Lava flow mapping Karangetang Volcano during 2019 eruption using Sentinel-2 Images and Random Forest model

Abstract

Karangetang is one of Indonesia’s most active volcanoes, located in northern Sulawesi. At least 200 people were evacuated due to the threat of lava during the nearly year-long eruption of 2019. In this study, we aim to map the lava flow using Sentinel-2 images. We used a random forest algorithm to separate lava and non-lava classes. Approximately 402 training points were visually interpreted from a pair of pre- and post-event images in 2019 classified as cloud, cloud shadow, bare land, settlement, vegetation, recent lava, and historical lava. To begin, we employed all bands and spectral indices previously identified as useful for separating lava from other materials. A region growing algorithm was used along with additional input data (temperature anomalies product, Normalized Hotspot Indices, and digital terrain model) to differentiate recent and old lava. Only the significant variables from the first run were kept that had a cumulative contribution to the model of greater than 10%. The top 6 important features are Digital Terrain Model, bands 11 and 12 (SWIR) of post-image and pre-image, and band 8A (NIR) of post-image. In the cross-validation of the Random Forest classification, our preliminary results indicate an accuracy of 97% for the test data (N-tree=100). The region’s growing algorithm helped distinguish between recent and historical lava. In the future, we intend to validate the map using an independent dataset and test the model at various locations

Numerical Simulation of Pyroclastic Flow of Karangetang Volcano Based on 2015 Eruption Activity

“…In the early period of 2015 the rate of lava ejection of Karangetang Volcano decreased, and reached its lowest point in April 2015, with an estimated volume on May 15, 2015 reaching 3.18 x 10 6 m 3 , (Table 3). The trend of lava discharge rate (Figure 6) and volume (Figure 7) increased from May 2015 to December 2015, and this is in line with the analysis of Kriswati and Alfianti (2019) that the rate of lava extrusion in the 2000-2019 period tends to increase due to lava glide activity, especially in the 2011 and 2015 eruption periods, with eruptive activity issued dominant lava flows from the Main Crater, towards the west-southwest (Santoso et al, 2022).…”

“…This condition can be caused by rainy weather, or the peak is covered with fog, and also smoke emissions from the peak. Santoso et al (2022) stated that conditions at the peak due to fog, and thin clouds can cause bias, and this can be overcome by using high-resolution satellite imagery. Based on MODIS satellite image data, the volcanism period of Karangetang Volcano shows an increase in lava extrusion rate and volume throughout 2015, with its activity centered on the Main Crater in the South.…”

“…The rate of lava extrusion of Karangetang Volcano since 2015 until now, indicates that there are several possibilities for pyroclastic flows that can come from the collapse of the lava dome at the summit and also from the tip of the tongue of the lava flow, as described in Session 3.4. According to Santoso et al, (2022), the most recent lava distribution in the summit area is on the south and west sides of the Main Crater, and the west side of the North Crater. With reference to the parameters and boundary conditions of numerical simulations in Sessions 3.3 and 3.4, for the south side of the Main Crater, if pyroclastic flows occur from the center of the Main Crater to the south, and if there is a change in the point of collapse of the lava dome, then the expansion of pyroclastic flows can reach the upper reaches of the Keting River and Kahetang River to the villages of Tatehadeng and Dame (Figure 1).…”