AUTHOR=Liang Yajie , Zhao Jieyu , Zhang Yiting , Li Jisheng , Ding Jieran , Jing Changyong , Ji Jiukun , Wu Dongtan 

TITLE=Developing an SSA-optimized attention-ConvGRU model for predicting and assessing soil contaminant distribution

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 12 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2024.1440296

DOI=10.3389/fenvs.2024.1440296

ISSN=2296-665X

ABSTRACT=Soil pollution, which includes a variety of contaminants such as heavy metals and organic compounds, poses significant environmental and health risks. Current predictive models often struggle with the complexity and diversity of soil contaminant behaviors, leading to limitations in their accuracy and applicability. To address these challenges, our study introduces a novel SSA-optimized Attention-ConvGRU model. This model integrates convolutional neural networks, gated recurrent units, and attention mechanisms, enhanced through optimization with the Sparrow Search Algorithm to improve predictive performance. Experimental results demonstrate that this model significantly outperforms traditional models. On the EPA dataset, the proposed model achieves a Mean Absolute Error (MAE) of 12.57 and a Root Mean Square Error (RMSE) of 20.74. These results highlight the superior performance and potential of the SSA-optimized Attention-ConvGRU model in predicting soil pollution, providing crucial support for environmental management and public health protection.