人工智能和专家系统在地学中的应用综述

本文所指的地学是以地理学为主包括地质、气象、水文等以地球表层为研究对象的学科,其研究对象具有多因素相互作用的复杂性。本文在回顾了地理学／地学研究方法发展过程的基础上,分析了人工智能、专家系统、地理信息系统的相互关系,综述了专家系统在地学中的应用实例,最后分析了地学专家系统的发展趋势。     

Prediction of Rock Size Distribution in Mine Bench Blasting Using a Novel Ant Colony Optimization-Based Boosted Regression Tree Technique

Natural Resources Research - In this paper, we used artificial intelligence (AI) techniques to investigate the relation between the rock size distribution (RSD) and blasting parameters for rock...     

Prediction of Blast-induced Air Over-pressure in Open-Pit Mine: Assessment of Different Artificial Intelligence Techniques

Air over-pressure (AOp) is one of the products of blasting operations for rock fragmentation in open-pit mines. It can cause structural vibration, smash glass doors, adversely affect the surrounding environment, and even be fatal to humans. To assess its dangerous effects, seven artificial intelligence (AI) methods for predicting specific blast-induced AOp have been applied and compared in this study. The seven methods include random forest, support vector regression, Gaussian process, Bayesian additive regression trees, boosted regression trees, k-nearest neighbors, and artificial neural network (ANN). An empirical technique was also used to compare with AI models. The degree of complexity and the performance of the models were compared with each other to find the optimal model for predicting blast-induced AOp. The Deo Nai open-pit coal mine (Vietnam) was selected as a case study where 113 blasting events have been recorded. Indicators used for evaluating model performances include the root-mean-square error (RMSE), determination coefficient (R²), and mean absolute error (MAE). The results indicate that AI techniques provide better performance than the empirical method. Although the relevance of the empirical approach was acceptable (R²?=?0.930) in this study, its error (RMSE?=?7.514) is highly significant to guarantee the safety of the surrounding environment. In contrast, the AI models offer much higher accuracies. Of the seven AI models, ANN was the most dominant model based on RMSE, R², and MAE. This study demonstrated that AI techniques are excellent for predicting blast-induced AOp in open-pit mines. These techniques are useful for blasters and managers in controlling undesirable effects of blasting operations on the surrounding environment.

     

地理空间中的空间关系表达和推理

针对地理空间中的应用,归纳了在空间关系的表达与推理中不同于人工智能领域研究的一些特点:在人工智能领域,更注重建立形式化的推理系统;而在地理信息科学中,则需更关注地理空间的特点以及地物的地理语义。该文基于地理空间和地理现象的本质且顾及地理空间认知,总结了地理空间中空间关系表达和推理的特点,具体包括空间的有限性、地球的球面特征、地物的地理语义、地物形状的复杂性、面状地物、特殊的空间关系、空间关系的层次性与尺度相应原则、不确定性、三维与时态特性九方面;进而介绍了地理空间关系表达的两个应用,即地理信息检索和基于对象的图像分析。该文的探讨可为地理信息科学中的相关研究提供方向性指导。     

U.K.USAGE OF CHEMOMETRICS AND ARTIFICIAL INTELLIGENCE IN QSAR ANALYSIS

A survey of members of the U.K.QSAR Discussion Group has been made to determine the extent ofuse and development of chemometric and artificial intelligence(AI)methods in the analysis ofmultivariate quantitative structure-activity relationship(QSAR)data in the U.K.Chemometric methodswere found to be well established in both industrial and educational establishments and there wassignificant method development occurring.AI methods were not employed to any great extent and thegeneral level of interest in these techniques was low compared to chemometric methods.A requirementfor more education in multivariate statistical methods and regression methods was indicated.A need fora user-friendly,comprehensive,commercially available multivariate statistical package containingmultivariate stability testing and regression diagnostic methods was identified.     

中国风沙地貌学研究的新进展——庆贺黄秉维教授80华诞

本文从历史回顾及新的进展二个大的方面,比较全面地总结了风沙地貌所取得的成绩以庆贺黄秉维教授80华诞。     

加强极地国际合作研究和考察的契机--2007-2008国际极地年

国际极地科学界正在酝酿一个大型的国际极地考察与研究合作计划--2007-2008国际极地年计划(IPY)。本文分析了提出IPY的科学背景,译介了IPY计划制订小组公布计划框架的5个科学主题。根据对IPY科学主题的分析,认为本次IPY反映了公众对于极地环境发生快速变化的深度关切。高密度、新技术、多学科的国际合作考察与研究将成为本次IPY最显著的特点。2007-2008IPY将是我国极地考察与研究加强国际合作,迅速提升研究水平的一个难得的契机。     

胡焕庸线两侧的人口分布与城镇化格局趋势——尝试回答李克强总理之问（英文）

In late November 2014, while attending a science exhibition on human settlement at the National Museum, Premier Li Keqiang posed a question to society and scientists regarding the Hu Huanyong Line, which the media subsequently dubbed "the Premier's question". This increased awareness and interest in the Hu Huanyong Line and launched a lively debate which provoked a variety of views. In an attempt to address the Premier's question, this paper firstly reviews the origins of the Hu Huanyong Line, named after the famous population geographer who proposed it in 1935 as part of a wider debate on domestic overpopulation. Using demographic data from China's first, fifth and sixth censuses, as well as the Arc GIS platform, we analyze the size, proportion and density of populations in the areas southeast and northwest of the Hu Huanyong Line, showing that urbanization and migration have not changed the pattern of population distribution observed by Hu Huanyong. Based on this, we suggest that the pattern of a dense population southeast of the line and sparse population northwest of the line will not fundamentally change for a relatively long time, nor will the situation of urban agglomerations being mainly found in the southeastern region. We also argue that climate and other physical geographic conditions determine that the Hu Huanyong Line shall remain in place. We believe that the question posed by Premier Li Keqiang is solvable, and that with positive policy guidance and rational spatial organization, the northwestern region can achieve more modernization and better quality urbanization, while the same is true for the central region.     

Population distribution and urbanization on both sides of the Hu Huanyong Line: Answering the Premier’s question

In late November 2014, while attending a science exhibition on human settlement at the National Museum, Premier Li Keqiang posed a question to society and scientists regarding the Hu Huanyong Line, which the media subsequently dubbed “the Premier’s question”. This increased awareness and interest in the Hu Huanyong Line and launched a lively debate which provoked a variety of views. In an attempt to address the Premier’s question, this paper firstly reviews the origins of the Hu Huanyong Line, named after the famous population geographer who proposed it in 1935 as part of a wider debate on domestic overpopulation. Using demographic data from China’s first, fifth and sixth censuses, as well as the ArcGIS platform, we analyze the size, proportion and density of populations in the areas southeast and northwest of the Hu Huanyong Line, showing that urbanization and migration have not changed the pattern of population distribution observed by Hu Huanyong. Based on this, we suggest that the pattern of a dense population southeast of the line and sparse population northwest of the line will not fundamentally change for a relatively long time, nor will the situation of urban agglomerations being mainly found in the southeastern region. We also argue that climate and other physical geographic conditions determine that the Hu Huanyong Line shall remain in place. We believe that the question posed by Premier Li Keqiang is solvable, and that with positive policy guidance and rational spatial organization, the northwestern region can achieve more modernization and better quality urbanization, while the same is true for the central region.     

高被引华人科学家知识网络的空间结构及影响因素

知识网络的空间结构特征与影响因素是经济地理学探讨的热点议题之一,以往研究侧重于产业案例的分析,主要关注国家和城市层面的知识网络,而对科学家等个人层面的网络研究较为缺乏。以2014—2015年全球高被引科学家为原始数据,筛选出高被引华人科学家,并基于Web of Science数据库,检索高被引华人科学家之间合著论文的数据构建知识网络,借助社会网络分析方法对高被引华人科学家知识网络的空间结构进行分析;并运用负二项回归模型,从地理邻近性、社会邻近性、制度邻近性3个维度,探讨高被引华人科学家知识网络的影响机制。研究发现：① 高被引华人科学家知识网络存在核心-边缘结构特征,且具有小世界网络的网络特征;② 此知识网络呈现“小集聚大分散”的空间结构特征,地理邻近性作用明显;③ 高被引华人科学家知识网络形成过程中会受到科学家自身科研能力等因素的影响,地理距离和科学家之间的联系呈现负相关关系,地理邻近性的影响仍然存在,社会邻近性和制度邻近性均对知识网络的形成有促进作用。     

东北地区资源环境基础与区域发展政策

作为我国21世纪资源开发的重要场所,东北地区资源环境开发利用将对国家社会经济发展起到举足轻重的作用。文章分析了东北地区资源本底特征、人地关系演进状态以及发展趋势。在此基础上,对未来区域发展政策提出了建议。     

青藏高原研究进入最佳期和青年肩负的责任

这是中国青藏高原研究会理事长刘东生院士在该会青藏高原青年科技奖第一次颁奖大会(1996年3月6日)上的演讲。本文指出了当前青藏高原研究的方向,表达了对青年一代的殷切期望。征得作者同意,以飨读者。青藏高原青年科技奖获奖者是:丁林、王保海、方小敏、刘晓东、刘燕华、张春光、高锐、姚檀栋、彭敏、廖俊国。     

近70年长江口海面变化研究及其意义

近70年来年平均海面趋势(已消去人为地面沉降)是上升的。其速率为10cm/世纪,与近百年来全球性海面上升速率相一致,而同期高潮位的上升速率为25cm/世纪,明显大于年平均海面的上升率。区域性的沉积基底构造下降在海面上升中所占的比重不超过1/3。1952年以来长江口海面变化亦是上升的,它是本世纪以来海面上升的延续。     

智能技术影响下的城市空间研究进展与思考

智能技术的影响已经渗透到城市的不同方面,空间要素的流动更快更复杂,城市功能需要进行调整以适应居民活动的变化,城市空间的智能化发展与运营管理也成为新的挑战。论文从城市空间要素组织、居民活动与空间功能、空间运营管理3个方面梳理当前智能技术对城市空间的影响,并展望未来5～10 a的城市空间应具有瞬时异地、空间智能化、复杂流动性以及韧性能力更强的特点,最后从城市空间组织、功能形态、运营管理与规划方法4个方面探讨了未来的城市空间研究需要关注的重点内容,以期为智能技术影响下的城市空间研究与规划设计提供参考。     

ARTIFICIAL INTELLIGENCE AND ITS APPLICABILITY TO GEOGRAPHICAL PROBLEM SOLVING

Artificial Intelligence (AI) may be regarded as an attempt to understand the processes of perception and reasoning that underlie successful problem-solving and to incorporate the results of this research in effective computer programs. At present, AI is largely a collection of sophisticated programming techniques. Many of these techniques are based on the premise that the manner in which knowledge is acquired, organized, accessed and modified in both humans and machines provides the basis of “intelligent” decision-making. The techniques of AI are applicable to a wide variety of geographical problems, including the modeling of individual and aggregate decision-making, and the construction of expert systems and “intelligent” geographical information systems.     

中国城市人工智能发展的时空演化特征及其影响因素

基于2000—2019年中国285个地级及以上城市面板数据,以关键词检索人工智能相关的专利申请数,运用标准差椭圆、探索性空间数据分析以及空间杜宾分解模型,探析中国城市人工智能的时空演变特征及其影响因素。结果表明：① 人工智能发展在时间上可分为起步期、成长期以及高速发展期;空间上呈明显的层级效应,东部沿海城市优势明显,中西部城市正加快崛起。② 人工智能存在较强的空间正向相关关系,局部地区城市形成集聚发展态势。空间分布沿“东北?西南”方向产生极化现象,沿“西北?东南”方向产生扩散现象。分布重心位于安徽省内,有持续向东南迁移的趋势。③ 市场化水平、人口密度、人力资本、外商投资水平和金融发展水平的提升有利于人工智能发展,存在正向空间溢出效应。政府干预与人工智能发展呈倒U型曲线关系,存在空间溢出效应。产业升级和基础设施建设水平的提升有利于人工智能发展,但空间溢出效应不明显。     

National Center for Geographic Information and Analysis

Abstract

Abstract. The growth of the remote sensing field has caused and explosion in the size and complexity of Earth satellite image databases. The explosion of data is already challenging current satellite-based GIS databases. New technologies for information management will be required in the future to maintain these large geographically-oriented systems created by projects such as NASA's Earth Observing System (EOS). This paper presents a technology adapted from the planning/scheduling field in Artificial Intelligence (AI) that promises to automate and facilitate the process of creating and storing satellite images and their associated data products.     

Seismic and volcanic hazards in Peru: changing attitudes to disaster mitigation

Over the last 15 years there have been dramatic shifts in the consensus over how best to cope with natural hazards in economically developing regions such as South America. One very positive outcome of the United Nations sponsored International Decade for Natural Disaster Reduction (IDNDR 1990–2000) has been that there is now greater interchange between the work of earth scientists examining the processes and mechanics of hazard occurrence and impact, and social scientists exploring the causes of human vulnerability to hazard – and thereby disaster. This paper traces the development of this new understanding with reference to earthquakes and volcanic eruptions in Peru, one of the most hazardous countries in South America. Particular focus is placed on the excellent progress currently being made by scientists in better understanding the physical dimensions of natural hazard exposure, and the ground-breaking work by social scientists in promoting new approaches to understanding and mitigating human vulnerability to disaster. The paper concludes by emphasizing the need to build on this research to produce more inclusive, incultured and unified strategies of disaster mitigation at the local, national and international levels.     

God's healing leaves: The colonial quest for medicinal plants in the Torrid Zone

The colonial era witnessed a fevered quest for exotic medicinal plants by European physicians and scientists. This essay explores the geographical principles that oriented the search towards the lands and peoples of the humid tropics. Believing that God had planted botanical cures for diseases in their places of origin, medicinal plant collectors concentrated their efforts in the pestilential equatorial latitudes. Although many subscribed to the ancient Doctrine of Signatures, colonial bioprospectors discovered early that indigenous and diasporic peoples represented storehouses of plant knowledge. Assuming that native knowhow constituted more instinct than intelligence, Europeans employed coercion, bribes, torture, and promises of freedom to extract their ethnomedical secrets. In the case of especially lucrative healing plants, imperial and colonial entities conspired to pilfer and naturalize endemic species in their distant colonies. In response to this legacy of inappropriate exploitation of native peoples and tropical plants during the colonial era, most present day bioprospectors follow established codes of ethnobotanical ethics.     

创新型人才流动的空间结构与影响因素——基于高被引华人科学家履历分析

创新型人才作为重要的生产要素,对促进区域创新和竞争力提升具有决定性的作用。高被引科学家作为科研人员的杰出代表,是创新型人才的重要组成部分。本文以全球高被引华人科学家为研究对象,基于履历数据分析其流动,特别是工作阶段的流动特征;运用Heckman二阶段选择模型,对科学家工作阶段流动的影响因素进行分析,探究复合的人口迁移理论在高端人才流动中的适用性。研究发现：① 高被引华人科学家的人才流动轨迹表明,科学家的移动迁入地主要是国内外的核心城市（度中心性较高的城市）。② 高被引华人科学家工作阶段流动主要发生在中国和美国之间,中国城市多为人才迁入地,美国城市多为人才迁出地。③ 复合的人口迁移模型对高被引华人科学家工作阶段的区位选择解释作用明显。④ 高被引华人科学家国内外城市移动选择的影响因素不同,科学家的国内流动受到地理距离的限制,而迁入城市的拉力是高被引华人科学家产生跨国移动的主要原因。