基于机器学习的无双矿光伏材料的预测和选
Juan Wang1, Yizhe Wang1, Xiaoqin Liu1
1Xi'an Key Laboratory of Advanced Photo-Electronics Materials and Energy Conversion Device, School of Electronic Information, Xijing University, Xi'an 710123, China.
Molecules (Basel, Switzerland)
|June 13, 2025
概括
机器学习识别了99种无双矿,它们的带隙非常适合高效的太阳能电池. 这项研究指导着为可持续能源解决方案设计稳定,无毒的光伏材料.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学的计算化学
- 可再生能源可再生能源是可再生能源.
背景情况:
- 开发高效和环保的能源解决方案需要稳定,无的矿材料.
- 传统的光伏材料通常含有等有毒元素,造成环境问题.
研究的目的:
- 采用机器学习来预测双矿的带隙和形成能量.
- 为光伏应用确定有前途的无双矿候选物.
主要方法:
- 从材料项目数据库中整理了1053个双矿的数据集.
- 使用皮尔森相关性和mRMR的特征选择确定了预测模型的关键描述符.
- XGBoost机器学习模型被训练并验证为预测带隙和形成能量,实现高精度 (R2 > 0.93).
- 使用SHAP分析来解释模型的预测,并确定有影响力的特征.
主要成果:
- 在预测带隙 (R2 = 0.934) 和形成能量 (R2 = 0.959) 方面,XGBoost表现出卓越的性能.
- 影响带隙的关键因素包括X位电子亲和力和B"位电离能.
- 形成能量主要由X位电离能和B'/B′′位电负性决定.
- 产生和选了4573个双矿,选择了2054个结构稳定的候选物.
- 确定了99种无双矿,具有光伏的最佳带隙 (1.31.4 eV).
- 四种已知的化合物和95种新的矿化合物被确定为有前途的候选物.
结论:
- 该研究成功地确定了99种无双矿,具有适合光伏应用的带隙.
- 特定的元素组合,特别是涉及X位元 (Se,S,O,C) 和B"位元 (Pd,Ir,Fe,Ta,Pt,Cu) 的元素,有利于狭窄的带隙.
- 这些发现为设计下一代无毒,高性能光伏材料提供了有价值的路线图.
相关概念视频
02:52Predicting Products: Substitution vs. Elimination
11.2K
When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:
The following factors can influence the mechanisms competing against each other:
11.2K
01:03Prediction Intervals
2.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.5K