Linear and nonlinear ensemble deep learning models for karst spring discharge forecasting

计算机科学 集成学习 非线性系统 支持向量机 人工智能 Boosting(机器学习) 集合预报 机器学习 量子力学 物理
作者
Renjie Zhou,Renjie Zhou
出处
期刊:Journal of Hydrology [Elsevier BV]
卷期号:627: 130394-130394 被引量:2
标识
DOI:10.1016/j.jhydrol.2023.130394
摘要

Forecasting karst spring discharge is crucial for groundwater resource management in karst aquifers. These aquifers, with their inherent heterogeneity and complexity influenced by a myriad of environmental factors and hydrological processes, often show nonlinear and nonstationary behaviors. This study introduces novel multivariate multi-step ensemble models, both linear and nonlinear, to forecast karst spring discharge based on predictions from long short-term memory (LSTM), gated recurrent units (GRU) and one-dimensional convolutional neural network (1D-CNN). Linear and nonlinear ensemble learners including simple average method (SAM), linear regression (LR) and support vector regression (SVR) with Bayesian optimization (BO) are used to aggregate obtained results from base models and produce the final ensemble results. These proposed models, named as Ensem-SAM, Ensem-LR and Ensem-SVR-BO, are implemented for daily spring discharge forecasting across various lead times and time steps at Barton Springs, Texas, USA. Notably, these ensemble models outperform the individual base models in prediction accuracy and consistency. The results demonstrate that the ensemble framework can effectively leverage the strengths of diverse deep learning models and complement their limitations, thereby gaining strong generalization capabilities and robust performance, especially with diversiform and nonlinear data. The most marked disparities between individual base models and ensemble models arise with a short time step or a long lead time. Among all, Ensem-SVR-BO exhibits the best generalization capability and delivers accurate and robust prediction results even when one or all base models stuck in local optima.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
AKYDXS完成签到,获得积分10
1秒前
昏睡的蟠桃应助Llllll采纳,获得200
1秒前
科研通AI2S应助hao采纳,获得10
1秒前
2秒前
2秒前
香蕉觅云应助阿湫采纳,获得10
3秒前
星辰大海应助星辰采纳,获得10
3秒前
阿卡宁完成签到,获得积分10
3秒前
lzw完成签到 ,获得积分10
3秒前
沉静烧仙草完成签到,获得积分20
4秒前
烟花应助嘉嘉琦采纳,获得10
4秒前
隐形曼青应助科研通管家采纳,获得10
4秒前
Hello应助科研通管家采纳,获得10
5秒前
Ava应助科研通管家采纳,获得10
5秒前
上官若男应助科研通管家采纳,获得10
5秒前
5秒前
赘婿应助科研通管家采纳,获得10
5秒前
烟花应助科研通管家采纳,获得10
5秒前
FashionBoy应助科研通管家采纳,获得10
5秒前
英俊的铭应助科研通管家采纳,获得10
5秒前
在水一方应助科研通管家采纳,获得10
5秒前
accepted应助科研通管家采纳,获得10
5秒前
脑洞疼应助科研通管家采纳,获得10
5秒前
5秒前
cdh1994应助kcmat采纳,获得10
5秒前
我是老大应助科研通管家采纳,获得10
5秒前
乐乐应助科研通管家采纳,获得10
5秒前
FashionBoy应助科研通管家采纳,获得10
5秒前
5秒前
上官若男应助科研通管家采纳,获得10
5秒前
5秒前
5秒前
5秒前
我是老大应助科研通管家采纳,获得30
5秒前
脑洞疼应助科研通管家采纳,获得20
6秒前
科目三应助科研通管家采纳,获得30
6秒前
6秒前
完美世界应助科研通管家采纳,获得10
6秒前
6秒前
6秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038524
求助须知:如何正确求助?哪些是违规求助? 3576221
关于积分的说明 11374737
捐赠科研通 3305912
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892688
科研通“疑难数据库(出版商)”最低求助积分说明 815048