Uncertainty quantification plays a crucial role in reporting machine learning models in soil spectroscopy. This study introduces Monte Carlo conformal prediction (MC-CP), a novel method for uncertainty quantification in deep-learning soil spectral models. MC-CP outperformed two established methods, providing the most reliable results. Its efficiency and robustness make it a practical choice for implementing soil spectral models in decision making.

This study explores the impact of converting forests to agricultural land on soil C stabilization. By analyzing soil samples from a forest and crop Andosols, we found that C-stabilizing mineral–organic associations were in the form of amorphous coprecipitates in both soils. However, their quantity was significantly lower in the crop topsoil, suggesting their vulnerability to agricultural conversion. This highlights the need to develop strategies to preserve these associations in crop soils.

Agriculture may play a significant role in climate change mitigation. For this reason, it is necessary to have good estimations of the greenhouse gas (GHG) emissions from agricultural activities. In this work, two different chamber systems to determine GHGs were compared. Our results highlighted that automated chamber systems, compared to manual chamber systems, are a powerful tool for quantifying GHG fluxes, allowing us to capture the large temporal variability that characterizes them.

This study explores how rubber plant root traits and soil organic matter improve soil stability via cohesive forces. Older plantations (>11 years) showed higher root density, soil organic matter, and optimal cellulose-to-lignin ratios, enhancing soil cohesion and aggregate stability. These findings highlight the role of mature rubber plants in reducing soil degradation and offer insights for sustainable land management and agricultural productivity in tropical regions like the island of Hainan.

This study evaluated the impact of contrasting cover crops on topsoil mineral nitrogen (SMN), N₂O emissions, and carbon (C) sequestration. Non-legume cover crops reduced SMN levels, showed potential for mitigating indirect N₂O emissions, and increased C sequestration but did not reduce cumulative N₂O emissions compared to fallow. The results highlight the need for tailored cover crop strategies to balance SMN capture, N₂O emissions, and C sequestration effectively.

This study examines soils in the highly industrialized Dunkerque agglomeration in France. Our work reveals the contamination of urban soils by metals from industrial dust, including Cr, Ni, Mo, Mn, Cd and Zn. While Cr, Ni and Mo are relatively stable in soils, Mn, Cd and Zn are more mobile and may pose environmental and health problems. Our findings highlight the need for careful consideration of future land use near industrial emitters, such as allotment gardens, due to these potential hazards.

Tropical forest soils are vital for methane uptake, but deforestation and agriculture can alter soil methane oxidation. An experiment in Thailand shows that fertilization significantly suppresses methane oxidation in rubber plantation soils, affecting depths up to 60 cm. Without fertilization, deeper soil layers (below 10 cm) actively oxidize methane. These findings suggest that fertilization negatively impacts the methane uptake capacity of deep-layer soils in rubber plantations.

We developed a method to estimate errors in soil moisture measurements using limited sensors and infrequent sampling. By analyzing data from 93 cropping cycles in agricultural fields in Belgium, we identified both systematic and random errors for our sensor setup. This approach reduces the need for extensive sensor networks and is applicable to agricultural and environmental monitoring and ensures more reliable soil moisture data, enhancing water management and improving model predictions.

This study develops a new method to improve the calibration and evaluation of models that predict soil erosion by water. By using advanced imaging techniques, we can capture detailed changes in the soil surface over time. This helps improve models that forecast erosion, especially as climate change creates new and unpredictable conditions. Our findings highlight the need for more precise tools to better model erosion of our land and environment in the future.