according to their growth stages. It will develop an AI-integrated analysis-based environmental variation prediction and response system for analyzing crop biological regulation in response to environmental changes.

It will provide public services through a web portal, including crop damage prediction information and environmental variation data affecting crop growth by region. It will also promote the opening of public data via open APIs to share information on crop damage and predictions related to climate, drought, and other factors.

Key technological features

• Data and biological information variation big data collected, analyzed, and generated through the integrated collection and analysis of internal biological responses exhibited by crops when exposed to various environmental factors (climate change, pests and diseases, soil conditions, etc.)
• Generating meaningful data dependencies and sets through big data analysis, and enabling early prediction of adverse environmental conditions for crops through AI learning and analysis

Expected outcomes

Contributes to mitigating food security crises by transitioning to an intelligent observation system based on crop environmental response biomarker big data and AI. Predictions, which previously took a week to detect external crop damage symptoms, can now be made within a minimum of 1 to 3 days through precise biomarker analysis.

Furthermore, it is expected to contribute to innovative development in agriculture and other industries by securing big data on biological information variations in environmentally responsive crops through continuous expansion of target crops and regions.

Launch year: 2025

Attribution

Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.1,  https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=28997&parentSeq=29036