SMART AGRICULTURE IN MALAYSIA

Presented by:

Assoc. Prof. Ts. Dr. Siti Khairunniza Bejo

Head
SMART Farming Technology Research Centre
Department of Biological and Agricultural Engineering
Faculty of Engineering
Universiti Putra Malaysia
[email protected]
 OUTLINE
1. SMART Farming Technology Research Centre (SFTRC)
2. Challenges in the Future of Agriculture
3. Agricultural Revolution
4. Agriculture in Malaysia
5. Precision Agriculture
a. Agriculture 4.0
b. Remote Sensing Platform
c. Drone
d. Image Sensors
e. IoT
f. Artificial Intelligence
6. Video: Smart Online System for Disease Detection and Monitoring
7. Video: Smart Farming at Chili Farm
8. Video: Smart Farming at Durian Plantation
9. Video: Smart Vertical Farming
10. Summary
2
RESEARCH CENTRE

3
SMART FARMING TECHNOLOGY RESEARCH
CENTRE

4
CHALLENGES IN THE FUTURE
OF AGRICULTURE

5
 AGRICULTURAL REVOLUTION

Agriculture 4.0 implies a transformation of the production infrastructures

6
with respect to
connected farms, connected tractors and new agricultural equipment.
 AGRICULTURE IN MALAYSIA
Agriculture is one of the most
significant components of the National
Key Economic Areas (NKEA) because of
its ability to boost economic growth by
producing more jobs and improving
farmers' income. As the population of
Malaysia is projected to increase to
more than 45 million by 2050, there
will be an increase in food demand and
consumption.

7
 PRECISION AGRICULTURE / FARMING

• Precision Agriculture started when GPS signals were made available to the general
public.
• Precision Agriculture enables vehicle guidance and site-specific monitoring and
control.
• The objective is to give each plant (or animal) exactly what it needs to grow
optimally, with the aim to improve the agronomic output while reducing the
input (= producing ‘more with less’).
• Therefore, Precision Agriculture is actually a management strategy to optimise
the existing inputs and fertilizers, tillage tools, fields and crops, for the purpose
of improved control and measurement of farm yields.
 Precision agriculture cycle

Quantification of
spatial and/or
temporal
variability

Action based
on variability Link the
map variability to
management
actions

9
 Agriculture 4.0: A smart farm in action

Agriculture 4.0, which

incorporates precision
farming, IoT, and big data,
helps to enhance crop
yields, improve farming
efficiency, reduce demand
for farmland, and limit the
migration of workers to
urban areas.

In this digital agriculture

development, farmers
have greater control over
their operations such as
the irrigation equipment,
soil moisture, crop
growth, and the level of
livestock feeds without
the need for their
presence. 10
Source: Thales / Nesta.
 National Policy on IR4.0
The Malaysian government launched the National Policy on IR4.0 (Industry4WRD)
in October 2018 to position Malaysia as a total solutions provider for the
manufacturing sector in the Asia Pacific by 2025.

11
Remote Sensing 600 – 1000 km
Space
Platform
3 – 10 km
Sky
➢ Satellite
➢ Space shuttle 300 m – 3 km
➢ Aircraft Sky
➢ Ground based
100 – 300 m
Sky

1m – 5 m
Ground
13
Image Sensors

14
 Applications of UAV in oil palm plantation

More than 50
drone companies in
Malaysia work in
oil palm industry

▪ The most common applications of UAV in oil palm plantation can be categorized into
four major activities: surveillance, mapping, monitoring and spraying.

Canopy Sizing
Plant Counting
15
Siti Khairunniza Bejo. (2017). Use of Unmanned Aerial Vehicle (UAV) in Oil Palm Plantation. Jurutera. October 2017, pp. 24-26.
 Spraying
DJI AGRAS MG-1P AGRICULTURE
DRONE

Sanyeong Agricultural Solutions Sdn Bhd

• Capacity: max 10 kg liquid payloads, including pesticides and fertilizers.

• The combination of speed and power means that an area of 4,000-6,000 m² can be
covered in just 10 minutes, or 40 to 60 times faster than manual spraying operations.
• The intelligent spraying system automatically adjusts its spray according to the flying
speed so that an even spray is always applied. This way, the amount of pesticide or
fertilizer is precisely regulated to avoid pollution and economize operations.
• By integrating a microwave radar together with the MG-1's intelligent flight control
system, the aircraft can scan the terrain below it in real-time to keep a constant,
centimeter-accurate height above crops.
16
 Internet of Things (IoT)
▪ The Internet of Things (IoT) refers to a system of interrelated, internet-connected
objects that are able to collect and transfer data over a wireless network
without human intervention.

17
 Benefits of IoT Technology for Agriculture

Indoor Farm
Outdoor Farm

18
 Artificial Intelligence in Agriculture
• Hypothetically, it is possible for machines to learn
to solve any problem on earth relating to the
physical interaction of all things within a defined or
contained environment by using artificial
intelligence and machine learning.
• Put more plainly, as the system receives an
increasing amount of similar sets of data that can
be categorized into specified protocols, its ability
to rationalize increases, allowing it to better
“predict” on a range of outcomes.

The Artificial Intelligence in Agriculture Market is is projected to reach USD 4.0 billion by
2026, at a CAGR of 25.5% between 2020 and 2026. (MarketsandMarkets™)

The market growth is driven by the increasing implementation of data generation through
sensors and aerial images for crops, increasing crop productivity through deep-learning
technology, and government support for the adoption of modern agricultural techniques.
Application of Artificial Intelligence in Agriculture

Figure 1. The four generic categories in agriculture exploiting machine learning techniques.

20
Early detection of G. boninense infection in oil palm seedling using hyperspectral
image and Machine Learning (ML) technique
DEEP LEARNING
Leaves spectral CONVENTIONAL MACHINE LEARNING (SEMI-AUTOMATIC)
(AUTOMATIC)
(Hyperspectral SVM
camera) 7 Machine &
Learning Single band
SVM Band
Sensor classifiers [4]
[1] reduction [3]
[2]

Number of bands: Wavelength

Number of bands: 23 machine 5, 4, 3, 2, 1 number: 938 nm
35, 18, 14, 9, 5 learning
models
RESULTS:
RESULTS: Classifier: SVM RESULTS:
RESULTS: Model: linear SVM Model: VGG16
Band: NIR
Classifier: SVM (lowest CV score) NO segmentation
Frond number: 1 and 2
Model: coarse Accuracy: 94.80% Accuracy: 91.93%
RESULTS: Gaussian SVM Wavelength: 938nm F-score: 91.72%
Number of bands: 35, 18, 14, 9, 5 Accuracy: 94.21% Time: 0.08s
Accuracy: 94-100% F-score: 95.21%
Time: 1.71s
References:
[1] Aiman Nabilah Noor Azmi, Siti Khairunniza-Bejo, Mahirah Jahari, Farrah Melissa Muharam, Ian Yule and Nur Azuan Husin. (2020). Early Detection of Ganoderma boninense in Oil Palm Seedlings Using Support
Vector Machines. Remote Sensing, 12(3920): 1-23. (Q1). (JCR)
[3] Aiman Nabilah Noor Azmi, Siti Khairunniza-Bejo, Mahirah Jahari, Farrah Melissa Muharam, and Ian Yule. (2021). Identification of a Suitable Machine Learning Model for Detection of Asymptomatic Ganoderma
boninense Infection in Oil Palm Seedlings Using Hyperspectral Data. Applied Sciences, 2021, 11, 11798. 8. https://doi.org/10.3390/app112411798 (Q2). (JCR)
[3] Khairunniza-Bejo, Siti, Muhamad S. Shahibullah, Aiman N.N. Azmi, and Mahirah Jahari (2021). Non-Destructive Detection of Asymptomatic Ganoderma boninense Infection of Oil Palm Seedlings Using NIR-
Hyperspectral Data and Support Vector Machine. Applied Sciences, 11(22): 10878. https://doi.org/10.3390/app112210878 (Q2). (JCR)
[4] Lai Zhi Yong, Siti Khairunniza-Bejo, Mahirah Jahari and Farrah Melissa Muharam. (2021). Effect of Points Position on Bands Selection of Hyperspectral Data for Early Basal Stem Rot Detection in21
Oil Palm Seedling.
Presented at the 1st International Conference on Plantation Technology, 23-24 November 2021.
Early detection of G. boninense infection in oil palm
seedling using soil sensor with an IoT and ML
technique
Soil Sensor Network System (SSNS)
Soil sensor network system (SSNS) detects G. boninense by monitoring the
condition of soil properties. Data taken by the sensors were transferred from the
field to the cloud by using the Third Generation (3G) cellular connection. Users can
view the data in the web application and receive alert notifications if the data
exceeds a certain value. The system can detect G. boninense in an oil palm
seedling (age: 5 months) as early as 12 weeks (3 months) after infection with
98% accuracy, using a Machine Learning technique.

Online system

Plant status

References:
[1] Mohd Hamim Abdul Aziz, Siti Khairunniza-Bejo, Fazirulhisyam Hashim, Nur Hidayah Ramli, and Desa Ahmad. (2019). Evaluations of Soil Resistivity in
Relation to Basal Stem Rot Incidences Using Soil Moisture Sensor. Pertanika J. Sci. & Technol, 27(S1), pp. 225 – 234. (Scopus index)
[2] Aziz, Mohd H.A., Siti Khairunniza-Bejo, Aimrun Wayayok, Fazirulhisyam Hashim, Naoshi Kondo, and Aiman N.N. Azmi (2021). Temporal Changes Analysis of
Soil Properties Associated with Ganoderma boninense Pat. Infection in Oil Palm Seedlings in a Controlled Environment. Agronomy 11, (11): 2279.
https://doi.org/10.3390/agronomy11112279 (Q1). (JCR) 22
[3] Copyright: Khairunniza-Bejo, S., Abdul Aziz, M. H., Wayayok, A., Hashim, F. (2022). Soil Sensor Network System (SSNS) for Ganoderma Boninense Infection
Detection in Oil Palm Seedlings. [LY2021W06066]
SMART ONLINE SYSTEM FOR DISEASE
DETECTION AND MONITORING

23
SMART FARMING AT CHILI FARM

24
SMART FARMING AT DURIAN PLANTATION

25
SMART VERTICAL FARMING

26
 SUMMARY
1. Sensing technologies, IoT, Big Data, Cloud Computing, AI and
Autonomous Robot are the push factors that will influence how much Smart
Agriculture/ Farming technology adaption and integration can be made across
the food production system.
2. Technologies can help produce higher yield, better crop quality, less labour,
remote monitoring, reduce crop loss, and reduce the usage of fertilizers and
pesticides.
3. Indoor farm – AI is focusing on how to get good recipes to produce high
quality vegetables; Outdoor farm – Need to consider a pest and disease
attack; a lot of machine vision usage.
4. The evolvement of IoT and Precision Agriculture might attract youngsters to
join the agriculture sector where more gadgets are involved and it can provide
higher income.
5. Smart Farming technology can create more highly-skilled jobs in agriculture
which thus can solve the issue of the high unemployment rate.
6. Collaboration of all players in the agricultural value chain is needed for a clear
overview on the part of actors working in agrifood and digital products –
including private sector, governments and other agencies – on how to exploit
the opportunities of smart agriculture. 27
 Any Questions?

Terima Kasih/ Thank You

Assoc. Prof. Ts. Dr. Siti Khairunniza Bejo

[email protected]
28