Spatial Data Mining for Drought Monitoring: An Approach Using temporal NDVI and Rainfall Relationship

Disclaimer This document describes work undertaken as part of a programme of study at the International Institute for Geo-information Science and Earth Observation. All views and opinions expressed therein remain the sole responsibility of the author, and do not necessarily represent those of the institute. Abstract Drought is an insidious hazard of nature which is considered by many to be the most complex but least understood of all natural hazards. Large historical datasets are required in order to study drought which involves complex interrelationship between the climatological and meteorological data. Extraction of valuable information from such large data archives demands an automated and efficient way. Data mining is answer to above problem as it has the potential to search for hidden pattern and identify the relationship between the data. For this work, two advance techniques i.e. Association rule and Independent Component Analysis (ICA) were used for extracting the spatial and temporal pattern of drought. Rainfall data from 1970-2004 was used to compute Standardized Precipitation Index (SPI) and NOAA-AVHRR NDVI for the period 1981-2003 was used to calculate Vegetation Condition Index (VCI). For association rule, both SPI and VCI were used as input parameters for generating the rules. Interesting rules were developed identifying the relationship between user-specified target episodes and other climatic and meteorological events. In case of ICA, an emerging technology, which provides a new approach to capture and gain insights into dynamics of complex spatio-temporal processes, VCI input sequence from 1999-2003 was used. The input image is separated into physical meaningful components that are not detectable with covariance based decomposition for detecting drought pattern. Hence, the utility of this technique is explored in this study. To validate the findings from SPI, Govt. based drought assessment reports were used and correlation coefficient of 0.89 was achieved, which indicates strong positive correlation. ii Acknowledgements I would like to express my earnest gratitude and thankfulness to Dr.V.K.Dadhwal, Dean, IIRS for his constant support, timely guidance, encouragement, valuable advice and suggestions throughout the research work. His deep interest and dedication towards the improvement of my research thesis will always be remembered. I am greatly indebted to Mr.C.Jeganathan, Geo-informatics division (GID), Indian Institute of Remote Sensing, Dehradun. I am thankful to him for his timely advice, constructive suggestions, kind support, guidance and encouragement that has resulted in the completion of this thesis. guidance through out the research work which has led to the completion …

[1]  Heikki Mannila,et al.  Rule Discovery from Time Series , 1998, KDD.

[2]  Donald A. Wilhite,et al.  Drought : a global assessment , 2000 .

[3]  Andrew D. Back,et al.  A First Application of Independent Component Analysis to Extracting Structure from Stock Returns , 1997, Int. J. Neural Syst..

[4]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[5]  Tsegaye Tadesse,et al.  Identifying drought and its associations with climatic and oceanic parameters using data mining techniques , 2002 .

[6]  Paul Arellano.  Missing information in Remote Sensing: Wavelet approach to detect and remove clouds and their shadows , 2003 .

[7]  A. Mathur,et al.  Denoising and wavelet-based feature extraction of MODIS multi-temporal vegetation signatures , 2005, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005..

[8]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[9]  V. Smakhtin,et al.  The use of remote sensing data for drought assessment and monitoring in Southwest Asia. , 2004 .

[10]  James V. Stone.  Independent component analysis: an introduction , 2002, Trends in Cognitive Sciences.

[11]  Mark A. Friedl,et al.  Spatio-temporal deconvolution of NDVI image sequences using independent component analysis , 2003, IEEE Trans. Geosci. Remote. Sens..

[12]  C. O'Hara,et al.  Use and analysis of temporal map algebra for vegetation index compositing , 2005, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005..

[13]  Diansheng Guo,et al.  Mining Spatial Data Using An Interactive Rule-Based Approach , 2000 .

[14]  L. Chapman,et al.  The use of geographical information systems in climatology and meteorology , 2003 .

[15]  Jitender S. Deogun,et al.  Efficient Rule Discovery in a Geo-spatial Decision Support System , 2002, DG.O.

[16]  Hans-Peter Kriegel,et al.  Database Primitives for Spatial Data Mining , 1999, BTW.

[17]  V. Ravi Kumar,et al.  Simple denoising algorithm using wavelet transform , 1999, chao-dyn/9912038.

[18]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[19]  M. Shashanka,et al.  Independent Component Analysis and Receptive Fields , 2022 .

[20]  Fred C. Collins,et al.  A comparison of spatial interpolation techniques in temperature estimation , 1995 .

[21]  Simone G. O. Fiori,et al.  Overview of independent component analysis technique with an application to synthetic aperture radar (SAR) imagery processing , 2003, Neural Networks.

[22]  Hans-Peter Kriegel,et al.  Algorithms for Characterization and Trend Detection in Spatial Databases , 1998, KDD.

[23]  Juan Manuel Górriz,et al.  Maximum Entropy Guide for BSS , 2005 .

[24]  G. Obasi,et al.  WMO's Role in the International Decade for Natural Disaster Reduction , 1994 .

[25]  Sherri K. Harms,et al.  Drought Monitoring Using Data Mining Techniques: A Case Study for Nebraska, USA , 2004 .

[26]  T. Sakamoto,et al.  A crop phenology detection method using time-series MODIS data , 2005 .

[27]  Vladimir U. Smakhtin,et al.  Review, automated estimation and analyses of drought indices in South Asia , 2004 .