Dragon

DRAGON aims to overcome one of the main challenges in precision agriculture, the low rate of adoption of precision agriculture technologies and practices, especially concerning big data in agriculture. This is achieved by training and nurturing of young researchers to develop their career in data-driven precision agriculture and promotion of opportunities for further career development within the partner institutions BioSense (Serbia), Wageningen University (Netherlands) and Agri-EPI Centre (UK), and ultimately enable a data-driven precision agriculture eco-system.

Skill development in Dragon involves domain-specific capacity development for multisource data analytics spanning across scales, involving satellite, IoT, phenomics, genomics and meta-genomics data. It also focuses on soft-skill development, by developing capacity to communicate high-tech knowledge and related legislative matters in the precision agriculture sector to various stakeholders and non-scientific local community in order to achieve better dissemination/diffusion and subsequent adoption of innovative data-driven solutions.

Wageningen University and Research leads Dragon activities on enhancing scientific and technological expertise in data analytics using multiscale-multisource agricultural data.

Related publications:

• C. Pylianidis, M. G.J. Kallenberg, I. N. Athanasiadis, Domain adaptation with transfer learning for pasture digital twins, Environmental Data Science, 3:e8, 2024, doi:10.1017/eds.2024.6.
• M. Radulovic, S. Brdar, B. Pejak, P. Lugonja, I. Athanasiadis, N. Pajevic, D. Pavic, V. Crnojevic, Machine learning-based detection of irrigation in Vojvodina (Serbia) using Sentinel-2 data, GIScience and Remote Sensing, 60:2262010, 2023, doi:10.1080/15481603.2023.2262010.
• N. Grujic, S. Brdar, S. Osinga, G. J. Hofstede, I. N. Athanasiadis, M. Pljakic, N. Obrenovic, M. Govedarica, V. Crnojevic, Combining telecom data with heterogeneous data sources for traffic and emission assessments - an agent-based approach, ISPRS International Journal of Geo-Information, 11(7):366, 2022, doi:10.3390/ijgi11070366.
• C. Pylianidis, V. Snow, H. Overweg, S. Osinga, J. Kean, I. N. Athanasiadis, Simulation-assisted machine learning for operational digital twins, Environmental Modelling & Software, 148:105274, 2022, doi:10.1016/j.envsoft.2021.105274.
• P. Matavulj, S. Brdar, M. Rackovic, B. Sikoparija, I. N. Athanasiadis, Domain adaptation with unlabeled data for model transferability between airborne particle identifiers, 17th International Conference on Machine Learning and Data Mining (MLDM 2021), pg. 147-158, 2021, doi:10.5281/zenodo.5574164.
• C.Pylianidis, S. Osinga, I. N. Athanasiadis, Introducing digital twins to agriculture, Computers and Electronics in Agriculture, 184:105942, 2021, doi:10.1016/j.compag.2020.105942.
• C. Pylianidis, V.Snow, D. Holzworth, J. Bryant, I. N. Athanasiadis, Location-specific vs location-agnostic machine learning metamodels for predicting pasture nitrogen response rate, Lecture Notes in Computer Science (Pattern Recognition. ICPR International Workshops and Challenges), vol. 12666, pg. 96-109, 2021, Springer, doi:10.1007/978-3-030-68780-9_5.
• C.A. Midingoyi, C. Pradal, I.N. Athanasiadis, M. Donatelli, A. Enders, D. Fumagalli, F. Garcia, D. Holzworth, G. Hoogenboom, C. Porter, H. Raynal, P. Thorburn, P. Martre, Reuse of process-based models: automatic transformation into many programming languages and simulation platforms, in silico Plants, 2(1):diaa007, 2020, doi:10.1093/insilicoplants/diaa007.
• A. Samourkasidis, I. N. Athanasiadis, A semantic approach for timeseries data fusion, Computers and Electronics in Agriculture, 169:105171, 2020, doi:10.1016/j.compag.2019.105171.