Geo-Information Knowledge Base System for Drought Pattern Search

详细信息    查看全文

• 关键词：Drought patterns ; Logic ; based pattern search ; Pattern matching ; NOAA satellite data ; Geo ; information knowledge base system
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9788
• 期：1
• 页码：332-344
• 全文大小：3,835 KB
• 参考文献：1.Cohen, Y., Shoshany, M.: A national knowledge-based crop recognition in Mediterranean environment. Int. J. Appl. Earth Obs. Geoinf. 4, 75–87 (2002)CrossRef
  2.Goyal, R., Jayasudha, T., Pandey, P., Devi, D.R., Rebecca, A., Sarma, M.M., Lakshmi, B.: Knowledge based system for satellite data. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XL-8, 1233–1236 (2014)CrossRef
  3.Kahya, O., Bayram, B., Reis, S.: Land cover classification with an expert system approach using Landsat ETM imagery: a case study of Trabzon. Environ. Monit. Assess. 160(1), 431–438 (2010)CrossRef
  4.Kartikeyan, B., Majumder, K.L., Dasgupta, A.R.: An expert system for land cover classification. IEEE Trans. Geosci. Remote Sens. 33(1), 58–66 (1995)CrossRef
  5.Kerdprasop, K., Kerdprasop, N.: Integrating inductive knowledge into the inference system of biomedical informatics. In: Kim, T.-h., Adeli, H., Cuzzocrea, A., Arslan, T., Zhang, Y., Ma, J., Chung, K.-i., Mariyam, S., Song, X. (eds.) DTA/BSBT 2011. CCIS, vol. 258, pp. 133–142. Springer, Heidelberg (2011)CrossRef
  6.Kerdprasop, K., Kerdprasop, N.: Automatic knowledge acquisition tool to support intelligent manufacturing systems. Adv. Sci. Lett. 13, 199–202 (2012)CrossRef
  7.Kerdprasop, N., Intharachatorn, K., Kerdprasop, K.: Prototyping an expert system shell with the logic-based approach. Int. J. Smart Home 7(4), 161–174 (2013)
  8.Kerdprasop, N., Kerdprasop, K.: Autonomous integration of induced knowledge into expert system inference engine. In: IMECS 2011 – International MultiConference of Engineers and Computer Scientists, vol. 1, pp. 90–95 (2011)
  9.Krapivin, V.F., Phillips, G.W.: A remote sensing-based expert system to study the Aral-Caspian aquageosystem water regime. Remote Sens. Environ. 75, 201–215 (2001)CrossRef
  10.Lucas, R., Rowlands, A., Brown, A., Keyworth, S., Bunting, P.: Rule-based classification of multi-temporal satellite imagery for habitat and agricultural land cover mapping. ISPRS J. Photogramm. Remote Sens. 62, 165–185 (2007)CrossRef
  11.McKeown, D.M.: The role of artificial intelligence in the integration of remotely sensed data with geographic information systems. Technical report CMU-CS-86-174, Computer Science Department, Carnegie Mellon University, USA (1986)
  12.Shesham, S.: Integrating expert system and geographic information system for spatial decision making. Master Theses & Specialist Projects, Paper 1216, Western Kentucky University, U.S.A. (2012)
  13.Shoshany, M.: Knowledge based expert systems in remote sensing tasks: quantifying gain from intelligent inference. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XXXVII, Part B7, 1085–1088 (2008)
  14.Stefanov, W.L., Ramsey, M.S., Christensen, P.R.: Monitoring urban land cover change: an expert system approach to land cover classification of semiarid to arid urban centers. Remote Sens. Environ. 77, 173–185 (2001)CrossRef
  15.Thorat, S.S., Rajendra, Y.D., Kale, K.V., Mehrotra, S.C.: Estimation of crop and forest areas using expert system based knowledge classifier approach for Aurangabad district. Int. J. Comput. Appl. 121, 43–46 (2015)
  
• 作者单位：Kittisak Kerdprasop (22)
  Nittaya Kerdprasop (22)
  
  22. Data and Knowledge Engineering Research Unit, School of Computer Engineering, Suranaree University of Technology, Nakhon Ratchasima, 30000, Thailand
  
• 丛书名：Computational Science and Its Applications -- ICCSA 2016
• ISBN：978-3-319-42111-7
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9788

文摘

This paper presents a novel idea of utilizing a first-order logic technique to create, search and match for drought patterns in the specific area of interest. Drought patterns in this work have been drawn from the regression analysis using weekly time period and vegetation health index (VHI) obtained from the National Oceanic and Atmospheric Administration (NOAA) satellite data. To show the devised search facility, we use drought situations in the northeast provinces of Thailand as demonstrative cases. Drought trend of each province can be inferred from the percentage of provincial area that has the value of VHI below 35; the lower VHI value, the more severe drought. According to NOAA, this VHI threshold indicates moderate-to-high drought level. The proposed method is a kind of geo-information knowledge base system that allows users to search for drought pattern in some specific area at a particular time of the year. Moreover, the system also reports other area in the same region of study that shows similar drought trend. The drought trend is recognized from a regression coefficient in which the positive coefficient is the sign of increasing drought level, whereas the negative value implies the decrease of drought level.