Predictions and mechanism analyses of the fatigue strength of steel based on machine learning

Yan, Feng; Song, Kai; Liu, Ying; Chen, Shaowei; Chen, Jiayong

doi:10.1007/s10853-020-05091-7

Cited by 60 publications

(27 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tree‐based machine learning models are extremely popular nonlinear models for the prediction and attribution analysis of ecosystem dynamics (Green et al, 2022; Wang et al, 2015; Yuan et al, 2019), and they are usually more accurate than neural networks in many applications and outperform standard deep‐learning models on tabular‐style data sets (Lundberg et al, 2020). Extreme gradient boosting (XGB) is an ensemble learning algorithm based on an iterative decision tree model with many decision trees, which is typically used in classification and regression fields (Chen et al, 2016; Yan et al, 2020). This method can perform multithreaded calculations, use shrinkage technology to scale newly added weights at each boosting step to avoid overfitting (Meng et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

Exploring complex water stress–gross primary production relationships: Impact of climatic drivers, main effects, and interactive effects

Wang

Yan

Ciais

et al. 2022

Global Change Biology

View full text Add to dashboard Cite

The dominance of vapor pressure deficit (VPD) and soil water content (SWC) for plant water stress is still under debate. These two variables are strongly coupled and influenced by climatic drivers. The impacts of climatic drivers on the relationships between gross primary production (GPP) and water stress from VPD/SWC and the interaction between VPD and SWC are not fully understood. Here, applying statistical methods and extreme gradient boosting models—Shapley additive explanations framework to eddy‐covariance observations from the global FLUXNET2015 data set, we found that the VPD‐GPP relationship was strongly influenced by climatic interactions and that VPD was more important for plant water stress than SWC across most plant functional types when we removed the effect of main climatic drivers, e.g. air temperature, incoming shortwave radiation and wind speed. However, we found no evidence for a significant influence of elevated CO2 on stress alleviation, possibly because of the short duration of the records (approximately one decade). Additionally, the interactive effect between VPD and SWC differed from their individual effect. When SWC was high, the SHAP interaction value of SWC and VPD on GPP was decreased with increasing VPD, but when SWC was low, the trend was the opposite. Additionally, we revealed a threshold effect for VPD stress on GPP loss; above the threshold value, the stress on GPP was flattened off. Our results have important implications for independently identifying VPD and SWC limitations on plant productivity, which is meaningful for capturing the magnitude of ecosystem responses to water stress in dynamic global vegetation models.

show abstract

Section: Methodsmentioning

confidence: 99%

Exploring complex water stress–gross primary production relationships: Impact of climatic drivers, main effects, and interactive effects

Wang

Yan

Ciais

et al. 2022

Global Change Biology

View full text Add to dashboard Cite

show abstract

“…SHAP method is based on game theory and local explanations, satisfying the following properties: local accuracy, missingness, and consistence [66]- [68]. This method calculates the shapley value for variable i to estimate its contribution to model output (v(N)) using the formula [69]:…”

Section: ) Model Interpretationmentioning

confidence: 99%

Identification of Soil Texture Classes Under Vegetation Cover Based on Sentinel-2 Data With SVM and SHAP Techniques

Zhou

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Understanding the spatial variability of soil texture classes is essential for agricultural management and environment sustainability. Sentinel-2 data offer valuable vegetation information as proxies for soil properties inference. However, the applications of them in soil texture classification are still limited. This study investigated the usefulness of Sentinel-2 data for predicting soil texture class using an interpretable machine learning (ML) strategy. Specifically, multitemporal Sentinel-2 images were used to get exhaustive vegetation cover information. Basic digital elevation map (DEM) derivatives and stratum were extracted. Three support vector machines with different input parameters (purely DEM derivatives and stratum, purely Sentinel-2, and Sentinel-2 plus DEM derivatives and stratum) were developed. Moreover, in order to improve the transparency in black box ML models, the novel SHapley Additive exPlanations (SHAP) method was applied to interpret the outputs and analyze the importance of individual variables. Results showed that the model with all variables provided desirable performance with overall accuracy of 0.8435, F1-score of 0.835, kappa statistic of 0.7642, precision of 0.8388, recall of 0.8355, and area under the curve of 0.9451. The model with purely Sentinel-2 data performed much better than that with solely DEM derivatives and stratum. The contributions of Sentinel-2 data to explain soil texture class variability were about 17%, 41%, and 28% for sandy, loamy and clayey soils, respectively. The SHAP method visualized the decision process of ML and indicated that elevation, stratum, and red-edge factors were critical variables for predicting soil texture classes. This study offered much-needed insights into the applications of Sentinel-2 data in digital soil mapping and ML-assisted tasks. Index Terms-Machine learning (ML), sentinel-2, shapley additive explanations (SHAP), soil texture classes. I. INTRODUCTION S OIL texture controls soil water holding capacity, permeability, solute movement and aeration [1], and then drives soil physical, chemical, biological, and hydrological processes that are closely related to plant growth and soil erosion [2], [3].

show abstract

“…Therefore, rationalized design parts, selecting materials, and formulating cold and heat resistant materials were deemed possible using the technique. 38 Micromechanical models accurately represented material behavior and its relationship to thermal history from the early stages of computational materials science. 39 However, when out-of-range data were used to train ML models, projected grain sizes varied significantly from reference values.…”

Section: Comparative Aspects Of the Current Studymentioning

confidence: 99%

“…According to the results, the SHAP approach showed much potential for evaluating fatigue strength indicators. Therefore, rationalized design parts, selecting materials, and formulating cold and heat resistant materials were deemed possible using the technique 38 . Micromechanical models accurately represented material behavior and its relationship to thermal history from the early stages of computational materials science 39 .…”

Section: Introductionmentioning

confidence: 99%

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Awd

Münstermann

Walther

2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

The posterior statistical distributions of fatigue strength are determined using Bayesian inferential statistics and the Metropolis Monte Carlo method.This study explores how structural heterogeneity affects ultrahigh cycle fatigue strength in additive manufacturing. Monte Carlo methods and procedures may assist estimate fatigue strength posteriors and scatter. The acceptable probability in Metropolis Monte Carlo relies on the Markov chain's random microstructure state. In addition to commonly studied variables, the proportion of chemical composition was demonstrated to substantially impact fatigue strength if fatigue lifetime in crack propagation did not prevail due to high threshold internal notches. The study utilizes an algorithm typically used for quantum mechanics to solve the complicated multifactorial fatigue problem. The inputs and outputs are modified by fitting the microstructural heterogeneities into the Metropolis Monte Carlo algorithm. The main advantage here is applying a general-purpose nonphenomenological model that can be applied to multiple influencing factors without high numerical penalty.

show abstract

Predictions and mechanism analyses of the fatigue strength of steel based on machine learning

Cited by 60 publications

References 36 publications

Exploring complex water stress–gross primary production relationships: Impact of climatic drivers, main effects, and interactive effects

Exploring complex water stress–gross primary production relationships: Impact of climatic drivers, main effects, and interactive effects

Identification of Soil Texture Classes Under Vegetation Cover Based on Sentinel-2 Data With SVM and SHAP Techniques

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Contact Info

Product

Resources

About