Machine learning in geosciences and remote sensing

Learning incorporates a broad range of complex procedures. Machine learning（ML） is a subdivision of artificial intelligence based on the biological learning process. The ML approach deals with the design of algorithms to learn from machine readable data. ML covers main domains such as data mining, difficultto-program applications, and software applications. It is a collection of a variety of algorithms（e.g. neural networks, support vector machines, self-organizing map, decision trees, random forests, case-based reasoning, genetic programming, etc.） that can provide multivariate, nonlinear, nonparametric regression or classification. The modeling capabilities of the ML-based methods have resulted in their extensive applications in science and engineering. Herein, the role of ML as an effective approach for solving problems in geosciences and remote sensing will be highlighted. The unique features of some of the ML techniques will be outlined with a specific attention to genetic programming paradigm. Furthermore,nonparametric regression and classification illustrative examples are presented to demonstrate the efficiency of ML for tackling the geosciences and remote sensing problems.

Major contribution to carbon neutrality by China’s geosciences and geological technologies

In the context of global climate change,geosciences provide an important geological solution to achieve the goal of carbon neutrality,China’s geosciences and geological technologies can play an important role in solving the problem of carbon neutrality.This paper discusses the main problems,opportunities,and challenges that can be solved by the participation of geosciences in carbon neutrality,as well as China’s response to them.The main scientific problems involved and the geological work carried out mainly fall into three categories:(1)Carbon emission reduction technology(natural gas hydrate,geothermal,hot dry rock,nuclear energy,hydropower,wind energy,solar energy,hydrogen energy);(2)carbon sequestration technology(carbon capture and storage,underground space utilization);(3)key minerals needed to support carbon neutralization(raw materials for energy transformation,carbon reduction technology).Therefore,geosciences and geological technologies are needed:First,actively participate in the development of green energy such as natural gas,geothermal energy,hydropower,hot dry rock,and key energy minerals,and develop exploration and exploitation technologies such as geothermal energy and natural gas;the second is to do a good job in geological support for new energy site selection,carry out an in-depth study on geotechnical feasibility and mitigation measures,and form the basis of relevant economic decisions to reduce costs and prevent geological disasters;the third is to develop and coordinate relevant departments of geosciences,organize and carry out strategic research on natural resources,carry out theoretical system research on global climate change and other issues under the guidance of earth system science theory,and coordinate frontier scientific information and advanced technological tools of various disciplines.The goal of carbon neutrality provides new opportunities and challenges for geosciences research.In the future,it is necessary to provide theoretical and technical support from various aspects,enhance the ability of climate adaptation,and support the realization of the goal of carbon peaking and carbon neutrality.

Climate change impacts on environmental geosciences: Introduction

Climate change and its impacts have become topical issues of global news,scientific research and conferences.Environmental Geosciences incorporate the various disciplines of geosciences and their multifaceted interactions with life.Research discussions on the interaction of climate change,geosciences and environment may often be blur,and Schmidt-Thoméet al.(2010)stated that“Often past climate changes that can be deduced from geological records may help in understanding the speed of potential climate change effects,i.e.how quickly have sea levels changed,how drastic has nature reacted to ups and downs in temperature,etc.These analyses of past events help in giving outlooks on potential changes in our living environment.It is also of important to understand the magnitude and potential effects of extreme events,such as droughts and floods”.

Progress of machine learning in geosciences:Preface

In the past two decades, artificial intelligence （AI） algorithms have proved to be promising tools for solving several tough scientific problems, As a broad subfield of AI, machine learning is concerned with algorithms and techniques that allow computers to ＂learn＂. The machine learning approach covers main domains such as data mining, difficult-to-program applications, and soft- ware applications. It is a collection of a variety of algorithms that can provide multivariate, nonlinear, nonparametric regression or classification. The remarkable simulation capabilities of the ma- chine learning-based methods have resulted in their extensive ap- plications in science and engineering. Recently, the machine learning techniques have found many applications in the geoscien- ces and remote sensing. More specifically, these techniques are proved to be practical for cases where the system＇s deterministic model is computationally expensive or there is no deterministic model to solve the problem （Lary, 2010）.

Recent progress in submarine geosciences in China

In China submarine geosciences represents a newly established discipline of oceanography, focusing on the oceanic lithosphere, and its interface with the hydrosphere and biosphere. Recently, supported by the National High Technology Research and Development Program and other high-tech development projects, significant progress has been made in the development of advanced technologies and equipment. This en- ables the scientists in China to carry out explorations of the international seabed area in the Pacific Ocean and on the Southwest Indian Ridge. In addition, they have been active in the research activities associated the mid-ocean ridges and western Pacific marginal seas. It is anticipated that this research field will continue to be highly fruitful in the near future.

Special Issue of Mathematical Geosciences for the 33^(rd) IGC

The papers published in this issue are selected from manuscripts submitted by invited authors and most of these papers will be presented at the 33^rd International Geological Congress （33^rd IGC） in Oslo, August 2008. It receives 25 manuscripts and 16 were accepted after going through the journal normal peer reviewing process. The topics of the papers cover various aspects of ＂metallogenic complex processes and mineral resource quantitative assessment＂, one of the strategic research areas of the State Key Laboratory of Geological Processes Resources （GPMR） sponsored by the Science and Technology and the and Mineral Ministry of Ministry of Education of China. Researches in the area are also supported by the National Natural Science Foundation and Ministry of Land and Resources of China as well as by mining companies. Thanks are due to these funding programs and organizations for supporting the research activities of GPMR. Sincere thanks are due to those who have reviewed the manuscripts and provided critical comments and even English editing of some of the papers. We are very appreciated for the assistance of the editorial office especially Professor Wang, the editor-in-chief, Ms. Yuan and many others who have worked hard to make this issue be printed before the event of 33^rd IGC. Special thanks are given to Professor Xie Shuyun, Xu Deyi and Tali Neta and many other members in the Geomatics Research Lab of York University for handling the manuscripts during the reviewing processes.

An Introduction to China University of Geosciences(Beijing)

China University of Geosciences（Beijing）（CUGB）,is one of the leading universities listed in"Project 211,"a national program that offers more government financial support for the advancement of 100 top national universities in 21st-century China.CUGB is also supported by the Ministry of Education for its uniquely strong strengths in geological disciplines.CUGB could be traced back to the former Beijing College of Geology,which was founded in 1952 by combining the Departments of Geology from Peking University, Tsinghua University,Tianjin University and Tangshan Railway College.In 1987,the predecessor of CUGB was renamed China University of Geosciences（Beijing）.

China University of Geosciences in Beijing

FOUNDED in 1952, China University of Geosciences in Beijing （CUGB） is a national key university under the direct auspices of the Ministry of Education. Over the past 60 years, it has developed from a geological college tbcused on a single discipline to a multi- disciplinary comprehensive university, offering courses in geology, natural resources, environment and geological engineering.

地球系统科学基本原理与应用展望

地球系统科学是一门应时代之需产生的科学,它革新了地球科学工作者的思维方式、工作范式。自地球系统科学产生以来,围绕其是否是一门科学、具有何种应用前景等一直存在争议。从地球系统科学的主要理论与基本原理视角出发,对地球系统科学的概念内涵、理论体系及与地球科学之间的关系等本质特征进行剖析,并对地球系统科学的方法技术进行了总结。针对解决的不同问题,提出了地球系统科学在地球深部过程、岩石圈与外部圈层交互作用、外部圈层交互作用3个领域的应用展望。分析认为,地球系统科学既是基于地球科学与系统论的科学观,又是一套量化研究各圈层交互作用的先进工作方法体系,是揭示地球圈层交互奥秘、解决地球宜居性的钥匙。

环境地球科学国家自然科学基金项目资助情况与学科热点变化

为更好地了解环境地球科学的国家自然科学基金资助情况,使申请者更熟悉本学科的资助趋势,利用统计分析、主题聚类等方法,以2010—2019年的数据为依据,对环境地球科学国家自然科学基金项目情况、二级学科与主要研究方向等进行分析,在环境地球科学领域获得国家自然科学基金项目资助的679个依托单位中选择具有代表性的3家科研机构和3所高校,深入分析环境地球科学的国家自然科学基金项目资助情况、学科热点变化与热点领域,阐述该学科的研究发展动态,以期为科研人员设计研究选题提供指导,为科技创新、管理决策及基金项目申报提供数据参考。

地学类“测量学”虚拟仿真实践教学体系建设探讨

在高等教育信息化建设背景下,基于虚拟仿真技术的地学类“测量学”实践教学体系有待完善。综合测绘新技术,融合地学类专业的差异,分别设计了技术基础模块、设计与综合模块和创新模块等模块;并在此基础上探讨了实践教学方法、教学管理、实践教学评价和实践教学保障等内容,进而形成了具有地学特色的“测量学”虚拟仿真实践教学体系。该实践教学体系以学生为中心,为不同专业学生提供多项选择,培养学生的实践能力及复杂工程能力,进而提升大地学专业学生的综合创新能力。

油气储层勘探建模技术新进展及未来展望

油气储层建模利用地质统计学等方法,综合测井、地质、地震等多学科信息,是油气田开发研究的利器,油藏地质模型可以将油藏各种地质特征在三维空间的变化及分布定量表征出来,是油气藏的类型、几何形态、规模、油藏内部结构、储层参数及流体分布的高度概括,储层地质模型是油藏地质模型的核心,可以对储层的沉积特征、非均质性、物性及流体等特征进行综合表征。但在勘探阶段,面对大尺度沉积体系和稀疏井网条件下的储层展布规律表征的建模难点为:①地质知识的量化表达问题,包括地质专家的经验认识如何数字化表征。②稀疏井网条件下无法直接用钻井资料对地质体的发育规模、展布方向和结构特征准确定量描述及构建地质模式,大尺度空间中复杂沉积体系无法用简单数学函数表征。③传统地质统计学等方法在勘探模型构建中如何实现地震、测井、地质、油藏等多维度数据的融合问题。因此,基于确定性建模和传统地质统计学等随机建模的储层建模理论和技术遇到极大挑战。笔者在系统剖析传统储层建模技术流程和方法的基础上,通过构建涵盖地质、测井、地震、分析化验等信息的多学科地学大数据知识库,开展多维数据凝聚层次聚类的沉积相模式库表征和基于生成式网络的智能建模,提出了多学科协同的油气储层勘探建模技术对策及技术体系,实现了构造、沉积及储层之间匹配关系的定量表征。该技术体系在东营凹陷北部陡坡带、洼陷带勘探部署中开展系统应用,构建融合古地貌、古物源、搬运通道、测井及地震属性等多信息的岩相、物性及油气运聚的地质模型,基于模型新范式指导部署井位,支撑了陆相断陷盆地复杂砂砾岩体、页岩油等勘探实践。笔者通过深度剖析东营凹陷北部陡坡带勘探建模实践难点及精度问题,进一步探讨了未来油气储层勘探建模技术发展趋势和应用前景。

数据质量特征视角下的地球科学数据重用影响因素研究——三个科学数据平台的比较分析

开放科学时代,科学数据的开放共享成为必然要求,而数据重用是其主要目标。尽管国内外已建设了多种科学数据开放共享平台,但对于这些平台的数据重用效果与数据开放特征之间的关系仍缺乏深入的研究。本文立足地球科学领域,对3个国内外的开放数据平台(国家青藏高原科学数据中心、NCAR研究数据档案和Figshare)进行了定量分析,旨在探讨影响科学数据重用的关键因素。研究发现:数据质量对科学数据的重用有显著影响。据此,本文从数据平台、科研人员、图书馆和期刊出版商4个维度提出了促进科学数据重用的策略建议。