Informations et ressources scientifiques
sur le développement des zones arides et semi-arides

Accueil du site → Master → Pays Bas → Spatial data mining for drought monitoring : an approach using temporal NDVI and rainfall relationship

University of Twente (ITC) (2006)

Spatial data mining for drought monitoring : an approach using temporal NDVI and rainfall relationship

Sharma Aditi

Titre : Spatial data mining for drought monitoring : an approach using temporal NDVI and rainfall relationship

Auteur : Aditi Sharma

Université de soutenance : University of Twente (ITC)

Grade : Master of Science in Geo-information Science and Earth Observation in Hazard & Risk Analysis 2006

Résumé
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 inter-relationship 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.

Mots Clés : Drought, Data mining, Associations rule, ICA, Standardized Precipitation Index (SPI), Vegetation Condition Index (VCI), spatio-temporal processes.

Version intégrale

Page publiée le 29 décembre 2011, mise à jour le 19 octobre 2018