The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms
As a critical factor of earth’s ecosystem, vegetation is sensitive to climate change and its feedback has a pronounced effect on climate, hydrology, and ecology, etc. The quantitative sensitivity of Normalized Difference Vegetation Index (NDVI) to climate change has been investigated in the Yellow-H...
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Elsevier
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/d73b4daef40844eeabf58080b317b0cd |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:d73b4daef40844eeabf58080b317b0cd |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:d73b4daef40844eeabf58080b317b0cd2021-12-01T04:46:19ZThe sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms1470-160X10.1016/j.ecolind.2021.107443https://doaj.org/article/d73b4daef40844eeabf58080b317b0cd2021-05-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21001084https://doaj.org/toc/1470-160XAs a critical factor of earth’s ecosystem, vegetation is sensitive to climate change and its feedback has a pronounced effect on climate, hydrology, and ecology, etc. The quantitative sensitivity of Normalized Difference Vegetation Index (NDVI) to climate change has been investigated in the Yellow-Huai-Hai River Basin (YHHRB) covering multiple climatic zones. Based on multicollinearity test using the Variance Inflation Factor, four climatic factors and six landuse types were used as independent variables for NDVI simulation. The calibrated and validated statistical vegetation models denoted good performance using four machine learning algorithms. The ensemble results from the four machine learning modelling were used to assess the sensitivity of NDVI to temperature and precipitation change on annual and monthly scale. Based on historical climatic variability and future scenarios, eight hypothetical climatic scenarios for the changes in temperature and precipitation were used in this study. The results indicated that there were positive responses of NDVI to temperature and precipitation change. As an one °C increase in temperature, the NDVI was going to increase by 3.03%–5.79%, and it would increase by 3.35%–4.80% when the precipitation increased 10% in the YHHRB. Relatively, the NDVI was more sensitive to precipitation decrease than increase. The sensitivity of NDVI to temperature or precipitation was non-linear as temperature or precipitation changing for a specified climatic zone. Monthly, the sensitivity of NDVI to temperature change varied among the four climatic zones, but as precipitation increasing, the higher and lower sensitivity of NDVI were investigated in wetter and drier months, respectively. Spatially, the NDVI was more sensitive to temperature and precipitation in colder and drier areas, respectively. Landuse also has a significant impact on the sensitivity of NDVI to climate change. The results might be useful for understanding the climate-vegetation dynamics and landuse management under future climate change.Zhenxin BaoJianyun ZhangGuoqing WangTiesheng GuanJunliang JinYanli LiuMiao LiTao MaElsevierarticleSensitivityVegetationClimate changeNDVIMachine learningYellow-Huai-Hai River BasinEcologyQH540-549.5ENEcological Indicators, Vol 124, Iss , Pp 107443- (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Sensitivity Vegetation Climate change NDVI Machine learning Yellow-Huai-Hai River Basin Ecology QH540-549.5 |
| spellingShingle |
Sensitivity Vegetation Climate change NDVI Machine learning Yellow-Huai-Hai River Basin Ecology QH540-549.5 Zhenxin Bao Jianyun Zhang Guoqing Wang Tiesheng Guan Junliang Jin Yanli Liu Miao Li Tao Ma The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| description |
As a critical factor of earth’s ecosystem, vegetation is sensitive to climate change and its feedback has a pronounced effect on climate, hydrology, and ecology, etc. The quantitative sensitivity of Normalized Difference Vegetation Index (NDVI) to climate change has been investigated in the Yellow-Huai-Hai River Basin (YHHRB) covering multiple climatic zones. Based on multicollinearity test using the Variance Inflation Factor, four climatic factors and six landuse types were used as independent variables for NDVI simulation. The calibrated and validated statistical vegetation models denoted good performance using four machine learning algorithms. The ensemble results from the four machine learning modelling were used to assess the sensitivity of NDVI to temperature and precipitation change on annual and monthly scale. Based on historical climatic variability and future scenarios, eight hypothetical climatic scenarios for the changes in temperature and precipitation were used in this study. The results indicated that there were positive responses of NDVI to temperature and precipitation change. As an one °C increase in temperature, the NDVI was going to increase by 3.03%–5.79%, and it would increase by 3.35%–4.80% when the precipitation increased 10% in the YHHRB. Relatively, the NDVI was more sensitive to precipitation decrease than increase. The sensitivity of NDVI to temperature or precipitation was non-linear as temperature or precipitation changing for a specified climatic zone. Monthly, the sensitivity of NDVI to temperature change varied among the four climatic zones, but as precipitation increasing, the higher and lower sensitivity of NDVI were investigated in wetter and drier months, respectively. Spatially, the NDVI was more sensitive to temperature and precipitation in colder and drier areas, respectively. Landuse also has a significant impact on the sensitivity of NDVI to climate change. The results might be useful for understanding the climate-vegetation dynamics and landuse management under future climate change. |
| format |
article |
| author |
Zhenxin Bao Jianyun Zhang Guoqing Wang Tiesheng Guan Junliang Jin Yanli Liu Miao Li Tao Ma |
| author_facet |
Zhenxin Bao Jianyun Zhang Guoqing Wang Tiesheng Guan Junliang Jin Yanli Liu Miao Li Tao Ma |
| author_sort |
Zhenxin Bao |
| title |
The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| title_short |
The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| title_full |
The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| title_fullStr |
The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| title_full_unstemmed |
The sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| title_sort |
sensitivity of vegetation cover to climate change in multiple climatic zones using machine learning algorithms |
| publisher |
Elsevier |
| publishDate |
2021 |
| url |
https://doaj.org/article/d73b4daef40844eeabf58080b317b0cd |
| work_keys_str_mv |
AT zhenxinbao thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT jianyunzhang thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT guoqingwang thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT tieshengguan thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT junliangjin thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT yanliliu thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT miaoli thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT taoma thesensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT zhenxinbao sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT jianyunzhang sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT guoqingwang sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT tieshengguan sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT junliangjin sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT yanliliu sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT miaoli sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms AT taoma sensitivityofvegetationcovertoclimatechangeinmultipleclimaticzonesusingmachinelearningalgorithms |
| _version_ |
1718405795258826752 |