ABSTRACT:
Mango is one of the most important tropical fruits with high economic value, but it suffers from significant post-harvest losses due to improper handling, storage, and transportation conditions. Conventional post-harvest practices depend on manual monitoring and fixed storage parameters, which often fail to respond to dynamic environmental changes. Digital Twin technology provides a smart solution by creating a virtual representation of the physical mango fruit and its post-harvest environment.
This article presents a comprehensive study on the application of digital twin technology for mango post-harvest management. The proposed approach integrates IoT sensors, cloud computing, and data analytics to monitor fruit quality in real time, predict spoilage risks, and optimize storage and transportation decisions. The study highlights the process, benefits, challenges, and future scope of digital twin implementation in the mango supply chain.
INTRODUCTION:
Mango is widely cultivated in tropical and subtropical regions and plays a major role in the agricultural economy. Despite high production levels, a large percentage of harvested mangoes are lost before reaching consumers due to poor post-harvest management. Factors such as temperature variation, humidity imbalance, ethylene accumulation, mechanical damage, and delayed transportation contribute to rapid ripening and spoilage. Traditional post-harvest systems rely heavily on periodic manual inspection and predefined storage conditions. These methods lack real-time visibility and predictive capability. Digital Twin technology, which creates a real-time virtual replica of a physical system, has emerged as a promising solution for intelligent post-harvest management. By continuously synchronizing physical mango conditions with a digital model, the system enables proactive decision-making and quality preservation.
Concept of Digital Twin in Post-Harvest Agriculture:
A digital twin is a virtual model that accurately reflects the behavior and condition of a physical object using real-time data. In the context of mango post-harvest management, the physical entity consists of harvested mango batches, storage facilities, and transport units. The digital twin continuously updates based on sensor data and simulates future scenarios such as ripening rate and spoilage risk.Unlike static monitoring systems, a digital twin supports continuous learning and prediction. It enables stakeholders to understand how environmental changes affect fruit quality and allows timely corrective actions to minimize losses.
System Architecture:
The digital twin–based mango post-harvest management system consists of the following components:
Physical Layer:
This layer includes harvested mango fruits stored in cold storage facilities or transported through supply chains. Each batch is identified using labels or codes for traceability.
Sensor Layer:
IoT sensors are deployed to measure key parameters such as:
- Temperature
- Relative humidity
- Ethylene gas concentration
- Visual appearance of fruit surface
Data Acquisition and Communication Layer:
Sensor data is collected through IoT gateways and transmitted to cloud servers using wireless communication technologies.
Digital Twin Layer:
A virtual mango model is created in the cloud platform. This model mirrors the real-time condition of mango batches and updates dynamically as new data arrives.
Analytics and Decision Support Layer:
Data analytics and machine learning algorithms analyze trends, detect anomalies, and predict shelf life. Recommendations and alerts are generated for users.
User Interface Layer:
A web or mobile dashboard displays real-time status, alerts, and suggested actions to farmers, warehouse managers, and logistics operators.
Digital Twin Process for Mango Post-Harvest Management
The process begins immediately after harvesting. Initial fruit characteristics such as maturity level, weight, and color are recorded. During storage and transportation, environmental parameters are continuously monitored. The digital twin model processes this data to simulate fruit behavior under current conditions. If abnormal conditions are detected, such as temperature rise or excessive ethylene concentration, the system generates alerts and suggests corrective measures like ventilation adjustment or expedited delivery to markets.
Case Study Implementation:
A digital twin system was implemented for mango batches stored in a controlled warehouse and transported to urban markets. Sensors recorded temperature, humidity, and ethylene levels every 10 minutes. The digital twin analyzed ripening trends and predicted shelf life for each batch.
Results Observed:
- Post-harvest losses reduced significantly
- Shelf life improved through controlled interventions
- Manual inspection frequency reduced
- Better coordination between storage and transportation units
Block diagram:
Benefits of Digital Twin–Based Post-Harvest Management:
- Reduction in fruit spoilage and wastage
- Improved quality consistency
- Extended shelf life of mangoes
- Real-time visibility across supply chain
- Increased profitability for farmers and distributors
Challenges and Limitations:
- Despite its advantages, digital twin implementation faces certain challenges
- High initial investment cost
- Requirement for reliable internet connectivity
- Need for technical training for farmers and workers
- Sensor maintenance and calibration issues
Comments
Post a Comment