Data-Driven Soil Organic Carbon Sampling: Integrating Spectral Clustering with Conditioned Latin Hypercube Optimization

Soil organic carbon (SOC) monitoring often relies on selecting representative field sampling locations based on environmental covariates. We propose a novel hybrid methodology that integrates spectral clustering - an unsupervised machine learning technique with conditioned Latin hypercube sampling (cLHS) to enhance the representativeness of SOC sampling. In our approach, spectral clustering partitions the study area into $K$ homogeneous zones using multivariate covariate data, and cLHS is then applied within each zone to select sampling locations that collectively capture the full diversity of environmental conditions. This hybrid spectral-cLHS method ensures that even minor but important environmental clusters are sampled, addressing a key limitation of vanilla cLHS which can overlook such areas. We demonstrate on a real SOC mapping dataset that spectral-cLHS provides more uniform coverage of covariate feature space and spatial heterogeneity than standard cLHS. This improved sampling design has the potential to yield more accurate SOC predictions by providing better-balanced training data for machine learning models.

Soil nitrogen forecasting from environmental variables provided by multisensor remote sensing images

This study introduces a framework for forecasting soil nitrogen content, leveraging multi-modal data, including multi-sensor remote sensing images and advanced machine learning methods. We integrate the Land Use/Land Cover Area Frame Survey (LUCAS) database, which covers European and UK territory, with environmental variables from satellite sensors to create a dataset of novel features. We further test a broad range of machine learning algorithms, focusing on tree-based models such as CatBoost, LightGBM, and XGBoost. We test the proposed methods with a variety of land cover classes, including croplands and grasslands to ensure the robustness of this approach. Our results demonstrate that the CatBoost model surpasses other methods in accuracy. This research advances the field of agricultural management and environmental monitoring and demonstrates the significant potential of integrating multisensor remote sensing data with machine learning for environmental analysis.