.png){kind=icon}
Return
Reliable and explainable machine-learning methods for accelerated material discovery
.png){kind=icon}
OA
AI
DOI：10.1038/s41524-019-0248-2.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Despite ML's impressive performance in commercial applications, several unique challenges exist when applying ML in materials science applications. In such a context, the contributions of this work are twofold. First, we identify common pitfalls of existing ML techniques when learning from underrepresented/imbalanced material data. Specifically, we show that with imbalanced data, standard methods for assessing quality of ML models break down and lead to misleading conclusions. Furthermore, we find that the model's own confidence score cannot be trusted and model introspection methods (using simpler models) do not help as they result in loss of predictive performance (reliability-explainability trade-off). Second, to overcome these challenges, we propose a general-purpose explainable and reliable machine-learning framework. Specifically, we propose a generic pipeline that employs an ensemble of simpler models to reliably predict material properties. We also propose a transfer learning technique and show that the performance loss due to models' simplicity can be overcome by exploiting correlations among different material properties. A new evaluation metric and a trust score to better quantify the confidence in the predictions are also proposed. To improve the interpretability, we add a rationale generator component to our framework which provides both model-level and decision-level explanations. Finally, we demonstrate the versatility of our technique on two applications: (1) predicting properties of crystalline compounds and (2) identifying potentially stable solar cell materials. We also point to some outstanding issues yet to be resolved for a successful application of ML in material science.
Keywords:
CRYSTAL-STRUCTURE
DESIGN
PREDICTION
VALIDATION
MODELS
Journal
IF:
11.9
Papers:
2.4K
Citations:
1.7W
Organization
Cited Papers
Synthesis and structure of free-standing germanium quantum dots and their application in live cell imaging.png)
RSC AdvancesOAAI
RSC AdvancesIF0
OAAIShareSaveShareSaveShareSave
Kings, Cattle and Blacksmiths: Royal Insignia and Religious Symbolism in the Interlacustrine States
PREAI
ShareSaveArsenic removal from aqueous solutions by adsorption using novel MIL-53(Fe) as a highly efficient adsorbentRSC Advances
RSC AdvancesIF0
PREAI
ShareSaveShareSaveRobust Optimization of Power Consumption for Public Buildings Considering Forecasting Uncertainty of Environmental FactorsEnergiesOAAI
EnergiesIF0
OAAIShareSave
View more