Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches
In recent decades, catastrophic wildfire episodes within the Sumatran peatland have contributed to a large amount of greenhouse gas emissions. The El-Nino Southern Oscillation (ENSO) modulates the occurrence of fires in Indonesia through prolonged hydrological drought. Thus, assessing peatland vulne...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/6/828 |
| _version_ | 1797487474665062400 |
|---|---|
| author | Lilik Budi Prasetyo Yudi Setiawan Aryo Adhi Condro Kustiyo Kustiyo Erianto Indra Putra Nur Hayati Arif Kurnia Wijayanto Almi Ramadhi Daniel Murdiyarso |
| author_facet | Lilik Budi Prasetyo Yudi Setiawan Aryo Adhi Condro Kustiyo Kustiyo Erianto Indra Putra Nur Hayati Arif Kurnia Wijayanto Almi Ramadhi Daniel Murdiyarso |
| author_sort | Lilik Budi Prasetyo |
| collection | DOAJ |
| description | In recent decades, catastrophic wildfire episodes within the Sumatran peatland have contributed to a large amount of greenhouse gas emissions. The El-Nino Southern Oscillation (ENSO) modulates the occurrence of fires in Indonesia through prolonged hydrological drought. Thus, assessing peatland vulnerability to fires and understanding the underlying drivers are essential to developing adaptation and mitigation strategies for peatland. Here, we quantify the vulnerability of Sumatran peat to fires under various ENSO conditions (i.e., El-Nino, La-Nina, and Normal phases) using correlative modelling approaches. This study used climatic (i.e., annual precipitation, SPI, and KBDI), biophysical (i.e., below-ground biomass, elevation, slope, and NBR), and proxies to anthropogenic disturbance variables (i.e., access to road, access to forests, access to cities, human modification, and human population) to assess fire vulnerability within Sumatran peatlands. We created an ensemble model based on various machine learning approaches (i.e., random forest, support vector machine, maximum entropy, and boosted regression tree). We found that the ensemble model performed better compared to a single algorithm for depicting fire vulnerability within Sumatran peatlands. The NBR highly contributed to the vulnerability of peatland to fire in Sumatra in all ENSO phases, followed by the anthropogenic variables. We found that the high to very-high peat vulnerability to fire increases during El-Nino conditions with variations in its spatial patterns occurring under different ENSO phases. This study provides spatially explicit information to support the management of peat fires, which will be particularly useful for identifying peatland restoration priorities based on peatland vulnerability to fire maps. Our findings highlight Riau’s peatland as being the area most prone to fires area on Sumatra Island. Therefore, the groundwater level within this area should be intensively monitored to prevent peatland fires. In addition, conserving intact forests within peatland through the moratorium strategy and restoring the degraded peatland ecosystem through canal blocking is also crucial to coping with global climate change. |
| first_indexed | 2024-03-09T23:48:12Z |
| format | Article |
| id | doaj.art-d9c7e4b4c7ae4affbb54908e38841db6 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-09T23:48:12Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-d9c7e4b4c7ae4affbb54908e38841db62023-11-23T16:39:52ZengMDPI AGForests1999-49072022-05-0113682810.3390/f13060828Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning ApproachesLilik Budi Prasetyo0Yudi Setiawan1Aryo Adhi Condro2Kustiyo Kustiyo3Erianto Indra Putra4Nur Hayati5Arif Kurnia Wijayanto6Almi Ramadhi7Daniel Murdiyarso8Department of Forest Resource Conservation and Ecotourism, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaDepartment of Forest Resource Conservation and Ecotourism, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaDepartment of Forest Resource Conservation and Ecotourism, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaCenter for Remote Sensing Technology and Data, Deputy of Remote Sensing Affairs, Indonesian National Institute of Aeronautics and Space (LAPAN), Jakarta 13710, IndonesiaDepartment of Silviculture, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaDepartment of Computer Science, Faculty of Mathematics and Natural Sciences, IPB University, Bogor 16680, IndonesiaDepartment of Forest Resource Conservation and Ecotourism, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaDepartment of Silviculture, Faculty of Forestry and Environment, IPB University, Bogor 16680, IndonesiaCenter for International Forestry Research (CIFOR), Jl. CIFOR, Bogor 16115, IndonesiaIn recent decades, catastrophic wildfire episodes within the Sumatran peatland have contributed to a large amount of greenhouse gas emissions. The El-Nino Southern Oscillation (ENSO) modulates the occurrence of fires in Indonesia through prolonged hydrological drought. Thus, assessing peatland vulnerability to fires and understanding the underlying drivers are essential to developing adaptation and mitigation strategies for peatland. Here, we quantify the vulnerability of Sumatran peat to fires under various ENSO conditions (i.e., El-Nino, La-Nina, and Normal phases) using correlative modelling approaches. This study used climatic (i.e., annual precipitation, SPI, and KBDI), biophysical (i.e., below-ground biomass, elevation, slope, and NBR), and proxies to anthropogenic disturbance variables (i.e., access to road, access to forests, access to cities, human modification, and human population) to assess fire vulnerability within Sumatran peatlands. We created an ensemble model based on various machine learning approaches (i.e., random forest, support vector machine, maximum entropy, and boosted regression tree). We found that the ensemble model performed better compared to a single algorithm for depicting fire vulnerability within Sumatran peatlands. The NBR highly contributed to the vulnerability of peatland to fire in Sumatra in all ENSO phases, followed by the anthropogenic variables. We found that the high to very-high peat vulnerability to fire increases during El-Nino conditions with variations in its spatial patterns occurring under different ENSO phases. This study provides spatially explicit information to support the management of peat fires, which will be particularly useful for identifying peatland restoration priorities based on peatland vulnerability to fire maps. Our findings highlight Riau’s peatland as being the area most prone to fires area on Sumatra Island. Therefore, the groundwater level within this area should be intensively monitored to prevent peatland fires. In addition, conserving intact forests within peatland through the moratorium strategy and restoring the degraded peatland ecosystem through canal blocking is also crucial to coping with global climate change.https://www.mdpi.com/1999-4907/13/6/828vulnerability assessmenttropical peatlandclimate variabilityensemble modelSumatera |
| spellingShingle | Lilik Budi Prasetyo Yudi Setiawan Aryo Adhi Condro Kustiyo Kustiyo Erianto Indra Putra Nur Hayati Arif Kurnia Wijayanto Almi Ramadhi Daniel Murdiyarso Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches Forests vulnerability assessment tropical peatland climate variability ensemble model Sumatera |
| title | Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches |
| title_full | Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches |
| title_fullStr | Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches |
| title_full_unstemmed | Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches |
| title_short | Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches |
| title_sort | assessing sumatran peat vulnerability to fire under various condition of enso phases using machine learning approaches |
| topic | vulnerability assessment tropical peatland climate variability ensemble model Sumatera |
| url | https://www.mdpi.com/1999-4907/13/6/828 |
| work_keys_str_mv | AT lilikbudiprasetyo assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT yudisetiawan assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT aryoadhicondro assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT kustiyokustiyo assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT eriantoindraputra assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT nurhayati assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT arifkurniawijayanto assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT almiramadhi assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches AT danielmurdiyarso assessingsumatranpeatvulnerabilitytofireundervariousconditionofensophasesusingmachinelearningapproaches |