2019
DOI: 10.1109/jstars.2019.2902375
|View full text |Cite
|
Sign up to set email alerts
|

Geo-Object-Based Soil Organic Matter Mapping Using Machine Learning Algorithms With Multi-Source Geo-Spatial Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
16
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
4

Relationship

2
7

Authors

Journals

citations
Cited by 39 publications
(17 citation statements)
references
References 60 publications
1
16
0
Order By: Relevance
“…In recent years, the extreme gradient boosting (XGBoost) algorithm has been gradually developed and has become a potential algorithm [66,70]. XGBoost has been used to achieve good outcomes in soil digital mapping of arid regions [71]. Moreover, it has been evaluated as a better model with efficiency and robustness for estimating soil parameters from actual soil information and environmental variables [72].…”
Section: Methods Advantage Disadvantage Referencesmentioning
confidence: 99%
See 1 more Smart Citation
“…In recent years, the extreme gradient boosting (XGBoost) algorithm has been gradually developed and has become a potential algorithm [66,70]. XGBoost has been used to achieve good outcomes in soil digital mapping of arid regions [71]. Moreover, it has been evaluated as a better model with efficiency and robustness for estimating soil parameters from actual soil information and environmental variables [72].…”
Section: Methods Advantage Disadvantage Referencesmentioning
confidence: 99%
“…Moreover, XGBoost has unique advantages. For instance, a regularization technique borrowing from the RF algorithm reduces overfitting and shortens the calculation costs [71]. It possesses customizable objective functions and more effective tree pruning mechanisms.…”
Section: Xgboostmentioning
confidence: 99%
“…The basis of this study is the geo-parcel [34,35,36], which is defined as the smallest visually perceivable spatial entity in geography. The features of geo-parcels can be represented by the spatial form and spectral information.…”
Section: Methodsmentioning
confidence: 99%
“…. , m) using spatial analysis technologies such as downscaling using area weighted interpolation, bicubic resampling, and overlay analysis based on polygons [27], [28]. The indicators of population density, including residential geo-objects' spectral and texture characteristics, area, building existence index, terrain slope, night light intensity, density of POI and road network from Internet electronic maps, locational factors such as the distances from road and river, and existing grid-based population data are jointly applied as the environmental variables of each geo-object a j (j = 1, .…”
Section: B Construction Of a Structured Multiattribute Tablementioning
confidence: 99%