See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/358503899

Bandung Rainfall Forecast and Its Relationship with Niño 3.4 Using Nonlinear
Autoregressive Exogenous Neural Network

Article  in  Atmosphere · February 2022

DOI: 10.3390/atmos13020302

CITATIONS READS

2 398

5 authors, including:

Resa septiani Pontoh Toni Toharudin

Universitas Padjadjaran Universitas Padjadjaran
27 PUBLICATIONS   181 CITATIONS    78 PUBLICATIONS   575 CITATIONS   

SEE PROFILE SEE PROFILE

Budi Nurani Ruchjana

Universitas Padjadjaran
130 PUBLICATIONS   426 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Marine capture fisheries production and intensity of rainfall: An application of autoregressive distributed lag (ARDL) model View project

Spatio Temporal Data Mining and Optimization Modeling View project

All content following this page was uploaded by Toni Toharudin on 10 February 2022.

The user has requested enhancement of the downloaded file.

Article

Bandung Rainfall Forecast and Its Relationship with Niño 3.4

Using Nonlinear Autoregressive Exogenous Neural Network
Resa Septiani Pontoh 1,*, Toni Toharudin 1, Budi Nurani Ruchjana 2, Novika Sijabat 1 and Mentari Dara Puspita 1

1 Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran,

Sumedang 45363, Indonesia; [email protected] (T.T.); [email protected] (N.S.);
[email protected] (M.D.P.)
2 Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran,

Sumedang 45363, Indonesia; [email protected]

* Correspondence: [email protected]

Abstract: The city of Bandung, as the capital city of West Java, is one of several areas in Indonesia
with high rainfall. This situation can cause disasters, such as floods and landslides, that can harm
many parties. Rainfall in Indonesia, particularly on the island of Java itself, is closely related to the
global phenomenon of Niño 3.4. In the period from January 2001–November 2021, the rainfall and
Niño 3.4 showed some extreme values. In order to foresee the disasters, an accurate rainfall forecast
should be performed. For this reason, we try to construct a model of rainfall forecast and its relation
to the global phenomenon of Niño 3.4 using the nonlinear autoregressive exogenous neural network
(NARX NN). The result shows that NARX NN (13-7-1) with a Mean Absolute Percentage Error
(MAPE) value of 6.26% and R2 of 85.37% is best suited for the prediction of this phenomenon. In
addition, this study provides forecast results for the next six periods, which can be used as a refer-
Citation: Pontoh, R.S.; Toharudin, ence for the relevant authorities to foresee the possibility of flooding in Bandung city. From the
T.; Ruchjana, B.N.; Sijabat, N.; forecast results, it can be concluded that the highest rainfall forecasts in the city of Bandung are in
Puspita, M.D. Bandung Rainfall February 2022, and will slowly decrease in March 2022. To prevent hydro-meteorological disasters,
Forecast and Its Relationship with
such as floods in Bandung city, the community can clear waterways, such as clogged drains, rivers,
Niño 3.4 Using Nonlinear
and dams, as well as prepare tools for evacuation.
Autoregressive Exogenous Neural
Network. Atmosphere 2022, 13, 302.
Keywords: rainfall; Bandung; Niño 3.4; NARX NN
https://doi.org/10.3390/
atmos13020302

Academic Editors: Baojie He,

Ayyoob Sharifi, Chi Feng and Jun 1. Introduction
Yang
The earth is a habitat and a place to live for various creatures in the world, including
Received: 13 January 2022 humans. However, due to global warming, the earth is becoming hotter by the day. Global
Accepted: 4 February 2022 warming is one of the most important environmental issues facing the world today.
Published: 10 February 2022
Global warming is a form of ecosystem imbalance on earth due to the process of increas-
Publisher’s Note: MDPI stays neu- ing the average temperature of the earth’s atmosphere, sea, and land [1]. The effects of
tral with regard to jurisdictional global warming cause climate change. Climate change is characterized by the frequent
claims in published maps and institu- occurrence of extremely high temperatures [2]. This leads to natural disasters [3], such as
tional affiliations. floods, which have severe socio-economic impacts [4]. Therefore, the early detection of
climate change is necessary for the prevention of disasters that harm people.
Indonesia is a maritime country located at the equator and flanked by two large
Copyright: © 2022 by the authors. Li- oceans, namely the Pacific and the Indian Ocean and two large continents, namely the
censee MDPI, Basel, Switzerland. Asian and the Australian continent [5]. This geographical location causes the weather and
This article is an open access article climate in Indonesia to be very dynamic and complex [6]. Abnormal weather and climate
distributed under the terms and con- conditions often occur in Indonesia, which is caused by various global climate phenom-
ditions of the Creative Commons At- ena, such as the Asia–Australia monsoon, Indian Ocean Dipole (IOD), El Niño, east–west
tribution (CC BY) license (https://cre- circulation (Walker circulation), and north–south circulation (Hadley circulation), as well
ativecommons.org/licenses/by/4.0/).
as some circulations due to local influences [7]. The authors of [8,9] conducted a research

Atmosphere 2022, 13, 302. https://doi.org/10.3390/atmos13020302 www.mdpi.com/journal/atmosphere

Atmosphere 2022, 13, 302 2 of 17

study that links the role of global phenomena, namely ENSO, IOD, and monsoon varia-
bility, to precipitation, temperature, and humidity in Myanmar, a monsoon region. Indo-
nesia itself is an area affected by the monsoon.
El Niño–Southern Oscillation (ENSO) is an east–west circulation that occurs in the
equatorial Pacific Ocean [10]. The interaction of the atmosphere and oceans causes an in-
crease and decrease in sea surface temperature that exceed the 30-year long-term average
temperature, and thus deviations occur. If the deviation is positive, then the sea surface
temperature will rise or commonly called El Niño, whereas if the deviation is negative,
then the sea surface temperature will decrease or commonly called La Niña [11].
The occurrence of El Niño and La Niña is affected by shifts in the Walker circulation.
The Walker circulation is an atmospheric circulation, in which convection centers or warm
“pools” in the western and eastern Pacific are displaced [12]. In the El Niño incident, the
Walker circulation center (convection center) was shifted from the warm “pool” area in
the north of the island of Papua to the more eastern region in the central Pacific. As a
result, wind movements occur in Indonesia and the surrounding area, which are charac-
terized by a very drastic reduction in precipitation. At La Niña events, the Walker circu-
lation increases with a larger convection center in the western Pacific and stronger wind
exchange. As a result, Indonesia and the surrounding area saw an increase in rainfall [13].
ENSO values refer to the Southern Oscillation index (SOI), Niño 2, Niño 3, Niño 4,
Niño 3.4, and Ocean Niño index (ONI) [14]. In a study conducted by Kartika Nur Anisa,
the Niño 3.4 index was stated as the best ENSO indicator in identifying the rainfall rela-
tionship in Indonesia [15]. Therefore, in this study, the Niño 3.4 input series is used to
predict rainfall.
The city of Bandung, as the capital of West Java, has a strategic position and role with
a large amount of potential for development in economic, agricultural, and tourism as-
pects [16]. The development of this potential is influenced by the location of the city of
Bandung. Geographically, the city of Bandung city is located at coordinates 1070 36′ east
longitude and 60 55′ south latitude [17]. Meanwhile, topographically, the city of Bandung
is located at an average altitude of 791 m above sea level (asl), the highest point in the
north with an altitude of 1050 m and the lowest in the south with an altitude of 675 m
above sea level [17]. The map of the city of Bandung is shown in Figure 1.

Figure 1. Map of Bandung City. Source: https://maps.google.com (accessed on 2 February 2022).

Atmosphere 2022, 13, 302 3 of 17

In particular, the northern part of the city of Bandung is a hilly area. Therefore, by
reviewing the topographical and geographical aspects, we can easily conclude that the
area of Bandung city is the upstream part of the drainage system, which will contribute
runoff water to the downstream part of Bandung city. In Figure 1, it can be seen that the
city of Bandung is an area with a humid mountainous climate and high rainfall. Rain with
high intensity can cause disasters, such as floods and landslides, that can harm many par-
ties [18].
In December 2007, the heavy rainfall caused flash floods in the district of Cidadap,
Bandung [19]. Then, in November 2016, there were floods at 16 points in the city of Ban-
dung, including Pagarsih, Pasirkaliki, Wastukancana, Lodaya, Pasirkoja, A. Yani, Sukaga-
lih, Sudirman, Waringin (Andir market), Laswi, Burangrang, Eastern Railway Station, Ke-
bon Jati, Caringin, Otista, and Jalan dr. Djundjunan. Moreover, the flood overwhelmed
several public institutions, such as the Bandung railway station, the Bandung Cicendo Eye
hospital, and shops on Jalan Lembong Merdeka [20]. In early and late 2018, Bandung city
also suffered flooding. Due to heavy rains, several points overwhelmed Bandung city [21].
In February 2020, according to a report by the Bandung city regional disaster management
agency (BPBD), floods in six subdistricts were caused by high precipitation factors in the
Bandung city region [22].
Figure 2 shows a graph of the Niño 3.4 index data with rainfall in the period from
January 2001–November 2021, with monthly precipitation data for Bandung city [23,24].
Visually, the Niño 3.4 data chart shows random data patterns with very strong fluctuating
data movements. Moreover, the data have extreme values or values that are very different
from other values. Meanwhile, the monthly precipitation data for Bandung city in the pe-
riod from January 2001–November 2021 show the highest precipitation value in December
2007, November 2016, and November 2021, where precipitation exceeds 800 mm/month
and the lowest precipitation is 13.82 mm/month in September 2019. From the rainfall data,
it can be seen that the city of Bandung is an area with an average rainfall of 261.2495
mm/month. With this condition, it can be concluded that the city of Bandung has a signif-
icantly high amount of rainfall. Therefore, information regarding weather forecasts, espe-
cially rainfall, is required.

Figure 1. Graph of the Niño 3.4 index with rainfall in Bandung city in the period from January 2001–
–November 2021. Source: https://apcc21 (Niño 3.4) and https://iridl.ldeo.columbia.edu (rainfall) (ac-
cessed on 13 January 2022).
Atmosphere 2022, 13, 302 4 of 17

Information regarding probable future rainfall can help in running the regional po-
tential activities more efficiently, such as agriculture, plantations, aviation, tourism, public
services, and natural disasters. Various managements use this information as a basis for
planning, monitoring, and decision-making.
Current precipitation information can be obtained through the media. However,
there are many methods that can be used for prediction or forecasting. In general, data
prediction methods, such as precipitation forecast are based on time series data, and fu-
ture forecasts are based on past data. This method creates a time series model from a series
of observations or observations of events, events or variables that are measured in time
series, for example, hours, daily, monthly, yearly, etc. In conjunction with the theory de-
scribed, the Niño 3.4 series is a series that affects the prediction of precipitation. Therefore,
it is necessary to conduct forecasts to predict the monthly precipitation, taking into ac-
count the influence of Niño 3.4 in the next periods of time. The analysis is carried out with
a time series analysis method that can record extreme values. Therefore, the forecast re-
sults can be used as a reference for Regional Disaster Management Agency (BPBD) and
the city administration of Bandung to initiate the assessment and anticipation steps in
areas at risk of flooding. As a result, the time series analysis used in this study is NARX
NN.
In Figure 2, the rainfall data in Bandung city shows a very strong fluctuating pattern,
and there is a random pattern or changes every month. Therefore, we need a method that
can capture random patterns from rainfall data, and then maps the effect of exogenous
variables on the response variable. Based on the research on sea wave energy prediction
[25], the artificial neural network method was found to be one of the right solutions for
modeling with nonlinear relationships. In addition, the artificial neural network method
has higher resistance (robust) against noise. The ANN method can learn and adapt data
patterns through repeated learning. Therefore, it can be used for forecasting without the
need for paying attention to the patterns from the original data [26].
Several previous studies have conducted rainfall forecasting using several other fore-
casting methods. The authors of [27] carried out rainfall forecasting using the hybrid
wavelet artificial neural network (WANN) to predict rainfall in Queensland, Australia
over a period of 1, 3, 6, and 12 months in advance. The RMSE values obtained are 90, 52,
32, and 15%, respectively. Furthermore, the authors of [28] conducted research that con-
centrates on the ability of the ANN model in predicting several weather phenomena, such
as rainfall, temperature, flooding, and tidal levels, etc. Finally, it has been concluded that
the major architectures, namely BPN, RBFN, and MLP are best suited for the prediction
of this weather phenomenon. In a comparative study between various ANN techniques,
BPN and RBFN were found to be the right solution for long-term weather forecasting. The
authors of [29] conducted research using the adaptive network based fuzzy inference sys-
tem optimized with particle swarm optimization (PSOANFIS), artificial neural networks
(ANN), and support vector machines (SVM) for the prediction of daily rainfall in Hoa
Binh province, Vietnam. By adding the variables of maximum temperature, the minimum
temperature, wind speed, relative humidity, and solar radiation are used as input varia-
bles. The results of the study show that all of the artificial intelligent (AI) models provide
reasonable daily rainfall predictions. However, SVM was found to be the best method for
the prediction of rainfall. Moreover, the authors of [30] carried out rainfall forecasting us-
ing eight statistical methods and machine learning. In this study, the results indicate that
neural networks are found to perform best for the prediction of rainfall occurrence.
Herein, the research has been conducted to explore the relationship between the atmos-
pheric phenomena, including the Sunspot (SS), East Asian summer monsoon index
(EASMI), ACI, South Asian summer monsoon index (SASMI), and the rainfall that occurs
in Bangladesh [31].
The nonlinear autoregressive exogenous neural network (NARX NN) is a develop-
ment method of ANN, in which there are additional exogenous variables to achieve better
results. The nonlinear autoregressive neural network (NARX) method has been used in
Atmosphere 2022, 13, 302 5 of 17

various studies, such as the research in [32], which predicts energy consumption in public
buildings using nonlinear autoregressive (NAR) and nonlinear autoregressive neural net-
work (NARX) methods. The NARX method uses historical temperature data as an exoge-
nous variable. In this study, the data were split 70% for training data and 30% for test data.
The MSE value obtained from the NAR method is 1.67, while the NARX method is 0.66.
The NARX method uses the exogenous variable information to achieve better results.
The authors of [33] conducted research to compare the NARX method to other meth-
ods. This study compared the NARX method with ARIMAX in predicting wheat yield on
Kanpur land in Uttar Pradesh by considering the weather variable, namely the maximum
temperature at the critical root initiation (CRI) stage, as an exogenous variable. The re-
search results showed that the NARX method outperformed the ARIMAX model in mod-
eling and forecasting. The MAPE value obtained from the ARIMAX model is 2.93 and the
value from the NARX model is 1.94. Research using NARX NN has also been carried out
for the forecasting of the groundwater level for several wells in southwest Germany, in-
volving exogenous variables, which are precipitation and temperature variables [34].

2. Materials and Methods

In this study, the data used are secondary data in the form of monthly historical data,
which are derived from open data and extracted from the UCSB CHRIPS website
(www.iridl.ldeo.columbia.edu accessed on 13 January 2022) [23] and the APCC website
(www.apcc21.org accessed on 13 January 2022) [24]. In particular, precipitation data are
the main variables and Niño 3.4 data are the exogenous variables. The time interval used
for the precipitation data and Niño 3.4 starts in the period from January 2001–November
2021. There was no update from the UCSB CHRIPS website for the December 2021 data.
The nonlinear autoregressive exogenous neural network (NARX NN) analysis was per-
formed using the R software for the prediction of precipitation data.
The nonlinear autoregressive exogenous (NARX) is a nonlinear time series model
with exogenous variable inputs. Exogenous variables are external variables that have an
impact on the observed variables. Algebraically, the NARX model can be written as fol-
lows:
= ( + +⋯+ + + +⋯)+ , (1)
where is the main variable to be observed and is the exogenous variable that ex-
plains [35].
The artificial neural network (ANN), also referred to as neural network (NN), is an
information processing system that works in the same way with biological neural net-
works [36]. According to the study in [26], the main benefit of NN is a flexible nonlinear
modeling function. Modeling with NN does not require any specific initial model specifi-
cations. Instead, the model is built based on the properties of the data. One of the devel-
opments of the neural network prediction method is the NARX NN method. The NARX
NN method is a nonlinear autoregressive method that uses the neural network (NN) func-
tion to predict time series data using additional exogenous variables (in addition to the
main observed variables) to produce more accurate estimates [37,38]. Based on the net-
work architecture, NARX NN is divided into two parts, namely the serial–parallel model,
which is the feed-forward neural network (FFNN), and the parallel model, which is the
recurrent neural network (RNN). In the series–parallel model, the future value of the time
series is derived from the current and/or past values of and the actual past values of
the time series [39].
The analysis stages were carried out on the basis of eight criteria:
1. Splitting data according to the rolling origin cross-validation (ROCV) series
Initially, prior to performing the procedures to form a network architecture, we need
to split the data into two parts, namely data training and data testing. The purpose of data
splitting is to collect the ideal amount of data for the training and exam process. Therefore,
Atmosphere 2022, 13, 302 6 of 17

the obtained results are optimal. Testing data are usually around 20% of the amount of
data in total, although their value can be changed depending on the length of the overall
data and the forecast that will be conducted. The ideal amount of test data is at least as
much as the length of the prediction to be performed [40]. The data released are carried
out according to the ROCV series.
2. Structure of the network architecture
An architecture network is an arrangement of units in the coating and the pattern of
the relationship between the layers. This research uses the NARX NN series–parallel
model with feed-forward architecture. The multi-layer perceptron (MLP) is used in the
NARX NN architecture since MLP has a structure, which can learn non-linear mapping.
The steps required in forming a network architecture are the determination of the number
of input units, the number of hidden layers, the number of hidden units, and the number
of output units, which are used in the network. The unit input of the network NARX NN
series–parallel model is the value of time (t), the observed variable (Y), and the exogenous
variable (X).
3. Selection of the activation function
The activation function is used in order to convert the input signal into an output
signal of each unit in the hidden layer and the output layer. There are no specific rules in
the selection of the activation function to be used. However, a non-linear activation func-
tion is required for multi-layer networks. Moreover, the activation function can be deter-
mined based on the algorithm in which the training was used. The activation function,
which is used for the algorithm backpropagation, must be continuous, differentiable, and
is a function which is not reduced in monotone. In this study, we will use tanh for the
hidden activation function and linear activation function of the output layer.

( )=
(2)
or ( ) = [1 + ( )][1 − ( )]

4. Normalization of data
Prior to performing the training process, especially in the run-up to any normaliza-
tion of data, the input data must be in the interval of the used activation function. The
data can be normalized using the min–max scaling technique with the following formula:
( − )( − )
= + (3)
−
where is the value of the data after normalization, is the original value of the data,
is the minimum value of the entire original data, is the maximum value of the
entire original data, a is the minimum range value, and b is the maximum range value.
5. Implementation of training and testing processes
The purpose of the training and testing process is to find the optimal specification
model, which produces minimal errors. The training process is carried out using an algo-
rithm and the most commonly used algorithm is backpropagation. The backpropagation
algorithm has several development versions, one of which is resilient backpropagation
(Rprop). Rprop is an algorithm with adaptive learning and convergence, which is faster
than backpropagation. The Rprop algorithm is divided into two parts, namely Rprop
without weight backtracking (Rprop-) and Rprop with weight backtracking (Rprop+). The
difference is the so-called pullbacks, which indicate that if the sign derivative partial
changes in the Rprop+ algorithm, then the amount of weight is directly reduced by the
amount of change in the weight of the previous iteration. In this study, the training pro-
cess was performed using an elastic backpropagation algorithm with weight backtracking
(Rprop+).
6. Evaluation of the forecast model from the MAPE value
Atmosphere 2022, 13, 302 7 of 17

The process of training and testing is carried out for more network architectures with
different hidden units. The model evaluation was conducted to find model specifications
with certain hidden units, which produce minimal error. The size of the model error is
calculated using MAPE from the prediction error value of each roll. MAPE can be calcu-
lated using the following formula:

1 −
= × 100% (4)

where the calculated value of R2 shows how effective the models are in forecasting. The
R2 equation is as follows:
∑( − )
= (5)
∑( − )

7. Prediction of exogenous variables

The prediction of the exogenous variables can be carried out using a forecasting
method that fits with the characteristics of the variables. In this study, the prediction was
performed using FFNN.
8. Prediction of main variables
The NARX NN models, with the smallest error size corresponding to results of the
evaluation, are used to predict the observed variables. Forecasting is accomplished with
all of the current and combined data on a natural logarithmic scale. Since the results from
the NARX NN model will have a value within the normalization interval on a natural
logarithmic scale, it is necessary to de-normalize the results to obtain the original forecast
value.

3. Results
3.1. NARX NN Model Formation
The NARX NN model was constructed using rainfall data as the observed variable
and Niño 3.4 index data as the exogenous variable. Prior to the formation of the NARX
NN model, the rainfall data were divided into training and testing data, while all of the
Niño 3.4 index data were used as input for training the NARX NN model. Figure 2 shows
the splitting of the training data (blue) and the testing data (green). Then, the NARX NN
architecture is created. The number of hidden layers used is one layer. The number of
hidden units used is determined by trial and error, where the number of hidden units
creates the smallest error size. The number of output units used is one unit since the de-
sired output is only one, which is the result of the rainfall forecast. The NARX NN rainfall
model network architecture is shown in Table 1.

Table 1. NARX NN rainfall model network architecture.

Unit Specifications
13 units, consisting of lag 1, 2, …, 365 from rainfall and the current
Input unit
value of Niño 3.4 index
Hidden layer 1 layer
Hidden unit 1, 2, 3, 4, 5, 6, 7 unit (trial and error)
Output unit 1 unit

Following the formation of the network architecture, the next stage is the process of
training and testing the model evaluation. The rainfall data and Niño 3.4 index data used
in the training process were first normalized using the min−max scaling technique with
the values of a = −0.8 and b = 0.8. The training process includes the determination activa-
Atmosphere 2022, 13, 302 8 of 17

tion functions and training algorithms. For the testing process, the network from the train-
ing process is used to forecast a period in advance. The training and testing processes
were carried out for seven rainfall model network architectures with different hidden
units. The training and testing processes of each network architecture are repeated with
each rolling, as shown in Figure 3 (ROCV method). Then, the model is evaluated by cal-
culating the MAPE value for each network architecture with certain hidden units. The
results of trial and error of the seven network architectures with different numbers of hid-
den units can be seen in Table 2.

Rolling to-
1 1 2 3 …............. 200 201
2 1 2 3 …..................... 201 202
3 1 2 3 …............................ 202 203
4 1 2 3 …................................... 203 204
5 1 2 3 ….......................................... 204 205
6 1 2 3 …................................................. 205 206
7 1 2 3 …........................................................ 206 207
8 1 2 3 …............................................................... 207 208
9 1 2 3 …...................................................................... 208 209
10 1 2 3 …............................................................................. 209 210
⋮ 1 2 3 ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋱ ⋱
51 1 2 3 …........................................................................................... 250 251
Figure 3. Rainfall data distribution.

Table 2. The error size of the NARX NN rainfall model.

Architecture Hidden Unit MAPE Test

1 6.399138
2 6.935423
3 6.613024
Input unit = 13
4 6.587894
Hidden layer = 1
5 6.809819
6 6.857698
7 6.259928

In Table 2, it can be seen that the network architecture that generates the minimum
error size is the architecture with thirteen input units, one hidden layer, seven hidden
units, and one output unit or it can be seen as the NARX NN model (13-7-1) with a MAPE
value of 6.26% and R2 of 85.37%. A visualization of the comparison result of the training
process prediction with the test data according to the ROCV method can be seen in Figure
4. The NARX NN (13-7-1) model is applied to all of the data and is used to predict rainfall
data. The rainfall is known to be influenced by the Niño 3.4 index. Therefore, to achieve
the rainfall forecast result, it is first necessary to forecast the Niño 3.4 index.
Atmosphere 2022, 13, 302 9 of 17

Figure 2. Graphically compare the forecast of the training process with rainfall data.

The network architecture visualization of the NARX NN model (13-7-1) is shown in

Figure 5.

Figure 3. The network architecture of NARX NN model for rainfall.

3.2. Forecasting Exogenous Variables (Niño 3.4)

The Niño 3.4 forecasting is conducted with the feed-forward neural network (FFNN).
The steps performed are similar to the steps in Section 3.1. The model architecture for the
FFNN model for the Niño 3.4 prediction is shown in Table 3.

Table 3. The FFNN model network architecture.

Unit Specifications
Input unit 12 unit (lag 1, 2, …, 12)
Hidden layer 1 layer
Hidden unit 1, 2, 3, 4, 5, 6, 7 unit (trial and error)
Output unit 1 unit
Atmosphere 2022, 13, 302 10 of 17

Following the formation of the network architecture, the next stage is the process of
training and testing and model evaluation. The Niño 3.4 data used in the training process
were first normalized using the min−max scaling technique with the values of a = −0.8 and
b = 0.8. Using the same training and testing phases as in Section 3.1, we performed seven
network architectures with different numbers of hidden units of trial and error. The re-
sults for the MAPE value of Niño 3.4 data are shown in Table 4.

Table 4. The error size of the FFNN model.

Architecture Hidden Unit MAPE Test

1 4.53155
2 4.501856
3 4.514769
Input unit = 12
4 4.500933
Hidden layer = 1
5 4.443294
6 4.623074
7 7.566102

In Table 4, it can be seen that the network architecture that produces the minimum
error size is the architecture with twelve input units, one hidden layer, five hidden units,
and one output unit or it can be seen as the FFNN model (12-5-1) for the Niño 3.4 with a
MAPE of 4.44% and R2 of 95.27%. A visualization of the comparison result of the training
process prediction with the testing data according to the ROCV method can be seen in
Figure 6. The following plot is a comparison between the actual data and the predicted
data of the FFNN (12-5-1) model for all of the Niño 3.4 data. Figure 6 shows a visualization
of the actual and forecast Niño 3.4 data. Figure 7 shows the actual and predicted value of
all the Niño 3.4 data.

Figure 4. A comparison plot of the training process forecasting results on the Niño 3.4 testing data.
Atmosphere 2022, 13, 302 11 of 17

Figure 7. Graphs of the actual and predicted value of all the Niño 3.4 data.

The network architecture visualization of the FFNN model (12-5-1) is shown in Fig-
ure 8.

Figure 8. The network architecture of the FFNN model for Niño 3.4.

The FFNN (12-5-1) model from all of the data is used to forecast Niño 3.4. The forecast
period for Niño 3.4 is at least as long as the forecast period for the rainfall. In this study,
forecasts are conducted for the next six periods and the results of the Niño 3.4 forecast are
shown in Table 5. Here, the Niño 3.4 forecast results are combined with the actual Niño
3.4 data to produce 261 combined periods of Niño 3.4 data, comprising 251 periods of
actual data, in addition to six periods of the Niño 3.4 forecast results. The combined Niño
3.4 data are used to input the exogenous variables in the best NARX NN model to predict
rainfall.
Atmosphere 2022, 13, 302 12 of 17

Table 5. Niño 3.4 forecast results.

Period Forecast
December 2021 −0.6212955
January 2022 −0.6976738
February 2022 −0.5343275
March 2022 −0.4814957
April 2022 −0.3752520
May 2022 −0.2630829

3.3. Forecasting the Main Variable (Rainfall)

In Section 3.1, the process of creating the NARX NN model was carried out using
actual data on the rainfall and actual data on the Niño 3.4. Following the receival of the
Niño 3.4 forecast results in Section 3.2, the rainfall forecast can be carried out with the best
NARX NN model obtained, namely NARX NN (13-7-1). The NARX NN (13-7-1) model is
applied to all of the current rainfall data with the combined Niño 3.4 data as the exogenous
variable. In Figure 9, a plot is shown between the actual data and predicted data from the
NARX NN model (13-7-1) when applied to all of the rainfall data. The rainfall forecast for
the next six periods using all of the current rainfall data and the combined Niño 3.4 data
are shown in Table 6. In Figure 10, a comparison is shown of the actual data and the fore-
cast results of the rainfall variables and the Niño 3.4 variables.

Figure 9. Graph of the actual and predicted values of all rainfall data.

Table 6. Forecast rainfall results.

Period Forecast
December 2021 277.7361
January 2022 273.1235
February 2022 342.9711
March 2022 335.8127
April 2022 276.0515
May 2022 170.4804
Atmosphere 2022, 13, 302 13 of 17

Figure 10. Graph of rainfall and Niño 3.4 results.

Based on the forecast results of the Niño 3.4 index, the prediction is that it will rain
or still be in the rainy season for the next 6 months. In Table 6, it can be seen that the
Bandung city rainfall forecast using the NARX NN model provides a prediction that the
rainfall will be high in February and March 2022. In Figure 6, it can be seen that the Ban-
dung city rainfall forecast in the period from December–May 2021 provides a fluctuating
forecast value, depending on the historical data or rainfall data in the previous period.
The forecast results can be used as a reference for relevant agencies in anticipating the
possibility of flooding in the city of Bandung and taking extra care, especially during Feb-
ruary and March.

4. Discussion
The rainfall is a variable that is affected by Niño 3.4. In addition, the city of Bandung
has several extreme points with very high rainfall. Very high levels of rainfall can cause
flooding. Therefore, in order to cope with the flooding, it is necessary to forecast the rain-
fall using an exogenous variable, namely Niño 3.4. The forecast results can be used as a
reference for relevant authorities to foresee the possibility of flooding in Bandung city.
The amount of data used for the training process affects the ability of the system in
the forecasting process. This study uses data with 80% training data and 20% testing data
[41]. Here, the number of testing data was 51 and the rainfall data were distributed using
a number of ROCV methods. The past value of the rainfall and the current value of the
Niño 3.4 are used to predict the rainfall. The past value of the rainfall used is 12 lags since
the data interval used is monthly data [42], where is influenced by , ,…, .
In addition, is affected by the current Niño 3.4 value, which is referred to as . There-
fore, the number of units used is 12 units, comprising , ,…, and . As the
activation function, the tanh activation function in the hidden layer and the linear activa-
tion function in the output layer are used [43]. In addition, the training algorithm used is
currently Rprop+ [44] and the Niño 3.4 data are used as an exogenous variable.
Based on trial and error, the best model for NARX NN (13-7-1) was obtained with a
MAPE value of 6.26% (Table 2). In Figure 4, a comparison is shown of the training process
forecast results to the test data from the rainfall. The best model for the exogenous variable
is the (12-5-1) FFNN model with a MAPE value of 4.44% (Table 4). In Figure 6, a compar-
ison is shown of the training process prognosis results with the test data from the Niño
Atmosphere 2022, 13, 302 14 of 17

3.4. The results of this study show that the Niño 3.4 affects the movement of rainfall. In
addition, the results predict the value of rainfall for the next six periods and Niño 3.4 as
input for exogenous variables using the best NARX NN model (Table 5).
Moreover, the results provide suggestions for further research, which can be based
on trial and error for the determination of input and hidden layers. There are two alterna-
tives to predict Y with the NARX NN model, namely by predicting the X variable first, as
in the study or by building a NARX NN model with lag X (without ). Both approaches
have limitations. Predicting the Y variable first causes uncertainty, while using lag X as-
sumes that Y is only related to lag X, where the assumption does not necessarily agree
with the theory. The forecast results from the neural network method are only available
in the form of values. The Bayesian approach, Monte Carlo dropout or resampling with
the jackknife and bootstrap methods can be used to obtain forecast results in the form of
intervals [45].
There are several studies regarding the physical mechanism, in which these rainfall
cycles are increasing over the regions. The authors of [46] investigated the spatiotemporal
changes in drought characteristics in Pakistan during the Rabi and Kharif cropping sea-
sons. This study used the nonparametric Mann–Kendall, Sen’s Slope, and Sequential
Mann–Kendall test methods to determine the significance and historical trends of climate
factors on drought. From this study, it was found that the Niño 3.4 index, sea surface
temperature, and the multivariate El Niño–Southern Oscillation (ENSO) are factors that
strongly influence seasonal droughts across Pakistan. Furthermore, in [47], the research
on drought in South Asia related to agriculture is known to indicate that MERRA-2, CPC,
FLDAS (soil moisture), GPCC, and CHIRPS (precipitation) are equal and constant across
the entire four regions of South Asia (Northwest, Southwest, Northeast, and Southeast).
On the other hand, GLDAS and ERA5 remain poor compared to the other soil moisture
products and the identified drought conditions in regions one (Northwest) and three
(Northeast).
The authors of [48] carried out research on the same topic regarding drought affect-
ing food and agricultural security in South Asia, but with attention to the performance of
the evaporative stress index (ESI), vegetation health index (VHI), enhanced vegetation
index (EVI), and standardized anomaly index (SAIs). The authors of [49] carried out re-
search on the possible cycles, precursors, and associated mechanisms of drought over Pa-
kistan by paying attention to the rainfall behavior in Pakistan using monthly rainfall data
in the period from 1981–2017. The study also analyzed other climatic factors, and it was
found that extreme drought events are highly correlated with wind patterns and intrinsic
weather systems in The Pacific and Indian Oceans.
The authors of [50] analyzed spatiotemporal changes in air temperature in Myanmar
using nonparametric analysis. Based on this study, significant results of the temperature
trend are shown. In addition, it is known the Indian Ocean Dipole (IOD) influence on air
temperature over Myanmar is more prevalent than the El Niño–Southern Oscillation
(ENSO). Another study on the research area of Myanmar is regarding the interdecadal
variability in monsoon rainfall [51]. It is known that the Myanmar summer monsoon rain-
fall is positively correlated with the Atlantic multidecadal oscillation (AMO) and nega-
tively correlated with the Pacific decadal oscillation (PDO).

5. Conclusions
In conclusion, the prediction of the rainfall value is conducted using the NARX NN
method with the Rprop+ algorithm. The results show that NARX NN (13-7-1) with a
MAPE value of 6.26% and R2 of 85.37% is best suited for the prediction of this phenome-
non. To utilize the NARX NN model, it is necessary to forecast the Niño 3.4 with the FFNN
using the Rprop+ algorithm. This produces the best FFNN model (12-5-1) with a MAPE
value of 4.44% and R2 of 95.26%. In addition, this study produces forecast results for the
next six periods, which can be used as a reference for relevant authorities to foresee the
possibility of flooding in Bandung city. From the forecast results, it can be concluded that
Atmosphere 2022, 13, 302 15 of 17

the highest rainfall forecasts in the city of Bandung are in February 2022, and will slowly
decrease in March 2022. To prevent hydro-meteorological disasters, such as floods in Ban-
dung city, the community can clear waterways, such as clogged drains, rivers, and dams,
as well as prepare tools for evacuation [52]. The NARX NN model may be an alternative
for the prediction of rainfall value, which has the capability to follow random patterns
from rainfall data and capture extreme rainfall values. Meanwhile, the FFNN method can
be an alternative for the prediction of Niño 3.4 value.
For the next investigation, predictions can be conducted using other input variables
related to precipitation, such as B. AUSMI and WNPMI. Then, the prediction can be con-
ducted using other methods, such as the Bayesian approach, Monte Carlo dropout or
resampling with the jackknife and bootstrap methods in the form of intervals [53].

Author Contributions: Conceptualization, R.S.P., T.T. and B.N.R.; Data curation, R.S.P.; Formal
analysis, M.D.P., N.S., R.S.P., T.T. and B.N.R.; Methodology, N.S. and M.D.P., R.S.P., T.T. and B.N.R.;
Project administration, T.T., R.S.P., and B.N.R.; Resources, N.S., M.D.P., R.S.P., T.T. and B.N.R.; Soft-
ware, M.D.P. , N.S., R.S.P., T.T. and B.N.R.; Supervision, R.S.P.; Visualization, N.S. and M.D.P.; Writ-
ing—original draft, N.S., M.D.P., R.S.P., T.T. and B.N.R.; Writing—review & editing, M.D.P., N.S.,
R.S.P., T.T. and B.N.R. All authors have read and agreed to the published version of the manuscript.
Funding: This research is supported by Department of Statistics, Padjadjaran University and Rector
Universitas Padjadjaran who supported this research by Academic Leaderships Grant (ALG) with
contract number 1959/UN6.3.1/PT.00/2021.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: UCSB CHIRPS v2p0 Monthly Global CHIRPS Precipitation available
online: https://iridl.ldeo.columbia.edu/SOURCES/.UCSB/.CHIRPS/.v2p0/.monthly/.global/.precipi-
tation/X/%28110.85E%29VALUES/T/%28Jan2021%29%28Sep2021%29RANGEEDGES/Y/%287.075
S%29VALUES/datatables.html (accessed on 13 January 2022) and APCC. Pacific SST Indices Moni-
toring available online: https://apcc21.org/ser/indic.do?lang=en (accessed on 13 January 2022).
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Utina, R. Global Warming. In Jurnal SAINTEK UNG; 2009; pp. 1–11. Available online: https://repository.ung.ac.id/kar-
yailmiah/show/324/pemanasan-global-dampak-dan-upaya-meminimalisasinya.html (accessed on 2 February 2022).
2. Iyakaremye, V.; Zeng, G.; Yang, X.; Zhang, G.; Ullah, I.; Gahigi, A. Science of the Total Environment Increased high-temperature
extremes and associated population exposure in Africa by the mid-21st century. Sci. Total Environ. 2021, 790, 148162.
https://doi.org/10.1016/j.scitotenv.2021.148162.
3. Mulyani, A.S. Global Warming, Causes, Impacts and Anticipation. 2021. Available online: http://reposi-
tory.uki.ac.id/4908/1/PEMANASANGLOBAL.pdf (accessed on 2 February 2022).
4. Iyakaremye, V.; Zeng, G.; Ullah, I.; Gahigi, A.; Mumo, R.; Ayugi, B. Recent Observed Changes in Extreme High-Temperature
Events and Associated Meteorological Conditions over Africa. Int. J. Climatol. 2021, https://doi.org/10.1002/joc.7485.
5. Sipayung, S. The Spectrum Analysis of Meteorogical Elements in Indonesia. Master’s Thesis, Nagoya University, Nagoya, Ja-
pan, 1995.
6. Pramudia, A. Climate Dynamics in Indonesia; Agricultural Research and Development Agency: Jakarta, Indonesia, 2020.
7. McBride, M.; Haylock, M.R.; Nicholls, N. Relationships between the Maritime Continent Heat Source and the El Niño–Southern
Oscillation Phenomenon Relationships between the Maritime Continent Heat Source and the El Niño–Southern Oscillation
Phenomenon. J. Clim. 2003, 0442, 2905–2914. https://doi.org/10.1175/1520-0442(2003)016<2905:RBTMCH>2.0.CO;2.
8. Sein, Z.M.M.; Ullah, I.; Iyakaremye, V.; Azam, K.; Ma, X.; Syed, S.; Zhi, X. Observed spatiotemporal changes in air temperature,
dew point temperature and relative humidity over Myanmar during 2001–2019. Meteorol. Atmos. Phys. 2022, 134, 10–15.
https://doi.org/10.1007/s00703-021-00837-7.
9. Sein, Z.M.M.; Zhi, X.; Ullah, I.; Azam, K.; Ngoma, H.; Saleem, F.; Xing, Y.; Iyakaremye, V.; Syed, S.; Hina, S.; et al. Recent
variability of sub-seasonal monsoon precipitation and its potential drivers in Myanmar using in-situ observation during 1981–
2020. Int. J. Climatol. 2021, https://doi.org/10.1002/joc.7419.
10. Robinson, P.J.; Henderson-Sellers, A. Contemporary Climatology; Routledge: New York, NY, USA, 2014.
11. Tjasyono, B. Meteorologi Indonesia; Meteorology Climatology and Geophysics Council Meteorology, Climatology and Geophys-
ics Agency: Jakarta, Indonesia, 2012; Volume 1.
Atmosphere 2022, 13, 302 16 of 17

12. IPRC. International Pasific Research Center. IPRC Climate. 2012. Available online: http://iprc.soest.hawaii.edu/ (accessed on 2
February 2022).
13. Ina, J.; Ruminta Bayong, T.H.; Atika, L.; Harijono, S.B. The Effect of El Niño, La Niña and Indian Ocean Dipole on Pentad
Rainfall in Indonesia. J. Bionatura 2008, 10, 168–177. Available online:
https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwjVx92QlfX1AhU3iv0HHZsQBgkQFno
ECAwQAQ&url=https%3A%2F%2Fsiteproxy.ruqli.workers.dev%3A443%2Fhttps%2Fjurnal.unpad.ac.id%2Fbionatura%2Farticle%2Fdownload%2F7735%2F3591&usg=AOv-
Vaw1eWTNIOGVSUyHyXFO-HL1t (accessed on 13 January 2022).
14. Rudiyanto, A. Atmospheric Climate Projection, Bappenas, Jakarta, Indonesia. 2018. Available online: https://lcdi-
indonesia.id/wp-content/uploads/2020/05/Proyeksi-Iklim-Atmosferik (accessed on 2 February 2022).
15. Anisa, K.N. Analysis of the Relationship between Rainfall and El-Nino Southern Oscillation Indicators in East Java Rice Pro-
duction Centers Using the Copula Approach. J. Sains Seni 2015, 4, 146.
16. Oded, M. Government Agencies Performance, PPIDBandung, Bandung, Indonesia. 2020. Available online:
https://ppid.bandung.go.id/wp-content/uploads/2021/07/LKIP-Kota-Bandung-2020 (accessed on 2 February 2022).
17. Jabar. Prov, Bandung City Profile. PPIDBandung, Bandung, Indonesia. 2020. Available online:
https://ppid.bandung.go.id/?media_dl=9872 (accessed on 2 February 2022).
18. Gutomo, M.d.T. Flood and Landslide Natural Disasters and Community Efforts in Mitigating. J. PKS 2015, 14, 437–452.
19. Tempo.co. Hegarmanah, Bandung Hit by Flood. 2008. Available online: https://nasional.tempo.co/read/116481/hegarmanah-
bandung-diterjang-banjir (accessed on 2 February 2022).
20. Putra, M.A. A Total of 16 Points in Bandung Were Submerged by Floods. 2016. Available online:
https://www.cnnindonesia.com/nasional/20161114000828-20-172377/sebanyak-16-titik-di-bandung-terendam-banjir (accessed
on 2 February 2022).
21. Kartika, T.; Sulandari, W.; Pratiwi, H. Forecasting rainfall in the city of Bandung using singular spectrum analysis. J. Ilm. Mat.
2021, 8, 56–65.
22. Danung, A. Floods Inundate Six Districts in Bandung Regency. 2020. Available online: https://bnpb.go.id/berita/banjir-rendam-
enam-kecamatan-di-kabupaten-bandung (accessed on 2 February 2022).
23. UCSB CHIRPS v2p0 Monthly Global CHIRPS Precipitation. 2021. Available online: https://iridl.ldeo.colum-
bia.edu/SOURCES/.UCSB/.CHIRPS/.v2p0/.monthly/.global/.precipitation/X/%28110.85E%29VAL-
UES/T/%28Jan2021%29%28Sep 2021%29RANGEEDGES/Y/%287.075 S%29VALUES/datatables.html (accessed on 13 January
2022).
24. APCC. Pacific SST Indices Monitoring. 2021. Available online: https://apcc21.org/ser/indic.do?lang=en (accessed on 13 January
2022).
25. Desouky, M.A.A.; Abdelkhalik, O. Wave prediction using wave rider position measurements and NARX network in wave
energy conversion. Appl. Ocean Res. 2019, 82, 10–21. https://doi.org/10.1016/j.apor.2018.10.016.
26. Zhang, G.; Patuwo, B.E.; Hu, M.Y. Forecasting with artificial neural networks: The state of the art. Int. J. Forecast. 1998, 14, 35–
62.
27. Ghamariadyan, M.; Imteaz, M.A. A wavelet artificial neural network method for medium-term rainfall prediction in Queens-
land (Australia) and the comparisons with conventional methods. Int. J. Climatol. 2021, 41, E1396–E1416.
https://doi.org/10.1002/joc.6775.
28. Shrivastava, G. Application of Artificial Neural Networks in Weather Forecasting: A Application of Artificial Neural Networks
in Weather Forecasting: A Comprehensive Literature Review. Int. J. Comput. Appl. 2012, 51, 17–29. https://doi.org/10.5120/8142-
1867.
29. Pham, B.T.; Le, L.M.; Le, T.-T.; Bui, K.-T.T.; Le, V.M.; Ly, H.-B.; Prakash, I. Development of advanced artificial intelligence
models for daily rainfall prediction. Atmos. Res. 2020, 237, 104845. https://doi.org/10.1016/j.atmosres.2020.104845.
30. Diez-Sierra, J.; Jesus, M. Long-term rainfall prediction using atmospheric synoptic patterns in semi- arid climates with statistical
and machine learning methods. J. Hydrol. 2020, 586, 124789. https://doi.org/10.1016/j.jhydrol.2020.124789.
31. Rahman, S.; Reza, A. Are precipitation concentration and intensity changing in Bangladesh overtimes? Analysis of the possible
causes of changes in precipitation systems. Sci. Total Environ. 2019, 690, 370–387. https://doi.org/10.1016/j.scitotenv.2019.06.529.
32. Ruiz, L.G.B.; Cuéllar, M.P.; Calvo-Flores, M.D.; Jiménez, M.D.C.P. An Application of Non-Linear Autoregressive Neural Net-
works to Predict Energy Consumption in Public Buildings. Energies 2016, 9, 684. https://doi.org/10.3390/en9090684.
33. Ranjit, K.P.; Sinha, K. Forecasting crop yield: A comparative assessment of arimax and narx model. Indian Agric. Stat. Res. Inst.
2016, 1, 77–85.
34. Wunsch, A.; Liesch, T.; Broda, S. Forecasting groundwater levels using nonlinear autoregressive networks with exogenous in-
put (NARX). J. Hydrol. 2018, 567, 743–758. https://doi.org/10.1016/j.jhydrol.2018.01.045.
35. Boussaada, Z.C. A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct
Solar Radiation. Energies 2018, 11, 620. https://doi.org/10.3390/en11030620
36. Fausett, L. Fundamentals of Neural Networks Architectures, Algorithms, and Applications; Prentice Hall, Inc.: London, UK, 1994.
37. Cadenas, E.; Rivera, W.; Campos-Amezcua, R.; Heard, C. Wind Speed Prediction Using a Univariate ARIMA Model and a
Multivariate NARX Model. Energies 2016, 9, 109. https://doi.org/10.3390/en9020109
38. Chen, R.J.; Bloomfield, P.; Fu, J.S. An evaluation of alternative forecasting methods to recreation visitation. J. Leis. Res. 2003, 35,
441–454. https://doi.org/10.1080/00222216.2003.11950005
Atmosphere 2022, 13, 302 17 of 17

39. Gao, Y.; Er, M.J. NARMAX time series model prediction: feedforward and recurrent fuzzy neural network approaches. Fuzzy
Sets Syst. 2014, 150, 331–350.
40. Hyndman, R.J.; Athanasopoulos, G. Forecasting: Principles and Practice; Monash University: Melbourne, Australia, 2018.
41. Rianto, Y.; Kuntoro, A.Y. Prediction of Netizen Tweets Using Random Forest, Decision Tree, Naïve Bayes, and Ensemble Algo-
rithm. Sinkron 2020, 5, 58–71.
42. Ladiray, D.; Palate, J.; Mazzi, G.; Proietti, T. Seasonal Adjustment of Daily Data. In Proceedings of the 16th Conference of IAOS,
Paris, France, 19–21 September 2018; pp. 1–26.
43. Feng, J.; Lu, S. Performance Analysis of Various Activation Functions in Artificial Neural Networks. J. Phys. 2019, 1237, 022030.
44. Anastasiadis, A.D.; Magoulas, G.D.; Vrahatis, M.N. An Efficient Improvement of the Rprop Algorithm. In Artificial Neural Net-
works in Pattern Recognition (ANNPR 2003), Proceedings of the First International Association of Pattern Recognition-TC3 Workshop
(IAPR 2003), Florence, Italy, 12–13 September 2003; Gori, M., Marinai, S., Eds.; Springer: Berlin/Heidelberg, Germany, 2003; pp.
197–201.
45. Ghoshal, B.; Tucker, A.; Sanghera, B.; Wong, W.L. Estimating uncertainty in deep learning for reporting confidence to clinicians
in medical image segmentation and diseases detection. Comput. Intell. 2019, 37, 701–734.
46. Ullah, I.; Ma, X.; Yin, J.; Saleem, F.; Syed, S.; Omer, A.; Habtemicheal, B.A.; Liu, M.; Arshad, M. Observed changes in seasonal
drought characteristics and their possible potential drivers over Pakistan. Int. J. Climatol. 2021, https://doi.org/10.1002/joc.7321.
47. Shahzaman, M.; Zhu, W.; Ullah, I.; Mustafa, F.; Bilal, M.; Ishfaq, S.; Nisar, S.; Arshad, M.; Iqbal, R.; Aslam, R.W. Comparison of
multi-year reanalysis, models, and satellite remote sensing products for agricultural drought monitoring over south asian coun-
tries. Remote Sens. 2021, 13, 3294. https://doi.org/10.3390/rs13163294.
48. Shahzaman, M.; Zhu, W.; Bilal, M.; Habtemicheal, B.A.; Mustafa, F.; Arshad, M.; Ullah, I.; Ishfaq, S.; Iqbal, R. Remote sensing
indices for spatial monitoring of agricultural drought in south asian countries. Remote Sens. 2021, 13, 2059.
https://doi.org/10.3390/rs13112059.
49. Hina, S.; Saleem, F.; Arshad, A.; Hina, A.; Ullah, I. Droughts over Pakistan: possible cycles, precursors and associated mecha-
nisms. Geomat. Nat. Hazards Risk 2021, 12, 1638–1668. https://doi.org/10.1080/19475705.2021.1938703.
50. Sein, Z.M.M.; Ullah, I.; Syed, S.; Zhi, X.; Azam, K.; Rasool, G. Interannual variability of air temperature over myanmar: The
influence of enso and iod. Climate 2021, 9, 35. https://doi.org/10.3390/cli9020035.
51. Sein, Z.M.M.; Ullah, I.; Saleem, F.; Zhi, X.; Syed, S.; Azam, K. Interdecadal variability in myanmar rainfall in the monsoon season
(May–october) using eigen methods. Water 2021, 13, 729. https://doi.org/10.3390/w13050729.
52. Jati, R. Susur Sungai Upaya Cegah Potensi Bahaya Banjir Bandang. BNPB. 2020. Available online: https://bnpb.go.id/berita/su-
sur-sungai-upaya-cegah-potensi-bahaya-banjir-bandang- (accessed on 2 February 2022).
53. Toharudin, T.; Pontoh, R.S.; Caraka, R.E.; Zahroh, S.; Lee, Y.; Chen, R.C. Employing long short-term memory and Facebook
prophet model in air temperature forecasting. Commun. Stat.-Simul. Comput. 2021.
https://doi.org/10.1080/03610918.2020.1854302

View publication stats