Variance based fusion of VCI and TCI for efficient classification of agriculture drought using MODIS data
- 2 November 2020
- journal article
- research article
- Published by Taylor & Francis in Geocarto International
- Vol. 37 (10) , 2871-2892
Abstract
Overall health condition of the vegetation is obtained by combining satellite data derived moisture and thermal stresses present in vegetation condition index (VCI) and thermal condition index (TCI), respectively and improves the accuracy of drought classification. Although vegetation health index fuses the information present in VCI and TCI, the relative contribution of each index depends on prior knowledge of the study area. Therefore, the random weighing method is used to obtain optimal weights of VCI and TCI based on variances of individual indices. The obtained fusion results of a normal and drought year demonstrate that the random weighing fusion achieves better estimation of agriculture drought without requiring apriori information and the obtained drought classification results are in line with the available ground truth precipitation records. In addition, the correlation analysis of the obtained optimal weights and standardized precipitation evapotranspiration index exhibited a strong correlation with a Pearson’s correlation coefficient of above 0.8. The study also showed that the relative contribution of VCI is prevalent in normal conditions while TCI in dry to extreme dry conditions.Keywords
This publication has 31 references indexed in Scilit:
- Assessing drought probability for agricultural areas in Africa with coarse resolution remote sensing imageryRemote Sensing of Environment, 2011
- A Multiscalar Drought Index Sensitive to Global Warming: The Standardized Precipitation Evapotranspiration IndexJournal of Climate, 2010
- Random weighting estimation of parameters in generalized Gaussian distributionInformation Sciences, 2008
- Water content estimation from hyperspectral images and MODIS indexes in Southeastern ArizonaRemote Sensing of Environment, 2008
- Comments on the use of the Vegetation Health Index over MongoliaInternational Journal of Remote Sensing, 2006
- Vegetation and temperature condition indices from NOAA AVHRR data for drought monitoring over IndiaInternational Journal of Remote Sensing, 2003
- A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture statusRemote Sensing of Environment, 2002
- Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imageryIEEE Transactions on Geoscience and Remote Sensing, 2001
- Remote sensing of weather impacts on vegetation in non-homogeneous areasInternational Journal of Remote Sensing, 1990
- Concepts of Independence for Proportions with a Generalization of the Dirichlet DistributionJournal of the American Statistical Association, 1969