ISMC News 1 October 2024
Announcements
Webinar 2024 ISMC awards now available at YouTube
The recordings of the lectures from the webinar for the 2024 ISMC van Genuchten Award by Paolo Nasta and Young Scientist Award by Nasrollah Sepehrnia are now available at YouTube.
Paolo presented his research in the Alento Hydrological Observatory and the lecture can be found here. The ISMC organization also has to apologize for some confusion generated by posting a wrong time for the webinar.
Nasrollah presented his research on Modelling Bacterial Transport and Fate: Investigating the Impact of Soil Water Repellency Dynamics and the lecture can be found here.
Webinar organized by the ISMC working group on biophysics and soil structure:
The Soil Structure Library for sharing CT data on soil structure
In this webinar to be held 10th December 3pm - 5pm (German Time) we discuss the possibilities and perspectives of the Soil Structure Library to jointly tackle new research questions or to tackle old challenges with new approaches. If you would like to contribute own CT data and you are interested to join this webinar please contact Hans-Jörg Vogel (hjvogel@ufz.de).
Advanced Technologies for Hydrological Monitoring
As part of the Erasmus+ program, the University of Naples (UNINA), Helmholtz Centre for Environmental Research (UFZ), Carinthia University of Applied Sciences (CUAS), University of Debrecen (UD), Politehnica University Timisoara (PUT), University of Twente (UT), and Technische Universität Dresden (TUD) are organizing a Blended Intensive Programme at the University of Naples from October 16, 2024, to July 23, 2024.
The initiative aims to promote innovative monitoring strategies, leveraging the international experience gained from the HARMONIOUS project. This proposal serves as a natural extension of the training activities undertaken within HARMONIOUS, intending to establish harmonized monitoring practices and disseminate the latest advancements in Unmanned Aerial Systems (UAS) methodologies.
The program will foster stronger institutional ties between the participating universities, with the goal of creating an innovative framework for using UAS to monitor vegetation dynamics, river systems, and soil processes with unprecedented spatio-temporal resolutions. The objective is to develop a course that provides participants with guidelines, technical support, and practical experience to enhance their knowledge both theoretically and practically. Additionally, students will gain hands-on field experience through practical exercises, enabling the immediate application of the proposed techniques and methods to real-world case studies. More information can be found here
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.
Evaluating the extrapolation potential of random forest digital soil mapping
Spatial soil information is essential for informed decision-making in a wide range of fields. Digital soil mapping (DSM) using machine learning algorithms has become a popular approach for generating soil maps. DSM capitalises on the relation between environmental variables (i.e., features) and a soil property of interest. It typically needs a training dataset that covers the feature space well. Mapping in areas where there are no training data is challenging, because extrapolation in geographic space often induces extrapolation in feature space and can seriously deteriorate prediction accuracy. The objective of this study was to analyse the extrapolation effects of random forest DSM models by predicting topsoil properties (OC, clay, and pH) in four African countries using soil data from the ISRIC Africa Soil Profiles database. The study was conducted in eight experiments whereby soil data from one or three countries were used to predict in the other countries. We calculated similarities between donor and recipient areas using four measures, including soil type similarity, homosoil, dissimilarity index by area of applicability (AOA), and quantile regression forest (QRF) prediction interval width. The aim was to determine the level of agreement between these four measures and identify the method that had the strongest agreement with common validation metrics. The results indicated a positive correlation between soil type similarity, homosoil and dissimilarity index by AOA. Surprisingly, we observed a negative correlation between dissimilarity index by AOA and QRF prediction interval width. Although the cross-validation results for the trained models were acceptable, the extrapolation results were unsatisfactory, highlighting the risk of extrapolation. Using soil data from three countries instead of one increased the similarities for all measures, but it had a limited effect on improving extrapolation. Also, none of the measures had a strong correlation with the validation metrics. This was particularly disappointing for AOA and QRF, which we had expected to be strong indicators of extrapolation prediction performance. Results showed that homosoil and soil type methods had the strongest correlation with validation metrics. The results for this case study revealed limitations of using AOA and QRF as measures of extrapolation effects, highlighting the importance of not relying on these methods blindly. Further research and more case studies are needed to address the effects of extrapolation of DSM models.
More information can be found here
Featured Soil Modeller (Jianzhi Dong)
Multiscale modeling of soil-plant interactions
Dr. Jianzhi Dong is a professor at Tianjin University, China. He earned his PhD from Delft University of Technology (TU-Delft), specializing in soil physics and data assimilation. He has also completed post-doctoral research at the USDA and MIT, where he studied large-scale soil-plant-atmosphere coupling processes using remote sensing and land surface modeling techniques.
- Please tell us briefly about yourself and your research interest
My expertise lies in the joint use of multi-scale observations and models to understand soil water and heat transfer processes. Our goal is to enhance soil process modeling in Earth System Models (ESMs), thereby increasing the credibility of future climate change projections. Over the past 10 years, my group and I have focused on developing sophisticated data merging frameworks to create accurate large-scale datasets of meteorological forcing, soil states, and land surface energy fluxes. Using these datasets, we have developed bias-free frameworks to quantify the coupling indices of water and energy fluxes within the soil-plant-atmosphere system. These coupling indices have been applied to track error sources in ESMs and develop pixel-wise soil parameter datasets for land surface modeling. Currently, we are also interested in integrating physical models, remote sensing, and machine learning to enhance our capabilities in large-scale soil and water modeling.
- How did you first become interested in soil modelling and learn about ISMC?
My interest in soil modeling began during my graduate studies at TU-Delft, where I was truly fascinated by a numerical experiment demonstrating how the Richards equation could capture observed soil moisture changes. Through studying soil physics, I discovered that soil water and heat fluxes are critical for accurately estimating large-scale water, energy, and carbon balances. This realization deepened my passion for soil modeling. Over the years, I heard about the International Soil Modeling Consortium (ISMC) from my colleagues and attended the fourth ISMC conference in 2024.
-Can you share with us your current research focus? And, please tell us briefly how your research could contribute to ISMC Science Panel’s activities
My research group focuses on enhancing soil physical processes in land surface models and Earth System Models (ESMs). We explore techniques to provide high-quality observation datasets and use them to diagnose large-scale models. Currently, we combine uncertainty analysis and machine learning algorithms to develop accurate datasets of precipitation, soil moisture, evapotranspiration, irrigation, and more. We use these datasets to investigate land surface modeling errors and provide more reliable soil physical schemes and parameters. Ultimately, we aim to create a physically based and data-driven framework to improve our large-scale soil modeling capabilities. I believe my current research interests could contribute significantly to the ISMC Soil Model Intercomparison and help develop new generations of soil models.
-Please tell us how can ISMC help you advance in your career?
The International Soil Modeling Consortium (ISMC) provides great opportunities to connect with the broader soil modeling community. During the conference, I learned a lot about state-of-the-art techniques and emerging challenges in the field.
- 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?
I believe soil modeling skills can greatly benefit early career members of ISMC. In addition, I recommend that early career members study soil models in the context of Earth System Modeling or land surface modeling. Workshops with hands-on experiences can be extremely helpful for early career members, providing practical knowledge and fostering a deeper understanding of the field.