Predicting Viticulture Potential through an Ensemble of U-Net and a Geospatial Foundation Model

Jorge Ignacio Perez; Hwaai Kang Kee; Lucas Rassbach

Predicting Viticulture Potential through an Ensemble of U-Net and a Geospatial Foundation Model

Computer Vision and Pattern Recognition 2026-07-09 v1 Machine Learning

Authors: Jorge Ignacio Perez , Hwaai Kang Kee , Lucas Rassbach

Abstract

Determining agricultural potential is fundamental to sustainable land management and agricultural planning. Remote sensing data is increasingly valuable as an avenue for agricultural potential due to the cost of traditional methods (surveys, in-situ measurements, soil testing, etc). ImageCLEF AI4Agri 2026: Subtask 1 is concerned with the prediction of viticulture potential in Southern France. The DS@GT ARC's submission for Subtask 1 introduces an ensemble of U-Net and a Geospatial Foundation Model (Prithvi-2.0). Our best model achieved a $\pm$ 1 accuracy of 68.32 on the leaderboard, ranking 2nd among 7 teams. The implementation for this work is publicly available at https://github.com/dsgt-arc/imageclef-ai4agri-2026 .

Keywords

viticulture potential agricultural potential prediction remote sensing U-Net geospatial foundation model ensemble learning

Cite

@article{arxiv.2607.08449,
  title  = {Predicting Viticulture Potential through an Ensemble of U-Net and a Geospatial Foundation Model},
  author = {Jorge Ignacio Perez and Hwaai Kang Kee and Lucas Rassbach},
  journal= {arXiv preprint arXiv:2607.08449},
  year   = {2026}
}

Comments

To be published in CLEF 2026 Working Notes