RESUMO
In this study, we investigated the impact of fluctuating water levels on the distribution of lead (Pb) and zinc (Zn) in soil and sediments at a historical Pb-Zn smelting site along the Xiangjiang River. Despite the high pH levels (7 to 11) in the study area, which generally inhibits heavy metal solubility, we found that regular changes in water levels still affect Pb-Zn movement. Soil analysis revealed distinct redox zones within the unconfined aquifer, as shown by the variable Fe/Mn and Ce/Ce* ratios. Advanced techniques such as Mn K-edge XAFS, Mössbauer spectroscopy, and TOF-SIMS indicated persistent Fe-Mn redox cycling and highlighted the presence of Pb and Zn-rich manganese oxides near sulfur-bearing minerals. These findings suggest that acidic microzones produced by the oxidation of sulfur-bearing minerals become "refuges" for microbial and heavy metal activity. Considering that sulfur-containing minerals are widespread waste types in nonferrous metal smelting sites, these findings are instructive for a better understanding of the transformation mechanisms of heavy metal ions in nonferrous metal smelting-polluted environments and for guiding pollution remediation strategies.
RESUMO
Sequential recommendation aims to choose the most suitable items for a user at a specific timestamp given historical behaviors. Existing methods usually model the user behavior sequence based on transition-based methods such as Markov chain. However, these methods also implicitly assume that the users are independent of each other without considering the influence between users. In fact, this influence plays an important role in sequence recommendation since the behavior of a user is easily affected by others. Therefore, it is desirable to aggregate both user behaviors and the influence between users, which are evolved temporally and involved in the heterogeneous graph of users and items. In this article, we incorporate dynamic user-item heterogeneous graphs to propose a novel sequential recommendation framework. As a result, the historical behaviors as well as the influence between users can be taken into consideration. To achieve this, we first formalize sequential recommendation as a problem to estimate conditional probability given temporal dynamic heterogeneous graphs and user behavior sequences. After that, we exploit the conditional random field to aggregate the heterogeneous graphs and user behaviors for probability estimation and employ the pseudo-likelihood approach to derive a tractable objective function. Finally, we provide scalable and flexible implementations of the proposed framework. Experimental results on three real-world datasets not only demonstrate the effectiveness of our proposed method but also provide some insightful discoveries on the sequential recommendation.
