数字地形分析应用适配性知识的案例表达与推理方法

doi:10.18306/dlkxjz.2016.01.010

Abstract

Abstract:

Application of digital terrain analysis (DTA) relies heavily on the DTA-domain knowledge on the match between the chosen algorithm (and its parameter-settings) and the application context (such as target task, terrain condition of the study area, and DEM resolution)—the so-called application-matching knowledge. This type of knowledge has a direct impact on the quality of DTA modelling when users of DTA, especially non-expert users, do not have sufficient amount of such knowledge to support their DTA applications. Existing DTA-assisted tools often cannot use application-matching knowledge because this type of knowledge has not been formalized in DTA to be available for inference in these tools. This is mainly because this type of DTA knowledge is currently inaccurate and non-systematic, and often exists in documents for specific case studies, or as personal knowledge of domain experts. This situation makes the DTA modelling process difficult for users, especially for non-expert users. Case-based reasoning method that originated from artificial intelligence is appropriate for formalization and inference of non-systematic knowledge. In this article, we propose a case-based formalization and inference method for the application-matching knowledge in DTA. The specific design of the proposed case-based method can be divided into two parts: formalization of the application-matching knowledge, and inference method. The case of this knowledge consists of a series of indices to formalize the DTA application-matching knowledge and the corresponding similarity calculation methods for inference based on the case. To evaluate the performance of the proposed method, we implemented it in a software prototype of DTA modelling environment and then applied it to a DTA application of river network extraction. In the experiment we prepared 32 cases of river network extraction in the USA. The results of cross validation preliminarily show that the proposed case-based method is suitable for using the application-matching knowledge in DTA. It reduced the modelling burden greatly for users.

Key words: Digital Terrain Analysis (DTA), modelling knowledge, case, river network extraction

Xuewei WU, Chengzhi QIN, Axing ZHU. Case-based formalization and inference method of application-matching knowledge on digital terrain analysis[J].PROGRESS IN GEOGRAPHY, 2016, 35(1): 89-97.

Figures/Tables 7

Fig.1

Tab.1

Tab.2

Case representation for DTA application-matching knowledge"

应用上下文	考虑因素	指标	单一指标的相似度计算方法
应用目的	计算目的	计算目的名称	布尔函数
数据特征	分辨率	栅格分辨率/m	$S i = 2 - (\| lg R new - lg R i) 0.5$
研究区特征	面积	面积/km²	$S i = 1 - S i' max S i'$ $S i' = lg Are a new - lg Are a i$
	地形特征	地形起伏度/m	$S i = 1 - S i' max S i'$ $S i' = Relie f new - Relie f i$
		坡度分布(高程—坡度累计频率分布)	$S i = ∑ min SlpRl f new, SlpRl f i ∑ max SlpRl f new, SlpRl f i$
		发育特征(面积—高程积分曲线)	$S i = 1 - S i' max 1 - H I new, H I new$ $S i' = H I new - H I i$

Tab.2

Fig.2

Tab.3

Fig.3

Tab.4

References 20

[1]	江净超, 朱阿兴, 秦承志, 等. 2013. CyberSoLIM: 基于知识驱动的在线数字土壤制图原型系统[J]. 土壤学报, 50(6): 1216-1220. doi: 10.11766/trxb201303040100
	[Jiang J C, Zhu A X, Qin C Z, et al.2013. CyberSoLIM: knowledge-driven on-line digital soil mapping prototype system[J]. Acta Pedologica Sinica, 50(6): 1216-1220.] doi: 10.11766/trxb201303040100
[2]	卢岩君. 2012. 知识驱动下的数字地形分析可视化建模环境构建研究[D]. 北京: 北京师范大学.
	[Lu Y J. 2012. Construction of a knowledge-driven and visualized modelling environment for digital terrain analysis[D].Beijing, China: Beijing Normal University.]
[3]	秦承志, 朱阿兴, 李宝林, 等. 2006. 基于栅格DEM的多流向算法述评[J]. 地学前缘, 13(3): 91-98. doi: 10.3321/j.issn:1005-2321.2006.03.012
	[Qin C Z, Zhu A X, Li B L, et al.2006. Review of multiple flow direction algorithms based on gridded digital elevation models[J]. Earth Science Frontiers, 13(3): 91-98.] doi: 10.3321/j.issn:1005-2321.2006.03.012
[4]	汤国安, 宋佳. 2006. 基于DEM坡度图制图中坡度分级方法的比较研究[J]. 水土保持学报, 20(2): 157-160. doi: 10.3321/j.issn:1009-2242.2006.02.038
	[Tang G A, Song J.2006. Comparison of slope classification methods in slope mapping from DEMs[J]. Journal of Soil and Water Conservation, 20(2): 157-160.] doi: 10.3321/j.issn:1009-2242.2006.02.038
[5]	周启鸣, 刘学军. 2006. 数字地形分析[M]. 北京: 科学出版社. [Zhou Q M, Liu X J. 2006. Digital terrain analysis[M]. Beijing, China: Science Press.]
[6]	朱梅, 李发源. 2009. 坡度分级对地面坡谱的影响研究[J]. 测绘科学, 34(6): 165-167.
	[Zhu M, Li F Y.2009. Influence of slope classification on slope spectrum[J]. Science of Surveying and Mapping, 34(6): 165-167.]
[7]	Aamodt A, Plaza E.1994. Case-based reasoning: foundational issues, methodological variations, and system approaches[J]. AI Communications, 7(1): 39-59. doi: 10.3233/AIC-1994-7104
[8]	Chang K T, Tsai B W.1991. The effect of DEM resolution on slope and aspect mapping[J]. Cartography and Geographic Information Systems, 18(1): 69-77. doi: 10.1559/152304091783805626
[9]	Grohmann C H.2015. Effects of spatial resolution on slope and aspect derivation for regional-scale analysis[J]. Computers & Geosciences, 77: 111-117. doi: 10.1016/j.cageo.2015.02.003
[10]	Hengl T, Reuter H I.2009. Geomorphometry: concepts, software, applications[M]. Amsterdam, Netherlands: Elsevier.
[11]	Kaster D S, Medeiros C B, Rocha H V.2005. Supporting modeling and problem solving from precedent experiences: the role of workflows and case-based reasoning[J]. Environmental Modelling & Software, 20(6): 689-704. doi: 10.1016/j.envsoft.2004.03.014
[12]	Kolodner J.1993. Case-based reasoning[M]. San Mateo, CA: Morgan Kaufmann Publishers.
[13]	Lu Y, Qin C Z, Zhu A X, et al.2012. Application-matching knowledge based engine for a modelling environment for digital terrain analysis[R]. GeoInformatics 2012, 15-17 June. Hong Kong, China: The Chinese University of Hong Kong.
[14]	Qin C Z, Jiang J C, Zhan L J, et al.2013. A browser/server-based prototype of heuristic modelling environment for digital terrain analysis[R]. Geomorphometry 2013, 15-20 October. Nanjing, China:Nanjing Normal University.
[15]	Qin C Z, Lu Y J, Zhu A X, et al.2011. Software prototyping of a heuristic and visualized modeling environment for digital terrain analysis[C]//Proceedings of the 11th International Conference on GeoComputation, 20-22 July. London, UK: University College London.
[16]	Russell S, Norvig P.2009. Artificial intelligence: a modern approach[M]. 3rd ed. New Jersey, NJ:Prentice Hall.
[17]	Schank R C.1983. Dynamic memory: a theory of reminding and learning in computers and people[M]. New York, NY: Cambridge University Press.
[18]	Strahler A N.1952. Hypsometric(area-altitude)analysis of erosional topography[J]. Geological Society of America Bulletin, 63(11): 1117-1142.
[19]	Watson I, Abdullah S.1994. Developing case-based reasoning systems: a case study in diagnosing building defects[C]//Case Based Reasoning: Prospects for Applications (Digest No. 1994/057). UK. IET: 1-3.
[20]	Watson I, Marir F.1994. Case-based reasoning: a review[J]. The Knowledge Engineering Review, 9(4): 327-354. doi: 10.1017/S0269888900007098

案例组成	DTA应用适配性知识的组成
案例问题	应用目的
	数据特征(分辨率、数据源等)
	研究区特征(研究区位置、面积、地形特征、其他环境条件等)
解决方案	DTA算法(及其参数值设置)
案例输出(可选)	(不需考虑)

结果合理性	应用问题案例 [阈值/km²]	最相似案例 [阈值/km²]	案例综合相似度
合理	WA_01[1.60]	ME_03[1.27]	0.43
	WA_03[0.26]	WA_02[0.74]	0.69
	WA_05[0.61]	WA_05A[0.61]	0.62
	AR_05[1.02]	ME_09[0.72]	0.62
	AR_06[17.42]	AR_08[7.96]	0.65
	ME_04[0.79]	ME_05[0.84]	0.94
	ME_05[0.84]	ME_04[0.79]	0.93
	ME_06[0.81]	ME_04[0.79]	0.82
	ME_07[0.78]	ME_04[0.79]	0.88
	ME_08[0.74]	ME_04[0.79]	0.75
	AR_08A[7.96]	AR_08[7.96]	0.62
	WA_05A[0.61]	WA_05[0.61]	0.62
	WA_06A[0.08]	WA_06[0.08]	0.62
	WA_04A[1.26]	WA_04[1.26]	0.62
	WA_04[1.26]	WA_04A[1.26]	0.62
	WA_06[0.08]	WA_06A[0.08]	0.62
较为合理	AR_07[2.16]	ME_06[0.81]	0.76
	AR_08[7.96]	ME_01[1.22]	0.87
	AR_03A[0.08]	AR_02A[0.06]	0.86
	AR_02A[0.06]	AR_03A[0.08]	0.87
	AR_02[0.06]	AR_03[0.08]	0.87
	AR_03[0.08]	AR_02[0.06]	0.86
	ME_09[0.72]	ME_05[0.84]	0.85
偏差较大	WA_02[0.74]	AR_03[0.08]	0.65
	AR_01[0.11]	ME_08[0.74]	0.64
	AR_04[0.03]	ME_02[0.28]	0.82
	ME_01[1.22]	AR_08[7.96]	0.87
	ME_02[0.28]	AR_04[0.03]	0.82
	ME_03[1.27]	AR_07[2.16]	0.65
	AR_03A[0.08]	AR_07A[2.16]	0.65
	ME_09A[0.72]	AR_07A[2.16]	0.62
	AR_04A[0.03]	ME_09A[0.72]	0.65

案例编号	分辨率相似度	面积相似度	面积高程积分曲线相似度	地形起伏度	高程—坡度累积频率相似度	综合相似度	汇水面积阈值/km²
AR_07	1	0.65	0.98	0.98	0.75	0.65	2.16
ME_05	1	0.62	0.94	0.97	0.94	0.62	0.84
AR_07A	0.62	0.65	0.98	0.98	0.71	0.62	2.16
ME_07	1	0.61	0.83	0.96	0.92	0.61	0.78
ME_09	1	0.61	0.89	0.94	0.84	0.61	0.72
ME_09A	0.62	0.60	0.93	0.96	0.90	0.60	0.72
ME_04	1	0.55	0.92	0.95	0.95	0.55	0.79
AR_05	1	0.98	0.84	0.91	0.54	0.54	1.02
AR_08	1	0.48	0.79	0.95	0.80	0.48	7.96
AR_08A	0.62	0.48	0.80	0.95	0.85	0.48	7.96
ME_06	1	0.46	0.94	0.96	0.81	0.46	0.81
ME_01	1	0.45	0.9	0.97	0.89	0.45	1.22
WA_02	1	0.66	0.79	0.82	0.35	0.35	0.74
WA_01	1	0.32	0.82	0.69	0.80	0.32	1.62
AR_06	1	0.28	0.88	0.89	0.56	0.28	17.42
AR_03A	0.62	0.28	0.66	0.98	0.41	0.28	0.08
AR_03	1	0.28	0.66	0.98	0.44	0.28	0.08
WA_03	1	0.19	0.94	0.82	0.31	0.19	0.26
ME_02	1	0.17	0.88	0.95	0.79	0.17	0.28
ME_08	1	0.17	0.96	0.95	0.79	0.17	0.75
AR_01	1	0.17	0.88	0.87	0.45	0.17	0.11
WA_05A	0.62	0.71	0.92	0.41	0.16	0.16	0.61
WA_05	1	0.71	0.90	0.43	0.16	0.16	0.61
AR_02	1	0.08	0.76	0.99	0.39	0.08	0.06
WA_06	1	0.08	0.91	0.56	0.22	0.08	0.08
WA_06A	0.62	0.08	0.91	0.55	0.22	0.08	0.08
AR_02A	0.62	0.08	0.76	0.99	0.38	0.08	0.06
WA_04	1	0.55	0.70	0.02	0.35	0.02	1.26
AR_04A	0.62	0	0.80	0.90	0.79	0	0.03
AR_04	1	0	0.82	0.90	0.85	0	0.03
WA_04A	0.62	0.55	0.70	0	0.34	0	1.26

Case-based formalization and inference method of application-matching knowledge on digital terrain analysis

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 20

Related Articles 3

Metrics

Comments

Recommended 10

[1]	Qingyan HUANG, Kai BAI. Tourist self-concept in time and space: A case study on typical online travel notes [J]. PROGRESS IN GEOGRAPHY, 2017, 36(5): 644-654.
[2]	HU Xuemei, QIN Chengzhi. Effects of different topographic attributes on determining appropriate DEM resolution [J]. PROGRESS IN GEOGRAPHY, 2014, 33(1): 50-56.
[3]	SUN Yeran, DU Yunyan, SU Fenzhen, ZHOU Chenghu. Study on the Suitability of CBR Method in the Estimation of Land Use Change [J]. PROGRESS IN GEOGRAPHY, 2011, 30(7): 912-919.