Site-Independent Mapping of Clay Content in Vineyard Soils via Mobile Proximal Gamma-Ray Spectrometry and Machine Learning Calibrations.

Vineyards hold considerable soil variability between regions and plots, and there is frequently large soil heterogeneity within plots. Clay content in vineyard soils is of interest with respect to soil management, environmental monitoring, and wine quality. However, spatially resolved clay mapping is laborious and expensive. Gamma-ray spectrometry (GS) is a suitable tool for predicting clay content in precision agriculture when locally calibrated, but it has scarcely been tested site-independently and in vineyards. This study evaluated GS to predict clay content with a site-independent calibration and four machine learning algorithms (Support Vector Machines, Random Forest, k-Nearest Neighbors, and Bayesian regulated neuronal networks) in eight vineyards from four German vine-growing regions. Clay content in the studied soils ranged from 62 to 647 g kg-1. The Random Forest calibration was most suitable. Test set evaluation revealed good model performance for the entire dataset with RPIQ = 4.64, RMSEP = 56.7 g kg-1, and R2 = 0.87; however, prediction quality varied between the sites. Overall, GS with the Random Forest model calibration was appropriate to predict the clay content and its spatial distribution, even for heterogeneous geopedological settings and in individual plots. Therefore, GS is considered a valuable tool for soil mapping in vineyards, where clay content and product quality are closely linked.

Deep incorporation of organic amendments into soils of a 'Calardis Musqué' vineyard: effects on greenhouse gas emissions, vine vigor, and grape quality.

Background: Traditional wine growing regions are increasingly endangered by climatic alterations. One promising approach to mitigate advancing climate change could be an increase of soil organic matter. Here, especially subsoils are of interest as they provide higher carbon storage potential than topsoils. In this context, vineyard subsoils could be particularly suitable since they are deeply cultivated once before planting and afterwards, left at rest for several decades due to the perennial nature of grapevines. Methods: For this purpose, a biochar compost substrate and greenwaste compost were incorporated in up to 0.6 m depth before planting a new experimental vineyard with the fungus-resistant grapevine cultivar 'Calardis Musqué'. The influence of this deep incorporation on greenhouse gas emissions and grapevine performance was evaluated and compared to a non-amended control using sensor-based analyses. Results: Increased CO2 emissions and lower N2O emissions were found for the incorporation treatments compared to the control, but these differences were not statistically significant due to high spatial variability. Only few plant traits like chlorophyll content or berry cuticle characteristics were significantly affected in some of the experimental years. Over the course of the study, annual climatic conditions had a much stronger influence on plant vigor and grape quality than the incorporated organic amendments. Discussion: In summary, organic soil amendments and their deep incorporation did not have any significant effect on greenhouse gas emissions and no measurable or only negligible effect on grapevine vigor, and grape quality parameters. Thus, according to our study the deposition of organic amendments in vineyard subsoils seems to be an option for viticulture to contribute to carbon storage in soils in order to mitigate climate change.