“大智移云 + 遥感”赋能遥感科学与技术专业研究生创新人才培养模式研究

Research on the Innovation Talent Cultivation Model for Postgraduates of Remote Sensing Science and Technology Empowered by “Artificial Intelligence, Cloud Tech and Remote Sensing”

摘要: 针对时空智能背景下，河北地质大学遥感科学与技术专业特色不足，跨多个学科，学习知识点复杂、学生个性化学习需求不同及学情评价精度不足等多个问题，本研究集成现有国家/省级教学与科研平台，提升教学环境，优化教学资源，构建“理论–技术–应用”三位一体的培养体系，创建“空间理论–地理智能–行业应用”三级课程体系，建立“双导师 + 企业命题”的培养模式。同时基于生成式AI结构化特性的学科知识图谱构建与教学资料重组，搭建“筑根基–厚地理–精测绘–强遥感–融智能–通开发–用地经”的阶梯式AI + 时空智能课程链，嵌入“机器学习理论–深度建模框架–行业开发实践”的人工智能理论体系。构建智慧课程新生态，实现个性互动深融合，对学生学习全过程进行跟踪监测，因材施教，最终实现“一生一册”的个性化教学，提升遥感科学与技术研究生培养质量，形成可推广的“大智移云 + 遥感 + 地经渗透”教育模式。

Abstract: In the context of spatiotemporal intelligence, the remote sensing science and technology major at Hebei GEO University faces several challenges, including a lack of distinctive program characteristics, highly interdisciplinary content, complex knowledge structures, diverse individual learning needs, and insufficient precision in learning assessment. To address these issues, this project integrates existing national and provincial teaching and research platforms to enhance the teaching environment and optimize educational resources. We aim to construct a tripartite cultivation framework encompassing “Theory-Technology-Application”. We also establish a three-tier curriculum system structured around “Spatial Theory-Geographic Intelligence-Industry Application”, and implement a “Dual-Supervisor plus Enterprise-Proposed Projects” training model. Furthermore, by utilizing the structured knowledge representation capabilities of generative AI, we will develop a disciplinary knowledge graph and reorganize teaching materials to form a stepwise curriculum chain from fundamentals to AI and geo-economic applications. Through these efforts, a new smart education ecosystem will be established, facilitating personalized interaction and deep integration. The entire learning process will be tracked and monitored, enabling truly individualized instruction through a “one plan per student” approach. Ultimately, this model aims to comprehensively enhance the quality of graduate education in remote sensing science and technology, forming a replicable educational framework characterized by the integration of AI, remote sensing and geo-economics.