Nationwide Prediction of Drought Conditions in Iran Based on Remote Sensing Data

Applications of unsupervised auto segmentation on Dhule area hyperspectral image for drought and yield prediction

“…DCHCi,j) = IIHi -Hjll (5) Where H denotes the color of histogram where histogram merging is the universal contrast handling practice and equalize the saturation and intensity components in the image.…”

“…After above step it will use SVM Binary Classification Technique [2] after matching the features steps it will have two SVM classes if 80% or more features match will there that put in one class and other image features in other class. Then it wills calculating the NDVI [5] of class where one class of SVM where 80% or more image features matches. Then using NDVI it will Calculate Standardized Precipitation Index [5] .Then SPI value is used for drought predictions analysis's In this Project our main focus is on First part that is Image Segmentation where we taking the image of Dhule Agriculture plot image [4] then First we Edge Detection algorithm for processing the Image Then in proposed system we studied JSEG [1] algorithm and in analysis phase we will put scaled output of JSEG [1] algorithm.…”

Utilization of Near Real-Time Noaa-Avhrr Satellite Output for El Niño Induced Drought Analysis in Indonesia (Case Study: El Niño 2015 Induced Drought in South Sulawesi)

“…Outcomes NOAA-AVHRR from Smoothed and Normalized Difference Vegetation Index (NDVI or smoothed) (SMN) is commonly used as a substitute for rainfall data in quantifying drought (Jiang et al 2008;Jalili et al, 2014). Vegetation health index (VHI), vegetation condition index (VCI) and temperature condition index (TCI) are other drought indices that can be used for drought quantification using satellite technology.…”

“…Vegetation health index (VHI), vegetation condition index (VCI) and temperature condition index (TCI) are other drought indices that can be used for drought quantification using satellite technology. VHI has been widely used throughout the world (Zargar et al, 2011;Kogan et al, 2013) to quantify the agricultural drought, such as the United States (Kogan et al 2012;Anderson et al 2013), Rusia , Iran (Jalili et al, 2014), India (Bhuiyan et al, 2006), Bangladesh (Nizamuddin et al, 2015), China (Zhang et al, 2016) and West Java Indonesia (Sholihah et al, 2016). The objectives of this study was to carry out the drought potential and evolution in South Sulawesi during strong El Niño event in 2015 using VHI, VCI and TCI from NOAA-AVHRR Near Real-Time outcomes.…”

Drought prediction using co-active neuro-fuzzy inference system, validation, and uncertainty analysis (case study: Birjand, Iran)

“…Although, compared to other natural disasters drought is not very frequent, its financial and personal losses ranks first in Iran (FAO 2008). Therefore, drought, as a natural disaster, must be studied, investigated, and predicted (Dastorani and Afkhami 2011;Jalili et al 2013).…”