DRYAD Software

DRYAD software provides powerful tools for analyzing earth observation data, such as satellite images and meteorological data, in raster (.tif) format. The software helps to calculate complicated drought indices in few minutes, and provides deep-leaning based semantic segmentation. 

U-NET

DRYAD provides U-net based image segmentation function. Users can design U-net architecture and optimize hyper-parameters in GUI environment.

The software displays real time prediction results, loss, and accuracy, so the users can decide when to finish training. The trained parameters can be saved in 'h5' format manually or the best performing parameters are saved automatically in auto save mode. The saved parameters (h5) can be loaded, so the users can applied them to diverse datasets. 

service_unet.png

Time Series NDVI Reconstruction

ts_NDVI.png

DRYAD provides a time series NDVI reconstruction function for minimizing the effect of cloud or cirrus on NDVI product. The program is based on the algorithm proposed by Jin Chen(2004) which uses a series of Sav-Gol filter to correct the pixel values. 

It applies a long term filter which is applied for one time initially, and a short term filter which is applied iteratively until it finds the best fitting value. For more information about the algorithm please find the citation below.

Citation:

Chen, J., Jönsson, P., Tamura, M., Gu, Z., Matsushita, B., & Eklundh, L. (2004). A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky–Golay filter. Remote sensing of Environment, 91(3-4), 332-344.

Standardized Precipitation Index (SPI)

The SPI, developed by McKee et al. (1993), is an index to identify meteorological drought using time-series precipitation.

DRYAD provides a convenient and powerful tool for calculating SPI  by using rasterized precipitation data. 

DRYAD fits time series precipitations to gamma distribution with log-likelihood method and converts them to Z-score of standard normal distribution.

Citation:

McKee, T. B., Doesken, N. J., & Kleist, J. (1993, January). The relationship of drought frequency and duration to time scales. In Proceedings of the 8th Conference on Applied Climatology (Vol. 17, No. 22, pp. 179-183).

service_spi.png

Standardized Precipitation
Evapo-transpiration Index (SPEI)

service_spei.png

The SPEI, developed by Vicente-Serrano et al. (2010), is calculated in a similar way to SPI, but it takes into account of the effect of temperature to water balance. extention index of the SPI by using both time-series precipitation and potential evapotranspiration (PET). This index also computes for different time scale (eg. -3, -6, -9, and - 12 month etc.) and captures impact of increased temperature on water demand.

Citation:

Vicente-Serrano, S. M., Beguería, S., & López-Moreno, J. I. (2010). A multiscalar drought index sensitive to global warming: the standardized precipitation evapotranspiration index. Journal of climate, 23(7), 1696-1718.

Vegetation Temperature Condition Index (VTCI)

DRYAD provides various algorithms for calculating VTCI, which were derived from diverse researches (such as flattening cold edge, integrating air temperature with land surface temperature ect.) Especially, it provides an automatic edge selection function to assist users to calculate the index efficiently and consistently. User also can draw the edges manually through the displayer window.

*VTCI = 1 - TVDI(Temperature Vegetation Dryness Index)

service_vtci.png