An Artificial Intelligence Application for Post-Earthquake Damage Mapping in Palu, Central Sulawesi, Indonesia

Abstract

A Mw 7.4 earthquake hit Donggala County, Central Sulawesi Province, Indonesia, on 28 September 2018, triggering a tsunami and liquefaction in Palu City and Donggala. Around 2101 fatalities ensued and 68,451 houses were damaged by the earthquake. In light of this devastating event, a post-earthquake map is required to establish the first step in the evacuation and mitigation plan. In this study, remote sensing imagery from the Landsat-8 and Sentinel-2 satellites was used. Pre- and post-earthquake satellite images were classified using artificial neural network (ANN) and support vector machine (SVM) classifiers and processed using a decorrelation method to generate the post-earthquake damage map. The affected areas were compared to the field data, the percentage conformity between the ANN and SVM results was analyzed, and four post-earthquake damage maps were generated. Based on the conformity analysis, the Landsat-8 imagery (85.83%) was superior to that of Sentinel-2 (63.88%). The resulting post-earthquake damage map can be used to assess the distribution of seismic damage following the Palu earthquake and may be used to mitigate damage in the event of future earthquakes.

Contributions and Risks of Artificial Intelligence (AI) in Building Smarter Cities: Insights from a Systematic Review of the Literature

“…Given the ability of AI to analyze large amounts of data, scenarios to deal with potential threats could be constructed simultaneous to the detection of threats [161]. This would give decision-makers and other authorities more time to respond to threats such as natural disasters [132], house fires [123], or other incidents. Furthermore, AI can be used to assess the extent of damage caused by these events helping authorities better respond to, and mitigate any damage caused [101,132].…”

“…Syifa et al [132] An artificial intelligence application for post-earthquake damage mapping in Palu, Central Sulawesi, Indonesia…”

Source Characteristics of the 28 September 2018 Mw 7.4 Palu, Indonesia, Earthquake Derived from the Advanced Land Observation Satellite 2 Data

“…Both the USGS and the gCMT (global CMT: https//:www.globalcmt.org) provided the focal mechanism solutions, which indicated that the earthquake occurred on the north section of the Palu-Koro Fault, a predominantly sinistral fault with a normal component. The event resulted in catastrophic soil liquefaction; it heavily destroyed infrastructure and dwellings, and killed around 2101 people in the central Sulawesi region [6]. Another important factor that led to such a severe disaster was the tsunami that followed the main shock.…”

Vulnerability Levels of Liquefaction Zones as a Spatial Planning Concept Based the Disaster Mitigation in Pariaman City—Indonesia

“…This thing causes damage to the building, such as the collapse. This liquefaction event has been proven through history that has occurred in the world, such as the earthquake in Niigata, Japan in 1964 [4,5], and the latest earthquake and tsunami in Donggala-Palu in Central Sulawesi Province with its trigger, one of which was of the Palu-Koro fault [6,7].…”