No abstract

This study explored the use of participatory mapping and several machine learning algorithms (Naïve Bayes, GMO Maxent, SVM, CART, and Random Forest) to map climate induced landslide susceptibility in Lembeh Island, North Sulawesi, based on Earth Observation data available in Google Earth Engine. Participatory mapping on landslide incidents were conducted in three villages, i.e., Kareko, Pintu Kota, and Pasir Panjang. Data used include digital elevation model from SRTM, multispectral imageries from Sentinel 2, and precipitation from CHIRPS. Terrain modelling was done to DEM to come up with elevation, slope, curvature, and aspect. A cloud free mosaic of Sentinel Images was created using the median reducer and then NDVI was calculated. Precipitation data from CHIRPS was sampled and interpolated using kriging and reduced to maximum and mean. Each algorithm was trained using 70% participatory mapping data and then the prediction was tested for accuracy using the last 30%. Results showed that Random Forest, SVM, CART, and GMO Maxent gave 0.98 testing accuracy and Naïve Bayes only 0.90. The map showed that due to the terrain condition, Lembeh Island is prone to Landslide and even though previously BNPB already provide a landslide hazard risk map, there were many areas not included on that map. Therefore, the map could become an input for BNPB and the Bitung City for developing a mitigation and adaptation strategy. Machine learning and cloud computing along with participatory mapping could also complement mechanistic or multi-criteria analysis using GIS model for landslide susceptibility mapping.

Indonesia as an archipelagic country has a high biodiversity of coral reefs but is very vulnerable to various threats, one of the causes of damage to coral reefs is by ship aground. The damage causes minor injuries to the degradation of the reef structure. The location of the grounding sometimes on the small islands with calm currents, but sometimes in straits with strong currents. However, the assessment must be carried out, so it is necessary to develop an approach to assessing that. The purpose of this study is to assess the damage of coral reefs, to quantify the extent of damage, and identify species of corals affected. The observation used ground truth (underwater photo transect), aerial photography, machine learning, and species distribution modeling. The results obtained from aerial photography show that the MV Pazifik has damage to coral reefs reaching 613.63 m2. Based on the coral genera distribution model, it was found 35–55 genera (control location), while at the ship aground, were found 3–5 genera. Therefore, the control location is a coral reef ecosystem that is dominated by corals, while at the ship aground it can be the habitat for several hard coral genera.

This study investigates the locations of coral bleaching events in Indonesia based on the Sea Surface Temperature Anomaly (SSTA) from the 2015-2019 period. SST was downloaded from the satellite with a resolution of 4 km. The method used was the Hotspot Index and Degree Heating Week issued by the National Ocean Atmospheric Administrations (NOAA) through the Coral Reef Watch (CRW) program. Results obtained from the Hotspots index shows that almost all Indonesian waters have the potential to experience coral bleaching and the area that has a high potential is West Sumatra with the Death Index Degree Heating Week reaching 8-12 °C - weeks with Alert Level 2 status. an increase in temperature by 1.5°C as a result of global warming, then the area with the most massive death impact was West Sumatra with an increase of 3.82 - 6.32°C - weeks. The relationship between SST anomaly and coral reef mortality is 55 - 56%, so it is a strong relationship category.

No abstract