A decision tree based on spatial relationships for predicting hotspots in peatlands
Predicting hotspot occurrence as an indicator of forest and land fires is essential in developing an early warning system for fire prevention. This work applied a spatial decision tree algorithm on spatial data of forest fires. The algorithm is the improvement of the conventional decision tree algor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan and Institute of Advanced Engineering and Science
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/36155/1/A%20decision%20tree%20based%20on%20spatial%20relationships%20for%20predicting%20hotspots%20in%20peatlands.pdf |
| _version_ | 1825948786538577920 |
|---|---|
| author | Sitanggang, Imas Sukaesih Yaakob, Razali Mustapha, Norwati Nuruddin, Ahmad Ainuddin |
| author_facet | Sitanggang, Imas Sukaesih Yaakob, Razali Mustapha, Norwati Nuruddin, Ahmad Ainuddin |
| author_sort | Sitanggang, Imas Sukaesih |
| collection | UPM |
| description | Predicting hotspot occurrence as an indicator of forest and land fires is essential in developing an early warning system for fire prevention. This work applied a spatial decision tree algorithm on spatial data of forest fires. The algorithm is the improvement of the conventional decision tree algorithm in which the distance and topological relationships are included to grow up spatial decision trees. Spatial data consist of a target layer and ten explanatory layers representing physical, weather, socio-economic and peatland characteristics in the study area Rokan Hilir District, Indonesia. Target objects are hotspots of 2008 and non-hotspot points. The result is a pruned spatial decision tree with 122 leaves and the accuracy of 71.66%. The spatial tree has produces higher accuracy than the non-spatial trees that were created using the ID3 and C4.5 algorithm. The ID3 decision tree has accuracy of 49.02% while the accuracy of C4.5 decision tree reaches 65.24%. |
| first_indexed | 2024-03-06T08:34:29Z |
| format | Article |
| id | upm.eprints-36155 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T08:34:29Z |
| publishDate | 2014 |
| publisher | Universitas Ahmad Dahlan and Institute of Advanced Engineering and Science |
| record_format | dspace |
| spelling | upm.eprints-361552016-01-26T02:56:10Z http://psasir.upm.edu.my/id/eprint/36155/ A decision tree based on spatial relationships for predicting hotspots in peatlands Sitanggang, Imas Sukaesih Yaakob, Razali Mustapha, Norwati Nuruddin, Ahmad Ainuddin Predicting hotspot occurrence as an indicator of forest and land fires is essential in developing an early warning system for fire prevention. This work applied a spatial decision tree algorithm on spatial data of forest fires. The algorithm is the improvement of the conventional decision tree algorithm in which the distance and topological relationships are included to grow up spatial decision trees. Spatial data consist of a target layer and ten explanatory layers representing physical, weather, socio-economic and peatland characteristics in the study area Rokan Hilir District, Indonesia. Target objects are hotspots of 2008 and non-hotspot points. The result is a pruned spatial decision tree with 122 leaves and the accuracy of 71.66%. The spatial tree has produces higher accuracy than the non-spatial trees that were created using the ID3 and C4.5 algorithm. The ID3 decision tree has accuracy of 49.02% while the accuracy of C4.5 decision tree reaches 65.24%. Universitas Ahmad Dahlan and Institute of Advanced Engineering and Science 2014-06 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/36155/1/A%20decision%20tree%20based%20on%20spatial%20relationships%20for%20predicting%20hotspots%20in%20peatlands.pdf Sitanggang, Imas Sukaesih and Yaakob, Razali and Mustapha, Norwati and Nuruddin, Ahmad Ainuddin (2014) A decision tree based on spatial relationships for predicting hotspots in peatlands. TELKOMNIKA, 12 (2). pp. 511-518. ISSN 1693-6930; ESSN: 2302-4046 http://journal.uad.ac.id/index.php/TELKOMNIKA/article/view/68 |
| spellingShingle | Sitanggang, Imas Sukaesih Yaakob, Razali Mustapha, Norwati Nuruddin, Ahmad Ainuddin A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title | A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title_full | A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title_fullStr | A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title_full_unstemmed | A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title_short | A decision tree based on spatial relationships for predicting hotspots in peatlands |
| title_sort | decision tree based on spatial relationships for predicting hotspots in peatlands |
| url | http://psasir.upm.edu.my/id/eprint/36155/1/A%20decision%20tree%20based%20on%20spatial%20relationships%20for%20predicting%20hotspots%20in%20peatlands.pdf |
| work_keys_str_mv | AT sitanggangimassukaesih adecisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT yaakobrazali adecisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT mustaphanorwati adecisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT nuruddinahmadainuddin adecisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT sitanggangimassukaesih decisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT yaakobrazali decisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT mustaphanorwati decisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands AT nuruddinahmadainuddin decisiontreebasedonspatialrelationshipsforpredictinghotspotsinpeatlands |