Page 36 - AI for Good-Innovate for Impact

AI for Good-Innovate for Impact

peatland becomes extremely easy to burn, and in case of fire, it will further release transboundary
haze. In order to protect the peatland, an improved tropical peatland fire weather index (FWI)
system is proposed by combining the ground water level (GWL) with the drought code (DC).
LoRa based IoT system for peatland management and detection was deployed in Raja Musa
Forest Reserve (RMFR) in Kuala Selangor, Malaysia. Then, feasibility of data collection by the
IoT system was verified by comparing the correlation between the data obtained by the IoT
system and the data from Malaysian Meteorological Department (METMalaysia).

An improved model was proposed to apply the ground water level (GWL) for Fire Weather
Index (FWI) formulation in Fire Danger Rating System (FDRS). Specifically, Drought Code (DC)
is formulated using GWL, instead of temperature and rain in the existing model. From the GWL
aggregated from the IoT system, the parameter is predicted using machine learning based on a
neural network. The results show that the Drought Code (DC), Duff Moisture Code (DMC) and
Fire Weather Index (FWI) alternatively calculated from GWL profiled from the IoT system has
high correlation with the data released by METMAlaysia. This shows that DC can be calculated
using predicted GWL as well as other Fire Danger Rating System (FDRS) indices. The Machine
Learning prediction is essential for tropical peatland Fire Danger Rating System (FDRS). The
IoT system can be enhanced by including CO2 sensors to measure carbon emission from the
peatland soil and from human activities in the area. In turn, the innovation can be used to help
predict and reduce the fire risk of tropical peatland, which could lead to transboundary haze
in the region [1], [2], [3], [4].

UN Goals:

• SDG 9: Industry, Innovation and Infrastructure,
• SDG15: Life on Land

Justify UN Goals selection: The project use Machine Learning (ML) to predict Fire Danger
Rating System (FDRS) indices such as Drought Code (DC), Duff Moisture Code (DMC) and
Fire Weather Index (FWI) using Ground Water Level (GWL) obtained from the IoT system
deployed at Raja Musa Forest Reserve (RMFR). The project has received local and regional
awards especially in managing transboundary haze in ASEAN region. We would like to extend
the project by measuring carbon emission from the peatland forest and how net-zero can be
achieved by managing the peatland better, both using IoT technology and through community-
based management.

Partner name: Selangor Forest Department Partner

4�2�2 Future work

Proof of concept development, Create new variations/extensions to the same use case,
Standards development related to the use case.

Elaborate proposal: There are about 25 million hectares of peat swamp forest in Southeast
Asia. To date, poor monitoring and lack of sustainable peatland forest management have led
to rapid forest degradation. This is a major threat not only to biodiversity ecosystems, but also
to humans, especially from transboundary fog caused by forest fires. From the research so
far, we have learned that observations centered on the Underground water level and Ground
surface level are important for CO2 emission, disaster prevention (especially fires), and climate
change. However, the system and structure for solving the importance of this observation data
and problem solving are not in place.

20