Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies
The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for g...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Bao, Yilin [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, - Marine, Combe ELSEVIER, 2021, an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution, New York, NY [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:195 ; year:2020 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.catena.2020.104703 |
|---|
| Katalog-ID: |
ELV051633051 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV051633051 | ||
| 003 | DE-627 | ||
| 005 | 20230626032241.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210910s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.catena.2020.104703 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica |
| 035 | |a (DE-627)ELV051633051 | ||
| 035 | |a (ELSEVIER)S0341-8162(20)30253-8 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 333.7 |a 610 |q VZ |
| 084 | |a 43.12 |2 bkl | ||
| 084 | |a 43.13 |2 bkl | ||
| 084 | |a 44.13 |2 bkl | ||
| 100 | 1 | |a Bao, Yilin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| 264 | 1 | |c 2020transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. | ||
| 520 | |a The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. | ||
| 650 | 7 | |a Random forest model |2 Elsevier | |
| 650 | 7 | |a Hyperspectral reflectance |2 Elsevier | |
| 650 | 7 | |a Fuzzy K-means clustering |2 Elsevier | |
| 650 | 7 | |a Soil organic matter |2 Elsevier | |
| 650 | 7 | |a Decision trees |2 Elsevier | |
| 650 | 7 | |a Grouping strategies |2 Elsevier | |
| 700 | 1 | |a Meng, Xiangtian |4 oth | |
| 700 | 1 | |a Ustin, Susan |4 oth | |
| 700 | 1 | |a Wang, Xiang |4 oth | |
| 700 | 1 | |a Zhang, Xinle |4 oth | |
| 700 | 1 | |a Liu, Huanjun |4 oth | |
| 700 | 1 | |a Tang, Haitao |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier |a Marine, Combe ELSEVIER |t Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |d 2021 |d an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution |g New York, NY [u.a.] |w (DE-627)ELV006991912 |
| 773 | 1 | 8 | |g volume:195 |g year:2020 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.catena.2020.104703 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a SSG-OPC-GGO | ||
| 936 | b | k | |a 43.12 |j Umweltchemie |q VZ |
| 936 | b | k | |a 43.13 |j Umwelttoxikologie |q VZ |
| 936 | b | k | |a 44.13 |j Medizinische Ökologie |q VZ |
| 951 | |a AR | ||
| 952 | |d 195 |j 2020 |h 0 | ||
| author_variant |
y b yb |
|---|---|
| matchkey_str |
baoyilinmengxiangtianustinsusanwangxiang:2020----:isisetapeitomdlosiogncatrihifr |
| hierarchy_sort_str |
2020transfer abstract |
| bklnumber |
43.12 43.13 44.13 |
| publishDate |
2020 |
| allfields |
10.1016/j.catena.2020.104703 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica (DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 DE-627 ger DE-627 rakwb eng 333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Bao, Yilin verfasserin aut Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier Meng, Xiangtian oth Ustin, Susan oth Wang, Xiang oth Zhang, Xinle oth Liu, Huanjun oth Tang, Haitao oth Enthalten in Elsevier Marine, Combe ELSEVIER Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, 2021 an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution New York, NY [u.a.] (DE-627)ELV006991912 volume:195 year:2020 pages:0 https://doi.org/10.1016/j.catena.2020.104703 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO 43.12 Umweltchemie VZ 43.13 Umwelttoxikologie VZ 44.13 Medizinische Ökologie VZ AR 195 2020 0 |
| spelling |
10.1016/j.catena.2020.104703 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica (DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 DE-627 ger DE-627 rakwb eng 333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Bao, Yilin verfasserin aut Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier Meng, Xiangtian oth Ustin, Susan oth Wang, Xiang oth Zhang, Xinle oth Liu, Huanjun oth Tang, Haitao oth Enthalten in Elsevier Marine, Combe ELSEVIER Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, 2021 an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution New York, NY [u.a.] (DE-627)ELV006991912 volume:195 year:2020 pages:0 https://doi.org/10.1016/j.catena.2020.104703 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO 43.12 Umweltchemie VZ 43.13 Umwelttoxikologie VZ 44.13 Medizinische Ökologie VZ AR 195 2020 0 |
| allfields_unstemmed |
10.1016/j.catena.2020.104703 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica (DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 DE-627 ger DE-627 rakwb eng 333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Bao, Yilin verfasserin aut Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier Meng, Xiangtian oth Ustin, Susan oth Wang, Xiang oth Zhang, Xinle oth Liu, Huanjun oth Tang, Haitao oth Enthalten in Elsevier Marine, Combe ELSEVIER Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, 2021 an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution New York, NY [u.a.] (DE-627)ELV006991912 volume:195 year:2020 pages:0 https://doi.org/10.1016/j.catena.2020.104703 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO 43.12 Umweltchemie VZ 43.13 Umwelttoxikologie VZ 44.13 Medizinische Ökologie VZ AR 195 2020 0 |
| allfieldsGer |
10.1016/j.catena.2020.104703 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica (DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 DE-627 ger DE-627 rakwb eng 333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Bao, Yilin verfasserin aut Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier Meng, Xiangtian oth Ustin, Susan oth Wang, Xiang oth Zhang, Xinle oth Liu, Huanjun oth Tang, Haitao oth Enthalten in Elsevier Marine, Combe ELSEVIER Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, 2021 an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution New York, NY [u.a.] (DE-627)ELV006991912 volume:195 year:2020 pages:0 https://doi.org/10.1016/j.catena.2020.104703 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO 43.12 Umweltchemie VZ 43.13 Umwelttoxikologie VZ 44.13 Medizinische Ökologie VZ AR 195 2020 0 |
| allfieldsSound |
10.1016/j.catena.2020.104703 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica (DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 DE-627 ger DE-627 rakwb eng 333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Bao, Yilin verfasserin aut Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier Meng, Xiangtian oth Ustin, Susan oth Wang, Xiang oth Zhang, Xinle oth Liu, Huanjun oth Tang, Haitao oth Enthalten in Elsevier Marine, Combe ELSEVIER Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, 2021 an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution New York, NY [u.a.] (DE-627)ELV006991912 volume:195 year:2020 pages:0 https://doi.org/10.1016/j.catena.2020.104703 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO 43.12 Umweltchemie VZ 43.13 Umwelttoxikologie VZ 44.13 Medizinische Ökologie VZ AR 195 2020 0 |
| language |
English |
| source |
Enthalten in Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, New York, NY [u.a.] volume:195 year:2020 pages:0 |
| sourceStr |
Enthalten in Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, New York, NY [u.a.] volume:195 year:2020 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Umweltchemie Umwelttoxikologie Medizinische Ökologie |
| institution |
findex.gbv.de |
| topic_facet |
Random forest model Hyperspectral reflectance Fuzzy K-means clustering Soil organic matter Decision trees Grouping strategies |
| dewey-raw |
333.7 |
| isfreeaccess_bool |
false |
| container_title |
Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |
| authorswithroles_txt_mv |
Bao, Yilin @@aut@@ Meng, Xiangtian @@oth@@ Ustin, Susan @@oth@@ Wang, Xiang @@oth@@ Zhang, Xinle @@oth@@ Liu, Huanjun @@oth@@ Tang, Haitao @@oth@@ |
| publishDateDaySort_date |
2020-01-01T00:00:00Z |
| hierarchy_top_id |
ELV006991912 |
| dewey-sort |
3333.7 |
| id |
ELV051633051 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV051633051</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626032241.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.catena.2020.104703</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV051633051</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0341-8162(20)30253-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">333.7</subfield><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">43.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">43.13</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.13</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Bao, Yilin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Random forest model</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hyperspectral reflectance</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Fuzzy K-means clustering</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Soil organic matter</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Decision trees</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Grouping strategies</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Meng, Xiangtian</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ustin, Susan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Xiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Xinle</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Huanjun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tang, Haitao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Marine, Combe ELSEVIER</subfield><subfield code="t">Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex,</subfield><subfield code="d">2021</subfield><subfield code="d">an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution</subfield><subfield code="g">New York, NY [u.a.]</subfield><subfield code="w">(DE-627)ELV006991912</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:195</subfield><subfield code="g">year:2020</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.catena.2020.104703</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">43.12</subfield><subfield code="j">Umweltchemie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">43.13</subfield><subfield code="j">Umwelttoxikologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.13</subfield><subfield code="j">Medizinische Ökologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">195</subfield><subfield code="j">2020</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Bao, Yilin |
| spellingShingle |
Bao, Yilin ddc 333.7 bkl 43.12 bkl 43.13 bkl 44.13 Elsevier Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| authorStr |
Bao, Yilin |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV006991912 |
| format |
electronic Article |
| dewey-ones |
333 - Economics of land & energy 610 - Medicine & health |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies Elsevier |
| topic |
ddc 333.7 bkl 43.12 bkl 43.13 bkl 44.13 Elsevier Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies |
| topic_unstemmed |
ddc 333.7 bkl 43.12 bkl 43.13 bkl 44.13 Elsevier Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies |
| topic_browse |
ddc 333.7 bkl 43.12 bkl 43.13 bkl 44.13 Elsevier Random forest model Elsevier Hyperspectral reflectance Elsevier Fuzzy K-means clustering Elsevier Soil organic matter Elsevier Decision trees Elsevier Grouping strategies |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
x m xm s u su x w xw x z xz h l hl h t ht |
| hierarchy_parent_title |
Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |
| hierarchy_parent_id |
ELV006991912 |
| dewey-tens |
330 - Economics 610 - Medicine & health |
| hierarchy_top_title |
Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV006991912 |
| title |
Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| ctrlnum |
(DE-627)ELV051633051 (ELSEVIER)S0341-8162(20)30253-8 |
| title_full |
Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| author_sort |
Bao, Yilin |
| journal |
Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |
| journalStr |
Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex, |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
300 - Social sciences 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Bao, Yilin |
| container_volume |
195 |
| class |
333.7 610 VZ 43.12 bkl 43.13 bkl 44.13 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Bao, Yilin |
| doi_str_mv |
10.1016/j.catena.2020.104703 |
| dewey-full |
333.7 610 |
| title_sort |
vis-swir spectral prediction model for soil organic matter with different grouping strategies |
| title_auth |
Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| abstract |
The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. |
| abstractGer |
The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. |
| abstract_unstemmed |
The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA SSG-OPC-GGO |
| title_short |
Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies |
| url |
https://doi.org/10.1016/j.catena.2020.104703 |
| remote_bool |
true |
| author2 |
Meng, Xiangtian Ustin, Susan Wang, Xiang Zhang, Xinle Liu, Huanjun Tang, Haitao |
| author2Str |
Meng, Xiangtian Ustin, Susan Wang, Xiang Zhang, Xinle Liu, Huanjun Tang, Haitao |
| ppnlink |
ELV006991912 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth oth |
| doi_str |
10.1016/j.catena.2020.104703 |
| up_date |
2024-07-06T20:47:55.814Z |
| _version_ |
1803864114006589440 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV051633051</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626032241.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.catena.2020.104703</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001161.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV051633051</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0341-8162(20)30253-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">333.7</subfield><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">43.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">43.13</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.13</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Bao, Yilin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The effect of soil organic matter (SOM) on the spectral characteristics of soil differs among soil samples of different soil types with various mineral contents or mechanical compositions. SOM prediction models with visible and near-infrared and shortwave infrared (Vis-SWIR) spectral variables for grouping soil samples are more accurate than global modeling methods. However, the optimal grouping method must be explored. We measured the Vis-SWIR (400–2500 nm) spectral reflectance of 274 soil samples from the Songnen Plain and applied different grouping strategies, including traditional soil grouping, spectral clustering grouping and decision tree grouping considering both traditional grouping information and spectral information. The original reflectance, continuum removal, and first-derivative reflectance were analyzed with competitive adaptive reweighted sampling (CARS), and the results were used as inputs to establish a random forest model for SOM prediction. The following results were obtained: (1) the decision tree grouping method is the optimal grouping strategy for the SOM prediction model; (2) among different inputs, first-derivative reflectance is optimal; and (3) CARS is an effective way to reduce the number of inputs and improve the prediction accuracy of SOM. This study provides an effective soil grouping methodology for SOM estimation at the soil great group level.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Random forest model</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hyperspectral reflectance</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Fuzzy K-means clustering</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Soil organic matter</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Decision trees</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Grouping strategies</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Meng, Xiangtian</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ustin, Susan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Xiang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Xinle</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Huanjun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tang, Haitao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Marine, Combe ELSEVIER</subfield><subfield code="t">Towards unravelling the Rosette agent enigma: Spread and emergence of the co-invasive host-pathogen complex,</subfield><subfield code="d">2021</subfield><subfield code="d">an interdisciplinary journal of soil science, hydrology, geomorphology focusing on geoecology and landscape evolution</subfield><subfield code="g">New York, NY [u.a.]</subfield><subfield code="w">(DE-627)ELV006991912</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:195</subfield><subfield code="g">year:2020</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.catena.2020.104703</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">43.12</subfield><subfield code="j">Umweltchemie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">43.13</subfield><subfield code="j">Umwelttoxikologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.13</subfield><subfield code="j">Medizinische Ökologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">195</subfield><subfield code="j">2020</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.402895 |