GRID

Geotechnical Resilience through Intelligent Design

ABOUT US

Geotechnical engineering has long grappled with three inherent challenges: uncertainty stemming from incomplete knowledge, heterogeneity arising from diverse geomaterial compositions, geological processes and settings, and nonlinearity resulting from complex interactions. The compounding effects of climate change exacerbate these challenges, impeding traditional analytical and numerical approaches in accurately predicting geomaterial behaviour, crucial for designing resilient infrastructure, decision-making and conducting effective risk assessments. To surmount these obstacles, our research initiative advocates for a pioneering approach to fill the knowledge gap that integrates physics and machine learning in the form of Geotechnical Resilience through Intelligent Design.

NEWS

SIGN UP FOR THE FREE NEWSLETTER NOW AND NEVER MISS AN UPDATE!

T10_3_26_Q1_Newsletter_260119.pdf

QUARTERLY NEWSLETTER OUT NOW!

26.01.2026

We’re excited to share the newest edition of the GRID Newsletter with you where you can find the latest news on the project including Yanjie Song's physics‑informed neural networks for PDE solution, the GRID student contest, the new project partners and much more!

YANJIE SONG'S PRESENTATION @BOKU

21.11.2025

Today and during his one‑month secondment at BOKU, Leeds fellow Yanjie Song presented “Loss‑Attentional and Time‑Attentional AI Model for Solving PDE Problems,” a highlight of the Leeds‑led WP4 on Physics‑Informed Neural Networks.

GRID AT FOMLIG2025

20.10.2025

The GRID project actively participated in key sessions at the FOMLIG Workshop in Florence, including the application of LLMs to landslide studies, the "2nd GeoTechathon: Multiagent LLMs," and the EduHackathon on LLMs in geotechnical education. Prof. Andy Y.F. Leung chaired sessions on using ML/AI to analyze landslide hazards in Hong Kong, while other presentations explored topics like geospatial datasets, automated forensic landslide investigations, and ML-based soil analysis.

JOIN THE STUDENT CONTEST!

06.10.2025

We are excited to announce a student contest on Machine Learning algorithms for predicting soil shear parameters, co-organized by GRID, ISSMGE TC304, TC309, and JTC2. The prize ceremony will take place at ICITG26 in Graz, Austria, on October 13–16, 2026.

See the call details, guidelines and dataset.

Good luck!

GGU AND CIVILSERVE SECONDMENT @BOKU

19.09.2025

Simon Buß and Thomas Walkemeyer, CEOs of GGU and Civilserve, along with Daniel Schöler (GGU), enjoyed a productive week hosted by BOKU. This collaboration laid the foundation for WP3 GenAI applications and successfully integrated BOKU's GRAI Web-App into GGU Connect via an API for particle size distribution prediction from soil images. Dive deeper into the story by tuning into Thomas' podcast on Tiefgruending!

OUR PARTNERS

The GRID consortium is interdisciplinary and intersectoral, consisting of 9 beneficiaries and 4 associated partners. GRID involves major stakeholders in its team across the non-academic sectors of engineering design and machine learning consulting, which increases the exploitation potential of research outcomes. The interdisciplinary team of academic partners brings a wide spectrum of expertise, such as tunnelling, tailing dams, soil-structure interaction and geotechnical earthquake engineering, field testing, geohazard mitigation and constitutive modelling.