YGYu Gu

Yu Gu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yu Gu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting and Mapping the Phosphorus Adsorption Maximum and Phosphorus Adsorption Affinity Constant at Regional Scale

    by Yu Gu, Gerard H. Ros, Qichao Zhu, Dongfang Zheng, Jianbo Shen, Wim de Vries

    Insight into the variation of the soil phosphorus (P) adsorption maximum (Q max ) and the P adsorption affinity constant (K L ) is crucial for accurately assessing the dynamics of P availability, P uptake and P leaching in agricultural systems at regional scale. Data on the variation in soil P adsorption characteristics, derived from traditional batch experiments, combined with data on soil properties affecting them, such as pH, clay and organic matter content, can be used to assess the influence of soil properties on P adsorption characteristics. However, current studies are limited to explaining the variation in Q max using linear models, focusing on either noncalcareous or calcareous soils. This study aims to (1) identify the soil properties governing both Q max and K L for a combination of noncalcareous and calcareous soils, including nonlinear and interaction effects; and (2) create spatial maps depicting the variations in both soil P adsorption characteristics at the regional scale (two typical Chinese counties). We leveraged 83 data points of both Q max and K L from 16 publications with main soil properties affecting P adsorption, that is, pH and the content of soil organic matter (SOM), clay and oxalate extractable Fe and Al (Fe OX and Al OX ), to develop predictive models for soil P adsorption. General linear regression (GLM) and extreme gradient boosting (XGB) models were used to unravel the relationships between soil properties and P adsorption characteristics. The XGB model outperformed GLM model, explaining more than 80% of the variations in both Q max and K L in noncalcareous and calcareous soils, while the GLM model explained 52% for Q max and only 21% for K L . Key drivers influencing Q max were found to be Fe OX , Al OX and pH, while clay and pH played significant roles in explaining the variability in K L . When applying these models at the county level using county‐level inventory data, noncalcareous soils generally exhibited higher P sorption capacity and binding energy than calcareous soils. To enhance the accuracy of soil P sorption predictions and guide sustainable P fertiliser use, regional mapping of Fe OX and Al OX content is essential.


  • Water quality analysis based on LSTM and BP optimization with a transfer learning model

    by Qun Luo, Dingzhi Peng, Wenjian Shang, Yu Gu, Xiaoyu Luo, Zhongfan Zhu, Bo Pang

    In the urban water environmental management, a fast and effective method for water quality analysis should be established with the rapid urbanization. In this study, the Beijing’s sub-center was chosen as a case study, and long short-term memory (LSTM) and back propagation (BP) models were built, then a transfer learning model was proposed and applied to optimize the two models on the base of the upstream and downstream relationships in the rivers. The results indicated that the proposed deep learning model could improve NSE by 7% and 9% for LSTM and BP at the Dongguan Bridge gauge, respectively. At the Xugezhuang gauge in the Liangshui River, NSE was improved by 11% and 17%, respectively. At the Yulinzhuang gauge, it was improved by 16% and 13%, respectively. Because the upstream and downstream relationships were considered in the learning model, the model performance was obviously better. In brief, this method would provide an idea for the effective water quality model construction in the ungauged basins or regions.