返回
CoSMoR: Decoding decision-making process along continuous composition pathways in machine learning models trained for material properties
DOI:10.1103/PhysRevMaterials.7.043802.png)
摘要
En 中文
A key challenge in materials informatics is to decode the decision-making process of machine learning (ML) models that have been trained to predict material properties. The existing methods usually rank alloy features based on importance metrics and do not provide material-specific fundamental insights. Here, we present the Compositional Stimulus and Model Response (CoSMoR) framework that can be applied to any composition-based ML model (irrespective of the algorithm used) to calculate the exact contribution of each feature towards the manifestation of target material property along a continuous compositional pathway. CoSMoR utilizes the local partial dependencies of target property with respect to each feature and combines it with feature variations associated with discretized compositional variations to measure exact feature contributions. We showcase the importance of CoSMoR through implementation on phase-selection problem in multiprincipal element alloys (MPEAs), wherein it leads to physical insights into phase transitions. A detailed overview of the framework, along with the codes and step-by-step implementation of the algorithm, has been provided to enable extension to new or preexistent models.
Keyword:
HIGH-ENTROPY ALLOYS
CORROSION BEHAVIOR
PHASE
MICROSTRUCTURE
DESIGN
期刊
IF:
3.4
论文数:
5.2K
被引数:
1.7W
机构
引用论文
Effect of alloying elements on microstructure and properties of multiprincipal elements high-entropy alloys合金元素对多主元素高熵合金组织和性能的影响
Emerging materials intelligence ecosystems propelled by machine learning机器学习推动的新兴材料智能生态系统
NATURE REVIEWS MATERIALS
IF86.2
Effect of molybdenum content on the microstructure and corrosion behavior of FeCoCrNiMox high-entropy alloys钼含量对FeCoCrNiMox高熵合金组织和腐蚀行为的影响
Rapid Discovery of Ferroelectric Photovoltaic Perovskites and Material Descriptors via Machine Learning通过机器学习快速发现铁电光伏钙钛矿和材料描述符
SMALL METHODS
IF9.1

