In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classifi...In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classification models across three datasets:a simple slope binary classification dataset,an imbalanced rockburst dataset,and a highly discrete liquefaction dataset.First,a thorough review of machine-learning algorithms for geohazard assessment was conducted.Subsequently,three datasets were collected from real engineering practices,and their data structures were visualized.Bayesian optimization was then used to adjust the parameters of all models across all datasets.To ensure model interpretability,a global sensitivity analysis based on Sobol indices was performed,establishing an interpretable visual analysis of the model's decision-making process.For a fair evaluation,various metrics and repeated stratified 10-fold cross-validation were employed to comprehensively analyze the predictive results of the models.The results indicate that although the KAN model,based on the RBF kernel,achieves the expected performance on the binary classification dataset,it also performs well on imbalanced and highly discrete datasets,significantly surpassing other commonly used classification models.This demonstrated the broad application potential of the KAN model in geotechnical engineering.展开更多
Depressurization and heat injection are viewed as the main methods to be used in natural gas hydrate(NGH)exploitation.However,these methods have limitations,such as low energy-utilization efficiency or a limited extra...Depressurization and heat injection are viewed as the main methods to be used in natural gas hydrate(NGH)exploitation.However,these methods have limitations,such as low energy-utilization efficiency or a limited extraction range,and are still far from commercial exploitation.In this work,we propose a potential commercial method to exploit NGHs by effectively using geothermal energy inside deep reservoirs.Specifically,a loop well structure is designed to economically extract geothermal energy.Based on an analysis of our developed model,when the looping well is coupled with depressurization,the profits of high NGH production can surpass the drilling costs of extracting geothermal energy.Moreover,as the temperature of fluids from the geothermal layer exceeds 62℃,the fluid heat is mainly consumed by the rock matrix of the hydrate formation,instead of promoting NGH dissociation.Based on this threshold temperature,a loop well drilled to a depth of about 4000 m for hydrate sediment in the Shenhu area of the South China Sea would be able to efficiently extract geothermal energy,leading to an approximate73%increase in gas production in comparison with conventional depressurization.An economic analysis suggests that our proposed method can reduce the exploitation cost of methane to 0.46 USD·m^(-3).Furthermore,as the hydrate saturation increases to 0.5,the exploitation cost can be further reduced to 0.14 USD·m^(-3).Overall,a looping well coupled with geothermal energy and depressurization is expected to pave the way for commercial NGH exploitation.展开更多
<div style="text-align:justify;"> The analytical expression of the cross-spectral density of partially coherent elegant Laguerre-Gaussian beams propagating in free space has been derived. The coherence...<div style="text-align:justify;"> The analytical expression of the cross-spectral density of partially coherent elegant Laguerre-Gaussian beams propagating in free space has been derived. The coherence vortex properties of such beams have been investigated. The effect of the beam parameters, including the topological charge, radial mode index and coherence length on the coherent vortex, is analyzed. The results show that the higher order (lth) of coherent vortices split to lth first order of coherent vortex. New coherent vortices of opposite sign appear, and then pairs of coherent vortices form. The propagation distance and coherence length affect the generation of coherent vortices, while the radial mode index doesn’t affect the coherent vortices. These results might be helpful for potential application of such beams in optical communication. </div>展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42107214 and 42477157).
文摘In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classification models across three datasets:a simple slope binary classification dataset,an imbalanced rockburst dataset,and a highly discrete liquefaction dataset.First,a thorough review of machine-learning algorithms for geohazard assessment was conducted.Subsequently,three datasets were collected from real engineering practices,and their data structures were visualized.Bayesian optimization was then used to adjust the parameters of all models across all datasets.To ensure model interpretability,a global sensitivity analysis based on Sobol indices was performed,establishing an interpretable visual analysis of the model's decision-making process.For a fair evaluation,various metrics and repeated stratified 10-fold cross-validation were employed to comprehensively analyze the predictive results of the models.The results indicate that although the KAN model,based on the RBF kernel,achieves the expected performance on the binary classification dataset,it also performs well on imbalanced and highly discrete datasets,significantly surpassing other commonly used classification models.This demonstrated the broad application potential of the KAN model in geotechnical engineering.
基金supported by the National Natural Science Foundation of China(52288101,51991360,and U21B2069)。
文摘Depressurization and heat injection are viewed as the main methods to be used in natural gas hydrate(NGH)exploitation.However,these methods have limitations,such as low energy-utilization efficiency or a limited extraction range,and are still far from commercial exploitation.In this work,we propose a potential commercial method to exploit NGHs by effectively using geothermal energy inside deep reservoirs.Specifically,a loop well structure is designed to economically extract geothermal energy.Based on an analysis of our developed model,when the looping well is coupled with depressurization,the profits of high NGH production can surpass the drilling costs of extracting geothermal energy.Moreover,as the temperature of fluids from the geothermal layer exceeds 62℃,the fluid heat is mainly consumed by the rock matrix of the hydrate formation,instead of promoting NGH dissociation.Based on this threshold temperature,a loop well drilled to a depth of about 4000 m for hydrate sediment in the Shenhu area of the South China Sea would be able to efficiently extract geothermal energy,leading to an approximate73%increase in gas production in comparison with conventional depressurization.An economic analysis suggests that our proposed method can reduce the exploitation cost of methane to 0.46 USD·m^(-3).Furthermore,as the hydrate saturation increases to 0.5,the exploitation cost can be further reduced to 0.14 USD·m^(-3).Overall,a looping well coupled with geothermal energy and depressurization is expected to pave the way for commercial NGH exploitation.
文摘<div style="text-align:justify;"> The analytical expression of the cross-spectral density of partially coherent elegant Laguerre-Gaussian beams propagating in free space has been derived. The coherence vortex properties of such beams have been investigated. The effect of the beam parameters, including the topological charge, radial mode index and coherence length on the coherent vortex, is analyzed. The results show that the higher order (lth) of coherent vortices split to lth first order of coherent vortex. New coherent vortices of opposite sign appear, and then pairs of coherent vortices form. The propagation distance and coherence length affect the generation of coherent vortices, while the radial mode index doesn’t affect the coherent vortices. These results might be helpful for potential application of such beams in optical communication. </div>
