Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods
文献类型：期刊论文
| 作者 | Zhao, Chen2; Yang, Jun2,3; Shi, Huading1; Chen, Tongbin2,3 |
| 刊名 | JOURNAL OF HAZARDOUS MATERIALS
 |
| 出版日期 | 2022-02-15 |
| 卷号 | 424页码:10 |
| 关键词 | Regression Probability forecasting Arsenic Rice grain Soil |
| ISSN号 | 0304-3894 |
| DOI | 10.1016/j.jhazmat.2021.127375 |
| 通讯作者 | Yang, Jun(yangj@igsnrr.ac.cn) ; Shi, Huading(shihuading@tcare-mee.cn) |
| 英文摘要 | Probability models are preferred over regression models recently in contamination evaluation but lacking proper performance comparison between two model types. Linear regression, logistic regression, XGBoost-based regression, and probability models were built considering soil arsenic and certain soil physicochemical properties of 287 samples to predict arsenic in rice grains. The outputs of all models were binarily classified uniformly for comparison. The complex algorithm-based models-XGBoost-based regression (R-2 =0.046 +/- 0.036) and probability models (cross-entropy = 0.697 +/- 0.020)-did not surpass the simple linear regression (R-2 =0.046 +/- 0.031) and logistic regression models (cross-entropy = 0.694 +/- 0.021). Accuracy, sensitivity, specificity, precision, and Fl score showed that the probability models exhibit no advantage on regression models, although the indicators above did not serve as proper scoring rules for the probability model. When discretizing the contaminant concentration in grains for probabilistic modeling, the limit concentration was considered as the splitting point but not the structure of the datasets, which would reduce the inherent advantage of the probability model. When predicting the contamination of crops, the probability model cannot eliminate the regression model, and simple but robust algorithm-based models are preferred when the quality and quantity of the dataset are undesirable. |
| WOS关键词 | HEAVY-METAL CONCENTRATIONS ; LOGISTIC-REGRESSION ; ORGANIC-MATTER ; DISCRIMINANT-ANALYSIS ; CADMIUM UPTAKE ; HUMAN HEALTH ; HAN RIVER ; SOIL ; RISK ; CD |
| WOS研究方向 | Engineering ; Environmental Sciences & Ecology |
| 语种 | 英语 |
| WOS记录号 | WOS:000711847500009 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/167410]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Yang, Jun; Shi, Huading |
| 作者单位 | 1.Tech Ctr Soil, Agr & Rural Ecol & Environm, Minist Ecol & Environm, Beijing 100012, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Ctr Environm Remediat, 11 Datun Rd, Beijing 100101, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Chen,Yang, Jun,Shi, Huading,et al. Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods[J]. JOURNAL OF HAZARDOUS MATERIALS,2022,424:10. |
| APA | Zhao, Chen,Yang, Jun,Shi, Huading,&Chen, Tongbin.(2022).Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods.JOURNAL OF HAZARDOUS MATERIALS,424,10. |
| MLA | Zhao, Chen,et al."Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods".JOURNAL OF HAZARDOUS MATERIALS 424(2022):10. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。