Watershed groundwater level multistep ahead forecasts by fusing convolutional-based autoencoder and LSTM models

The development of deep learning-based groundwater level forecast models can tackle the challenge of high dimensional groundwater dynamics, predict groundwater variation trends accurately, and manage groundwater resources effectively, thereby contributing to sustainable water resources management. T...

Full description

Saved in:
Bibliographic Details
Published in:Journal of environmental management Vol. 351; p. 119789
Main Authors: Kow, Pu-Yun, Liou, Jia-Yi, Sun, Wei, Chang, Li-Chiu, Chang, Fi-John
Format: Journal Article
Language:English
Published: England Elsevier Ltd 01.02.2024
Subjects:
case studies
Convolutional neural network (CNN)
data collection
Deep learning
environmental management
groundwater
Groundwater level forecast
HBV-Light model
Long short-term memory neural network (LSTM)
neural networks
Taiwan
water management
water table
watersheds
Taiwan
Deep learning
Long short-term memory neural network (LSTM)
Convolutional neural network (CNN)
Groundwater level forecast
HBV-Light model
ISSN:0301-4797, 1095-8630, 1095-8630
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The development of deep learning-based groundwater level forecast models can tackle the challenge of high dimensional groundwater dynamics, predict groundwater variation trends accurately, and manage groundwater resources effectively, thereby contributing to sustainable water resources management. This study proposed a novel ConvAE-LSTM model, which fused a Convolutional-based Autoencoder model (ConvAE) and a Long Short-Term Memory Neural Network model (LSTM), to provide accurate spatiotemporal groundwater level forecasts over the next three months. The HBV-light and LSTM models are chosen as benchmarks. An ensemble of point data and the corresponding derived images concerning the past (observations) and the future (forecasts from a conceptual model) of groundwater levels at 33 groundwater wells in Jhuoshuei River basin of Taiwan between 2000 and 2019 constituted the case study. The findings showcase the effectiveness of the ConvAE-LSTM model in extracting crucial features from both point and imagery datasets. This model successfully establishes spatiotemporal dependencies between regional images and groundwater level data over diverse time frames, leading to accurate multi-step-ahead forecasts of groundwater levels. Notably, the ConvAE-LSTM model exhibits a substantial improvement, with the R-squared values showing an increase of more than 18%, 22%, and 49% for the R1, R2, and R3 regions, respectively, compared to the HBV-light model. Additionally, it outperforms the LSTM model in this regard. This study represents a noteworthy milestone in environmental modeling, offering key insights for designing sustainable groundwater management strategies to ensure the long-term availability of this vital resource. [Display omitted] •Build a novel ConvAE-LSTM groundwater forecast model by fusing ConvAE and LSTM.•ConvAE-LSTM deeply extracts features from observed (past) and simulated (future) data.•ConvAE-LSTM effectively extracts spatial information from high dimensional images.•ConvAE-LSTM outperforms HBV-light due to state transition overcoming data uncertainty.•ConvAE-LSTM makes accurate regional multi-horizon groundwater level forecasts.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0301-4797
1095-8630
1095-8630
DOI:10.1016/j.jenvman.2023.119789