Announcements

Farewell colloquium Harry Vereecken

Harry Vereecken, head of the Agrosphere Institute IBG-3 at the Forschungszentrum Jülich GmbH and co-founder and inaugural ISMC co-chair entered his well-deserved retirement in August of this year. In honour of his work, a farewell colloquium was held on 5th of September 2025 in Jülich and many former PhDs, colleagues, and friends were invited to celebrate this day with Harry. Michael Young as a long friend, inaugural ISMC co-chair, and ISMC member of first day gave a brief overview of  Harry’s contribution to the foundation of ISMC and the current ISMC co-Chair Yijian Zeng and past co-Chair Martine van der Ploeg and current ISMC coordinator Lutz Weihermüller handed over a certificate of honour for his outstanding contribution to ISMC. We wish Harry all the best, health and plenty of time with his family. 

Impression of the farewell colloquium of Harry Vereecken. Photo copyright: Forschungszentrum Jülich, Sacha Kreklau.

Summer school “Modeling Water Fluxes in the Soil–Plant System

From September 8th to September 12th the 2nd summer school “Modeling Water Fluxes in the Soil–Plant System” took place in Louvain-la-Neuve (Belgium), supported by ISMC. Thirty-five international students attended the intensive one-week program to deepen their understanding of water flow in the soil-rhizosphere-plant system, including the influence of plant physiology, as well as rhizosphere and soil hydraulics. After a beer tasting icebreaking event on Sunday evening, eight lecturers from the soil physics and biological science communities (from UCLouvain and FZ Jülich, and KULeuven) came over to teach various topics, including soil physics fundamentals to 3-D soil-plant functional and structural models. The program combined theoretical lectures, hands-on modelling sessions, group projects, and practical exercises using advanced numerical tools such as GRANAR, MECHA, and CPlantBox. The participants also visited laboratories for automated phenotyping and of soil and plant hydraulics. In addition, our invited speaker shared inspiring perspectives and cutting-edge research: Tom de Swaef (ILVO, Belgium) answered the question ‘What do a grass leaf, a tomato fruit and a tree stem have in common?’ using the latest development in turgor-driven plant growth modelling, and Simone Fatichi (National University of Singapore) presented the ‘Frontiers in mechanistic ecohydrological modelling ‘.

Featured Paper

Do you want your paper featured?

Please share your recent paper if you want to be featured in the ISMC newsletter. With your contributions, we will select one paper to be featured in every newsletter. Submission can be done here. 

Physics-Informed Neural Networks for Estimating a Continuous Form of the Soil Water Retention Curve From Basic Soil Properties

This paper presents a novel physics-informed neural network (PINN) approach for developing pedotransfer functions (PTFs) to predict continuous soil water retention curves (SWRCs) based on soil textural fractions, organic carbon content, and bulk density. In contrast to conventional parametric PTFs developed for specific SWRC models, the PINN learns a non-specific form of the SWRC from both measurements and physical constraints imposed during the training process. This approach allows the estimated SWRC to maintain its physical integrity from saturation to oven-dry conditions, even in scenarios with sparse data. The new approach is particularly effective for tackling the challenges encountered in developing PTFs on large SWRC data sets, which often have an imbalance toward the wet-end (pF < 4.2) and include numerous samples with limited and unevenly distributed measurements, many of which do not meet the requirements to fit traditional SWRC models. We compared the performance of the PINN with that of a conventional physics-agnostic neural network using a data set of 4,200 soil samples. While both networks performed similarly at the wet-end where data are abundant, with RMSE values of around 0.041 m³ m⁻³, the PINN excelled at the dry-end (pF > 4.2) where data are sparse and unevenly distributed, achieving a normalized RMSE of 0.172 (RMSE = 0.0045 m³ m⁻³) compared to a normalized RMSE of 0.522 (RMSE = 0.0136 m³ m⁻³) for the conventional neural network. The SWRC derived from the PINN is differentiable with respect to matric potential, making it well-suited for integration into models of water flow in the unsaturated zone. More Infoprmation can be found here.

Combining automated and manual chambers to provide reliable estimates of N₂O emissions in annual and perennial cropping systems

Perennials can produce more biomass and partially replace annual crops. However, environmental benefits of perennials over annuals in terms of nitrous oxide (N₂O) emissions have rarely been compared in a long-term field experiment. By combining automatic and manual chamber methods, we aimed to develop reliable N₂O estimates from annual and perennial systems. We measured N₂O emissions from: i. perennial grass during renovation including spring barley as catch crop (SB/RG); ii. perennial grass-clover mixture (GC); iii. triticale monoculture (Trit). Results showed that cumulative N₂O emissions from SB/RG were higher than GC or Trit. The highest emission rate was measured for SB/RG (258.9 µg N₂O - N m^-2 h^-1) after fertilization in spring. Increased N₂O emissions were also seen for a short period after direct grass seeding in August. For Trit, N₂O emissions increased after fertilization in March and ploughing in late September. In GC (fertilized with P and K), there was no N₂O peak after grass cutting. Both from manual and automatic chamber systems, “hot moments” of N₂O emissions contributed ∼16–79 % of cumulative emissions. By predicting hot moments and scheduling frequent measurements, manual chambers captured most of the N₂O dynamics. The results indicated that the hot moments of N₂O emissions were better quantified by automatic chambers, while some of the hot moments, for instance, fertilization and ploughing in Trit were accurately captured with manual chambers. Soil nitrate and ammonium were positively associated with N₂O emissions, whereas biomass N uptake was negatively associated. We conclude that perennial (GC) is a promising system for high biomass production with low environmental impact. Strategies such as growing spring barley as a catch crop, grass seeding with shallow tillage, and fertilization of newly seeded grass matching crop N demand are needed to reduce the higher risk for N losses. More Infoprmation can be found here.

Hybrid modelling of soil–plant–atmosphere interactions

I am a group leader at the Max Planck Institute for Biogeochemistry and the ELLIS (European Laboratory for Learning and Intelligent Systems) Unit Jena, where I lead the Machine Learning for Hydrological and Earth Systems group. My research examines interactions among climate, water, and ecosystems under environmental change, with a particular focus on hybrid and explainable machine learning methods that integrate data and physical knowledge.

 - Please tell us briefly about yourself and your research interest.

 My research centres on how ecosystems regulate water availability through soil–plant–atmosphere interactions. I am especially interested in feedbacks, where soils influence vegetation and climate but also respond in return. Because these processes are difficult to observe directly, I develop hybrid modelling approaches that combine physical constraints with data-driven methods to infer ecohydrological functions such as root-zone storage and plant water-use strategies. More broadly, I am motivated by the question of whether simple but robust principles can help explain complex environmental behaviour.

 -  How did you first become interested in soil modelling and learn about ISMC?

 I started as a catchment hydrologist and quickly saw that soil processes were among the most uncertain parts of our models. Parameters such as root depth and pedotransfer functions were often fixed, even though they strongly shape water and carbon dynamics. This challenge drew me to soil modelling, and hybrid approaches felt like a natural way to address it. Through colleagues and community exchanges, I came across ISMC and saw it as a natural platform to connect with others working on similar issues.

 -       Can you share with us your current research focus?

 My current work focuses on diagnosing plant-accessible water storage and the regulation functions that determine how ecosystems partition and retain water. I develop hybrid models that combine physical water balance principles with neural networks, constrained by multiple observations. This makes it possible to recover hidden ecohydrological processes and improve how soil–vegetation interactions are represented in Earth system models, particularly under drought and climate extremes.

 - Please tell us briefly how your research could contribute to ISMC Science Panel’s activities? Or the other way around, how do you wish ISMC science panels help/support your research activities?

 My work can contribute methodological advances for representing soil and root processes, particularly in reducing uncertainty around water storage and soil–plant interactions. These approaches could support ISMC’s benchmarking and model evaluation activities. At the same time, I would benefit from ISMC’s collaborative network and shared resources, which are essential for testing approaches across scales and regions. I see this as a two-way exchange, where methodological development and community collaboration reinforce one another.

 - What resources or skills would you recommend that early career members of ISMC should acquire? And how can ISMC help and support early career members in this regard?

 As an early career researcher, I found the hardest step was identifying interesting and meaningful research questions. Reading widely and attending workshops have been essential for spotting gaps and building connections. I think early career members should invest in both process understanding and computational skills, and ISMC can support this by strengthening community links, providing mentorship, and creating opportunities for collaboration. These are important for connecting individual research with the broader soil modelling community.