PhD « Optimized IoRT network for enhanced data quality supporting precision farming

Exceptional  36-months Double Degree PhD Scholarship  Phd in Computer Science

Position-A « 
Optimized IoRT network for enhanced data quality supporting precision farming
 »

All details are avaiable
here :  

EU Recruiting institutions

• Aarhus University, Electrical and Computer Engineering (ECE), Aarhus, Denmark (18 Months), Supervisor: Clause Aage Grøn Sørensen
• University Clermont Auvergne, Clermont-Ferrand, France (18 Months), Supervisor: Gerard Chalhoub

Exceptional benefits at a glance

• International PhD training excellence (here)
• Renowned supervisors & top-tier labs
• Interdisciplinary & multi sectoral research
• Competitive MSCA salary & allowances
• Global academic & industrial network
• Non-academic secondments

Salary (Gross amount)

Living Allowance Mobility Allowance*  Family Allowance**

EUR EUR EUR 660

How to apply

APPLY ONLY USING THE web portal project (not using Linkedin)

Timeline

· Application Deadline : April 15th 2026

· Selection Process : Mai 2026

· PhD Start Date : September-October 2026

It is possible to apply max to 3 PhD positions

This PhD  is fundend by the MSCA JD project

GreenFieldData : IoRT Data Management and Analysis for Sustainable Agriculture Project

3-year contract starting September/October 2026

GreenFieldData
Project at glance GreenFieldData: "
IoRT Data management and analysis for Sustainable Agriculture" is a project funded under the action HORIZON Marie Sklodowska-Curie Action (MSCA) Joint Doctoral N
etwork.

Description of the PhD "
Optimized IoRT network for enhanced data quality supporting precision farming"

Context:
Wireless communication systems are being used in many application fields. They offer a flexible solution for maintaining connectivity between connected devices. The focus of this PhD thesis is the use of wireless communications in the application of agricultural mobile robots in Precision Farming [1,2]. In such applications, robots need to be supervised during their missions on the field, and in some situations, they also need to be remotely controlled by a human operator. These robots continuously collect data and send it to a human operator who ensures that robots execute the right tasks with the collected data [3]. The decisions made by the operator depend on the quality of data collected by the robots and from all the other available sensors deployed on the field. In this regard, the communication system needs to provide the best quality of communication to make sure that all the required data are received with the needed quality. For example, the requested definition of the collected images should answer the needs of the operator to decide the exact action to take [4]. Even though there has been a lot of progress in telecommunication systems in the past 10 years, wireless communications are still prone to performance degradation depending on the current network conditions. For example, the presence of obstacles or high levels of interference might render the communication link unstable, which has a severe impact on the quality of experience of the operator [5]. Indeed, requiring high-level quality of data during the interval of performance degradation will make the system unresponsive and will further degrade the performance [6].

Objectives:
In this PhD, we will tackle the issue of real-time monitoring of the state of the network to explain the quality of data the operator receives. Data quality could be explained by differentiating between low and high-quality images on resolution, compression artifacts, or other factors. Once the monitoring system is in place, we will work on prediction algorithms, based on machine learning, that allow the system to anticipate performance degradation and inform the operator in real-time to make adjustments to acquire the right quality of data that the communication system can provide. We will also explore the use of hybrid communication systems, a solution known for enhancing the robustness of communications, to ensure minimum quality of communication at all times. For hybrid systems (e.g., cellular and Wi-Fi), the switching mechanism from one system to another will be implemented based on real-time monitoring. All the mentioned objectives can be listed as follow:

1. Provide precision agriculture methods for irrigation and robotized wedding (spraying and mechanical) operations of cereals production (Task 4.2)

2. Allow real-time monitoring of the state of the network (Task 1.1)

3. Predict the quality of the network with ML (Task 1.2)

4. Provide feedback to the operator about the quality of data in order to make adjustments to current communication system capacity (Task 3.1). These objectives will be achieved using the following work planning to grant their feasibility.

Work plan
:

1. State of art study [Duration: months 0-6]

2. Develop and blue-print of a system to monitor network quality in real-time and anticipate performance degradation. [Duration: months 6-12]

3. Calibration and Validation of the developed model by simulation and real-time monitoring of the state of the network using a dedicated robot. [Duration: months 12-15]

4. Develop a prediction model to anticipate the quality of the network based on Machine learning techniques. [Duration: months 14-20]

5. Calibration and Validation of the prediction model by simulation. [Duration: months 20-23]

6. Develop novel methods for identifying data that can be summarized, without quality loss, and transmit only summaries to the next level of the architecture. [Duration: months 22-28]

7. Develop a user-friendly and interactive user interface dedicated to farmers to interact with the monitoring system. [Duration: months 27-33]

Expected Results

1. A system to monitor network quality in real-time and anticipate performance degradation,

2. Use hybrid communication systems (e.g. cellular and Wi-Fi) to ensure a minimum level of service.

3. Develop novel methods for identifying data that can be summarized, without quality loss, and transmit only summaries to the next level of the architecture.

4. Develop a user-friendly and interactive user interface dedicated to farmers to interact with the monitoring system.

5. Improve usage of resources for cereals fields