Study and verification on an improved comprehensive prediction model of landslide displacement

Bulletin of Engineering Geology and the Environment, Год журнала: 2024, Номер 83(3)

Опубликована: Фев. 29, 2024

Язык: Английский

---

Predicting corrosion of recycled aggregate concrete under sulfuric acid rain using machine learning and uncertainty analysis

Construction and Building Materials, Год журнала: 2024, Номер 438, С. 137146 - 137146

Опубликована: Июнь 21, 2024

Язык: Английский

---

High temporal resolution quasi-global landscape soil freeze–thaw map from spaceborne GNSS-R technology and SMAP radiometer measurements

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 128, С. 103777 - 103777

Опубликована: Март 21, 2024

Landscape freeze–thaw (F/T) state parameters are an integral part of research on terrestrial hydrological processes, vegetation growth dynamics, and terrestrial–atmospheric trace gas exchange. Therefore, the development large-scale, continuous, rapid F/T observation records is essential. This study proposes a scheme to effectively retrieve quasi-global daily soil states from spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) observations. method takes into account GNSS-R surface reflectivity its influence factor. Specifically, employed derived Cyclone (CYGNSS) data 2018 2020, along with opacity Soil Moisture Active Passive (SMAP) as input layers in random forests for retrieval. approach provides results scale, does not rely continuous observations, employs least ancillary data. To validate retrieval results, SMAP over same period temperature more than 100 ground stations were also used reference. Results showed that accuracy CYGNSS was 95.5% 82.0% respect independent situ stations, respectively. Given high temporal coverage improvement 23.3% compared actual observations scale. Furthermore, gap-filling complemented SMAP, can improve sample interval (accuracy 26.0%). More importantly, combination based monthly performance 85.1%, i.e., 20.5% better existing product. Overall, obtained measurements complement databases well-defined accuracy.

Язык: Английский

---

Artificial-Intelligence-Based Prediction of Crack and Shrinkage Intensity Factor in Clay Soils During Desiccation

Designs, Год журнала: 2025, Номер 9(3), С. 54 - 54

Опубликована: Апрель 29, 2025

Desiccation-induced cracking in clay soils significantly affects the structural performance and durability of geotechnical systems. This study presents a data-driven approach to predict Crack Shrinkage Intensity Factor (CSIF), comprehensive index quantifying both crack formation shrinkage behavior drying soils. A database 100 controlled desiccation tests was developed using five mixtures with varying plasticity indices, which were subjected range rates, soil thicknesses initial conditions. Four predictive models—Multiple Linear Regression (MLR), Classification Random Forest (CRRF), Artificial Neural Network (ANN) Genetic Programming (GP)—were evaluated. The ANN model Bayesian Regularization demonstrated superior (R = 0.99, MAE 5.44), followed by CRRF symbolic GP equations. Sensitivity analysis identified rate thickness as most influential parameters, while moisture content ambient conditions found be redundant when included. not only advances modeling but also introduces interpretable equations for practical engineering uses. models offer valuable tools risk assessment liners, covers expansive foundations.

Язык: Английский

---

Stability of soil slope in Almaty covered with steel slag under the effect of rainfall

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Апрель 2, 2024

Abstract The issue of rainfall-induced slope failure has attracted more attention from geotechnical engineers as a consequence global warming. Current cumulative waste disposal generated scientific interest in the utilization materials design for climate change adaptation measures. Taking into consideration effect height and angle, steel slag—a product derived production steel—was investigated cover against rainfall. To assess stability infiltration water soil, numerical analyses were conducted using both SEEP/W SLOPE/W software conjunction with rainfall conditions. Based on findings, it can be concluded that increasing slope's elevation inclination will have an adverse its safety factor. Steel slag nevertheless utilized minimizing rainwater slope, indicated by pore-water pressure variations graphs factor versus time. For 20-m height, slopes demonstrated lower difference comparison to initial without remediation. Regardless angle reduces marginally during

Язык: Английский

---

Study on the characteristics and influence factors of pull-out resistance of vetiver root in expansive soil

Environmental Earth Sciences, Год журнала: 2024, Номер 83(7)

Опубликована: Март 30, 2024

Язык: Английский

---

Assessment of ultimate bearing capacity of rock-socketed piles using hybrid approaches

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2024, Номер 7(4), С. 3673 - 3694

Опубликована: Апрель 20, 2024

Язык: Английский

---

Assessment of small strain modulus in soil using advanced computational models

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Дек. 18, 2023

Small-strain shear modulus ([Formula: see text]) of soils is a crucial dynamic parameter that significantly impacts seismic site response analysis and foundation design. [Formula: text] susceptible to multiple factors, including soil uniformity coefficient text]), void ratio (e), mean particle size confining stress text]). This study aims establish database suggests three advanced computational models for prediction. Nine performance indicators, four new indices, are employed calculate analyze the model's performance. The XGBoost model outperforms other two models, with all achieving values exceeding 0.9, RMSE below 30, MAE 25, VAF surpassing 80%, ARE 50%. Compared empirical formula-based traditional prediction proposed in this exhibits better IOS, IOA, a20-index, PI metrics values. has higher accuracy generalization ability.

Язык: Английский

---

Influence of Solid Waste Oyster Shell Powder on the Physical and Swell–Shrink Properties of Expansive Soils

Advances in Civil Engineering, Год журнала: 2024, Номер 2024(1)

Опубликована: Янв. 1, 2024

To explore the effects of solid waste oyster shell powder (SWOSP) on physical and swell–shrink properties expansive soils, soil in Ningming, Guangxi province (the classification code is CH), was taken as research object. A series tests were carried out samples with OSP contents 0%, 3%, 6%, 9%, 12%. The results show that incorporation can effectively enhance integrity soil, change distribution particle size reduce expansion contraction soil. free swelling ratio, unloaded loaded force, linear shrinkage rates tested decreased increasing content stabilized when 9%. provide theoretical basic data for improvement also offer a new approach green engineering.

Язык: Английский

---

Multi-View Graph Learning for Path-Level Aging-Aware Timing Prediction

Electronics, Год журнала: 2024, Номер 13(17), С. 3479 - 3479

Опубликована: Сен. 2, 2024

As CMOS technology continues to scale down, the aging effect—known as negative bias temperature instability (NBTI)—has become increasingly prominent, gradually emerging a key factor affecting device reliability. Accurate aging-aware static timing analysis (STA) at early design phase is critical for establishing appropriate margins ensure circuit reliability throughout chip lifecycle. However, traditional methods, typically based on Simulation Program with Integrated Circuit Emphasis (SPICE) simulations or libraries, struggle balance prediction accuracy computational cost. In this paper, we propose multi-view graph learning framework path-level prediction, which combines strengths of spatial–temporal Transformer network (STTN) and attention (GAT) models extract features paths from both timing-sensitive workload-sensitive perspectives. Experimental results demonstrate that our proposed achieves an average MAPE score 3.96% reduces by 5.8 times compared FFNN 2.2 PNA, while maintaining acceptable increases in processing time.

Язык: Английский

---