Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks.

Comput Intell Neurosci

Department of Water Resources and Environmental Modeling, Faculty of Environmental Sciences, Czech University of Life Sciences Prague, Kamycka 1176, Suchdol, 165 21 Prague 6, Czech Republic.

Published: October 2016

The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI) and the standardized precipitation evaporation index (SPEI) and were derived for the period of 1948-2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4736223PMC
http://dx.doi.org/10.1155/2016/3868519DOI Listing

Publication Analysis

Top Keywords

drought indices
16
neural network
12
indices integrated
8
artificial neural
8
neural networks
8
feedforward multilayer
8
multilayer perceptron
8
integrated neural
8
network model
8
standardized precipitation
8

Similar Publications

African elephants () are megaherbivores of the African savannas requiring extensive ranges that can provide critical resources for their survival and reproduction at different spatiotemporal scales. We studied seasonal differences in home range sizes and daily distance to the nearest surface water sources by five male and 10 female African elephants in the eastern Okavango Panhandle in northern Botswana between 2014 and 2017. We hypothesized that (i) elephant home ranges would be larger in the wet than in the dry season (because critical resources tend to be less localized in the wet than in the dry season), (ii) the daily distance of the elephants to the nearest ephemeral surface water sources would be larger in the dry than in the wet season because many of the ephemeral water sources would be dry in the dry season and elephants would start moving towards permanent water sources such as rivers, and lastly (iii) that the differences in elephant home ranges and daily distance to water would differ between sexes.

View Article and Find Full Text PDF

Pugionium cornutum (L.) Gaertn (P. cornutum) has strong tolerance to drought, salt and disease, but the tolerance mechanisms for such stresses in P.

View Article and Find Full Text PDF

Drought conditions severely curtail the ability of plants to accumulate biomass due to the closure of stomata and the decrease of photosynthetic assimilation rate. Additionally, there is a shift in the plant's metabolic processes toward the production of metabolites that offer protection and aid in osmoadaptation, as opposed to those required for development and growth. To limit water loss via non-stomatal transpiration, plants adjust the load and composition of cuticle waxes, which act as an additional barrier.

View Article and Find Full Text PDF

Comparative analysis of the gene family in the whole-genome of five gramineous plants.

Front Plant Sci

December 2024

Department of Plant Sciences, College of Life Sciences, Wuhan University, Wuhan, China.

The Jacalin-related lectins () gene family play a crucial role in regulating plant development and responding to environmental stress. However, a systematic bioinformatics analysis of the gene family in Gramineae plants has been lacking. In this study, we identified 101 JRL proteins from five Gramineae species and classified them into eight distinct clades.

View Article and Find Full Text PDF

Introduction: The increase in vapor pressure deficit (VPD) is among the expected change in futur climate, and understanding its effect on crop growth is of much significance for breeeding programs. Three groups (G1,G2 and G3) of pearl millet germplasm, originating from regions with different rainfall intensities, were grown in the field during period of high and low VPDs. The groups G1,G2 and G3 were respectively from Guinean (rainfall above 1000 mm), Soudanian (rainfall between 600 mm and 900 mm), and Sahelian zones (rainfall between 600 and 300 mm) of Africa.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!