MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA
Indonesia is one of the countries with the largest area of tropical peatlands in the world. These wide peatlands have a vital role in the carbon cycle and carbon storage in huge quantities, thus strict conservation in the area is necessary. One effort to carry out conservation is to understand the s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Asociatia Geographia Technica
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/281892/1/04_musthofa.pdf |
| _version_ | 1797037499130839040 |
|---|---|
| author | Musthofa, Faizal Widyatmanti, Wirastuti Arjasakusuma, Sanjiwana Umarhadi, Deha A. Putri, Demetria A. Raharja, Fahrudin F. Arrasyid, M.K. |
| author_facet | Musthofa, Faizal Widyatmanti, Wirastuti Arjasakusuma, Sanjiwana Umarhadi, Deha A. Putri, Demetria A. Raharja, Fahrudin F. Arrasyid, M.K. |
| author_sort | Musthofa, Faizal |
| collection | UGM |
| description | Indonesia is one of the countries with the largest area of tropical peatlands in the world. These wide peatlands have a vital role in the carbon cycle and carbon storage in huge quantities, thus strict conservation in the area is necessary. One effort to carry out conservation is to understand the spatial distribution of carbon stock in peatlands. This study aims to map the spatial distribution of carbon stock based on peat thickness modeling using machine learning algorithms, i.e., Random Forest (RF), Quantile Regression Forests (QRF), and Cubist. A case study was conducted in a part of Lake Sentarum National Park, Indonesia where human interference is still limited. Digital elevation model (DEM) and synthetic aperture radar (SAR) data were included as the input variables. The results showed that RF performed the best among other models to estimate peat thickness (mean = 1.877 m) with an RMSE (root mean square error) of 0.483 m and an R2 of 0.786. DEMs are the most important parameters in our analysis compared to SAR data. Based on the best model, we estimated the total volume of 5,112,687 m3 in the study area, produced at 12.5 m resolution, which was then converted to a total of carbon stock at 0.337 ± 0.106 Mt carbon. © 2022, Asociatia Geographia Technica. All rights reserved. |
| first_indexed | 2024-03-14T00:04:12Z |
| format | Article |
| id | oai:generic.eprints.org:281892 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:04:12Z |
| publishDate | 2022 |
| publisher | Asociatia Geographia Technica |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2818922023-11-20T03:14:37Z https://repository.ugm.ac.id/281892/ MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA Musthofa, Faizal Widyatmanti, Wirastuti Arjasakusuma, Sanjiwana Umarhadi, Deha A. Putri, Demetria A. Raharja, Fahrudin F. Arrasyid, M.K. Geography and Environmental Sciences Indonesia is one of the countries with the largest area of tropical peatlands in the world. These wide peatlands have a vital role in the carbon cycle and carbon storage in huge quantities, thus strict conservation in the area is necessary. One effort to carry out conservation is to understand the spatial distribution of carbon stock in peatlands. This study aims to map the spatial distribution of carbon stock based on peat thickness modeling using machine learning algorithms, i.e., Random Forest (RF), Quantile Regression Forests (QRF), and Cubist. A case study was conducted in a part of Lake Sentarum National Park, Indonesia where human interference is still limited. Digital elevation model (DEM) and synthetic aperture radar (SAR) data were included as the input variables. The results showed that RF performed the best among other models to estimate peat thickness (mean = 1.877 m) with an RMSE (root mean square error) of 0.483 m and an R2 of 0.786. DEMs are the most important parameters in our analysis compared to SAR data. Based on the best model, we estimated the total volume of 5,112,687 m3 in the study area, produced at 12.5 m resolution, which was then converted to a total of carbon stock at 0.337 ± 0.106 Mt carbon. © 2022, Asociatia Geographia Technica. All rights reserved. Asociatia Geographia Technica 2022 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/281892/1/04_musthofa.pdf Musthofa, Faizal and Widyatmanti, Wirastuti and Arjasakusuma, Sanjiwana and Umarhadi, Deha A. and Putri, Demetria A. and Raharja, Fahrudin F. and Arrasyid, M.K. (2022) MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA. Geographia Technica, 17 (1). 46 -57. https://technicalgeography.org/pdf/1_2022/04_musthofa.pdf 10.21163/GT_2022.171.04 |
| spellingShingle | Geography and Environmental Sciences Musthofa, Faizal Widyatmanti, Wirastuti Arjasakusuma, Sanjiwana Umarhadi, Deha A. Putri, Demetria A. Raharja, Fahrudin F. Arrasyid, M.K. MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title | MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title_full | MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title_fullStr | MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title_full_unstemmed | MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title_short | MACHINE LEARNING FOR MAPPING SPATIAL DISTRIBUTION OF THICKNESS AND CARBON STOCK OF TROPICAL PEATLAND BASED ON REMOTE SENSING DATA: A CASE STUDY IN LAKE SENTARUM NATIONAL PARK, INDONESIA |
| title_sort | machine learning for mapping spatial distribution of thickness and carbon stock of tropical peatland based on remote sensing data a case study in lake sentarum national park indonesia |
| topic | Geography and Environmental Sciences |
| url | https://repository.ugm.ac.id/281892/1/04_musthofa.pdf |
| work_keys_str_mv | AT musthofafaizal machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT widyatmantiwirastuti machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT arjasakusumasanjiwana machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT umarhadidehaa machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT putridemetriaa machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT raharjafahrudinf machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia AT arrasyidmk machinelearningformappingspatialdistributionofthicknessandcarbonstockoftropicalpeatlandbasedonremotesensingdataacasestudyinlakesentarumnationalparkindonesia |