8 Dec 2025

Improved Prediction of Soil Thermal Properties Using Gated Recurrent Unit Neural Networks

Abstract: Frost actions, such as frost depth penetration and thaw weakening, are damaging to airfields and roadways in cold regions. Machine learning techniques, such as recurrent neural networks, have been applied to this problem, but with a large focus on long short term memory (LSTM) neurons. Gated recurrent units (GRUs) are similar to LSTM neurons in terms of accuracy, but are more computationally efficient, and have yet to be applied to predicting soil thermal properties. Using a hyperparameter search, an optimal architecture for a recurrent neural network based on gated recurrent units was identified. A general model using temperature, thermal conductivity, and volumetric moisture content was found to predict temperatures effectively, having an error of less than 0.25°F across all depths. For predicting thermal conductivity, a model including temperature but not moisture content was found to be effective. For moisture content, the results were inconclusive as both models were affected by similar errors. Overall, the GRU-base recurrent neural networks were found to work well for predicting soil thermal properties in high-plasticity clays, and it is recommended to further expand the training datasets to include other frost-affected soil types.

17 Jul 2023

Testing Expedient Ground Anchor Solutions for Guyed Towers in Remote Cold Regions: Considerations for Cold Remote Regions with Limited Tools

Abstract: Ground anchors connected to guy wires for tower structures in cold climates suffer from frost heaving, which causes loss of wire tension and subsequent structural instability. It is necessary to understand what ground anchors are available to resist this tendency yet are still capable of expedient installation in remote areas. To that end, three metal, traditional ground-anchor types (arrowhead, bullet, and penetrating auger) and one novel polyvinyl chloride (PVC) T-post anchor were evaluated in frozen gravels and frozen silts at a research facility in Fairbanks, Alaska. Criteria included installation capability, failure loading, and removal ability. Additionally, expedient installation techniques for use in field conditions were also demonstrated. All three traditional ground anchors failed to penetrate frozen gravels. The penetrating auger also failed to penetrate frozen silts, but the arrowhead and bullet anchors did penetrate frozen silts with difficulty. The PVC anchor is capable of being installed only in a predrilled pilot hole. Under flexural load, the arrowhead anchor cable failed at 3686.72 lb, and the bullet anchor cable failed at 1753.44 lb. The PVC slid out of its hole at a direct-pull force of 1978.24 lb and failed under flexural stress at 202.32 lb.