教学目的、要求
预修课程
教材
教材或参考书 Kelly, G.A., 1970, A brief introduction to personal construct theory. In Perspectives in Personal Construct Theory, edited by D. Bannister (London: Academic Press), pp. 1-29. Kolodner, J. 1993. Case-Based Reasoning. Morgan Kaufmann Publishers, San Mateo, CA. Masters, Timothy, 1993. Practical Neural Network Recipes in C++, Academic Press, pp. 77-116. Miller, H. J., and J. Han, 2001, Geographic data mining and knowledge discovery: an overview. In Geographic Data Mining and Knowledge Discovery, edited by H. J. Miller and J. Han, (New York, NY: Taylor & Francis), pp. 3-32. Qi, F. and A.X. Zhu, 2003. Knowledge discovery from soil maps using inductive learning, International Journal of Geographic Information Science, In press. Shi, X., A.X. Zhu, J.E. Burt, F. Qi, and D. Simonson, 2003. A case-based reasoning approach to fuzzy soil mapping. Soil Science Society of America Journal, In press. Zhu, A.X., 1999. A personal construct-based knowledge acquisition process for natural resource mapping using GIS. International Journal of Geographic Information Science, Vol. 13, No. 2, pp. 119-141. Zhu, A.X., 2000. Mapping soil landscape as spatial continua: the neural network approach. Water Resources Research, 36, 663-677. Zhu, A.X., 2008. “Rule based mapping”. In: J.P. Wilson and A.S. Fotheringham (eds) Handbook of GIS, Blackwell, Malden, MA, 634 p. Zhu, A.X., B. Hudson, J. E. Burt, and K. Lubich, 2001. “Soil mapping using GIS, expert knowledge and fuzzy logic”, Soil Science Society of America Journal, Vol. 65, pp. 1463-1472. Zhu, A.X. and D.S, 2001. Mackay. “Effects of spatial detail of soil information on watershed modeling”, Journal of Hydrology, Vol. 248, pp. 54-77. Zhu, A.X., F. Liu, B.L. Li, T. Pei, C.Z. Qin, G.H. Liu, Y.J. Wang, Y.N. Chen, X.W. Ma, F. Qi, C.H. Zhou, 2010. “Differentiation of soil conditions over flat areas using land surface feedback dynamic patterns extracted from MODIS”, Soil Science Society of America Journal. DOI:10.2136/sssaj2008.0411. Zhu, A.X., L. Yang, B.L. Li, C.Z. Qin, T. Pei, B.Y. Liu, 2010. “Construction of quantitative relationships between soil and environment using fuzzy c-means clustering”, Geoderma, Vol. 155, No. 3-4, pp. 166-174.
主要内容
教学内容简介 There seems to be a shift in physical geography from a qualitative perspective to a more quantitative perspective. The increasing availability of vast amount of spatial data and the rapid advancement of GIS/RS and other spatial information processing techniques make this shift more viable. The central idea of this course is to illustrate how modern spatial information processing theory and techniques are used in quantifying the spatial variation of geographic variables in physical geography. This course focuses the application of GIS, artificial intelligence (A.I.) techniques and fuzzy logic concepts in solving physical geography problems. The discussion will be centered around the problem of detailed inventory of natural resources and natural hazards. The course will first present the need for detailed inventory of natural resources and susceptibility to hazards. It will highlight the challenges facing conventional approaches for conducting this type of inventory. It then presents how modern spatial information processing theory and techniques helps to overcome these challenges. The specific cases used in this course are soil resource inventory, landslide susceptibility and wildlife (monkey) habitats mapping. The techniques to be discussed include: personal construct-based knowledge acquisition, neural networks, case-based reasoning, and spatial data mining, purposive sampling, and VGI-based techniques. Each of the techniques will be introduced and discussed using a real application. Software and real world data set will be provided. 中英文双语教学 课程安排: Day One: Lecture 01: Course Overview Lecture 02: To more quantitative physical geography: the role of modern information processing techniques (The impact of GIScience on Geography:A direction change or paradigm shift) Lecture 03: The need of detailed spatial distribution and the existing approaches to produce it Lecture 04: Overview of the similarity based predictive approach: a) active learning (soft-knowledge) approach; b) lazy learning (VGI-based) approach. Day Two: Lecture 05: Characterizing the E (environmental covariates): the Fuzzy slope Lecture 06: Characterizing the E (environmental covariates): the SCI approach Lecture 07: Extraction and quantification of Knowledge: Active learning: Personal construct-based knowledge acquisition Day Three: Lecture 08: Extraction and quantification of Knowledge: Active learning: Knowledge: Neural networks Lecture 09: Extraction and quantification of Knowledge: Active learning: Knowledge: Spatial data mining Lecture 10: Extraction and quantification of Knowledge: Active learning: Knowledge: Purposive sampling Day Four: Lecture 11: Extraction and quantification of Knowledge: Active learning: Inference: Rule based evaluation Lecture 12: Extraction and quantification of Knowledge: Lazy learning (VGI-based) approach Lecture 13: Application 1: Detail soil mapping (SoLIM) Day Five: Lecture 14: Application 2: Mapping landslide susceptibility Lecture 15: Application 3: Monkey habitat Mapping and Course Summary Exam (open book in class, 开卷)