SSRS Journal B: Spatial Research

Assessment of Peatland Fire Susceptibility Using Biogeophysical Parameters in the Kahayan-Sebangau Peat Hydrological Unit, Central Kalimantan

Hanum Resti Saputri — 2025-12-25

Forest and land fires in peatland ecosystems of Central Kalimantan pose a serious threat to the environment and local communities, causing ecosystem degradation, loss of biodiversity, and health problems. This study aims to identify biophysical characteristics, analyze the relationships between environmental parameters and fire occurrences, and develop a vulnerability map based on the integration of remote sensing data and spatial modeling. Multisource data (Sentinel-2, Landsat-8, MODIS, CHIRPS, ERA5-Land, and TerraClimate) were used to obtain 15 variables representing topography, hydrology, vegetation, and climate, which were further analyzed to detect burned areas using the differenced Normalized Burn Ratio (dNBR). The dataset was divided into 70% for training and 30% for validation. Fire vulnerability mapping using the Random Forest Probability (RFP) method resulted in six risk classes: very low (143,994 ha), low (104,909 ha), moderate (85,718 ha), high (58,541 ha), very high (40,597 ha), and extreme (16,230 ha). The model demonstrated strong performance with an AUC value > 0.85, indicating consistent relationships between classification results and key environmental variables, where land surface temperature (LST), rainfall, and vegetation indices (NDVI and NDMI) were identified as the most influential factors affecting fire vulnerability. The findings provide recommendations for ecosystem-based peatland restoration, adaptive peat management, and fire mitigation strategies within the Kahayan–Sebangau PHU landscape.

Three Decades of Tropical Deforestation on Small Islands Due To Nickel Ore Mining Expansion: The Critical Insight from Indonesia Eastern and Post-Mining Revegetation Recommendations

Khairani Putri Marfi — 2025-12-25

Forest cover in Indonesia undergoes annual changes, particularly deforestation resulting from land-use changes. Nickel mining in eastern Indonesia is one of the causes of deforestation, extending even to small islands. Unfortunately, to date, information on deforestation on small islands due to nickel mining remains very limited. Therefore, this study aims to investigate deforestation on seven small islands in eastern Indonesia (across four regencies) caused by nickel ore extraction over the past three decades. Cloud computing via the Google Earth Engine geospatial platform and the machine learning random forest algorithm were employed in this study and proved capable of detecting deforestation across all islands. The most severe deforestation occurred on Gag Island, covering approximately 801 hectares between 1990 and 2025. Pisang Island has the lowest forest cover percentage in 2025, with only 5 hectares, or 19.76%. Forest cover detection using the random forest algorithm yielded the highest accuracy, reaching 0.93 (OA) and 0.86 (KS). This deforestation data represents the first such information for small islands and plays a crucial role in evaluating the negative impacts of nickel mining activities in Indonesia. To mitigate environmental impacts, revegetation efforts are essential for restoring the ecosystem functions of the seven small islands in the study area. The use of cloud computing in remote sensing approaches is considered vital for monitoring forest cover on small islands and can ensure the success of post-mining revegetation.

Three Decade Forest Change in the Bakiriang Key Biodiversity Area, Eastern Sulawesi Island

Aulia Ulfa — 2025-12-25

The Bakiriang Key Biodiversity Areas (KBAs) on the island of Sulawesi are one of the global biodiversity landscapes identified for species conservation and the provision of critical habitats for endemic and rare species on the island of Sulawesi. However, these KBAs have experienced forest fragmentation due to the expansion of smallholder agriculture and large-scale plantations. Information regarding forest loss within the KBAs on Sulawesi Island remains very limited, necessitating a spatial assessment of forest loss. Therefore, in this study, we used Landsat-5 and Landsat-8-9 satellite imagery to map forest cover in 1995 and 2025. Geospatial analysis of the Landsat imagery was conducted using the Google Earth Engine (GEE) geospatial platform and the random forest classification algorithm. The results show a decrease in forest area of 9,155.16 ha, or approximately 12.56%, between 1995 and 2025, with a rate of decline reaching 305.17 ha/year (-0.42%). In terms of spatial patterns, changes in forest cover are distributed along the direction of the river toward its headwaters, with elevations reaching 160.41 ± 148.91 meters above sea level. Under the protection of the national forest policy, 5,381.10 ha of forest cover has been damaged within the Bakiriang Wildlife Reserve conservation area, leaving 5,495.67 ha of forest cover remaining by 2025. This indicates a lack of role and effectiveness of conservation areas in protecting forest cover within the Bakiriang KBAs, which shelter several endemic and rare species. Landscape rehabilitation of the Bakiriang KBAs through agroforestry systems in non-protected areas is recommended to enhance ecosystem functions for the habitats of key species within the KBAs.

Species distribution modelling of Odonata using Citizen Science Data and Machine Learning Random Forest Algorithm in Sulawesi Island

Usnil Khotimah — 2025-12-25

Odonata are a group of insects that play an important role as natural bioindicators due to their sensitivity to changes in environmental quality, particularly in aquatic ecosystems. These insects are highly dependent on both aquatic and terrestrial habitats throughout their life cycles, making them highly vulnerable to ecological disturbances. Sulawesi Island, located in the Wallacea biogeographic zone, has a high diversity of Odonata species, including many endemic species. However, anthropogenic activities such as deforestation, agricultural expansion, and mining are putting pressure on the sustainability of their natural habitats. This study aims to map the potential distribution of Odonata species on Sulawesi Island using a Species Distribution Modeling (SDM) approach with the Random Forest machine learning algorithm. Species presence data were obtained from the Global Biodiversity Information Facility (GBIF) citizen science platform and combined with 12 bioclimatic variables, including temperature (bio1, bio2, bio4–bio11), seasonal temperature (bio3), and annual precipitation (bio12). The modeling results showed that there were 2,152 Odonata distribution records from 11 families, including endemic species and several species with an “Endangered” conservation status according to the IUCN. The bioclimatic variables that most significantly influence habitat suitability are annual precipitation (bio12) and daily temperature variation (bio2). These findings demonstrate that a citizen science-based SDM approach and algorithms. The modeling results show that there are 2,152 Odonata distribution records from 11 families, including endemic species and several species with an “Endangered” conservation status according to the IUCN. The bioclimatic variables that most influence habitat suitability are annual precipitation (bio12) and daily temperature variation (bio2). These findings suggest that a citizen science-based approach combined with the Random Forest algorithm can be an effective method for supporting biodiversity monitoring and conservation planning. This study also emphasizes the importance of habitat conservation strategies and the development of long-term monitoring systems to ensure the survival of Odonata species in the Wallacea region.

Monitoring Model for Coral Reef Ecosystems Affected by Mining Sedimentation on the Coast of North Konawe Regency

Izzah Aulia Inanda — 2025-12-25

Coral reefs support ocean life by providing habitats for marine life. The great potential of coral reefs has led to massive exploitation that degrades coastal ecosystems. The development of the mining industry damages coral reef ecosystems because it produces tailings from the remaining mining of valuable minerals from the mining industry. This research aims to develop an innovative model for monitoring coral reef ecosystems affected by mining sedimentation using the cloud computing-based DATAINDO InaCor platform for carbon cycle sustainability in the North Konawe Coast. This research uses the Landsat 5 satellite series with 7 TM and 4 MSS spectral bands to obtain classification data and the North Konawe coast mapping in 2000. Landsat 8 with 9 OLI-2 spectral bands and 2 TIRS-2 spectral bands was also used to obtain the same data in 2023. Through satellites, the differences in coastal conditions of North Konawe Regency between 2000 and 2023 are visible. This difference is caused by changes that occur in the form of a decrease in vegetated land to 28340.14 ha from 33776.46 ha and coral reef area from 5968.08 ha to 1388.79 ha. This was caused by the expansion of coastal mining that converted vegetated land and produced tailings that flowed into the sea, causing damage to coral reefs. High turbidity index values characterize coral reef damage, and chlorophyll index values can be seen from the analysis results through remote sensing.