A parsimonious model for predicting the NO3--N concentration in shallow groundwater in intensive agricultural areas using few easily accessible indicators and small datasets based on machine learning
文献类型： 外文期刊
作者： Wang, Panlei 1 ; Zhang, Dan 2 ; Tao, Xiang 3 ; Hu, Wanli 1 ; Fu, Bin 1 ; Yan, Hui 1 ; Pan, Yanhua 1 ; Chen, Anqiang 1 ;
作者机构： 1.Yunnan Acad Agr Sci, Agr Environm & Resources Inst, Kunming 650201, Peoples R China
2.Yunnan Agr Univ, Coll Resource & Environm, Kunming 650201, Peoples R China
3.Yunnan Acad Agr Sci, Kunming 650201, Peoples R China
关键词： E; Brookfield; Associate Editor; Shallow groundwater; NO 3; -N prediction; Machine learning; Intensive agricultural area
期刊名称：JOURNAL OF HYDROLOGY （ 影响因子：6.4； 五年影响因子：6.6 ）
ISSN： 0022-1694
年卷期： 2023 年 619 卷
页码：
收录情况： SCI
摘要： Groundwater nitrate poses a health risk to humans, and monitoring groundwater quality is time-consuming and expensive. To improve the efficiency and reduce the costs of monitoring groundwater nitrate, a parsimonious model was developed using easily accessible predictors and small datasets based on random forest (RF), neural network (NN), and support vector machine (SVM) algorithms. Groundwater NO3- -N concentrations of 1196 groundwater samples from intensive agricultural areas along with data on 13 predictors were obtained for the construction of prediction models. R2 and RMSE metrics were used to evaluate the models, with an emphasis on a minimal number of predictors and a low data size. The results showed that even with few readily available predictors (conductivity, EC; chemical nitrogen fertilization rate, NF; and precipitation, PPT) and a small dataset (260-700 observations), the three models achieved good precision, with R2 and RMSE values of 0.70-0.80 and 6.87-8.13, respectively. In these prediction models, EC was the primary predictor acting as an intrinsic factor, NF acted as a loading factor to supplement the blind area of EC for NO3- -N prediction, and PPT was introduced because of its accessibility to improve predictive performance. The final predictors applied in this study link the two currently dominant prediction methods by combining the high predictive accuracy of the intrinsic predictor with the accessibility of the extrinsic predictor, and the results demonstrate the practicability and applicability advantages of this model in groundwater NO3- -N prediction. This model provides technical support for the rapid and low-cost realization of the online monitoring of NO3- -N pollution in shallow groundwater in intensive agricultural areas.
- 相关文献
作者其他论文 更多>>
-
Organic substitution accumulates more nitrogen in soil while maintaining unchanged nitrogen use efficiency in rice-fava bean rotation system
作者：Wang, Panlei;Tang, Li;Wang, Panlei;Chen, Anqiang;Sun, Xi;Du, Caiyan;Zhu, Hongye;Pan, Yanhua;Wang, Panlei;Chen, Anqiang;Sun, Xi;Du, Caiyan;Zhu, Hongye;Pan, Yanhua;Wang, Bin;Tang, Li
关键词：drought-flood alternation; N use efficiency; organic substitution management; paddy-upland rotation; soil N pool
-
Prediction of phosphorus concentrations in shallow groundwater in intensive agricultural regions based on machine learning
作者：Yang, Heng;Ye, Yuanhang;Chen, Qingfei;Zhang, Dan;Wang, Panlei;Chen, Anqiang;Cui, Rongyang;Cui, Rongyang
关键词：Shallow groundwater; Phosphorus; Machine learning; Intensive agricultural region
-
Regulation of agronomic traits of bean by soil decomposer animals depends on cropping system and genotype
作者：Wang, Panlei;Fu, Libo;Pan, Yanhua;Sun, Xi;Wang, Zhiyuan;Wang, Panlei;Tang, Li;Wang, Zhiyuan;Erktan, Amandine;Scheu, Stefan;Erktan, Amandine;Cao, Weidong;Scheu, Stefan
关键词：Faba bean; Wheat; Mixed cropping; Earthworms; Collembolans
-
Shifts in the sources and fates of nitrate in shallow groundwater caused by agricultural intensification intensity: Revealed by hydrochemistry, stable isotopic composition and source contribution
作者：Cui, Rongyang;Fu, Bin;Yan, Hui;Hu, Wanli;Chen, Anqiang;Cui, Rongyang;Liu, Gangcai;Cui, Rongyang;Zhang, Dan;Wang, Hongyuan
关键词：Shallow groundwater; Water and nitrate isotopes; Nitrate source; Agricultural intensification intensity; Nitrogen transformation
-
Nitrogen in soil, manure and sewage has become a major challenge in controlling nitrate pollution in groundwater around plateau lakes, Southwest China
作者：Cui, Rongyang;Liu, Gangcai;Cui, Rongyang;Liu, Gangcai;Cui, Rongyang;Cui, Rongyang;Hu, Wanli;Zhao, Xinmei;Yan, Hui;Chen, Anqiang;Zhang, Dan
关键词：Groundwater; NO3- isotopes; NO3- pollution; N cycling
-
Electrical conductivity and dissolved oxygen as predictors of nitrate concentrations in shallow groundwater in Erhai Lake region
作者：Zhang, Dan;Wang, Panlei;Yang, Heng;Li, Guifang;Wang, Panlei;Chen, Anqiang;Cui, Rongyang;Wang, Hongyuan
关键词：Nitrogen concentration; Predictive model; Electrical conductivity; Dissolved oxygen; Shallow groundwater
-
Shift of lakeshore cropland to buffer zones greatly reduced nitrogen loss from the soil profile caused by the interaction of lake water and shallow groundwater
作者：Cui, Rongyang;Zhang, Dan;Cui, Rongyang;Liu, Gangcai;Cui, Rongyang;Liu, Gangcai;Cui, Rongyang;Wang, Panlei;Chen, Anqiang;Wang, Hongyuan
关键词：Soil nitrogen loss; Soil profile; Cropland buffer zone; Hyporheic zone
