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

TL;DR

This paper introduces Cerealia, a modular digital twin framework that detects weather data inconsistencies in real-time to improve agricultural decision-making, especially under imperfect data conditions.

Contribution

It presents a novel neural network-based framework, Cerealia, for anomaly detection in agricultural weather data using digital twins, with a prototype implementation on NVIDIA Jetson Orin.

Findings

Cerealia effectively detects weather data anomalies in real-time.

The prototype demonstrates practical applicability in commercial orchard settings.

Neural network models improve data consistency checks.

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.