2025-04-08, 18:35–18:39, W - Invite
Policy demands for robust soil health monitoring are steadily growing. Given that soil biota are critical to the ecosystem services soils provide, biological properties are well-suited as relevant indicators, complementing physicochemical characteristics. However, biological properties are highly dynamic across spatial and temporal scales, which presents a challenge when using them for monitoring purposes.
As part of AI4SoilHealth project, we conducted a comprehensive soil health assessment in the experimental grasslands of NEIKER, where a rotational grazing system has been in place since 2013, compared to a free grazing system. Our objectives were to test innovative methods for measuring soil health and to analyze the temporal dynamics of soil biological properties in relation to climatic and pasture conditions.
Plant and soil samples were collected every three weeks from April to November 2024 at two depths (0-20 cm and 20-50 cm). A broad array of descriptors related to pasture quality, production, and soil physicochemical and biological properties were assessed. Novel methods tested and compared to conventional approaches included: (i) DigitSoil – a tool that measures enzymatic activity, providing real-time data on organic matter decomposition and other key biological processes; (ii) microBIOMETER – a portable kit measuring microbial biomass and the fungi-to-bacteria ratio; (iii) Slakes – assessing aggregate stability through a mobile app; (iv) eDNA and eRNA metabarcoding of 16S rRNA and ITS, to differentiate total and active prokaryotic and fungal communities; (v) remote sensing from Planet to provide data on vegetation growth and greenness.
The novel diagnostic tools provided cost-effective and high quality soil health assessments. Nevertheless, preliminary results suggest that differences in soil biological properties were more pronounced across soil depths and over time than between grazing types. Therefore, their spatial and temporal variability must be considered when designing a soil health monitoring program.
Dr. Lur Epelde (https://orcid.org/0000-0002-4624-4946) is a researcher at NEIKER-Basque Institute of Agricultural Research & Development and the coordinator of its Soil Microbial Ecology Group (www.soilmicrobialecology.com). During her PhD (University of the Basque Country, 2009), she gained extensive experience in using microbial indicators of soil health to assess the efficiency of phytoremediation processes. Currently, she continues to study soil microbial properties, including high-throughput sequencing technologies, to monitor the impact of various environmental stressors (e.g., pollution, agricultural practices, and climate change). She is also interested in the spread of antibiotic resistance in agricultural soils fertilized with organic amendments of animal or human origin. Finally, she takes part in outreach activities promoting soil health using Soil Health Cards as a tool (www.lurzain.eus). Throughout her career, she has completed research stays at the Netherlands Institute of Ecology, the Institute for Environmental Genomics at the University of Oklahoma, the Genetics in Ecology department at the University of Vienna, and the Lawrence Berkeley National Laboratory.
Sonia is the Chief Technology Officer at Digit Soil, where she leads the development of affordable, advanced soil sensors to promote sustainable soil management on a global scale. With a PhD from ETH Zürich’s Plant Nutrition Group and a Master’s in Biotechnology from the Jagiellonian University in Krakow, Sonia combines a deep understanding of natural systems with cutting-edge engineering. Her work bridges soil science with practical technology, helping land managers access real-time data for smarter, more sustainable decision-making in soil health.
Lexy Ratering Arntz is product manager Planetary Variables at Planet. She strives to apply Planet's data building blocks and other remote sensing products to monitor - and thereby facilitate - the impact of regenerative farming on European landscapes. She has experience in climate (drought and flood) monitoring and agricultural risk management.
Dr. Asier Uribeetxebarria began working in the field of precision agriculture in 2014. He initially focused on precision viticulture, using non-invasive sensors to measure vineyard vigor variability and to identify areas with different requirements. In subsequent years, he worked with stone fruit trees, analyzing soil-tree interactions. For this purpose, he mapped soil variability through apparent electrical conductivity (ECa) and related certain field-measured soil variables to ECa intensity using multivariate statistical techniques. Tree vigor variability was measured through vegetative indices obtained by remote sensors (airplane, drone) and field sampling.
Since field measurements require substantial effort, Dr. Asier Uribeetxebarria also worked on optimizing sampling efforts by using auxiliary information-based sampling methods that capture crop variability and thus reduce sample numbers without sacrificing accuracy. The sampling techniques used were stratified sampling and rank sampling. Concurrently, while working with stone fruit trees, he continued his work in viticulture, but with a completely different focus, aiming this time to optimize pesticide dosage. However, one constant remained: the use of auxiliary information obtained through remote sensing and data analysis via multivariate and geostatistical techniques.
In recent years, his research has focused on optimizing fertilizer use in extensive crops. To achieve this, he has been working on fine-tuning yield estimation using machine learning techniques. Many of the data used to feed the algorithms come from remote sensors, such as satellites (primarily Sentinel-2) or LiDAR flights conducted by the Basque Government.
I am an environmental and soil scientist, having a broad education from Geoecology (Bachelor at the KIT, Karlsruhe), over Environmental Sciences (Master at the ETH Zürich), to Soil Science (PhD at the ETH Zürich the Federal Research Institute WSL, Birmensdorf). Now, I am working with our Startup Digit Soil on a portable device that can measure soil extracellular enzymatic activity. Within the AI4SoilHealth project we contribute to the section novel sensors and soil health parameters.