地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (2): 299-309.doi: 10.12082/dqxxkx.2022.210079

• 地球信息技术在国土空间规划中的应用 • 上一篇    下一篇

多源大数据支持的土地储备智能决策模型集研究

李军1(), 刘举庆1,*(), 游林2, 董恒3, 俞艳3, 张晓盼3, 钟文军4, 杨典华5   

  1. 1.中国矿业大学(北京)地球科学与测绘工程学院,北京 100083
    2.浙江时空智子大数据有限公司,宁波 315101
    3.武汉理工大学资源与环境工程学院,武汉 430070
    4.宁波市自然资源和规划大数据中心,宁波 315042
    5.京师天启(北京)科技有限公司,北京 100086
  • 收稿日期:2021-02-18 修回日期:2021-03-28 出版日期:2022-02-25 发布日期:2022-04-25
  • 通讯作者: *刘举庆(1995— ),男,山东临沂人,博士研究生,主要研究方向为地理大数据分析与挖掘。E-mail: liujvq@163.com
  • 作者简介:李 军(1987— ),男,湖北汉川人,副教授,主要从事地理信息科学理论与方法应用研究。E-mail: junli@cumtb.edu.cn
  • 基金资助:
    国家自然科学基金项目(41971355);国家重点研发计划项目(2018YFB0505405);中国矿业大学(北京)越崎青年学者资助计划;中央高校基本科研业务费专项资金资助(2015QD01)

An Intelligent Decision Model Set for Land Reserve based on Multi-source Big Data

LI Jun1(), LIU Juqing1,*(), YOU Lin2, DONG Heng3, YU Yan3, ZHANG Xiaopan3, ZHONG Wenjun4, YANG Dianhua5   

  1. 1. College of Geoscience and Surveying Engineering, China University of Mining & Technology, Beijing 100083, China
    2. Zhejiang Space-time Sophon Big Data Co., Ltd., Ningbo 315101, China
    3. School of Resource and Environment Engineering, Wuhan University of Technology, Wuhan 430070, China
    4. Ningbo Natural Resources and Planning Big Data Center, Ningbo 315042, China
    5. Image Sky Beijing technology Co., Ltd., Beijing 100086, China
  • Received:2021-02-18 Revised:2021-03-28 Online:2022-02-25 Published:2022-04-25
  • Supported by:
    National Natural Science Foundation of China(41971355);National Key Research and Development Program of China(2018YFB0505405);the Yueqi Young Scholar Project of China University of Mining and Technology at Beijing;the Fundamental Research Funds for the Central Universities(2015QD01)

摘要:

伴随着城镇化的快速推进,城乡建设用地资源日益紧张,但目前土地储备决策缺乏精准科学依据,无法有效地进行资源配置和宏观调控。针对此问题,本文深入剖析土地储备基本业务与决策环节,研究了一套面向土地储备的智能决策模型集,包括存量土地监测模型、收储成本预测模型、出让价格预测模型、储备平衡分析模型、相似地块分析模型、开发时序分析模型及病态地块识别模型,旨在将土地储备决策环节科学化、定量化和模型化,并重点为土地储备总量、效益、规模、结构、布局、时序的统筹安排提供建议。另外,该模型集具有体系化、高效灵活、智能化的特点,能够服务于储备业务全链条,满足即时决策应用需求和实现模型自主更新与进化,保证模型的时效性。最后,该模型集已经工程化应用于宁波市土地储备智能决策支持平台,实践验证了以上决策模型具有较高的准确度和实用性,表明模型集能够为土地储备的科学决策提供理论依据,有利于土地资源的集约利用和高效配置。

关键词: 国土空间规划, 土地储备, 多源大数据, 数据挖掘, 人工智能, 智能决策, 综合评价, 定量预测

Abstract:

With the rapid development of urbanization, urban construction land is becoming increasingly scarce. Therefore, as a macro-regulation policy for the intensive utilization and optimal allocation of land resources, land reserve is playing an increasingly important role. However, at present, land reserve decision-making lacks scientific basis and cannot effectively carry out resource allocation. In order to solve this problem, this paper puts forward seven intelligent decision-making models for land reserve through in-depth analysis of the basic services and decision-making processes of land reserves. The models are listed below. Firstly, Stock Land Monitoring Model based on the comprehensive quantitative evaluation method, which can dynamically monitor and discover the city stock land and then make recommendations for land reserve objects. Secondly, Land Reserve Cost Prediction Model based on the market comparison method, which can carry out a large range and efficiently predict the cost of stock land. Thirdly, Land Sale Price Prediction Model based on the Support Vector Machine (SVM), which can predict the reserve income of the land to be sold. Fourthly, Land Reserve Balance Analysis Model based on the gray forecast model, which can predict the amount of land reserve to promote coordinated regional development. Fifthly, Similar Land Query Model based on the comprehensive quantitative evaluation method, which can promote large-scale land development to form an agglomeration effect. Sixthly, Development Sequence Analysis Model based on the comprehensive quantitative evaluation method, which can optimize the spatial structure and formulate a reasonable development sequence to promote the continuous rolling of funds. Seventhly, Abnormal Land Identification Model based on spatial overlay analysis, which can improve the detection efficiency of various problematic plots. The purpose of this model set is to make the land reserve decision-making process scientific, quantitative, and model-based, which focuses on providing instructions for the overall arrangement of total land reserve, benefit, scale, structure, layout, and time sequence. In addition, through theoretical analysis and practical verification, we found that the model set has the characteristics of systematization, high efficiency, flexibility, and intelligence. It can serve the entire chain of land reserve service, meet the needs of real-time decision-making applications, and realize the independent update and evolution to ensure the timeliness of model computation. Finally, the model set has been engineered and applied to the Ningbo Land Reserve Intelligent Decision Support Platform. The effectiveness and practicality of the above decision-making models have been verified by simulating the entire land reserve decision-making processes based on this platform, indicating that the model set can provide a theoretical basis for the scientific decision-making of land reserves.

Key words: territorial spatial planning, land reserve, multi-source big data, data mining, artificial intelligence, intelligent decision, comprehensive evaluation, quantitative prediction