Spatio-temporal prediction of groundwater vulnerability based on CNN-LSTM model with self-attention mechanism: A case study in Hetao Plain, northern China

Zhao, Yifu; Yang, Liangping; Pan, Hongjie; Li, Yanlong; Shao, Yongxu; Li, Junxia; Xie, Xianjun

doi:10.1016/j.jes.2024.03.052

Cited by 3 publications

(2 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Groundwater vulnerability assessment and its concept are still evolving today (Zhao et al 2024). According to this definition, groundwater vulnerability is the tendency and ability of contaminants to spread to a specific location above the aquifer.…”

Section: Introductionmentioning

confidence: 99%

“…However, because the factors and weights are relatively fixed, index-based and stacked methods only sometimes yield consistent results (Zhu et al 2019). No matter how you adjust the weights and add or remove factors, the inherent characteristics of the index-based evaluation method make the results inflexible and inaccurate, causing major obstacles to the evaluation work and sustainable development of the region (Zhao et al 2024). Since then, convolutional neural network and LSTM models have been proposed as a solution for spatiotemporal prediction of groundwater vulnerability in the area (Alabdulkreem et al 2023;Alfwzan et al 2023;Docheshmeh Gorgij et al 2023).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of the river water environment carrying capacity using LSTM networks

Bui,

Tran,

Nguyen

2024

Water Supply

View full text Add to dashboard Cite

River basins receive wastewater from socio-economic activities. In such a context, a comprehensive assessment and forecast of load-bearing capacity needs to be developed. This capacity depends on many complex factors, such as hydrology, hydraulics, and environment, leading to applying a modelling approach. This study aims to propose a hybrid modelling approach to evaluate and predict the river water environmental capacity (RWEC) in a basin. Big data technology with Python is applied to process modelling results and RWEC forecasts. The long short-term memory (LSTM) model predicts RWEC on each reach of the river channel network. The {RWECP, i, P = Nitrate, BOD, Phosphate, i = hourly} data set and related factors form a time series of data used for the LSTM forecasting model. Forecast results are evaluated through the root mean square error (RMSE) and mean absolute error (MAE). The results show that the average level over all 24 reaches for 7 forecast days: RMSENitrate = 22.16 (kg/day), RMSEBOD = 38.92 (kg/day), and RMSEPhosphate = 0.79 (kg/day). This is an acceptable result for a complex system and 7-day forecast. The results of the study help significantly with pollution control.

show abstract

Section: Introductionmentioning

confidence: 99%