collaborators

5 papers

cs.LG2026

From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy

Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers +1

Visible and near-infrared (vis-NIR) and mid-infrared (MIR) spectroscopy enable rapid, cost-effective prediction of soil properties. Yet, translating high-dimensional, highly collin…

cs.LG2026

Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy

Jonas Schmidinger, Robin Gebbers, Marc-Olivier Gasser +3

Soil properties relevant to agricultural and environmental applications are conventionally measured using elaborate laboratory methods involving physical and chemical processing. W…

cs.LG2026

Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping?

Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers +1

In the field of pedometrics, tabular machine learning is the predominant method for soil property prediction from remote and proximal soil sensing data, forming a central component…

cs.LG2026

Kriging prior Regression: A Case for Kriging-Based Spatial Features with TabPFN in Soil Mapping

Jonas Schmidinger, Viacheslav Barkov, Sebastian Vogel +2

Machine learning and geostatistics are two fundamentally different frameworks for predicting and spatially mapping soil properties. Geostatistics leverages the spatial structure of…

cs.LG2025

LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping

J. Schmidinger, S. Vogel, V. Barkov +33

Digital soil mapping (DSM) relies on a broad pool of statistical methods, yet determining the optimal method for a given context remains challenging and contentious. Benchmarking s…