PulseAugur
EN
LIVE 09:49:11

ConvLSTM framework accurately predicts retaining wall deformation

Researchers have developed and validated a ConvLSTM framework designed to predict retaining wall deformation during staged excavation. This framework, trained on simulated data augmented with Gaussian noise, integrates multiple temporal resolutions via a stacking ensemble. Field data from 34 inclinometers across 11 South Korean excavation sites demonstrated the framework's effectiveness, achieving an average mean absolute error of 1.4 mm and a coefficient of determination of 0.93 for predicting deformations up to 5.0 m of excavation. AI

IMPACT This framework offers a novel approach to geotechnical engineering, potentially improving safety and efficiency in construction projects by accurately predicting structural deformations.

RANK_REASON Academic paper detailing a new framework and its field validation. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Jihoon Kim, Heejung Youn ·

    Field Validation of a Multi-Resolution ConvLSTM Framework for Retaining Wall Deformation Prediction

    arXiv:2606.05556v1 Announce Type: new Abstract: This study presents a comprehensive field validation of a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) framework for predicting retaining wall deformation during staged excavation. The framework is trained on Gau…