TITLE:
Dead Sea Starvation: Towards Enhanced Monitoring of Water Resources by Modeling Meteorological Variables and Remote Sensing Data
AUTHORS:
Nazeeh Ghatasheh, Ismail Al-Taharwa, Bilal Al-Ahmad, Mua’ad Abu-Faraj
KEYWORDS:
Analytics, Dead Sea, Machine Learning, Meteorological Modeling, Remote Sensing, Risk Prediction
JOURNAL NAME:
Journal of Software Engineering and Applications,
Vol.9 No.12,
December
30,
2016
ABSTRACT: Meteorological metrics have been used for
weather forecasting and climate prediction. Remote sensing images proved to be
a valuable resource to represent the terrain of earth’s surface. Recently,
there has been extensive research to model changes on the earth’s landscape
including water bodies using remote sensing images. Meanwhile, meteorological
data have been used mainly to model climate changes. This research tries to
leverage both resources to achieve enhanced monitoring of the Dead Sea
shrinkage: first, an attempt to model the relation between several
meteorological variables and Dead Sea shrinkage using machine learning; second,
formulating Dead Sea shrinkage in terms of water level and surface area using
data extraction from remote sensing images; finally, confronting the two models
to derive a novel approach for predicting Dead Sea shrinkage based on spatiotemporal
images and meteorological measures. The main machine learning algorithms for
modeling the water shrinkage in this empirical research are Decision Table,
Linear Regression, and Multi Layer Perceptron Neural Networks. The Mean
Absolute Error measure of the best model is 1.743 and 0.015. It is challenging
to model the relation between meteorological variables and the water level.
However, the obtained results are promising to formulate a model of the water
level decline rate, which in its turn will be an essential tool for estimating
the consumption limits and inflow needs to save the Dead Sea.