Forecasting regional in-situ thermal conductivity of soil based on tree-based ensemble learning DOI

Xuquan Li,

Mingyu Gong,

Jierui Dong

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2024, Volume and Issue: 159, P. 107996 - 107996

Published: Aug. 31, 2024

Language: Английский

Depth-driven responses of soil organic carbon fractions to orchard cover crops across China: A meta-analysis DOI Creative Commons
Weiting Ding,

Liangjie Sun,

Yiwei Fang

et al.

Soil and Tillage Research, Journal Year: 2024, Volume and Issue: 246, P. 106348 - 106348

Published: Nov. 4, 2024

Language: Английский

Citations

4
Soil Water Potential in Geosciences: An Overview DOI Creative Commons
Shay Nachum

Geosciences, Journal Year: 2025, Volume and Issue: 15(4), P. 123 - 123

Published: April 1, 2025

In geosciences, soil–water interactions are defined by soil water potential, which provides a quantitative estimate of the thermodynamic state. Due to between and particles, has different physical properties than free water; hence, analyzing may require methods approaches. Typically, potential is as sum three independent functions: gravitational, osmotic, matric. However, there problem with this definition because osmotic matric potentials exhibit coupling effects. Moreover, due its high values, dominates total whereas gravitational appear negligible. gravity lead flow mechanisms altering soil’s mechanical behavior. As result, it not be valid calculate algebraic potentials. There also mathematical challenges in common use potential; saturation decreases, can reach thousands kPa, requires balancing equations multiplying variable value near zero. multiples numbers magnitudes problematic from perspective, especially when applied numerical analysis. This paper discusses strengths limitations definitions formulations variable.

Language: Английский

Citations

0
Risk Assessment of Campus Waterlogging and Evacuation Route Planning DOI
Feng Jing, Yu Tian,

Zheng Dao Xie

et al.

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Prediction of Thermal Diffusivity of Non-Plastic Soil for the Design of Ground Heat Exchanger Using Machine Learning Approach DOI

Namit Jaiswal,

Pawan Kishor Sah, Shiv Shankar Kumar

et al.

Indian geotechnical journal, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

Citations

0
Prediction of thermal conductivity of frozen soils from basic soil properties using ensemble learning methods DOI Creative Commons

Xinye Song,

Sai K. Vanapalli, Junping Ren

et al.

Geoderma, Journal Year: 2024, Volume and Issue: 450, P. 117053 - 117053

Published: Oct. 1, 2024

Language: Английский

Citations

3
Comparing machine learning approaches for estimating soil saturated hydraulic conductivity DOI Creative Commons
Ali Akbar Moosavi, Mohammad Amin Nematollahi,

Mohammad Omidifard

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(11), P. e0310622 - e0310622

Published: Nov. 14, 2024

Characterization of near (field) saturated hydraulic conductivity (K fs ) the soil environment is among crucial components hydrological modeling frameworks. Since associated laboratory/field experiments are time-consuming and labor-intensive, pedotransfer functions (PTFs) that rely on statistical predictors usually integrated with existing measurements to predict K in other areas field. In this study some most appropriate machine learning approaches, including variants artificial neural networks (ANNs) were used for predicting by easily measurable attributes. The analyses performed using 100 Bajgah Agricultural Experimental Station. First, physico-chemical inputs as bulk density (BD), initial water content (W i ), s mean weight diameter (MWD), geometric (GMD) aggregates, pH, electrical (EC), calcium carbonate equivalent (CCE) measured. Then, radial basis (RBFNNs), multilayer perceptron (MLPNNs), hybrid genetic algorithm (GA-NNs), particle swarm optimization (PSO-NNs) utilized develop PTFs compared their accuracy traditional regression model (MLR) indices. assessment indicated PSO-NNs lowest RMSE MAPE well highest correlation coefficient (R) value provided accurate robust prediction . models ranked (R = 0.958; 0.343; 9.47), GA-NNs 0.949; 0.404; 11.83), MLPNNs 0.933; 0.426; 12.13), RBFNNs 0.926; 0.452; 14.30), MLR 0.675; 0.685; 22.54) terms performances test data set. Results revealed all NN particularly efficient However, further evaluations may be recommended conditions input variables quantify potential uncertainties wider versatility before they geographical locations/soil conditions.

Language: Английский

Citations

2
Random forest approach to estimate soil thermal diffusivity: Evaluation and comparison with traditional pedotransfer functions DOI

Peipei Peng,

Lanmin Liu,

T. A. Arkhangelskaya

et al.

Soil and Tillage Research, Journal Year: 2024, Volume and Issue: 244, P. 106233 - 106233

Published: July 14, 2024

Language: Английский

Citations

1
Predicting soil thermal properties in freeze-thaw cycles using EFAttNet: A comparative analysis DOI Creative Commons
Pengcheng Wang, Müge Elif ORAKOĞLU FIRAT,

Yi Lin

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(7), P. e0305529 - e0305529

Published: July 12, 2024

This study investigates the thermal conductivity ( λ ) and volumetric heat capacity C of sandy soil samples under a variety conditions, including freeze-thaw cycles at temperatures both above below zero differing moisture levels. To estimate these properties, novel predictive model, EFAttNet , was developed, which utilizes custom-designed embedding attention-based fusion networks. When compared to traditional de Vries empirical models other baseline algorithms, demonstrated superior accuracy. Preliminary measurements showed that values increased linearly with content but decreased temperature, whereas exhibited rising trend freezing temperature. Following cycles, were positively influenced by The -based model proved highly accurate in predicting particularly effective capturing nonlinear relationships among influencing factors. Among factors, degree saturation had most significant impact, followed number subzero temperatures, porosity, content. Notably, dry density exerted minimal influence on likely due overriding effects factors or specific characteristics, such as particle size distribution mineralogical composition. These findings have implications for construction engineering projects, especially terms sustainability energy efficiency. accuracy estimating properties various conditions holds promise practical applications. Although focused types insights gained can guide further research development managing across diverse environments, thereby enhancing our understanding application this field.

Language: Английский

Citations

0
Forecasting regional in-situ thermal conductivity of soil based on tree-based ensemble learning DOI

Xuquan Li,

Mingyu Gong,

Jierui Dong

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2024, Volume and Issue: 159, P. 107996 - 107996

Published: Aug. 31, 2024

Language: Английский

Citations

0