Weather-Driven Agricultural Decision-Making Using Digital Twins Under Imperfect Conditions

2025-08-09

AI Summary

Incomplete meteorological data undermines the reliability of agricultural digital twin systems. Method: This paper proposes Cerealia, a modular framework integrating dynamic virtual agricultural modeling with a multi-source data consistency verification mechanism. It employs a lightweight neural network for real-time anomaly detection, deployed on an NVIDIA Jetson Orin edge platform to enable on-device sensor data comparison and meteorological anomaly identification. Crucially, it achieves proactive inconsistency awareness under non-ideal input conditions—e.g., missing or noisy weather data—enhancing decision robustness. Contribution/Results: Evaluated on a commercial orchard’s in-situ weather network and public datasets, Cerealia achieves high anomaly detection accuracy (F1-score > 0.92) and demonstrates consistent performance across real-world deployments and cross-domain data. It provides a deployable, resource-efficient solution for precision agriculture automation in constrained-edge environments.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

By offering a dynamic, real-time virtual representation of physical systems, digital twin technology can enhance data-driven decision-making in digital agriculture. Our research shows how digital twins are useful for detecting inconsistencies in agricultural weather data measurements, which are key attributes for various agricultural decision-making and automation tasks. We develop a modular framework named Cerealia that allows end-users to check for data inconsistencies when perfect weather feeds are unavailable. Cerealia uses neural network models to check anomalies and aids end-users in informed decision-making. We develop a prototype of Cerealia using the NVIDIA Jetson Orin platform and test it with an operational weather network established in a commercial orchard as well as publicly available weather datasets.

Problem

• Detecting inconsistencies in agricultural weather data measurements
• Enhancing decision-making with digital twins under imperfect conditions
• Developing a modular framework for anomaly detection in weather data

Innovation

• Digital twins enhance real-time agricultural decision-making
• Modular framework Cerealia detects weather data inconsistencies
• Neural networks check anomalies for informed user decisions