Yuqing Zhang

Ms. Yuqing Zhang

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
LLLei LIU
Lei LIU
Yongzhang ZhouYongzhang Zhou
Yongzhang Zhou
Jianhua MaJianhua Ma
Jianhua Ma
YZYuqing Zhang
Yuqing Zhang
LHLuhao HE
Luhao HE
Carbon neutrality is a critical global objective in the fight against climate change. As relevant knowledge and technologies advance rapidly, there is an escalating demand for sophisticated intelligent services. While large language models (LLMs) have demonstrated considerable promise in knowledge processing and generation, their application within the domain of carbon neutrality remains in the early stages of exploration. This study develops a carbon neutrality knowledge base (CN Knowledge Base) using the ChatGLM3 model aimed at enhancing question-answering capabilities in areas such as carbon emission monitoring, policy interpretation, and technical optimization. By refining domain-specific corpora and integrating a Retrieval-Augmented Generation (RAG) mechanism, the model’s ability to generate accurate and relevant responses is improved. To evaluate the performance of the proposed system, a comprehensive quantitative comparison is conducted using established evaluation metrics, including BLEU (Bilingual Evaluation Understudy), BERT (Bidirectional Encoder Representations from Transformers), and METEOR (Metric for Evaluation of Translation with Explicit Ordering). The CN Knowledge Base is benchmarked against leading models such as GPT-4, Gemini, and Bing. The results demonstrate that the CN Knowledge Base outperforms other models in METEOR (0.2697) and is comparable to GPT-4o in both BLEU (0.8755) and BERT (0.8260) Scores (GPT-4o: BLEU: 0.8784, BERT: 0.8404). These findings underscore the knowledge base’s strong adaptability and its ability to generate high-quality, domain-specific content. The study suggests that specialized models can overcome the limitations of general-purpose LLMs, particularly in precise terminology and accurate application of domain knowledge. With continued development, such models could significantly enhance digital and intelligent solutions for carbon neutrality and related fields.

26 September 2025 in Minerals
Verified
Journal Article
Open access
PDF file
Jianhua MaJianhua Ma
Jianhua Ma
Yongzhang ZhouYongzhang Zhou
Yongzhang Zhou
LHLuhao HE
Luhao HE
QZQianlong Zhang
Qianlong Zhang
Muhammad Atif BilalMuhammad Atif Bilal
Muhammad Atif Bilal
YZYuqing Zhang
Yuqing Zhang
This study presents a domain-adapted retrieval-augmented generation (RAG) pipeline that integrates geological knowledge with large language models (LLMs) to support intelligent question answering in the metallogenic domain. Focusing on the Qin–Hang metallogenic belt in South China, we construct a bilingual question-answering (QA) corpus derived from 615 authoritative geological publications, covering topics such as regional tectonics, ore-forming processes, structural evolution, and mineral resources. Using the ChatGLM3-6B language model and LangChain framework, we embed the corpus into a semantic vector database via Sentence-BERT and FAISS, enabling dynamic retrieval and grounded response generation. The RAG-enhanced model significantly outperforms baseline LLMs—including ChatGPT-4, Bing, and Gemini—in a comparative evaluation using BLEU, precision, recall, and F1 metrics, achieving an F1 score of 0.8689. The approach demonstrates high domain adaptability and reproducibility. All datasets and codes are openly released to facilitate application in other metallogenic belts. This work illustrates the potential of LLM-based knowledge engineering to support digital geoscientific research and smart mining.

21 July 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LNLujia Niu
Lujia Niu
YZYongzhang Zhou
Yongzhang Zhou
BZBiaobiao Zhu
Biaobiao Zhu
CSChengyue Shi
Chengyue Shi
YZYuqing Zhang
Yuqing Zhang
Continental-scale assessment of soil heavy metal contamination is complicated by the contrasting environmental behaviour of individual metals and by spatial autocorrelation, which can lead to overly optimistic model evaluation. This study assessed As, Cu, Hg and Cd contamination in European topsoils using a harmonized 500 m dataset integrating soil properties, hydroclimatic and topographic conditions, socioeconomic indicators and anthropogenic emission sources. A graph-based mixture-of-experts (GMoE) model was used to jointly learn shared and metal-specific contamination patterns, while spatial-block hold-out testing evaluated its transferability to geographically independent regions. The model achieved the highest accuracy and macro-F1 among the evaluated approaches for all four metals, with the clearest improvements for As and Cu. Accuracy reached 76.96% for As and 75.43% for Cu, exceeding multi-gate mixture-of-experts (MMoE) by 4.79 and 2.86 percentage points, respectively. Routing diagnostics indicated broad but differentiated expert participation rather than reliance on a single expert. Spatial attribution further revealed that soil properties and hydroclimatic conditions strongly influenced contamination heterogeneity, whereas anthropogenic-source signals were more evident for As and Cd. These findings show that European topsoil contamination reflects both environmental filtering and source-related inputs, and demonstrate the value of combining spatially transferable multi-metal prediction with driver attribution for large-scale soil contamination assessment.

2 August 2026 in Minerals
Verified
Journal Article
Open access
PDF file
YZYuqing Zhang
Yuqing Zhang
Yongzhang ZhouYongzhang Zhou
Yongzhang Zhou
LNLujia Niu
Lujia Niu
XYXinhui Yu
Xinhui Yu
BZBiaobiao Zhu
Biaobiao Zhu
To address the difficulty of synergizing multi-source spatial data with geological text and the limited spatial reasoning of large language models (LLMs), this paper proposes an intention-driven hybrid semantic–spatial retrieval–augmented generation (RAG) method and a corresponding GIS visualization system. The method uses intent routing to direct queries to spatial parsing or text retrieval, extracts target entities, attribute constraints, and spatial relations from natural language via an LLM, and dynamically generates parameterized PostGIS (PostgreSQL Spatial Extension) queries through a rule-based parser, achieving deep coupling of semantic understanding and spatial computation. A spatial proximity verification module computes the minimum distances between target and reference entities, producing a verifiable target-reference list that provides precise spatial support for answers. The system implements a multi-source dynamic data management mechanism supporting unified heterogeneous data import, ArcGIS layer style parsing, adaptive point visualization, and user-defined mappings from data tables to geological entity types. It further integrates prospectivity prediction, geochemical association analysis, and intelligent QA into an end-to-end interactive GIS environment. Experimental results show that semantic filtering raises Precision@5 (Precision at rank 5) from 0.171 to 0.829, rule-based ranking improves NDCG@5 (Normalized Discounted Cumulative Gain at rank 5) by about 16%, and the spatial proximity verification module increases the spatial citation rate (distance coverage ratio) from 24.2% to 47.8% when computed over the 17 spatial-relation queries for which distance citations are applicable. Adding textual knowledge further boosts answer relevance to 0.863 while maintaining a comparable spatial citation rate (47.2% vs. 47.8%). To mitigate potential self-preference bias in the LLM-as-Judge setup, an independent evaluation using DeepSeek-V4-Flash was conducted, yielding high inter-evaluator agreement (Pearson r = 0.951 for faithfulness, 0.988 for relevance). These results suggest the method’s potential for query understanding, ranking optimization, and spatial interpretability, while also highlighting the need for larger-scale benchmarks and blinded expert evaluation.