Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia
Remote sensing has grown exponentially in the last 20 years, enabling scientists to study ecological phenomena with methods previously unavailable. Freely available satellite imagery in finer resolutions has increased, making it possible and more economical to analyze and monitor the Earth’s ecosyst...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National University of Mongolia
2019-07-01
|
| Series: | Mongolian Journal of Biological Sciences |
| Subjects: | |
| Online Access: | http://mjbs.num.edu.mn/uploads/files/MJBS%20Volume%2017%20Number%201%202019/PDF/mjbs-17-31-39-reece-2019.pdf |
| _version_ | 1819204899301228544 |
|---|---|
| author | Nanette Reece Ganchimeg Wingard Bayart Mandakh Richard P. Reading |
| author_facet | Nanette Reece Ganchimeg Wingard Bayart Mandakh Richard P. Reading |
| author_sort | Nanette Reece |
| collection | DOAJ |
| description | Remote sensing has grown exponentially in the last 20 years, enabling scientists to study ecological phenomena with methods previously unavailable. Freely available satellite imagery in finer resolutions has increased, making it possible and more economical to analyze and monitor the Earth’s ecosystems. Software and on-line platforms make it easier to investigate conservation areas of concern. Yet, remote areas such as Mongolia do not have freely available data, such as land cover and climate variables, at a fine scale in a Geographic Information System (GIS). Scientists depend on individual efforts and products produced for remote areas and the sharing of these data. In this paper, we report our findings in using Random Forest, a machine learning tree classifier, to categorize vegetative communities in the southern portion of Ikh Nart Nature Reserve in Mongolia. Our results produced 6 different vegetation community classes from a Landsat 8 image using 7 bands and collected on September 13, 2013. The vegetation communities are: ephemeral water, dense rock, low-density shrub/short grasses and forbs, short grasses and forbs, semi-shrub, and tall grasses. Our results provide a foundation for ecological studies in the region, such as those focusing on habitat selection by wildlife, and can inform broader-scale landscape planning. |
| first_indexed | 2024-12-23T04:43:08Z |
| format | Article |
| id | doaj.art-8d72f96feed64ab5b19a13405c3864a0 |
| institution | Directory Open Access Journal |
| issn | 1684-3908 2225-4994 |
| language | English |
| last_indexed | 2024-12-23T04:43:08Z |
| publishDate | 2019-07-01 |
| publisher | National University of Mongolia |
| record_format | Article |
| series | Mongolian Journal of Biological Sciences |
| spelling | doaj.art-8d72f96feed64ab5b19a13405c3864a02022-12-21T17:59:43ZengNational University of MongoliaMongolian Journal of Biological Sciences1684-39082225-49942019-07-01171313910.22353/mjbs.2019.17.05Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in MongoliaNanette Reece0Ganchimeg Wingard1Bayart Mandakh2Richard P. Reading3Department of Field Conservation, Denver Zoo, 2300 Steele St., Denver, Colorado 80205 USAMongolian Conservation Coalition, Ulaanbaatar, MongoliaMongolian Academy of Sciences, Institute of General and Experimental Biology, Ulaanbaatar, MongoliaCoalition for International Conservation & Department of Research & Conservation, Butterfly Pavilion 6252 West 104th Ave, Westminster, ColoradoRemote sensing has grown exponentially in the last 20 years, enabling scientists to study ecological phenomena with methods previously unavailable. Freely available satellite imagery in finer resolutions has increased, making it possible and more economical to analyze and monitor the Earth’s ecosystems. Software and on-line platforms make it easier to investigate conservation areas of concern. Yet, remote areas such as Mongolia do not have freely available data, such as land cover and climate variables, at a fine scale in a Geographic Information System (GIS). Scientists depend on individual efforts and products produced for remote areas and the sharing of these data. In this paper, we report our findings in using Random Forest, a machine learning tree classifier, to categorize vegetative communities in the southern portion of Ikh Nart Nature Reserve in Mongolia. Our results produced 6 different vegetation community classes from a Landsat 8 image using 7 bands and collected on September 13, 2013. The vegetation communities are: ephemeral water, dense rock, low-density shrub/short grasses and forbs, short grasses and forbs, semi-shrub, and tall grasses. Our results provide a foundation for ecological studies in the region, such as those focusing on habitat selection by wildlife, and can inform broader-scale landscape planning.http://mjbs.num.edu.mn/uploads/files/MJBS%20Volume%2017%20Number%201%202019/PDF/mjbs-17-31-39-reece-2019.pdfIkh Nart Nature ReserveMongoliaGISLandsatSupervised Classification |
| spellingShingle | Nanette Reece Ganchimeg Wingard Bayart Mandakh Richard P. Reading Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia Mongolian Journal of Biological Sciences Ikh Nart Nature Reserve Mongolia GIS Landsat Supervised Classification |
| title | Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia |
| title_full | Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia |
| title_fullStr | Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia |
| title_full_unstemmed | Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia |
| title_short | Using Random Forest to Classify Vegetation Communities in the Southern Area of Ikh Nart Nature Reserve in Mongolia |
| title_sort | using random forest to classify vegetation communities in the southern area of ikh nart nature reserve in mongolia |
| topic | Ikh Nart Nature Reserve Mongolia GIS Landsat Supervised Classification |
| url | http://mjbs.num.edu.mn/uploads/files/MJBS%20Volume%2017%20Number%201%202019/PDF/mjbs-17-31-39-reece-2019.pdf |
| work_keys_str_mv | AT nanettereece usingrandomforesttoclassifyvegetationcommunitiesinthesouthernareaofikhnartnaturereserveinmongolia AT ganchimegwingard usingrandomforesttoclassifyvegetationcommunitiesinthesouthernareaofikhnartnaturereserveinmongolia AT bayartmandakh usingrandomforesttoclassifyvegetationcommunitiesinthesouthernareaofikhnartnaturereserveinmongolia AT richardpreading usingrandomforesttoclassifyvegetationcommunitiesinthesouthernareaofikhnartnaturereserveinmongolia |