cs.LGMay 5, 2026

LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems

Authors: Kuangdai Leng, Simon Jeffery, Panos Panagos, Tarje Nissen-Meyer

Organizations: Earth Rover Program, 71-75 Shelton Street, London WC2H 9JQ, United Kingdom · Centre for Crop and Environmental Science, Harper Adams University, Newport, Shropshire TF10 8NB, United Kingdom · European Commission Joint Research Centre, Via E. Fermi, 2749, 21027 Ispra VA, Italy · Department of Mathematics and Statistics & Center for Environmental Intelligence, University of Exeter, Exeter EX4 4QF, United Kingdom

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Understanding soil is fundamental to agriculture, carbon cycling, and environmental sustainability, yet progress is limited by fragmented and heterogeneous datasets that constrain modeling to small-scale predictive settings rather than high-dimensional representation learning. We introduce LUCAS-MEGA, a large-scale multimodal dataset constructed through systematic data fusion of European soil-environment observations, with the LUCAS survey as its backbone. The fused dataset comprises over 70,000 samples and more than 1,000 features spanning physical, chemical, environmental, biological, and visual attributes, aggregated from 68 source datasets. To enable integration at scale, we develop SoilFuser, a multi-agent, human-in-the-loop data fusion pipeline that standardizes heterogeneous data formats and measurement protocols, resolves inconsistencies and invalid entries (e.g., unit inconsistencies, codebook mismatches, and erroneous values), incorporates natural language annotations, and harmonizes multimodal attributes and metadata into a unified, machine learning-ready feature space. The resulting dataset captures key characteristics of real-world soil observations, including multimodality, uneven feature coverage, and heterogeneous uncertainty. To demonstrate the usability of LUCAS-MEGA for data-driven modeling, we pretrain a multimodal tabular transformer (SoilFormer) using a self-supervised objective based on feature masking, achieving stable training, strong predictive performance, and representations that support uncertainty-aware prediction. We further show that the learned representations recover relationships consistent with established soil processes. LUCAS-MEGA is released with open access and is accompanied by composable, agent-friendly APIs that support structured querying and data-driven workflows.

Explore similar work

CardsList
Jun 15, 2026cs.LG

Multi-Modal Spatio-Temporal Graph Neural Network with Mixture of Experts for Soil Organic Carbon Prediction

Top-soil organic carbon (SOC) prediction is fundamental to agricultural sustainability, land use policy and fertilization planning. Existing approaches face two limitations: they pair hand-crafted covariates with classical ML or single-modal deep models that miss rich spectral and temporal information, and grid-based architectures ignore the irregular spatial structure of field measurements. We introduce SpTGNN, a multi-modal spatio-temporal graph neural network addressing both. SpTGNN represents soil measurements as nodes in a heterogeneous graph with three edge types (spatial proximity, spectral similarity, elevation), and applies relational graph attention to learn separate patterns per relation. A fine-tuned TerraMind encoder extracts node features from Sentinel-2, Sentinel-1 and DEM signals, combined with per-sample environmental covariates and learned positional and temporal embeddings. A sparse Mixture-of-Experts module fuses the four streams via top-kk routing. Uncertainty is captured by pairing heteroscedastic regression (aleatoric) with deep ensembles (epistemic), and a Moran's II penalty regularizes spatial autocorrelation. We evaluate on a global SOC corpus split into three regional instances (∼\sim49k samples globally, Africa ∼\sim26k, Europe ∼\sim14k). Our 5-member deep ensemble reports R2=0.762R^2=0.762, RMSE =3.51±0.48=3.51\pm0.48 g/kg and MAPE =22.9%=22.9\% on the Africa test split, improving over a tabular XGBoost baseline; the best single checkpoint reaches validation R2=0.864R^2=0.864. Ablations confirm the heterogeneous graph, MoE fusion and fine-tuned backbone each contribute substantively, and the ensemble UQ stack achieves post-calibration ECE of 0.0310.031 (hybrid) and 0.0260.026 (ββ-NLL). To our knowledge, this is the first framework to unify foundation-model feature extraction, heterogeneous graph attention and decomposed uncertainty quantification for SOC estimation.
Daniele Mos, Felipe Drummond, Anton Bossenbroek +1
Soil Moisture EstimationSoilTemporal Graph Neural NetworksCovariate ShiftNeural NetworkExperts
AskPDF
Aug 1, 2026cs.LG

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

Visible and near-infrared (vis-NIR) and mid-infrared (MIR) spectroscopy enable rapid, cost-effective prediction of soil properties. Yet, translating high-dimensional, highly collinear spectra into accurate soil property predictions remains challenging, particularly when employing machine learning. We systematically investigated regression models and dimensionality reduction approaches for spectroscopic modeling across 85 regression tasks from open benchmark datasets in pedometrics spanning field-scale digital soil mapping and a global soil spectral library. We compared an in-context learning tabular foundation model (TabPFN), a convolutional neural network (CNN), rule-based regression (Cubist), Random Forest, and partial least squares regression (PLSR) using full spectra as well as features derived from principal component analysis (PCA) and partial least squares (PLS) latent variables. TabPFN consistently delivered the best overall performance across scales, including large spectral library tasks with tens of thousands of soil samples. Notably, TabPFN applied directly to full spectra already surpassed all classical baselines, showing that explicit dimensionality reduction is not strictly required for strong performance. Further improvements were achieved through PLS, which proved to be an effective dimensionality reduction strategy for all models. Combining PLS latent variables with TabPFN yielded the best predictions overall. Our findings provide evidence-based guidance for spectroscopic calibration model selection across operational scales, demonstrating that the long-standing advantages of PLSR and modern tabular foundation models complement each other in chemometrics.
Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers +1
Soil Moisture EstimationSpectraTabular Foundation ModelsTabular Prior-Data Fitted NetworkLeast SquaresFoundation Model
AskPDF
Jun 20, 2026cs.LG

AgroSense 2.0: Cross-Modal Transformer Fusion with Geospatial Raster Integration and Interpretable Multi-Task Learning for Precision Crop Recommendation

Crop recommendation systems in precision agriculture have long suffered from a fundamental modality gap: visual soil characterization and chemical nutrient profiling are typically treated as independent inference problems, with fusion often reduced to late-stage feature concatenation. AgroSense2.0 addresses this limitation through three architectural advances. First, we introduce continental-scale geospatial integration via a seven-band soil raster (\texttt{india_soil_7bands.tif}) spanning India, encoding Nitrogen, pH, SOC, Clay, Sand, Silt, and Bulk Density as 32×3232\times32 spatial patches, a modality entirely absent from prior work. Second, we replace naive feature concatenation with a cross-modal Transformer fusion module, where tabular nutrient features attend over image representations via multi-head attention, enabling richer inter-modal dependency modeling than shallow fusion. Third, we adopt a multi-task objective jointly optimizing soil classification and crop recommendation through a shared backbone, improving generalization via complementary cross-task signal. To enhance interpretability, we apply TreeSHAP to the tabular branch, revealing crop-conditioned nutrient sensitivity: humidity and rainfall emerge as the most influential features globally, while crop-specific profiles diverge meaningfully rainfall dominates rice, nitrogen and potassium dominate maize, and humidity and nitrogen dominate coffee. These explanations provide transparency into model decisions and surface both agronomically consistent patterns and dataset-specific divergences worth further study. Together, these contributions establish AgroSense2.0 as a more principled, interpretable, and geospatially grounded framework for precision agriculture.
Vishal Pandey, Rishav Tewari, Ruzina Haque Laskar
Soil Moisture EstimationNormalized Difference Vegetation IndexImage CroppingGeospatialRgb-PointmapMulti--Task Learning+1
AskPDF