Academic Communication

CNU-MSU Joint "Remote Sensing Big Data and Artificial Intelligence" Series Course2019-05-09

Source: cnu       Clicks:       Size: small     middle       big

  CNU-MSU联合“遥感大数据与人工智能”系列课程

  (时间5月27日-6月21日)

  

  首都师范大学(Capital Normal University, CNU)与美国密歇根州立大学(Michigan State University, MSU)2017年签订了校级合作协议,在校级合作协议的框架下2019年成立了首都师范大学地理环境研究与教育中心。为了丰富学生的国际学习经验,促进与来自不同国家和大学的学生之间的交流与合作,首都师范大学与美国密歇根州立大学的教授学者将于5月27日-6月21日在首都师范大学开设与“遥感大数据与人工智能”相关的全英文课程。

  

  课程分两个时段

  A时段(5月27日-6月8日):地理空间研究设计、分析和实施

  B时段(6月10日-6月21日):地理空间研究设计、实施和交流

  允许学生自由选择两个时段的课程, A时段课程主要侧重地理空间技术和技能培养,B时段课程主要侧重研究设计和科学写作。学生主要来自MSU、CNU以及其他高校或研究院所,为确保与学生有足够的交流, A时段课程的学生总数不超过30人,B时段课程的学生总数不超过15人。

  全英文授课,参加A时段课程的学生须精通英语,可无障碍交流和深入讨论,有遥感、地理空间分析、或草地生态学习兴趣。参加B时段课程的学生须精通英语,可无障碍交流,可阅读和讨论专业文献,可英文写作,并且有遥感、地理空间分析、或草地生态专业知识。

  

  课程英文简介

  

  Segment A: Geospatial Research Design, Analysis, and Implementation

  Summer 2019 (May 27 – June 8)

  

  https://en.wikipedia.org/wiki/Image_analysis#/media/File:Object_based_image_analysis.jpg

  Instructors

  Ashton Shortridge, Raechel Portelli, & Jiaguo Qi. All are professors at Michigan State University.

  

  Course Objectives

  This course is an intensive two-week immersion in geospatial analysis of remote sensing data. The main objective of this course is to develop analytical processes for remotely sensed data to address fundamental and applied questions about grasslands ecology, modeling, or monitoring. Students will develop a machine learning workflow that can be implemented with remote sensing data, and they will develop a written description and justification for using these methods.

  

  Student Prerequisites

  This course is conducted in English. You must be proficient enough in English to follow verbal instructions and contribute to discussion. Students should also have a research focus and interest in remote sensing, geospatial analysis, and/or grassland ecology.

  

  Course Content and Hour Allocation

  Course is an intensive introduction to remote sensing and machine learning concepts and analyses. Topics are presented in the context of remote sensing use for grassland ecology applications. Remote sensing topics covered include geographic object-based image analysis (GEOBIA), implementation of GEOBIA through R statistical program, feature space reduction, and accuracy. Machine learning (ML) topics will include a general introduction to the topic, comparison of different types of ML techniques, and implementation in the R statistical program. These topics will be reinforced through participation in a series of instructor-led tutorials.

  

  This course includes 40 hours of teaching in the classroom, 20 hours of directed computer lab work, 8 hours of urban field data collection, and 8 hours of project time (76 contact hours).

  

  Grade Allocation

  30% Annotated bibliography

  30% Workflow write up

  20% Team Peer Assessment

  20% Participation

  

  Schedule

  Week 1 (May 27 – June 1): Geospatial Methods and Field Sampling

  Lecture and discussion. Topics include: GEOBIA concepts, statistical classification techniques, image pre-processing, classification of images using R and/or other geoprocessing software.

  Student assignments: Import remote sensing data into R. Read pertinent articles. Perform feature space reduction. Perform image classification. Perform post-classification accuracy assessment.

  

  Week 2 (June 3 – June 8): Geospatial Machine Learning

  Lecture and discussion. Topics include: statistical inference, machine learning, specific machine learning approaches, caveats of machine learning implementation, and its potential in the Data Science era.

  Student assignments: Perform a variety of machine learning analyses within R. Read pertinent articles. Perform post-classification accuracy assessment. Write a summarization of the techniques applied and create a plan for analytic methods for remote sensing data.

  

  Segment B: Geospatial Research Design, Implementation, and Communication

  Summer, 2019 (June 10 – June 21)

  

  https://commons.wikimedia.org/wiki/File:Bayanbulak_grassland.jpg

  Instructors

  Ashton Shortridge, Raechel Portelli, & Jiaguo Qi. All are professors at Michigan State University.

  

  Course Objectives

  This course is an intensive two-week immersion in geospatial research design, implementation, and communication. At its core is a field trip to Inner Mongolia to address fundamental and applied questions about grasslands ecology, modeling, monitoring, or assessments, in the broad context of climate change and human activities. Students will develop and deliver a scientific presentation and work with their research team to determine the next steps.

  

  Student Prerequisites

  This course is conducted in English. You must be proficient enough in English to read and discuss academic articles, to follow and contribute to discussion, and to write. Students should also have a research focus and interest in remote sensing, geospatial analysis, and/or grassland ecology.

  

  Course Content & Hour Allocation

  Content consists of a set of interconnected topics. Some are writing and presentation related: the research process and the role of communication and writing; literature review, narrative, peer-review; targeting an audience; figures that tell a story; research questions; discussing limitations of the research; and ethics in communication. Others are research design focused, with an emphasis on geospatial approaches to environmental remote sensing: sampling; sensor issues; designing a field campaign; data collection and storage. Other processing and analysis aspects will not be covered in this course, but may be essential for successful completion of the project.

  

  This course includes 26 hours of teaching in the classroom, 28 hours of directed discussion and research planning, three days (24 hours) of guided research on a field trip to Inner Mongolia, and 6 hours of presentations and interaction (84 contact hours).

  

  Grade Allocation

  20% Annotated bibliography

  10% Field Journal

  30% Presentation

  20% Team Peer Assessment 20% Participation

  

  

  Schedule

  Week 1 (June 10 – June 16): Research Design and Implementation

  Lecture and discussion. Topics include: scientific research and communication, identifying research objectives, spatial sampling theory, planning field data collection Field trip. Multi-day field trip to Inner Mongolia. Data collection, including field and remote sensing.

  Student assignments: Join a research team. Select a topic for the project. Read and summarize relevant articles. Prepare written responses on them. Maintain a journal during the field trip.

  

  Week 2 (June 17 – June 21): Analysis and Scientific Communication

  Lecture and discussion. Topics include: scientific paper framework and targeting, plagiarism, identifying the research question(s) and hypotheses, results vs. discussion, presentations vs. papers, visualization.

  Student assignments: Prepare a detailed outline of the joint presentation. Review an outline by another team. Obtain additional data (e.g., Landsat or other imagery) for the project. Conduct initial processing and analysis. Develop presentation slides. Construct good graphics and text. Review a presentation draft by another team. Deliver presentation. Review all presentations. Write review of the course. Develop plan to continue research with the team.

  

  联合教学团队简介

  Dr. Ashton Shortridge, Professor in Geography, Environment and Spatial Sciences

  Dr. Raechel Portelli, Professor in Geography, Environment and Spatial Sciences

  Dr. Jiaguo Qi, Professor in Geography, Environment and Spatial Sciences, Center for Global Change, Environmental Science and Policy Program and Office of China Programs.

  张爱武,博士,教授,资源环境与旅游学院,主要从事遥感载荷与人工智能、浮空探测与环境感知、草地遥感监测等方向研究

  朱琳,博士,教授,资源环境与旅游学院,主要从事环境遥感研究

  王艳慧,博士,教授,资源环境与旅游学院,主要从事GIS方法与应用研究

  邓磊,博士,教授,资源环境与旅游学院,主要从事无人机遥感与摄影测量研究

  王涛,博士,副教授,资源环境与旅游学院,主要从事空间数据库与城市信息模拟研究

  柯樱海,博士,副研究员,资源环境与旅游学院,主要从事资源环境遥感应用研究

  谢东海,博士,副教授,资源环境与旅游学院,主要从事摄影测量与深度学习研究

  段福洲,博士,副教授,资源环境与旅游学院,主要从事航空遥感数据采集技术研究

  胡卓玮,博士,副教授,资源环境与旅游学院,主要从事环境遥感研究

  刘晓萌,高级实验师,资源环境与旅游学院,主要从事环境遥感研究

  田金炎,博士,资源环境与旅游学院,主要从事植被遥感研究

  

  报名参加

  填写报名信息表,并在2019年5月20日前发至邮箱hyan4321@163.com,我们会在5月22日回复邮件,请及时查看。

  免费听课,食宿自理

  联系人:刘晓萌、孟佳、侯焱(hyan4321@163.com)

  联系电话:68907429、68903262

  报名邮箱:hyan4321@163.com

  

  

  首都师范大学资源环境与旅游学院

  首都师范大学地球空间信息科学与技术国际化示范学院

  首都师范大学地理环境研究与教育中心