{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T02:55:06Z","timestamp":1777949706181,"version":"3.51.4"},"reference-count":35,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Fund of Geological Data Intelligent Application Technology Innovation Center of Jiangsu Provincial Department of Natural Resources","award":["GDIATIC-XM-202502"],"award-info":[{"award-number":["GDIATIC-XM-202502"]}]},{"name":"Joint Fund of Collaborative Innovation Center of Geo-Information Technology for Smart Central Plains","award":["231202"],"award-info":[{"award-number":["231202"]}]},{"name":"Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education","award":["GLAB2024ZR08"],"award-info":[{"award-number":["GLAB2024ZR08"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>The scientific data of the Earth surface system is characterized by multi-source heterogeneity and dynamic correlation, so constructing an efficient data association network and enabling intelligent knowledge services is a hot topic. Nevertheless, confronted with the existing challenges of onerous data acquisition, inadequate precision of data recommendation, excessive time and labor consumption, as well as insufficient semantic reasoning in intelligent question-and-answer (Q&amp;A) systems, we propose an intelligent framework that integrates dynamic optimization and retrieval-augmented generation (RAG) technology to address the problems of strong subjectivity in the setting of edge weight thresholds in association networks and insufficient semantic inference in intelligent Q&amp;A. First, a multidimensional association network is constructed based on metadata features, redundant edge pruning is achieved through dynamic threshold analysis, and key nodes are identified by combining complex network centrality theory to optimize network structure and storage efficiency. Secondly, the RAG-based intelligent Q&amp;A model is designed to transform the association triples into a paragraph-based knowledge base, generate a domain Q&amp;A dataset using a large language model GPT-4o, and fine-tune the word embedding model to improve the semantic representation accuracy. Experiments show that the number of network edges is reduced by about 70% after optimization, and the node importance analysis accurately identifies key data nodes; the fine-tuned model improves each index by 6% on average in the retrieval task, and the Q&amp;A system significantly outperforms the traditional method in terms of indexes such as relevance and completeness. This study provides innovative solutions for the intelligent service of scientific data in Earth surface systems and promotes the deep integration of association networks and generative AI.<\/jats:p>","DOI":"10.3390\/ijgi15050199","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:15:02Z","timestamp":1777853702000},"page":"199","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval-Augmented Generation-Based Earth Surface System Association Network Optimization and Data Recommendation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2377-1241","authenticated-orcid":false,"given":"Jiangbing","family":"Sun","sequence":"first","affiliation":[{"name":"School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China"},{"name":"Geological Data Archives of Jiangsu Province, Nanjing 210012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Geological Data Archives of Jiangsu Province, Nanjing 210012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longxing","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer and Science, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiali","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Science, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Tian","sequence":"additional","affiliation":[{"name":"Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Geological Data Archives of Jiangsu Province, Nanjing 210012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liufeng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer and Science, China University of Geosciences, Wuhan 430074, China"},{"name":"Key Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinjun","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer and Science, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,2]]},"reference":[{"key":"ref_1","first-page":"1180","article-title":"Construction of Geospatial Metadata Association Network","volume":"36","author":"Zhao","year":"2016","journal-title":"Sci. Geogr. Sin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1080\/13658816.2017.1300805","article-title":"A similarity-based automatic data recommendation approach for geographic models","volume":"31","author":"Zhu","year":"2017","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1080\/17538947.2016.1266041","article-title":"Multidimensional and quantitative interlinking approach for Linked Geospatial Data","volume":"10","author":"Zhu","year":"2017","journal-title":"Int. J. Digit. Earth"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s10032-024-00508-4","article-title":"Document image layout detection from scientific literature using combined ConvNext and cascade mask RCNN networks","volume":"28","author":"Qiu","year":"2024","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, C., Shi, W., and Lv, H. (2023). Construction of remote sensing indices knowledge graph (RSIKG) based on semantic hierarchical graph. Remote Sens., 16.","DOI":"10.3390\/rs16010158"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2522388","DOI":"10.1080\/17538947.2025.2522388","article-title":"A construction method of a multidimensional and multilingual association network for earth surface system science data","volume":"18","author":"Qiu","year":"2025","journal-title":"Int. J. Digit. Earth"},{"key":"ref_7","first-page":"588","article-title":"Geological map-oriented knowledge graph construction and intelligent Q&A application","volume":"59","author":"Duan","year":"2024","journal-title":"Chin. J. Geol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ye, X., Yavuz, S., Hashimoto, K., Zhou, Y., and Xiong, C. (2021). Rng-kbqa: Generation augmented iterative ranking for knowledge base question answering. arXiv.","DOI":"10.18653\/v1\/2022.acl-long.417"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Huang, Q., Tao, Y., Ding, S., Zhang, H., Liu, J., and Wang, X. (2023, January 6\u20138). An Intelligent Q&A Module for Tea Diseases and Pests Based on Automatic Knowledge Graph Construction. Proceedings of the 2023 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), Trento, Italy.","DOI":"10.1109\/MetroAgriFor58484.2023.10424245"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, Z., Xu, Q., Zhang, W., Liu, Y., Chen, M., and Wang, L. (2021, January 5\u20137). An Approach and Implementation for Knowledge Graph Construction and Q&A System. Proceedings of the 2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Taiyuan, China.","DOI":"10.1109\/MLBDBI54094.2021.00086"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lin, C., Chen, S., Yang, X., Liu, Z., Huang, Y., and Zhao, Q. (2021, January 10\u201312). Research and application of knowledge graph technology for intelligent question answering. Proceedings of the 2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), Xi\u2019an, China.","DOI":"10.1109\/PAAP54281.2021.9720306"},{"key":"ref_12","first-page":"104712","article-title":"GeoGraphRAG: A graph-based retrieval-augmented generation approach for empowering large language models in automated geospatial modeling","volume":"142","author":"Liang","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lin, J., Dai, L., Han, R., Sui, Y., Wang, R., Sun, X., Wu, Q., Feng, M., Liu, H., and Xiong, H. (2025, January 3\u20137). Scirgen: Synthesize realistic and large-scale rag dataset for scientific research. Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto, ON, Canada.","DOI":"10.1145\/3711896.3737432"},{"key":"ref_14","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Huang, F., Deng, Y., Zhang, C., Guo, M., Zhan, K., Sun, S., Jiang, J., Sun, Z., and Wu, X. (2023, January 1\u20134). KOSA: KO enhanced salary analytics based on knowledge graph and LLM capabilities. Proceedings of the 2023 IEEE International Conference on Data Mining Workshops (ICDMW), Shanghai, China.","DOI":"10.1109\/ICDMW60847.2023.00071"},{"key":"ref_16","first-page":"478","article-title":"Semantic-driven construction of geographic entity association network and knowledge service","volume":"52","author":"Ling","year":"2023","journal-title":"Acta Geod. Cartogr. Sin."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"162638","DOI":"10.1109\/ACCESS.2024.3485877","article-title":"ChatTf: A Knowledge Graph-Enhanced Intelligent Q&A System for Mitigating Factuality Hallucinations in Traditional Folklore","volume":"12","author":"Xu","year":"2024","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Soman, K., Rose, P.W., Morris, J.H., Akbas, R.E., Smith, B., Peetoom, B., Villouta-Reyes, C., Cerono, G., Shi, Y., and Rizk-Jackson, A. (2024). Biomedical knowledge graph-optimized prompt generation for large language models. Bioinformatics, 40.","DOI":"10.1093\/bioinformatics\/btae560"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ravi, R., Ginde, G., and Rokne, J. (2024). PRAGyan\u2014Connecting the Dots in Tweets. arXiv.","DOI":"10.1007\/978-3-031-78548-1_25"},{"key":"ref_20","first-page":"107","article-title":"Design of University Research Management Question Answering System Integrating Knowledge Graph and Large Language Models","volume":"19","author":"Wang","year":"2025","journal-title":"J. Front. Comput. Sci. Technol."},{"key":"ref_21","first-page":"87","article-title":"A knowledge graph-based retrieval-augmented generation intelligence question answering technology","volume":"52","author":"Zhou","year":"2025","journal-title":"Comput. Sci."},{"key":"ref_22","unstructured":"Zhao, H.W. (2016). Construction and Application Research of Semantic Association Network for Geospatial Metadata. [Ph.D. Thesis, University of Chinese Academy of Sciences]."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Luo, Y. (2017, January 17\u201318). Degree centrality, betweenness centrality, and closeness centrality in social network. Proceedings of the 2017 2nd International Conference on Modelling, Simulation and Applied Mathematics (MSAM2017), Bangkok, Thailand.","DOI":"10.2991\/msam-17.2017.68"},{"key":"ref_24","first-page":"141","article-title":"Improved degree centrality in directed weighted networks","volume":"40","author":"Zhao","year":"2020","journal-title":"J. Comput. Appl."},{"key":"ref_25","first-page":"501","article-title":"Research and Implementation of Geospatial Data Similarity Calculation Method","volume":"6","author":"Dai","year":"2022","journal-title":"J. Glob. Change Data"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106070","DOI":"10.1016\/j.envsoft.2024.106070","article-title":"An interoperable software system to store, associate, visualize, and publish global open science data of earth surface system","volume":"178","author":"Qiu","year":"2024","journal-title":"Environ. Model. Softw."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Qiu, Q., Liu, J., Hao, M., Li, W., Wang, Y., Tao, L., Wu, L., and Xie, Z. (2025). DCKH-CNN: A Multimetric Graph-Based Convolutional Neural Network for Identifying Key Influential Nodes in Earth Surface Data Linked Networks. Trans. GIS, 29.","DOI":"10.1111\/tgis.70016"},{"key":"ref_28","first-page":"111","article-title":"Data Thesaurus of Earth Surface System Sciences","volume":"8","author":"Chen","year":"2024","journal-title":"J. Glob. Change Data Discov."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kaplan, A., Sayan, I.U., \u015eahan, H., Begen, E., and Bayrak, A.T. (2024, January 15\u201318). Response Performance Evaluations of ChatGPT Models on Large Language Model Frameworks. Proceedings of the 2024 32nd Signal Processing and Communications Applications Conference (SIU), Bodrum, T\u00fcrkiye.","DOI":"10.1109\/SIU61531.2024.10601055"},{"key":"ref_30","unstructured":"Wang, Y.S.Q.H.S. (2025, October 09). M3E: Moka Massive Mixed Embedding Model. Available online: https:\/\/huggingface.co\/moka-ai\/m3e-large."},{"key":"ref_31","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., and Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., and Liu, Z. (2024). Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref_33","unstructured":"Team GLM, Zeng, A., Xu, B., Wang, B., Zhang, C., Yin, D., Zhang, D., Rojas, D., Feng, G., and Zhao, H. (2024). Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mattmann, C.A., Downs, R.R., Ramirez, P.M., Goodale, C., and Hart, A.F. (2012, January 8\u201310). Developing an open source strategy for NASA earth science data systems. Proceedings of the 2012 IEEE 13th International Conference on Information Reuse & Integration (IRI), Las Vegas, NV, USA.","DOI":"10.1109\/IRI.2012.6303076"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.giq.2013.10.011","article-title":"Benchmarking open government: An open data perspective","volume":"31","author":"Stoimenov","year":"2014","journal-title":"Gov. Inf. Q."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/5\/199\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T04:16:17Z","timestamp":1777868177000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/5\/199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,2]]},"references-count":35,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["ijgi15050199"],"URL":"https:\/\/doi.org\/10.3390\/ijgi15050199","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,2]]}}}