Landscape Approach to Normalized Difference Vegetation Index Forecast by Artificial Neural Network: Example of Diyala River Basin

Abstract

This study examines the perspective of artificial neural networks for forecast Normalized Differential Vegetation Index (NDVI) on Diyala River basin and also how information about of bioclimatic landscapes will affect to forecasting performance. To do this, in the first stage of the experiment, a total of 20 perceptrons with different one hidden layer architectures were trained with sitespecific variables (latitude, longitude, minimal, maximal and mean height, landcover type) and seasonal meteorological variables (precipitation sum, and minimal, maximal and average daily temperatures) by error back propagation algorithm on the data of 2000-2010 years and tested on data for 2011-2016 years. It has been shown that the best performance, with determination coefficient R 2 of 0.78, was achieved by perceptron model with 12 hidden neurons the activated by logistic activation function and hyperbolic tangential activation of output value of NDVI. The large spatial heterogeneity of forecasting performance of the best perceptron was detected: in upper part of basin characterized according to Köppen-Trewartha bioclimatic classification, as landscapes of temperate mountain climate and the subtropical climate with dry summers, R 2 was 0.76-0.80, whereas in dry steppe landscapes and semi-desert landscapes of Diyala downstream R 2 was 0.6-0.7. The second stage of experiments with 20 models of perceptrons where the type of landscape was added as input variable or where 150 individual perceptrons were selected for each landscape, have shown that these approaches allows to R 2 increase up to 0.73-0.85. However, the strong contrast between characteristics of individual models complicates their use in the practice and requires to finding of new forecasting approaches.

The sensitivity of vegetation in the lower Tigris basin landscapes to regional and global climate variability

“…Note that the temporal delay in the vegetation response to environmental changes should be considered when looking for the sensitivity of ecosystems to climate variability (Wu et al, 2015). However, in our recent work (Alhumaima & Abdullaev, 2019), found that the maximum biological productivity during the growing season for Diyala river basin, a tributary of Tigris, is controlled by seasonal winter precipitation and January-March mean temperatures. Also showed that the neural network-based prediction of the spatiotemporal NDVI can be improved by using additional zonal landscape input predictor or by constructing an individual predicting model for each one of the zonal landscapes.…”

“…The maximum value compositing (MVC) method was used to produce monthly NDVI maps and minimize the effects of atmospheric, cloud contamination, and solar zenith angle (Alhumaima & Abdullaev, 2019). Additionally, NDVI pixels less than 0.1 were excluded from the analysis and considered as non-veg-etated (Xu et al, 2016;Alhumaima & Abdullaev, 2019).…”

“…Most of the Euphrates-Tigris basin, especially in southeastern Turkey as well as in northern Syria and Iraq (the lower Tigris basin), has a Mediterranean climate that is characterized by wet winters and dry summers (Food and Agriculture Organization of the United Nations [FAO], 2009). Hence, the vegetation of the region is highly sensitive to climatic variability (Alhumaima & Abdullaev, 2019).…”

Tigris Basin Landscapes: Sensitivity of Vegetation Index NDVI to Climate Variability Derived from Observational and Reanalysis Data

“…For example, in the spring seasons of 2000,2006,2008,2009,2011, and 2012 there were virtually no green areas. In fact, during these years, the Tigris and Euphrates basin experienced severe droughts (e.g., Kelley et al 2015;Muhaimeed and Al-Hedny 2013;Mathbout et al 2018;Alhumaima and Abdullaev 2018).…”