A Digital Twin for Grassland Management

Purcell, Warren; Klipic, Anja; Neubauer, Thomas

doi:10.1109/icecet55527.2022.9873446

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data assimilation refers to the practice of calibrating a numerical model based on observations. This technique has been applied for grassland management digital twins (Purcell et al, 2022), and digital twins for adaption to climate change (Bauer et al, 2021). Transfer learning refers to the utilization of knowledge obtained by training for a task, to solve a different but similar task.…”

Section: Introductionmentioning

confidence: 99%

Domain adaptation with transfer learning for pasture digital twins

Pylianidis,

Kallenberg,

Athanasiadis

2024

Environ. Data Science

View full text Add to dashboard Cite

Domain adaptation is important in agriculture because agricultural systems have their own individual characteristics. Applying the same treatment practices (e.g., fertilization) to different systems may not have the desired effect due to those characteristics. Domain adaptation is also an inherent aspect of digital twins. In this work, we examine the potential of transfer learning for domain adaptation in pasture digital twins. We use a synthetic dataset of grassland pasture simulations to pretrain and fine-tune machine learning metamodels for nitrogen response rate prediction. We investigate the outcome in locations with diverse climates, and examine the effect on the results of including more weather and agricultural management practices data during the pretraining phase. We find that transfer learning seems promising to make the models adapt to new conditions. Moreover, our experiments show that adding more weather data on the pretraining phase has a small effect on fine-tuned model performance compared to adding more management practices. This is an interesting finding that is worth further investigation in future studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Domain adaptation with transfer learning for pasture digital twins

Pylianidis,

Kallenberg,

Athanasiadis

2024

Environ. Data Science

View full text Add to dashboard Cite

show abstract

“…In agriculture, DTs facilitate tracking, simulating, and improving the performance of physical systems by creating virtual representations and connecting them to real-world data. This enhances decision-making and improves agricultural processes [24]. DTs are employed in creating cyberphysical systems for farmers, optimizing resource use, improving yields, and reducing environmental impact [25].…”

Section: Introductionmentioning

confidence: 99%

Advancing Mixed Reality Digital Twins Through 3D Reconstruction of Fresh Produce

Nair,

Fernandez

2024

IEEE Access

View full text Add to dashboard Cite

Access to safe and secure food is an essential human requirement for a sustainable world. Ensuring the safety of fresh food products necessitates accurate analytical techniques. This study presents an innovative food safety approach using rapid 3D reconstruction and digital twin analysis in mixed reality. While 3D models offer comprehensive insights into fresh food, conventional reconstruction methods are often complex due to multiple cameras or sensors. To address this, the research employs monocular depth estimation for detailed 3D reconstruction from a single camera view. This architecture uses web service protocols and the Global-Local Path Networks (GLPN) model for monocular depth perception, effectively translating 2D images into intricate 3D structures. These digital twins establish a strong foundation for enhanced analysis of food products, facilitating a better understanding of safety risks. The study also explores the applicability of transferring 3D models to Microsoft HoloLens 2, enabling immersive visualization and novel avenues for analysis. These techniques hold significance for the food industry, spanning scene comprehension, precision agriculture, robotics, augmented reality, and medical imaging. The methodology includes assessing surface degradation, with a focus on bruises on fresh produce. Employing a mesh overlay technique on the resulting 3D models distinctly showcases the impact of bruising. Sequential data recordings effectively track bruise expansion, shedding light on structural compromises. This technique dynamically portrays bruise progression, thus enriching comprehension of its implications on produce quality.

show abstract

“…Data assimilation refers to the practice of calibrating a numerical model based on observations. This technique has been applied for grassland management digital twins [169], and digital twins for adaption to climate change [109]. Transfer learning refers to the utilization of knowledge obtained by training for a task, to solve a different but similar task.…”

Section: Introductionmentioning

confidence: 99%

Operationalizing digital twins in agriculture with machine learning

Pylianidis

View full text Add to dashboard Cite

Back in 2019, when this work started, it was unclear if digital twins were already adopted in agriculture. Deployed digital twin applications were rare, the relevant literature was limited, and the articles describing digital twin applications were lacking implementation details. Reasons behind this delay included a lack of communication for the added value of digital twins, the risk involved in trusting technology applications for complex multidisciplinary problems in high uncertainty environments (especially when these applications automate actions based on analytics), as well as the cost and difficulty of developing them [13].Nowadays, the concept of digital twins in agriculture is considered attractive. Researchers are investigating ways to materialize the benefits of digital twins promised by other disciplines and there are ongoing discussions on ways to utilize them. Ideas emerge for digital twins in aquaponics to advance urban farming [14], attempts are made to improve the virtual 3D representation of leaves for digital twins in plant breeding [15], conceptual frameworks are created to design digital twins [16], prototypes of digital twins of arable and dairy farms [17] that monitor the nitrogen cycle are researched, and digital twins of tomato crops in greenhouses [17] that predict the effect of cultivation treatments in harvest and financial yield are developed.

show abstract

A Digital Twin for Grassland Management

Cited by 6 publications

References 18 publications

Domain adaptation with transfer learning for pasture digital twins

Domain adaptation with transfer learning for pasture digital twins

Advancing Mixed Reality Digital Twins Through 3D Reconstruction of Fresh Produce

Operationalizing digital twins in agriculture with machine learning

Contact Info

Product

Resources

About