数据与计算发展前沿 ›› 2020, Vol. 2 ›› Issue (3): 137-145.

doi: 10.11871/jfdc.issn.2096-742X.2020.03.012

所属专题： 下一代互联网络技术与应用

• 技术与应用 • 上一篇    

土地利用演变过程的人工智能建模

杨健鹏1,2(),罗泽1,*(),张应明3()   

  1. 1. 中国科学院计算机网络信息中心, 北京 100190
    2. 中国科学院大学, 北京 100049
    3. 广东车八岭国家级自然保护区管理局,广东 始兴 512526
  • 收稿日期:2020-03-13 出版日期:2020-06-20 发布日期:2020-08-19
  • 通讯作者: 罗泽
  • 作者简介:杨健鹏,中国科学院计算机网络信息中心,中国科学院大学,在读硕士研究生,主要研究方向为机器学习与数据挖掘。
    在本文主要负责模型的构建和模拟设计实现过程。
    Yang Jianpeng is a master student at Computer Network Information Center of the Chinese Academy of Sciences /University of Chinese Academy of Sciences. His main research directions are machine learning and data mining.
    In this paper, he is mainly responsible for model building and simulation process design.
    E-mail: yangjianpeng@cnic.cn|罗泽,中国科学院计算机网络信息中心,研究员,博士生导师,主要研究方向为海量数据分布处理理论和方法,数据挖掘和机器学习理论、方法和应用。
    在本文主要负责模型构建原理和研究方法。
    Luo Ze, Ph.D. Supervisor, is a research fellow at Computer Network Information Center, Chinese Academy of Sciences, Researcher. The main research directions are the theory and method of massive data distribution processing, data mining, and machine learning theory, method and application.
    In this paper, he is mainly responsible for the model construction principles and research methods.
    E-mail: luoze@cnic.cn|张应明,广东车八岭国家级自然保护区管理局,科长,林业工程师,主要从事自然保护地管理研究。
    在本文主要负责保护区的研究方向以及研究内容。
    Zhang Yingming is the Section chief and Forestry engineer at Guangdong Chebaling National Nature Reserve Administration. He is mainly engaged in the management of nature reserves.
    In this paper, I am mainly responsible for the research direction and content of the reserve.
    E-mail: cblbhq@163.com
  • 基金资助:
    广东省乡村振兴战略专项 《车八岭自然保护区科研监测信息化体系能力建设项目》;国家科技部国家科技基础条件平台项目(DKA2019-12-02-18)

Artificial Intelligence Modeling of Land Use Evolution Process

Yang Jianpeng1,2(),Luo Ze1,*(),Zhang Yingming3()   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
    3. Guangdong Chebaling National Nature Reserve Administration, Shixing, Guangdong 512526, China
  • Received:2020-03-13 Online:2020-06-20 Published:2020-08-19
  • Contact: Luo Ze

RichHTML

10

PDF

577

摘要：

【目的】土地是人类赖以生存和发展的基础,土地的变化情况对于人类的经济、政治、环境等有诸多影响。为了准确把握土地利用变化的规律以及演变过程,给土地利用演变研究提供方法。【方法】本文以广东车八岭国家自然保护区为例,采用基于LSTM的循环神经网络与元胞自动机的耦合模型对保护区2005—2017年的土地利用变化进行训练和模拟来得到土地利用的动态演变结果。模型主要包括数据预处理、循环神经网络、元胞自动机以及模型校验等模块。【结果】实验综合考虑自然因子、社会因素、距离因子等14个空间变量作为模型的输入变量,通过设置不同的阈值和随机变量进行校验和模拟。最后将模拟结果与实际土地利用对比发现无论是模拟精度还是Kappa系数都高于传统模型的模拟结果。【局限】实验中空间变量的个数和种类还较单一,还需进一步增加相关变量和驱动因子。【结论】采用基于LSTM的RNN-CA模型提高模拟的效果,可以满足土地利用变化的模拟研究,为土地利用变化的研究提供借鉴。

关键词: 循环神经网络（RNN）, 元胞自动机（CA）, 土地利用, 长短期记忆网络（LSTM）

Abstract:

[Objective] Land is the basis for human survival and development. It is of great significance to study how the land use changes the human economy, politics and the environment. In order to provide references for land use evolution research and understand the research status on land use clearly and thoroughly, a new model is proposed in this paper. [Methods] This paper takes the Chebaling Ecological Reserve in Guangdong Province as the study case for model verification in land use simulations. The model combines the Recurrent Neural Network based on LSTM and Cellular Automata to study the land use change data in 2005-2017. Spatial analysis of Chebaling Ecological Reserve is based on massive vector and raster data are made with the aid of ArcGIS 10.2. Driving force mechanism as studied by constructing the fourteen spatial variables which include natural factors, social factors, distance factors and so on. In addition, the experiments are conducted by different threshold settings and random disturbance adoptions for better simulation improvements in terms of accuracy. [Results] The simulated results are shown as follows: the improved model has higher precision and Kappa coefficient than traditional models. Besides, the threshold and random disturbance can be set conveniently by the new model. [Limitations] In the experiment, the number and types of spatial variables are relatively insufficient, and more relevant variables and driving factors need to be considered in later studies.[Conclusions] The proposed LSTM-based RNN-CA model verified by the improved simulation results satisfies the requirements and provides references for land use evolution researches.

Key words: Recurrent Neural Network(RNN), Cellular Automaton(CA), land use, Long Short-Term Memory network(LSTM)