Evaluation of the Groundwater and Irrigation Quality in the Zhuoshui River Alluvial Fan between Wet and Dry Seasons

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. 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.

Assessment of Ammonium–N and Nitrate–N Contamination of Shallow Groundwater in a Complex Agricultural Region, Central Western Taiwan

The characteristics of nitrogen contamination of shallow groundwater were evaluated through current status analysis and trend detection of ammonium–N and nitrate–N concentrations under various cropping patterns to assess the effectiveness of rational fertilization in the Choushui River alluvial fan, central Western Taiwan. The influence of cropping patterns on both ammonium–N and nitrate–N contamination associated with redox conditions/dissolved oxygen (DO) in shallow groundwater was also discussed in this study. The analysis revealed that shallow groundwater beneath double rice cropping and rotational cropping regions is still characterized by high ammonium–N concentration despite rational fertilization promotion. However, very few monitoring wells showed an upward trend of ammonium–N/nitrate–N concentrations, indicating that shallow groundwater is not further deteriorated by nitrogen pollution in most parts of the study area. Therefore, the remediation of nitrogen contaminated groundwater will be a long-term process and more effort must be invested. Moreover, the strict redox conditions defined by a single DO threshold value may not account for groundwater nitrogen pollution in the study area. It is difficult to determine the redox conditions and predominant nitrogen pollution patterns of shallow groundwater purely from cropping patterns. Instead, contamination may have resulted from an integrated process governed by several other factors. Tracing the potential sources of nitrogen pollution and establishing a more integral monitoring network should be implemented to formulate a more comprehensive nitrogen pollution control strategy in this area.