纯外生预测的时间分布深度学习模型:使用天气图像时间序列进行地下水位预测的应用

IF 4.8 2区 环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Matteo Salis , Abdourrahmane M. Atto , Stefano Ferraris , Rosa Meo
{"title":"纯外生预测的时间分布深度学习模型:使用天气图像时间序列进行地下水位预测的应用","authors":"Matteo Salis ,&nbsp;Abdourrahmane M. Atto ,&nbsp;Stefano Ferraris ,&nbsp;Rosa Meo","doi":"10.1016/j.envsoft.2025.106568","DOIUrl":null,"url":null,"abstract":"<div><div>Deep Learning (DL) models have revealed to be very effective in hydrology, especially in handling spatially distributed data (e.g. raster data). We have proposed two different DL models to predict the water table depth in the Grana-Maira catchment (Piedmont, IT) using only exogenous weather image time series. Both the models are made of a first Time Distributed Convolutional Neural Network (TDC) which encodes the images into hidden vectors. The first model, TDC-LSTM uses then a Sequential Module based on an LSTM layer to learn temporal relations and output the predictions. The second model, TDC-UnPWaveNet uses instead a new version of the WaveNet architecture, adapted for handling output of different length and completely shifted in the future to the input. Both models have shown remarkable results focusing on different learnable information: TDC-LSTM has focused more on bias while the TDC-UnPWaveNet more on the temporal dynamics maximizing correlation <span><math><mi>ρ</mi></math></span>, achieving mean BIAS (and standard deviation) −0.18(0.05), −0.25(0.19) and <span><math><mi>ρ</mi></math></span> 0.93(0.03), 0.96(0.01) respectively over all the sensors.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106568"},"PeriodicalIF":4.8000,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Time Distributed Deep Learning Models for Purely Exogenous Forecasting: Application to Water Table Depth Predictions Using Weather Image Time Series\",\"authors\":\"Matteo Salis ,&nbsp;Abdourrahmane M. Atto ,&nbsp;Stefano Ferraris ,&nbsp;Rosa Meo\",\"doi\":\"10.1016/j.envsoft.2025.106568\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Deep Learning (DL) models have revealed to be very effective in hydrology, especially in handling spatially distributed data (e.g. raster data). We have proposed two different DL models to predict the water table depth in the Grana-Maira catchment (Piedmont, IT) using only exogenous weather image time series. Both the models are made of a first Time Distributed Convolutional Neural Network (TDC) which encodes the images into hidden vectors. The first model, TDC-LSTM uses then a Sequential Module based on an LSTM layer to learn temporal relations and output the predictions. The second model, TDC-UnPWaveNet uses instead a new version of the WaveNet architecture, adapted for handling output of different length and completely shifted in the future to the input. Both models have shown remarkable results focusing on different learnable information: TDC-LSTM has focused more on bias while the TDC-UnPWaveNet more on the temporal dynamics maximizing correlation <span><math><mi>ρ</mi></math></span>, achieving mean BIAS (and standard deviation) −0.18(0.05), −0.25(0.19) and <span><math><mi>ρ</mi></math></span> 0.93(0.03), 0.96(0.01) respectively over all the sensors.</div></div>\",\"PeriodicalId\":310,\"journal\":{\"name\":\"Environmental Modelling & Software\",\"volume\":\"193 \",\"pages\":\"Article 106568\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2025-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Modelling & Software\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S136481522500252X\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Modelling & Software","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S136481522500252X","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

深度学习(DL)模型在水文学中非常有效,特别是在处理空间分布数据(如栅格数据)时。我们提出了两种不同的深度深度模型,仅使用外源天气图像时间序列来预测Grana-Maira流域(Piedmont, IT)的地下水位深度。这两个模型都是由第一次分布式卷积神经网络(TDC)组成的,该网络将图像编码为隐藏向量。第一个模型TDC-LSTM使用基于LSTM层的顺序模块来学习时间关系并输出预测结果。第二个模型,TDC-UnPWaveNet,使用了一个新版本的WaveNet架构,适应处理不同长度的输出,并在未来完全转移到输入。两种模型在不同的可学习信息上都显示出显著的结果:TDC-LSTM更关注偏差,而TDC-UnPWaveNet更关注时间动态最大化相关ρ,在所有传感器上分别实现了平均bias(和标准差)- 0.18(0.05),- 0.25(0.19)和ρ 0.93(0.03), 0.96(0.01)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Time Distributed Deep Learning Models for Purely Exogenous Forecasting: Application to Water Table Depth Predictions Using Weather Image Time Series
Deep Learning (DL) models have revealed to be very effective in hydrology, especially in handling spatially distributed data (e.g. raster data). We have proposed two different DL models to predict the water table depth in the Grana-Maira catchment (Piedmont, IT) using only exogenous weather image time series. Both the models are made of a first Time Distributed Convolutional Neural Network (TDC) which encodes the images into hidden vectors. The first model, TDC-LSTM uses then a Sequential Module based on an LSTM layer to learn temporal relations and output the predictions. The second model, TDC-UnPWaveNet uses instead a new version of the WaveNet architecture, adapted for handling output of different length and completely shifted in the future to the input. Both models have shown remarkable results focusing on different learnable information: TDC-LSTM has focused more on bias while the TDC-UnPWaveNet more on the temporal dynamics maximizing correlation ρ, achieving mean BIAS (and standard deviation) −0.18(0.05), −0.25(0.19) and ρ 0.93(0.03), 0.96(0.01) respectively over all the sensors.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Environmental Modelling & Software
Environmental Modelling & Software 工程技术-工程:环境
CiteScore
9.30
自引率
8.20%
发文量
241
审稿时长
60 days
期刊介绍: Environmental Modelling & Software publishes contributions, in the form of research articles, reviews and short communications, on recent advances in environmental modelling and/or software. The aim is to improve our capacity to represent, understand, predict or manage the behaviour of environmental systems at all practical scales, and to communicate those improvements to a wide scientific and professional audience.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信