从地理规律到地理空间人工智能

doi:10.11947/j.AGCS.2022.20220125

测绘学报 ›› 2022, Vol. 51 ›› Issue (6): 1062-1069.doi: 10.11947/j.AGCS.2022.20220125

从地理规律到地理空间人工智能

刘瑜^1,2, 郭浩¹, 李海峰³, 董卫华⁴, 裴韬⁵

1. 北京大学遥感与地理信息系统研究所, 北京 100871;
2. 北京大学人工智能研究院, 北京 100871;
3. 中南大学地球科学与信息物理学院, 湖南长沙 410083;
4. 北京师范大学地理科学学部, 北京 100875;
5. 中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室, 北京 100101

收稿日期:2022-02-24 修回日期:2022-04-11 发布日期:2022-07-02
作者简介:刘瑜(1971-),男,博士,教授,博士生导师,主要从事地理信息科学与地理大数据理论方法研究。E-mail:liuyu@urban.pku.edu.cn
基金资助:
国家自然科学基金(41830645;41971331)

A note on GeoAI from the perspective of geographical laws

LIU Yu^1,2, GUO Hao¹, LI Haifeng³, DONG Weihua⁴, PEI Tao⁵

1. Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China;
2. Institute for Artificial Intelligence, Peking University, Beijing 100871, China;
3. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China;
4. Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;
5. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China

Received:2022-02-24 Revised:2022-04-11 Published:2022-07-02
Supported by:
The National Natural Science Foundation of China(Nos. 41830645;41971331)

摘要/Abstract

摘要： 近年来,人工智能技术快速发展,影响了很多学科的研究范式。对于地理学而言,这种趋势也不例外。从知识发现的角度,地理学研究主要有两个任务,即揭示未知的具体事实和发现一般性的规律机理。在这两个方面,人工智能技术可帮助地理学家发现知识甚至自动提取知识。相对于地球科学其他学科,地理学自动提取知识的任务更为凸显。但是在寻求地理规律的过程中,需要处理一般性和地理异质性之间的权衡,其核心可以表述为人工智能学习过程中的基础问题:泛化及可解释性问题。因此,二者存在内在的逻辑一致性,积极引入人工智能技术有助于强化地理学的学科基础。本文通过实例给出了人工智能用于地理规律发现的一个简单框架,指出了未来地理空间人工智能发展的方向,以及地理信息科学在机制、模型、方法及应用方面潜在的新任务。

关键词: 地理异质性, 地理规律性, 地理空间人工智能, 地理信息科学

Abstract: Recently, the rapid development of artificial intelligence has reshaped the research paradigm of many disciplines. Regarding geography, this trend is no exception. From the perspective of knowledge discovery, geographical research has two major tasks: revealing big unknowns and discovering laws. Artificial intelligence helps geographers discover knowledge or even automatically extract knowledge from these two aspects. Compared with other geoscience disciplines, geography focuses more on discovering "universal" laws. However, in the process of seeking geographical laws, we need to deal with the trade-off between universality and geographical heterogeneity, the core in which can be expressed as the theoretical foundation in artificial intelligence learning: generalization and interpretability. Therefore, there is an inherent logical consistency between the two disciplines. Introducing artificial intelligence to geographical studies will help to strengthen the disciplinary basis. This paper gives an example framework for artificial intelligence to discover geographical laws, and points out the future directions of geospatial artificial intelligence and geographic information science.

Key words: geographical heterogeneity, geographical law, geospatial artificial intelligence, geographic information science

中图分类号:

P208

刘瑜, 郭浩, 李海峰, 董卫华, 裴韬. 从地理规律到地理空间人工智能[J]. 测绘学报, 2022, 51(6): 1062-1069.

LIU Yu, GUO Hao, LI Haifeng, DONG Weihua, PEI Tao. A note on GeoAI from the perspective of geographical laws[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1062-1069.

参考文献

[1] 白光润. 地理学的哲学贫困[J]. 地理学报, 1995, 50(3):279-287. BAI Guangrun. The philosophical predicament in the development of geography[J]. Acta Geographica Sinica, 1995, 50(3):279-287.
[2] HARTSHORNE R. The nature of geography:a critical survey of current thought in the light of the past[J]. Annals of the Association of American Geographers, 1939, 29(3):173.
[3] KEDRON P, HOLLER J. Replication and the search for the laws in the geographic sciences[J]. Annals of GIS, 2022, 28(1):45-56.
[4] BRUNSDON C. Quantitative methods Ⅰ:reproducible research and quantitative geography[J]. Progress in Human Geography, 2016, 40(5):687-696.
[5] BRUNSDON C. Quantitative methods Ⅱ:issues of inference in quantitative human geography[J]. Progress in Human Geography, 2017, 41(4):512-523.
[6] SUI D, KEDRON P. Reproducibility and replicability in the context of the contested identities of geography[J]. Annals of the American Association of Geographers, 2021, 111(5):1275-1283.
[7] ZHU Axing, LU Guonian, LIU Jing, et al. Spatial prediction based on Third Law of Geography[J]. Annals of GIS, 2018, 24(4):225-240.
[8] GOODCHILD M F. GIScience, geography, form, and process[J]. Annals of the Association of American Geographers, 2004, 94(4):709-714.
[9] 叶超, 蔡运龙. 地理学方法论变革的案例剖析:重新审视《地理学中的例外论》之争[J]. 地理学报, 2009, 64(9):1134-1142. YE Chao, CAI Yunlong. re-evaluating schaefer and his criticizing on exceptionalism in geography:a case study on the innovation of methodology[J]. Acta Geographica Sinica, 2009, 64(9):1134-1142.
[10] TAYLOR P J, JOHNSTON R J. Geographic information systems and geography[M]//Ground truth:the social implications of geographic information systems. New York:Guilford, 1995:51-67.
[11] MATHERON G. Principles of geostatistics[J]. Economic Geology, 1963, 58(8):1246-1266.
[12] FOTHERINGHAM A S, BRUNSDON C, CHARLTON M. Geographically weighted regression:the analysis of spatially varying relationships[M]. Hoboken:Wiley, 2002.
[13] GOODCHILD M F. The validity and usefulness of laws in geographic information science and geography[J]. Annals of the Association of American Geographers, 2004, 94(2):300-303.
[14] O'SULLIVAN D, MANSON S M. Do physicists have geography envy? and what can geographers learn from it?[J]. Annals of the Association of American Geographers, 2015, 105(4):704-722.
[15] WOLF L J, FOX S, HARRIS R, et al. Quantitative geography Ⅲ:future challenges and challenging futures[J]. Progress in Human Geography, 2021, 45(3):596-608.
[16] OPENSHAW S. The modifiable areal unit problem[M]. Norwick:Geo Books, 1983.
[17] KWAN M P. The uncertain geographic context problem[J]. Annals of the Association of American Geographers, 2012, 102(5):958-968.
[18] GOODCHILD M F, LI Wenwen. Replication across space and time must be weak in the social and environmental sciences[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(35):e2015759118.
[19] 高松. 地理空间人工智能的近期研究总结与思考[J]. 武汉大学学报(信息科学版), 2020, 45(12):1865-1874. GAO Song. A review of recent researches and reflections on geospatial artificial intelligence[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12):1865-1874.
[20] 张永生, 张振超, 童晓冲, 等. 地理空间智能研究进展和面临的若干挑战[J]. 测绘学报, 2021, 50(9):1137-1146. ZHANG Yongsheng, ZHANG Zhenchao, TONG Xiaochong, et al. Progress and challenges of geospatial artificial intelligence[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9):1137-1146.
[21] 陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005. CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping:fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005.
[22] DUQUE J C, RAMOS R, SURIÑACH J. Supervised regionalization methods:a survey[J]. International Regional Science Review, 2007, 30(3):195-220.
[23] TONG Daoqin, MURRAY A T. Spatial optimization in geography[J]. Annals of the Association of American Geographers, 2012, 102(6):1290-1309.
[24] LIU Yu. Core or edge? Revisiting GIScience from the geography-discipline perspective[J]. Science China Earth Sciences, 2022, 65(2):387-390.
[25] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE, 2016:770-778.
[26] SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529:484-489.
[27] BROWN T B, MANN B, RYDER N, et al. Language models are few-shot learners[C]//Proceedings of the 34th Conference on Neural Information Processing Systems.[S.l.]:CCFA, 2020.
[28] FODOR J A, PYLYSHYN Z W. Connectionism and cognitive architecture:a critical analysis[J]. Cognition, 1988, 28(1/2):3-71.
[29] KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6):422-440.
[30] GRAVES A, WAYNE G, REYNOLDS M, et al. Hybrid computing using a neural network with dynamic external memory[J]. Nature, 2016, 538:471-476.
[31] REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566:195-204.

从地理规律到地理空间人工智能

A note on GeoAI from the perspective of geographical laws

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	艾廷华, 张翔. 地理信息科学中尺度概念的诠释与表达[J]. 测绘学报, 2022, 51(7): 1640-1652.
[2]	慎利, 徐柱, 李志林, 刘万增, 崔秉良. 从地理信息服务到地理知识服务:基本问题与发展路径[J]. 测绘学报, 2021, 50(9): 1194-1202.