Smart farm digital twin model based on edge-cloud architecture for tomato monitoring and detection
With the rapid development of science and technology, agricultural production has begun to develop in the direction of digitalization and intelligence. The rise of digital twins has brought new ideas for building smart farms. Currently, there are few studies on smart agriculture solutions that combi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S277237552500485X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With the rapid development of science and technology, agricultural production has begun to develop in the direction of digitalization and intelligence. The rise of digital twins has brought new ideas for building smart farms. Currently, there are few studies on smart agriculture solutions that combine digital twins and edge-cloud architecture. The edge architecture has the limitations of low computing power, whereas the cloud one has the problems of excessive latency. To enhance the efficiency of smart agriculture, this paper proposed a digital twin model based on edge-cloud architecture that takes into account the advantages of both. The model architecture consists of three layers: the edge layer, the cloud layer and the application layer. The edge layer is responsible for collecting data at edge ports. The cloud layer deploys an artificial intelligence service to perform object detection on the collected data. The application layer creates a virtual model that simulates the physical farm scene through 3D modeling technology, providing users with a visual window and interactive terminal. We applied the model to detect the ripeness and size of tomatoes. The detection accuracy of this model reached 0.88, and the transmission time of the detection results was 15.92 milliseconds (50 samples). The results show that the smart farm digital twin model with edge-cloud architecture not only ensures the detection accuracy but also greatly reduces the delay in the data transmission. Therefore, applying the edge-cloud architecture to digital twins of building smart farms offers significant advantages. |
|---|---|
| ISSN: | 2772-3755 |