Search papers, labs, and topics across Lattice.
This study leverages an ensemble of U-Net and the Geospatial Foundation Model Prithvi-2.0 to predict viticulture potential in Southern France using remote sensing data. By addressing the limitations of traditional agricultural assessment methods, the model achieved a notable accuracy of 卤1 at 68.32, securing the second position in a competitive leaderboard. The findings underscore the effectiveness of integrating advanced machine learning techniques in agricultural planning and land management.
An ensemble approach combining U-Net and a geospatial model can accurately predict viticulture potential, outperforming traditional assessment methods.
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 .
