Big Data Analytics as Game Changer in Dealing Impact of Climate

Change in Malaysia: Present and Future Research

Mohammad Fikry Abdullah

1,2

, Mohd Zaki Mat Amin

, Zurina Zainol

and

Marini Mohamad Ideris

Leeds University Business School, University of Leeds, Leeds, U.K.

National Hydraulic Research Institute of Malaysia (NAHRIM), Selangor, Malaysia

Keywords: Big Data Analytics, Analytical Capabilities, Decision Making, Climate Change.

Abstract: Data has become a vital and vigorous resource to support the organisation in a data-driven decision-making

environment. The emergence of digital transformation has revolutionised data utilisation and management

ecosystem, which translated and upscaled the value of data to become a new asset in the organisation.

Realisation on the importance of data, Big Data Analytics (BDA) in organisations is part of initiatives to

harvest and maximise the potential use of data through data analytics capabilities. N-HyDAA development

has encapsulated BDA through integration and analytics of data, information, knowledge and expertise from

the expert group in dealing with issues related to the impact of climate change such as water-related disaster

and water resources management. Based on N-HyDAA capabilities, there are more potentials and

opportunities in the new research area to explore for better cohesion in supporting decision-making.

1 CLIMATE CHANGE &

MALAYSIA SCENARIO

Climate change (CC) is no longer rhetoric; it is real

and confirmed as the impact of CC is real and

happening. The changes in climate will aggravate the

risks and effects to the country, where it will cause

billions of losses from economic, environmental, and

social aspects. CC is not just a meteorological issue.

It is beyond such changes in temperature, rainfall

pattern or sea-level rise. The changes in one aspect

may lead to another aspect. Changes in rainfall

intensity will cause a significant effect on water level

and water quality. Changes in sea-level rise will affect

the land use development in the coastal area.

The evidence for rapid CC is getting compelling

and persuasive from series of indicators identified

such as global temperature rise, warming oceans,

shrinking ice sheets, glacial retreat, decreased snow

cover, sea-level rise, declining arctic sea ice, extreme

events, and ocean acidification. One of the significant

impacts of CC is the frequency and incidence of a

natural disaster where it becomes more extreme and

created dangerous consequences such as severe flood

and drought events. Unusual and unique events such

as tsunami, typhoon, landslide, which are previously

rare become more frequent and higher in magnitude

compare to the past.

Thus, extensive strategies are required in

employing mitigation and adaptation planning to

undermine the impact and vulnerability of CC.

Malaysia Government has given a serious

commitment in CC aspects at national and

international levels. Through 21

Conference of the

Parties to the United Nations Framework Convention

on Climate Change (COP21) in 2015, the

implementation of CC adaptation has been

emphasized by Malaysia especially for water security

and availability, coastal, food and health sectors.

During COP24, Malaysia has expressed its

continuing commitment to reducing Greenhouse

Gases emissions by 25% by 2030.

Climate-related natural disasters cost Malaysia

approximately USD1.8b from 1998 to 2018, where

the impact on Malaysia is apparent and varies from

floods, storms, droughts and other extreme weather

events (Zurairi, 2018). Recognising the impact of the

CC in Malaysia, NAHRIM's involvement in issues

related to impact of the CC has begun since 2008 with

the appointment of NAHRIM as the Regional Water

Knowledge Hub for Climate Change and Adaptation.

Since then, various studies have been exercised by

Abdullah, M., Mat Amin, M., Zainol, Z. and Mohamad Ideris, M.

Big Data Analytics as Game Changer in Dealing Impact of Climate Change in Malaysia: Present and Future Research.

DOI: 10.5220/0009794404610469

In Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS 2020), pages 461-469

ISBN: 978-989-758-426-8

461

NAHRIM for adaptation, adoption, and mitigation

strategies and policy in tackling issues in CC.

From studies conducted, voluminous data are

created and recreated which supports various R&D

activities aligned with sustainable development as

well as reduce the risk and impact of CC. Abdullah,

Ibrahim, and Zulkifli (2017a) mentioned data

management process for a natural disaster is

challenging due to its presence in large volume and

heterogeneous sources. In addition to that, the

emergence of technology and trend of using

projection data plays imperative roles in managing

issues related to CC nowadays.

2 BIG DATA ANALYTICS (BDA) &

DATA ANALYTICS

CAPABILITIES CONCEPT

2.1 Big Data Analytics (BDA) Concept

Kaisler, Armour, Espinosa, and Money (2013)

defined BDA as the amount of data beyond

technologies capability to store, manage and process

efficiently which the limitations are only discovered

by a robust analysis of the data itself, explicit

processing needs, and the capabilities of the tools

used to analyse it.

BDA has been escalating in various sectors as it

increases the value of data in organisations for

different purposes. The awareness and understanding

of BDA among top management have been

familiarised to ensure how data can be analysed,

improved and enriched to become a new key

economic factor that can alleviate an organisation’s

performance (Abdullah et al., 2017a).

As reported by Meulen and Rivera (2014)

decision-maker must expand their efforts and

understanding to move organisations from using

traditional Business Intelligence that addresses

descriptive analysis (what happened) to advanced

analytics, which complements by answering the

"why," the "what will happen," and "how we can

address it".

BDA movement is driven by the fact that massive

amounts of very high-dimensional or unstructured

data are continuously produced and stored with much

cheaper cost than they used to be (Fan, Han, & Liu,

2014). This trend will have a deep impact on science,

engineering and business that offer new opportunities

and new challenges in data analysis (Fan et al., 2014).

BDA creates a radical shift in how we think about

research, thus reframing critical questions about the

constitution of knowledge, research processes,

information engagement, and the nature and

categorisation of reality (Boyd & Crawford, 2012).

BDA give promises for (i) exploring the hidden

structures of each subpopulation of the data, which is

not feasible and been treated as ‘outliers’ when the

sample size is small; (ii) extracting important

common features across many subpopulations even

when there are large individual variations (Fan et al.,

2014).

2.2 Data Analytics Capabilities

BDA capabilities are a form of concept broadly used

to determine the ability to exploit data analytics to

develop capabilities which equip it to develop costly-

to-imitate capabilities in the big data environment,

where different levels of big data and BDA capability

can influence and inform organisation decisions

(Amankwah-Amoah & Adomako, 2019). Apart from

that, data analytics support streamlining organisation

internal processes, identify trends, interpret and

monitor emerging risks and build a mechanism for

feedback and improvement through analytical

interpretation, recommendation, explanation and

solutions (George, 2018; Singh, 2018).

Demand for delivery of data and analytics at the

optimal point of impact will drive innovative machine

learning and, predictive and prescriptive analytics

integration from the core to the edge of the enterprise

which capitalises and trigger opportunities that can be

identified based on active, dynamic and empowered

(Hagerty, 2016).

Data and analytics are the brains of the

organisations that require proactive and reactive plans

that drive modern organisation operations in

decisions, interactions and processes to support the

organisation and IT outcomes (Hagerty, 2016).

Understanding the purpose behind analytics, trends,

shifts, and patterns are among the critical elements

that will avoid issues and misunderstanding of BDA

project implementation where decision-makers need

to understand the correlations between key variables

and engaging in problem-solving (Mark, 2016).

3 BACKGROUND OF STUDY:

BDA FOR CC IN MALAYSIA

Studies conducted by Yang, Su, and Chen (2017) and

Rahman, Di, and Esraz-Ul-Zannat (2017) explained

BDA play a vital role and can help in all four phases

of disaster management: prevention, protection,

IoTBDS 2020 - 5th International Conference on Internet of Things, Big Data and Security

462

mitigation, response and recovery, and also help in

taking actions to improve resilience to disasters. The

impact of BDA in environment and natural resources

covered diversified areas such as data management

(Faghmous & Kumar, 2014), decision-making

(Abdullah et al., 2018; Ford et al., 2016); application

(Hassani, Huang, & Silva, 2019; Lopez &

Manogaran, 2016) and so forth.

Based on studies conducted in BDA for CC

ecosystem, NAHRIM as a water and environment

research institute had started data analytics journey in

2015 through development of framework on BDA for

natural disaster management in Malaysia (Abdullah

et al., 2017a) and later continued with development

of Malaysia Climate Change Knowledge Portal (N-

HyDAA) as a knowledge portal for analytical

processing of hydro climatic data (Abdullah, Ibrahim,

& Zulkifli, 2017b).

N-HyDAA used BDA technology to accelerate

data processing with customisable computation

functions by utilising multi-cores and many-cores

(GPU) technologies. N-HyDAA was developed to

assist NAHRIM in visualising and analysing 1450

simulation-years of projected hydro-climate data for

Peninsular Malaysia based on 3,888 grids for 90

years. There are eight modules developed in N-

HyDAA, namely Drought, Drought & Temperature,

Rainfall & Runoff, Storm Centre, Streamflow,

Climate Change Factor, Water Stress Index (WSI)

and WSI Simulation.

Stimulation and optimisation of hydro climatic

data using BDA technology support the digital

transformation by revolutionising the way data has

been treated to support decision-making in dealing

with CC issues. The development of N-HyDAA was

recognised at the national level and international level

(Geospatial World, 2018) (APICTA, 2017) for its

innovation on applying BDA technology as a new

instrument for handling issues in environment and

water resources, especially in CC.

Details on N-HyDAA’s development and

application in various domain related to water and

environment can be read from Abdullah et al. (2018),

Abdullah et al. (2017b), Mat Amin (2016), Mohamed,

Mat Amin, Md Adnan, and Abdullah (2018) and

Ideris, Abdullah, Mat Amin, and Zainol (2018).

4 N-HyDAA: CASES STUDY OF

WATER YIELDS & WATER

STRESS IN MALAYSIA

Future water yields based on simulated future runoff

were evaluated on four different gas emissions

scenarios (B1, A1B, A2 and A1FI) by means of an

average of 14 projections (A1B, A2 and B1), average

A1B, average A2 and average B1 for period 2010 –

2100. The historical simulations were based on the

average runoff from three control run GCMs

(CCSM3, ECHM5 and MRI). Using N-HyDAA the

voluminous simulated data has been investigated

thoroughly using N-HyDAA. The result of water

yields for historical and future periods of 2030 and

2050 for 80 districts are given in Figures 1 and 2

respectively.

Figure 1: Comparison between simulated historical and

future water yields in 2030 (billion cubic meter) BCM.

Water yields in 2030 under the average of 14

scenarios, A1B and A2 are projected to increase

compared to historical period (by 2 BCM to 8 BCM)

except for B1 where the water yield is projected to

decrease by 3 BCM (Figure 1). In 2050, water yields

for all scenarios are projected to increase with a range

of 8 BCM to 17 BCM and the largest change of 195

BCM was obtained from the average A2 scenario.

Generally, the projected water yields for all districts

show increasing trends (more water), with the

exception of a few districts in Kedah and Johor.

In the context of WSI, the approach developed by

Stephen Pfister was used to construct the district-

based water stress indices through projected water

yield and water demand that is possibly impacted by

CC conditions. WSI is defined as an index calculated

based on Stephen Pfister’s model to represent the

level of water stress in a specific area by means of a

ratio of total water demand or consumption against

water yield or availability (Brown & Matlock, 2011).

Big Data Analytics as Game Changer in Dealing Impact of Climate Change in Malaysia: Present and Future Research

463

Figure 2: Comparison between simulated historical and

future water yields in 2050 (BCM).

Figure 3: WSI for each scenario based on district in 2030.

Figure 4: WSI for each scenario based on district in 2050.

The constructed district based on WSI for the

respective districts and time horizons are given in

Figure 3 and 4 for 2030 and 2050 respectively. WSI

is divided in to five stress categories namely, low

(<0.1); medium-low (0.1-0.2); moderate (0.2-0.5);

high (0.5-0.8) and extremely high (>0.8). Nearly high

and extremely high WSI are located in the West Coast

particularly in urban and high populated areas, and

also irrigation schemes. Overall, the highest and

smallest average WSI are projected Penang-Perlis-

Kedah-Klang Valley-Johor Bharu and Pahang-

Terengganu respectively.

Figure 5 shows the constructed WSI for the

average 14 scenarios in 2030 and 2050 whereby the

marked areas are the projected districts with the

increased WSI. For example, the high WSI in Sabak

Bernam, Selangor would affect the irrigation water

availability for Barat Laut Selangor Integrated

Agricultural Development Authority (IADA-BLS)

irrigation scheme, On the other hand, the extremely

high WSI in Johor Bharu will pose challenges to

Syarikat Air Johor (SAJ) to provide sufficient treated

water supply to the consumers.

Figure 5: WSI Comparison for AIB scenario in 2030 and

2050.

5 DISCUSSION AND FUTURE

RESEARCH AREA

BDA has reformed the way of data optimisation for

better utilisation and value with the integration of

analytical skills and representation of data and

information. The capability of BDA to create and

transform data to insight for supporting decision-

making evolved since the introductory of BDA in

various domains of application such as human

resource, disaster management, and business and how

it can improve the efficiency and effectiveness of the

business process, whether in supporting, operational

and management processes.

Decision-making becoming vital in managerial

process for a quality and cohesive decisions. Multi-

criteria decision making (MCDM), is a decision-

making process based on the progression of using

methods and procedure of multiple conflicting

criteria into the management planning process (Umm

e, Asghar, & Ieee, 2009) which is a target to resolve

problems having multiple objectives (Liu & Stewart,

2004).

IoTBDS 2020 - 5th International Conference on Internet of Things, Big Data and Security

464

MCDM can be defined as a collection of

methodologies for comparison, ranking and selecting

multiple alternatives having multiple attributes

(Levy, 2005). Numerous factors involved in decision-

making, which is impossible to rely on a single

criterion attribute or point of view (Zopounidis &

Doumpos, 2000). Thus, decision-maker is required to

select among several quantifiable or non-quantifiable

and several criteria (Pohekar & Ramachandran,

2004). Therefore, MCDM emerged as a hallmark and

new branch for supporting the decision-making

process (Umm e et al., 2009).

Table 1 summarised initial finding based on the

MCDM methods on three domains which revealed

natural disaster, water resource management and

policy and strategy planning are the most applied

MCDM method. Through a further details study, the

domain can be expanded and covering more extensive

areas related to CC focusing on projection data from

N-HyDAA.

Table 1: Application of MCDM in CC Domains.

Domain Sub-Domain Autho

Natural

Disaster

flood,

drought

Karamouz, Zeynolabedin,

and Olyaei (2015); Lee,

Choi, and Jun (2017); Song

and Chung (2016);

Zahmatkesh and Karamouz

(2017)

Policy

& Strategy

Planning

adaptation,

mitigation,

sustainable

development,

vulnerability

Buyukozkan and Uzturk

(2018); Chakraborty,

Sahoo, Majumdar, Saha,

and Roy (2019); Mardani,

Jusoh, Zavadskas,

Cavallaro, and Khalifah

(2015); Mensour, El

Ghazzani, Hlimi, and Ihlal

(2019); Ramya and Devadas

(2019); Simsek, Watts, and

Escobar (2018); Zavadskas,

Cavallaro, Podvezko,

Ubarte, and Kaklauskas

(2017); Zhu, Li, and Feng

(2019); ;

Water

Resource

Management

water

allocation,

groundwater

study,

water

system,

Alhumaid, Ghumman,

Haider, Al-Salamah, and

Ghazaw (2018); Amineh,

Hashemian, and Magholi

(2017); Birgani and

Yazdandoost (2018); Chung

and Kim (2014); Duan,

Deng, Deng, and Wang

(2016); Golfam, Ashofteh,

Rajaee, and Chu (2019)

Based on a study conducted by Akter and Wamba

(2017), there are a lot of opportunities to discover

significant research on big data and disaster

management area. In the area of a crisis analytics

platform, potential research can be focusing on

prescriptive analytics and models that integrate the

knowledge and expertise from subject matter experts,

practitioner and stakeholders. Integration knowledge

and insight from expert groups in N-HyDAA are

crucial in supporting the decision-making process

apart from relying on analytical data.

Leveraging the culture of BDA must be part of

strategic management, where emphasising on a

holistic and cohesive BDA culture across various

business core function without neglecting the

analytical competencies of the organisation either

from aspect technology, analytical capacity (people)

and process. It is imperative to develop skills in

analytics capabilities and to nurture the competence

for ensuring organisational agility, which requires

more knowledge exploration and experience that

needs to be shared and disseminate within the

organisation.

Apart from that, in every analysis stage, different

data analytics capabilities are essential and required

further understanding of analytics elements and data,

information, knowledge and wisdom concept can be

implemented in supporting the decision-making

process (Lokers, Knapen, Janssen, van Randen, &

Jansen, 2016). Factors or elements that contributed to

building data analytics capabilities need further

consideration for better delivery of hindsight, insight

and foresight among others is to practice right-fit

analytics in the BDA project (Deloitte, 2019).

Analysing data in BDA helps in answering

questions (1) What happened?, (2) Why did it

happen?, (3) What will happen? and How we can

make it happen? which requires automated and semi-

automated analysis techniques (computation,

statistical analysis, optimisation and AI) to detect

patterns, identify anomalies and extract knowledge

(S, 2017) which explores the potential and value of

data for a better result.

Based on the data analytics techniques adopted in

N-HyDAA, NAHRIM has implied a practice of using

right-fit data analytics capabilities where statistical

analysis is the analytics tools to optimise the value of

the hydroclimatic data to support data and fact-driven

decision-making. Analytics in N-HyDAA focusing

on data-driven data analytics which eminence on

answering questions. The analytics capabilities used

in N-HyDAA are focusing more on descriptive,

diagnostic and predictive analytics; meanwhile,

prescriptive analytics is an area of opportunity to

discover further. According to Delen and Demirkan

(2013), predictive analytics used data and

mathematical algorithms which can rely on data,

expert knowledge or combination of both through

optimisation, simulation, multi-criteria decision,

Big Data Analytics as Game Changer in Dealing Impact of Climate Change in Malaysia: Present and Future Research

465

Table 2: Indicators for CC Vulnerability in Malaysia.

Sector

Indicator

Exposure Sensitivity Adaptive capacity

Water

1. Projected Change of

Water Availability

2. Freshwater withdrawal rate 3. Water storage capacity

4. Projected Decrease in Dry

Season Flow

5. Low flow restricts water

abstraction

6. Supplementary flow from

Off River Storage

7. Projected Change of

Rainfall and Dry Spell

8. Number of farmers affected 9. Dam and pump capacity

10. Projected change in

Groundwater recharge

11. Changes in groundwater

level

12. Conjunctive use of

surface and groundwater

Food &

Commodity

1. Projected change of paddy

yields

2. Paddy field area 3. Agriculture capacity

4. Projected change in palm

oil production

5. Oil palm plantation area

6. Water conservation

practices

Infrastructure

1. Projected change of flood 2. Flood prone area

3. Structural and non-

structural approaches

4. Sea Level Rise Projection

5. Population living below 3m

above mean sea level.

6. Disaster preparedness

7. Projected increase in

extreme flow

8. Frequency of dam overspill

9. Risk Management

Plan/dam upgrading/dam

safet

review

10. Projected change of river

runoff

11. Reduction in the

hydropower energy

generation

12. Renewable Energy (RE)

expert system and group support systems where the

outcome either best course of action, rich set of

information and expert opinions to be provided to

decision-maker.

Apart from data analytics capabilities, data

produced from N-HyDAA are valuable for further

utilisation in potential CC studies such as CC index

vulnerability and readiness. Using an approach

developed by the University of Notre-Dame through

the Notre-Dame Global Adaptation Index (Chen et

al., 2015), future research in NAHRIM will be

focusing on identifying the current status of CC

vulnerability through assimilation of data from N-

HyDAA with a various dataset. The research will

deliberate various aspects of CC vulnerability

through exposure, sensitivity and adaptive capacity

by developing a customised indicator which

significant in CC scenarios from Malaysia’s context.

This potential research help Malaysia in

identifying the vulnerable areas which are lacking

attention to overcome the impacts of CC. Table 2

shows a list of indicators for vulnerability developed

through customisation by NAHRIM based on

Malaysia CC scenario. Three main sectors have been

identified that are vulnerable and affected due to the

impact of CC in Malaysia. The combination and

simulation of N-HyDAA with identified indicator

data able to provide an index of vulnerability where

the mechanism of the index calculation is still open

for future discussion. Methodology as discussed

earlier, such as MCDM, has the potential to be

imposed in this future research as well as normal

statistical analysis or replicating the same method as

developing in ND-GAIN.

For future research opportunities, N-HyDAA

showing the potential and capability of serving an

immerse application domain in the CC area and its

analytical capabilities have a considerable potential to

be explored and studied further.

6 CONCLUSIONS

As a conclusion, through the composition of data

analytics capabilities, management of CC data would

be improved, where data preparation, data integration

and data analysis able to enhance decisions and

decision-making process in handling issues impact of

CC.

IoTBDS 2020 - 5th International Conference on Internet of Things, Big Data and Security

466

Innumerable BDA projects showed a significant

and impactful result on how BDA give a competitive

advantage in term valuing the data and improved

decision-making in various domain. New research

areas for BDA implementation should be explored

more to improve the result and to expand the

capability with the enablement of other domain such

as analytical capabilities, decision-making

methodology, strategic and knowledge management.

The opportunity to discover beyond the current BDA

technology would expand the capabilities and enrich

the outcome and ability of BDA.

ACKNOWLEDGEMENTS

This project funded by the Ministry of Water, Land

and Natural Resources of Malaysia (KATS) and we

are thankful to our environmental engineer and

hydrologist for the technical expertise.

REFERENCES

Abdullah, M. F., Ibrahim, M., & Zulkifli, H. (2017a). Big

Data Analytics Framework for Natural Disaster

Management in Malaysia. Paper presented at the The

2nd International Conference on Internet of Things, Big

Data and Security (IoTBDS 2017), Porto, Portugal.

Abdullah, M. F., Ibrahim, M., & Zulkifli, H. (2017b). Big

Data Technology Implementation in Managing Water

Related Disaster: NAHRIM's Experience

Abdullah, M. F., Mat Amin, M. Z., Mohamad, M. F.,

Mohamad Ideris, M., Zurina, Z., & Yussof, N. Y.

(2018). N-HyDAA - Big Data Analytics for Malaysia

Climate Change Knowledge Management. Paper

presented at the HIC 2018. 13th International

Conference on Hydroinformatics, Palermo, Italy.

Akter, S., & Wamba, S. F. (2017). Big data and disaster

management: a systematic review and agenda for future

research. Annals of Operations Research, 1-21.

Alhumaid, M., Ghumman, A. R., Haider, H., Al-Salamah,

I. S., & Ghazaw, Y. M. (2018). Sustainability

Evaluation Framework of Urban Stormwater Drainage

Options for Arid Environments Using Hydraulic

Modeling and Multicriteria Decision-Making. Water,

10(5). doi:10.3390/w10050581

Amankwah-Amoah, J., & Adomako, S. (2019). Big data

analytics and business failures in data-Rich

environments: An organizing framework. Computers in

Industry, 105, 204-212.

Amineh, Z. B. A., Hashemian, S., & Magholi, A. (2017).

Integrating Spatial Multi Criteria Decision Making

(SMCDM) with Geographic Information Systems

(GIS) for delineation of the most suitable areas for

aquifer storage and recovery (ASR). Journal of

Hydrology, 551, 577-595. doi:10.1016/j.jhydrol.2017.

05.031

APICTA. (2017). APICTA 2017 Winner. Retrieved from

https://www.apicta.org/winners/2017-bangladesh

Birgani, Y. T., & Yazdandoost, F. (2018). An Integrated

Framework to Evaluate Resilient-Sustainable Urban

Drainage Management Plans Using a Combined-

adaptive MCDM Technique. Water Resources

Management, 32(8), 2817-2835. doi:10.1007/s11269-

018-1960-2

Boyd, D., & Crawford, K. (2012). Critical questions for big

data: Provocations for a cultural, technological, and

scholarly phenomenon. Information, communication &

society, 15(5), 662-679.

Brown, A., & Matlock, M. (2011). A review of water

scarcity indices and methodologies. The Sustainability

Consortium, 106, 19. Retrieved from https://pdfs.

semanticscholar.org/7f3d/b485feaf71fad95863ca4b56

0bb5b27770ec.pdf

Buyukozkan, G., & Uzturk, D. (2018). 2-tuple combined

group decision making methodology for climate change

strategy selection (Vol. 11).

Chakraborty, S., Sahoo, S., Majumdar, D., Saha, S., & Roy,

S. (2019). Future Mangrove Suitability Assessment of

Andaman to strengthen sustainable development.

Journal of Cleaner Production, 234, 597-614.

doi:10.1016/j.jclepro.2019.06.257

Chen, C., Noble, I., Hellmann, J., Coffee, J., Murillo, M., &

Chawla, N. (2015). University of Notre Dame Global

Adaptation Index Country Index Technical Report.

Retrieved from https://gain.nd.edu/assets/254377/

nd_gain_technical_document_2015.pdf

Chung, E. S., & Kim, Y. (2014). Development of fuzzy

multi-criteria approach to prioritize locations of treated

wastewater use considering climate change scenarios.

Journal of Environmental Management, 146, 505-516.

doi:10.1016/j.jenvman.2014.08.013

Delen, D., & Demirkan, H. (2013). Data, information and

analytics as services. Decision Support Systems, 55(1),

359-363. doi:https://doi.org/10.1016/j.dss.2012.05.044

Deloitte. (2019). Building your data analytics capabilities,

Deliver hindsight, insight and foresight. Retrieved from

https://www2.deloitte.com/ng/en/pages/deloitte-

analytics/articles/building-your-data-analytics-

capabilities.html

Duan, H. J., Deng, Z. D., Deng, F. F., & Wang, D. Q.

(2016). Assessment of Groundwater Potential Based on

Multicriteria Decision Making Model and Decision

Tree Algorithms. Mathematical Problems in

Engineering. doi:10.1155/2016/2064575

Faghmous, J., & Kumar, V. (2014). A Big Data Guide to

Understanding Climate Change: The Case for Theory-

Guided Data Science. Big data, 2, 155-163.

doi:10.1089/big.2014.0026

Fan, J., Han, F., & Liu, H. (2014). Challenges of big data

analysis. National science review, 1(2), 293-314.

Ford, J. D., Tilleard, S. E., Berrang-Ford, L., Araos, M.,

Biesbroek, R., Lesnikowski, A. C., . . . Bizikova, L.

(2016). Opinion: Big data has big potential for

applications to climate change adaptation. Proceedings

Big Data Analytics as Game Changer in Dealing Impact of Climate Change in Malaysia: Present and Future Research

467

of the National Academy of Sciences, 113(39), 10729-

10732. doi:10.1073/pnas.1614023113

George, A. (2018). Business analytics: The essentials of

data-driven decision-making. Retrieved from

https://www.zdnet.com/article/business-analytics-the-

essentials-of-data-driven-decision-making/

Geospatial World. (2018). Asia Geospatial Awards 2017

winners announced at GeoSmart Asia. Retrieved from

https://www.geospatialworld.net/news/asia-geospatial-

awards-2017-winners-announced/

Golfam, P., Ashofteh, P. S., Rajaee, T., & Chu, X. F.

(2019). Prioritization of Water Allocation for

Adaptation to Climate Change Using Multi-Criteria

Decision Making (MCDM). Water Resources

Management, 33(10), 3401-3416. doi:10.1007/s11269-

019-02307-7

Hagerty, J. (2016). 2017 Planning Guide for Data and

Analytics. Retrieved from https://www.gartner.com/en/

documents/3471553/2017-planning-guide-for-data-

and-analytics

Hassani, H., Huang, X., & Silva, E. (2019). Big Data and

Climate Change. Big Data and Cognitive Computing,

3(1). doi:10.3390/bdcc3010012

Ideris, M., Abdullah, M. F., Mat Amin, M. Z., & Zainol, Z.

(2018). Big Data Analytics Technology for Water Risk

Assessment and Management. Retrieved from New

Delhi, India:

Kaisler, S., Armour, F., Espinosa, J. A., & Money, W.

(2013). Big data: Issues and challenges moving

forward. Paper presented at the 2013 46th Hawaii

International Conference on System Sciences.

Karamouz, M., Zeynolabedin, A., & Olyaei, M. A. (2015).

Mapping Regional Drought Vulnerability: A Case

Study. In H. Arefi & M. Motagh (Eds.), International

Conference on Sensors & Models in Remote Sensing &

Photogrammetry (Vol. 41, pp. 369-377). Gottingen:

Copernicus Gesellschaft Mbh.

Lee, G., Choi, J., & Jun, K. S. (2017). MCDM Approach

for Identifying Urban Flood Vulnerability under Social

Environment and Climate Change. Journal of Coastal

Research, 209-213. doi:10.2112/si79-043.1

Levy, J. K. (2005). Multiple criteria decision making and

decision support systems for flood risk management.

Stochastic Environmental Research and Risk

Assessment, 19(6), 438-447.

Liu, D., & Stewart, T. J. (2004). Integrated object-oriented

framework for MCDM and DSS modelling. Decision

Support Systems, 38(3), 421-434.

Lokers, R., Knapen, R., Janssen, S., van Randen, Y., &

Jansen, J. (2016). Analysis of Big Data technologies for

use in agro-environmental science. Environmental

Modelling & Software, 84, 494-504.

Lopez, D., & Manogaran, G. (2016). Big data architecture

for climate change and disease dynamics. The human

element of big data: issues, analytics, and performance,

301-331.

Mardani, A., Jusoh, A., Zavadskas, E. K., Cavallaro, F., &

Khalifah, Z. (2015). Sustainable and Renewable

Energy: An Overview of the Application of Multiple

Criteria Decision Making Techniques and Approaches.

Sustainability, 7(10), 13947-13984.

doi:10.3390/su71013947

Mark, S. (2016). 5 Key Elements Of Analytics To Consider.

In (Vol. 2020).

Mat Amin, M. Z. (2016). Applying Big Data Analytics

(BDA) to Diagnose Hydrometeorlogical related risk

due to Climate Change. Paper presented at the GEO

Smart Asia 2016, Putrajaya, Malaysia.

Mensour, O. N., El Ghazzani, B., Hlimi, B., & Ihlal, A.

(2019). A geographical information system-based

multi-criteria method for the evaluation of solar farms

locations: A case study in Souss-Massa area, southern

Morocco. Energy, 182, 900-919. doi:10.1016/j.energy.

2019.06.063

Meulen, R. v. d., & Rivera, J. (2014). Gartner Says

Advanced Analytics Is a Top Business Priority.

Retrieved from https://www.gartner.com/en/newsroom/

press-releases/2014-10-21-gartner-says-advanced-

analytics-is-a-top-business-priority

Mohamed, A., Mat Amin, M. Z., Md Adnan, N. H., &

Abdullah, M. F. (2018). Projected Hydroclimate Data

Analysis using Big Data Analytics (BDA) Technology

for Smart and Resilient City. Paper presented at the

Smart Cities: Re-Imaging Smart Solutions in Today's

Digital Age Kuala Lumpur, Malaysia.

Pohekar, S., & Ramachandran, M. (2004). Application of

multi-criteria decision making to sustainable energy

planning—A review. Renewable and sustainable

energy reviews, 8(4), 365-381.

Rahman, M. S., Di, L., & Esraz-Ul-Zannat, M. (2017). The

role of big data in disaster management Paper

presented at the Proceedings, International Conference

on Disaster Risk Mitigation.

Ramya, S., & Devadas, V. (2019). Integration of GIS, AHP

and TOPSIS in evaluating suitable locations for

industrial development: A case of Tehri Garhwal

district, Uttarakhand, India. Journal of Cleaner

Production, 238. doi:10.1016/j.jclepro.2019.117872

S, A. (2017). An Overview of Big Data Applications in

Water Resources Engineering. 2, 10-18. doi:10.11648/

j.mlr.20170201.12

Simsek, Y., Watts, D., & Escobar, R. (2018). Sustainability

evaluation of Concentrated Solar Power (CSP) projects

under Clean Development Mechanism (CDM) by using

Multi Criteria Decision Method (MCDM). Renewable

& Sustainable Energy Reviews, 93, 421-438.

doi:10.1016/j.rser.2018.04.090

Singh, H. (2018). Using Analytics for Better Decision-Making.

Retrieved from https://towardsdatascience.com/using-

analytics-for-better-decision-making-ce4f92c4a025

Song, J. Y., & Chung, E. S. (2016). Robustness,

Uncertainty and Sensitivity Analyses of the TOPSIS

Method for Quantitative Climate Change Vulnerability:

a Case Study of Flood Damage. Water Resources

Management, 30(13), 4751-4771. doi:10.1007/s11269-

016-1451-2

Umm e, H., Asghar, S., & Ieee. (2009). A Survey on Multi-

Criteria Decision Making Approaches.

Yang, C., Su, G., & Chen, J. (2017, 10-12 March 2017).

Using big data to enhance crisis response and disaster

IoTBDS 2020 - 5th International Conference on Internet of Things, Big Data and Security

468

resilience for a smart city. Paper presented at the 2017

IEEE 2nd International Conference on Big Data

Analysis (ICBDA)

Zahmatkesh, Z., & Karamouz, M. (2017). An uncertainty-

based framework to quantifying climate change

impacts on coastal flood vulnerability: case study of

New York City. Environmental Monitoring and

Assessment, 189(11), 20. doi:10.1007/s10661-017-

6282-y

Zavadskas, E. K., Cavallaro, F., Podvezko, V., Ubarte, I.,

& Kaklauskas, A. (2017). MCDM Assessment of a

Healthy and Safe Built Environment According to

Sustainable Development Principles: A Practical

Neighborhood Approach in Vilnius. Sustainability,

9(5). doi:10.3390/su9050702

Zhu, S. Y., Li, D. Z., & Feng, H. B. (2019). Is smart city

resilient? Evidence from China. Sustainable Cities and

Society, 50. doi:10.1016/j.scs.2019.101636

Zopounidis, C., & Doumpos, M. (2000). PREFDIS: a

multicriteria decision support system for sorting

decision problems. Computers & Operations Research,

27(7-8), 779-797.

Zurairi, A. (2018). Climate-related natural disasters cost

Malaysia RM8b in last 20 years. MalayMail.

Big Data Analytics as Game Changer in Dealing Impact of Climate Change in Malaysia: Present and Future Research

469