TULLAHAN RIVER’S WATER LEVEL

FORECASTING IN MARULAS, VALENZUELA

CITY USING ARTIFICIAL NEURAL
NETWORK
Arvien D. Lidres*, Mark Vincent A. Tulinao†,and Kaye V. Velilla§ Commented [JLT1]: Symbols for emails should be as
Department of Civil Engineering, Pamantasan ng Lungsod ng Valenzuela follows:
Valenzuela, Philippines * , †, ‡, §, ¶
Adviser: Engr. Mark Paulo Alcala, CE
Email: *arvienlidres@gmail.com, †markvincenttulinao@yahoo.com,
§
kayevelilla0818@gmail.com Commented [JLT2]: Symbols for emails should be as
follows:
* , †, ‡, §, ¶

Abstract—This electronic document is a “live” template and

already defines the components of your paper [title, text, heads, II. DATA USED
etc.] in its style sheet. *CRITICAL: Do Not Use Symbols, Special Any dependent variables (output parameters) may be a
Characters, Footnotes, or Math in Paper Title or Abstract.
function one or more independent variables (input
(Abstract)
parameters). The water level in Ugong and Quirino Bridge
Keywords—algorithm, ANN, hydrologic hazard, Matlab, where the river flows and different rain station within
nodes Marulas, Valenzuela City along with their antecedent values
of four months have been taken as input to determine the best
number of input parameters.
The primary information to complete this research paper
I. INTRODUCTION
will be the gathering of data. In PAGASA (Philippine
Tullahan River is one of the three major rivers Atmospheric Geophysical and Astronomical Services
interconnecting in the boundaries of Valenzuela City. It starts Administration), the researchers gathered the data of rainfall
from La Mesa reservoir flow through Malabon and intensity and past water level.
Valenzuela to Manila Bay and is one of the major The past water level data of Tullahan River along Ugong
contributors of flood in the low lying area of the cities. and Quirino Bridge were listed according to 10-minute data
In recent years, floods have worsened, occurring more which is from 7 am to 7 am in the next day. The goal of this
frequently and reaching levels of several feet deep. Most research is to predict the water level in a daily basis thus, the
affected are families in the communities that are along or near data of water levels were averaged to get the past daily water
the riverbanks. The river has become narrower and shallower level. The precipitations were also a 10-minute basis so the
over the years, and its capacity to hold water has decreased. researchers summed the precipitations in a 24-hour basis.
With more frequent intense rains, the riverbanks flood
regularly and flooding reaches farther into low-lying and
densely populated areas of the city.
Artificial Neural Network (ANN) are computer programs
that simulate the human brain process information to gather
the knowledge by detecting the patterns and relationship in
data and learn from experience not in programming. ANN
can combine and incorporate both literature based and
experimental data to solve problems. There is various
application of ANN it can summarized into classification or
pattern recognition, prediction and modeling.
A neural network is a system of hardware and/or software
patterned after the operation of neurons in the human brain.
Neural networks -- also called artificial neural networks -- are
a variety of deep learning technologies. Commercial
applications of these technologies generally focus on solving
complex signal processing or pattern recognition problems.
Examples of significant commercial applications since 2000
include handwriting recognition for check processing,
speech-to-text transcription, oil-exploration data analysis,
weather prediction and facial recognition.
This study is focusing on the forecasting of water level in
Tullahan River at Marulas using ANN. This model will be the
tool of the researchers to come up to the desired result. This
research aims to give daily forecasting of water level on
Tullahan River in BBB, Marulas using artificial network.
The researchers are analyzing the data that can affect
Tullahan River limited along the river flow and at Marulas,
Valenzuela City.
 1st College of Engineering Research Colloquium – Pamantasan ng Lungsod ng Valenzuela
March 19, 2019, PLV Maysan Auditorium, Valenzuela, Philippines

III. METHODOLOGY

Neural Networks are data processing system that uses a

multilayered technique to estimated compound mathematical
Actual Data Predicted Data
function of data. In this study, the researchers used the Feed 13.50 13.47
Forward Back Propagation Neural Network (FFBPNN). In 13.48 13.46
this network, the data that were input will undertake to the 13.69 13.76
input nodes and multiply by its weight and it will pass to the 13.51 13.44
hidden nodes. The hidden layer is the same process as output 13.50 13.43
nodes. 13.48 13.41
The researchers used a software application called 13.43 13.40
MATLAB to simulate the ANN. 13.48 13.54
ANN established to predict the water level in different 13.54 13.61
algorithms, learning rates, and the number of hidden neurons. 13.46 13.43
ANN aims to generate or give the best result. 13.45 13.42
13.38 13.37
Backpropagation used by the network to simulate the learning
13.40 13.36
algorithm is called Scale Conjugate Gradient.
13.38 13.31
This algorithm aimed to avoid the time-consuming line 13.38 13.36
research. This requires more repetition to congregate, but the 13.43 13.48
number of computations in each repetition must be reduced 13.63 13.70
because no line search is achieved. 13.40 13.37
The input node has a past water level in Ugong and Quirino 13.38 13.35
Bridge where the river flows and different rain station within 13.49 13.42
Marulas, Valenzuela City. As the researchers expected the 13.46 13.44
output that they get from the network is the water level on the 13.39 13.31
current day. 13.37 13.32
13.35 13.43
IV. RESULTS AND DISCUSSION 13.37 13.40
13.33 13.41
By using the MATLAB Software on the nntool, the
13.34 13.28
independent variables (Past water level of Quirino and Ugong 13.34 13.32
Bridge, Precipitation from Pacweld and Valenzuela National 13.31 13.29
High School rain station, Temperature) will serve as an input 13.88 13.86
and the water level as dependent variables. In this work, the 13.49 13.56
researchers developed models to predict the water level of the
Tullahan River. A process of Feed-Forward Back
Propagation was used to simulate the network. The number
of neurons used is 3 and the number of layers is 2 to get a
satisfying results. The selection of the final structures, the
number of hidden nodes, was a trial and-error procedure until
ACKNOWLEDGMENT (Heading 5)
it satisfies the given R Value. The R Values are shown below.
The preferred spelling of the word “acknowledgment” in
America is without an “e” after the “g”. Avoid the stilted
expression “one of us (R. B. G.) thanks ...”. Instead, try “R.
V. CONCLUSION AND RECOMMENDATION B. G. thanks...”. Put sponsor acknowledgments in the
unnumbered footnote on the first page.
REFERENCES
The template will number citations consecutively within
brackets [1]. The sentence punctuation follows the bracket [2].
Refer simply to the reference number, as in [3]—do not use
“Ref. [3]” or “reference [3]” except at the beginning of a
sentence: “Reference [3] was the first ...”
 1st College of Engineering Research Colloquium – Pamantasan ng Lungsod ng Valenzuela
March 19, 2019, PLV Maysan Auditorium, Valenzuela, Philippines

Number footnotes separately in superscripts. Place the

actual footnote at the bottom of the column in which it was
cited. Do not put footnotes in the abstract or reference list. Use
letters for table footnotes.
Unless there are six authors or more give all authors’
names; do not use “et al.”. Papers that have not been
published, even if they have been submitted for publication,
should be cited as “unpublished” [4]. Papers that have been
accepted for publication should be cited as “in press” [5].
Capitalize only the first word in a paper title, except for proper
nouns and element symbols.
For papers published in translation journals, please give
the English citation first, followed by the original foreign-
language citation [6].

[1] G. Eason, B. Noble, and I. N. Sneddon, “On certain integrals of

Lipschitz-Hankel type involving products of Bessel functions,” Phil.
Trans. Roy. Soc. London, vol. A247, pp. 529–551, April 1955.
(references)
[2] J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed.,
vol. 2. Oxford: Clarendon, 1892, pp.68–73.
[3] I. S. Jacobs and C. P. Bean, “Fine particles, thin films and exchange
anisotropy,” in Magnetism, vol. III, G. T. Rado and H. Suhl, Eds. New
York: Academic, 1963, pp. 271–350.
[4] K. Elissa, “Title of paper if known,” unpublished.
[5] R. Nicole, “Title of paper with only first word capitalized,” J. Name
Stand. Abbrev., in press.
[6] Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, “Electron spectroscopy
studies on magneto-optical media and plastic substrate interface,” IEEE
Transl. J. Magn. Japan, vol. 2, pp. 740–741, August 1987 [Digests 9th
Annual Conf. Magnetics Japan, p. 301, 1982].
[7] M. Young, The Technical Writer’s Handbook. Mill Valley, CA:
University Science, 1989.