Pontificia Universidad Católica Madre y Maestra

Evaluating domain generalization in agricultural deep learning through multi-seed LOSO validation and explainable AI

Abstract Conventional validation schemes may overestimate model robustness in agricultural deep learning when spatial domain shifts are not explicitly considered. This study evaluated convolutional neural networks for pasture biomass estimation using the CSIRO Image2Biomass datas...

Toward Climate-Responsive Ocean–Terrestrial Biorefineries: Integrating Algae and Agricultural Residues for Circular Bioeconomies

Abstract This paper evaluates climate-responsive biorefineries that integrate pelagic Sargassum with agricultural residues to advance circular bioeconomies. Building on scientific priorities emphasized at the 2025 One Ocean Science Congress and emerging policy directions from the...