Spatial and temporal monitoring of drought conditions using the satellite rainfall estimates and remote sensing optical and thermal measurements

Drought is an important natural disaster that causes devastating impacts on the ecosystem, livestock, environment, and society. So far, various remote-sensing methods have been developed to estimate drought conditions, each of which has advantages and restrictions. This study aims to monitor the real-time drought indices at the field scales via the integration of various earth observations. Our proposed method consists of two steps. In the first step, the relationships between long-term standardized precipitation indices (SPI) derived from PERSIANN-CDR rainfall data and two drought-dependent parameters derived from MODIS products, including normalized NDVI and soil-air temperature gradient, are obtained at the spatial resolution of PERSIANN-CDR grid (approximately 25 km). As the next step, the corresponding relationships are applied to estimate the drought index maps at the spatial resolution of MODIS products (1 km). Numerous analyses are carried out to evaluate the proposed method. The results revealed that, from various drought indices, including SPIs of different timescales (1, 3, 6, and 12-months), SPI-3 and SPI-6 are more appropriate to the proposed method in terms of correlation with temperature and vegetation parameters. The findings also demonstrate the competency of the proposed method in estimating SPI indices with average RMSE 0.67 and the average correlation coefficient of 0.74.     

Evaluating the statistical performance of less applied algorithms in classification of worldview-3 imagery data in an urbanized landscape

In recent decade, analyzing the remotely sensed imagery is considered as one of the most common and widely used procedures in the environmental studies. In this case, supervised image classification techniques play a central role. Hence, taking a high resolution Worldview-3 over a mixed urbanized landscape in Iran, three less applied image classification methods including Bagged CART, Stochastic gradient boosting model and Neural network with feature extraction were tested and compared with two prevalent methods: random forest and support vector machine with linear kernel. To do so, each method was run ten time and three validation techniques was used to estimate the accuracy statistics consist of cross validation, independent validation and validation with total of train data. Moreover, using ANOVA and Tukey test, statistical difference significance between the classification methods was significantly surveyed. In general, the results showed that random forest with marginal difference compared to Bagged CART and stochastic gradient boosting model is the best performing method whilst based on independent validation there was no significant difference between the performances of classification methods. It should be finally noted that neural network with feature extraction and linear support vector machine had better processing speed than other.