Interval Prediction of Total Nitrogen Using a Hybrid BiLSTM-Res Model and Bayesian Optimization: A Case Study in the Pearl River Delta
文献类型：期刊论文
| 作者 | Zhang, Hanzhi1; Niu, Guoqiang2; Li, Xiaoyong1; Lin, Mi1; Fan, Kai3; Yi, Xiaohui1; Huang, Mingzhi1 |
| 刊名 | WATER
 |
| 出版日期 | 2026-02-27 |
| 卷号 | 18期号:5页码:578 |
| 关键词 | total nitrogen interval prediction deep learning BILSTM model |
| DOI | 10.3390/w18050578 |
| 产权排序 | 3 |
| 文献子类 | Article |
| 英文摘要 | This study develops a hybrid deep learning framework for point and interval prediction of Total Nitrogen (TN) concentrations in the Pearl River Delta, China. To address the inherent stochasticity of water quality systems, Bidirectional Long Short-Term Memory (BiLSTM) networks are integrated with residual learning blocks (Res) and Bayesian Optimization (BO). The resulting BiLSTM-Res-BO framework is evaluated within a comparative analysis of eight forecasting models that combine BiLSTM and BiGRU architectures with two uncertainty quantification approaches: Quantile Regression (QR) and Monte Carlo Dropout (MCD). Results from 37 monitoring stations demonstrate that the effectiveness of residual learning is highly context-dependent. For point forecasting, BiLSTM-Res achieves substantial performance gains (12.5-15% RMSE reduction) at complexity-sensitive sites, while providing negligible or slightly degraded performance under hydrologically stable conditions. For interval forecasting, QR-based residual models-particularly Q-BiLSTM-Res-produce notably narrower prediction intervals, with interval width reductions of 16.7-27.3% relative to the baseline BiLSTM model, under comparable levels of empirical coverage. In contrast, MC-dropout-based methods tend to yield wider intervals with different coverage-width trade-offs, reflecting distinct uncertainty propagation behaviors across modeling frameworks. |
| URL标识 | 查看原文 |
| WOS关键词 | WATER-QUALITY |
| WOS研究方向 | Environmental Sciences & Ecology ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001713364400001 |
| 出版者 | MDPI |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221221]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Yi, Xiaohui; Huang, Mingzhi |
| 作者单位 | 1.South China Normal Univ, Sch Environm, Guangzhou 510006, Peoples R China; 2.South China Univ Technol, State Key Lab Pulp & Paper Engn, Guangzhou 510640, Peoples R China; 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Hanzhi,Niu, Guoqiang,Li, Xiaoyong,et al. Interval Prediction of Total Nitrogen Using a Hybrid BiLSTM-Res Model and Bayesian Optimization: A Case Study in the Pearl River Delta[J]. WATER,2026,18(5):578. |
| APA | Zhang, Hanzhi.,Niu, Guoqiang.,Li, Xiaoyong.,Lin, Mi.,Fan, Kai.,...&Huang, Mingzhi.(2026).Interval Prediction of Total Nitrogen Using a Hybrid BiLSTM-Res Model and Bayesian Optimization: A Case Study in the Pearl River Delta.WATER,18(5),578. |
| MLA | Zhang, Hanzhi,et al."Interval Prediction of Total Nitrogen Using a Hybrid BiLSTM-Res Model and Bayesian Optimization: A Case Study in the Pearl River Delta".WATER 18.5(2026):578. |
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。