- 데이터 세트 제공
- 2001-01-01T00:00:00Z–2017-01-01T00:00:00Z
- 데이터 세트 제작자
- iSDA Google Earth Engine
- 태그
설명
토양 깊이 0~20cm 및 20~50cm에서 추출 가능한 알루미늄, 예측된 평균 및 표준 편차
픽셀 값은 exp(x/10)-1로 역변환해야 합니다.
토양 속성 예측은 Innovative Solutions for Decision Agriculture Ltd. (iSDA)에서 원격 감지 데이터 및 분석된 100,000개 이상의 토양 샘플의 학습 세트와 결합된 머신러닝을 사용하여 30m 픽셀 크기로 수행했습니다.
자세한 내용은 FAQ 및 기술 정보 문서를 참고하세요. 문제를 제출하거나 지원을 요청하려면 iSDAsoil 사이트를 방문하세요.
밀림이 우거진 지역 (일반적으로 중앙 아프리카)에서는 모델 정확도가 낮으므로 밴딩 (줄무늬)과 같은 아티팩트가 표시될 수 있습니다.
대역
픽셀 크기
30m
밴드
| 이름 | 단위 | 최소 | 최대 | 픽셀 크기 | 설명 |
|---|---|---|---|---|---|
mean_0_20 |
ppm | 3 | 80 | 미터 | 알루미늄, 추출 가능, 0~20cm 깊이에서 예측된 평균 |
mean_20_50 |
ppm | 4 | 79 | 미터 | 알루미늄, 추출 가능, 20~50cm 깊이에서 예측된 평균 |
stdev_0_20 |
ppm | 1 | 53 | 미터 | 알루미늄, 추출 가능, 0~20cm 깊이의 표준 편차 |
stdev_20_50 |
ppm | 1 | 51 | 미터 | 알루미늄, 추출 가능, 20~50cm 깊이에서의 표준 편차 |
이용약관
이용약관
인용
인용:
Hengl, T., Miller, M.A.E., Križan, J., et al. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Sci Rep 11, 6130 (2021). doi:10.1038/s41598-021-85639-y
Hengl, T., Miller, M.A.E., Križan, J., et al. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Sci Rep 11, 6130 (2021). doi:10.1038/s41598-021-85639-y
DOI
Earth Engine으로 탐색
코드 편집기(JavaScript)
var mean_0_20 = '<RasterSymbolizer>' + '<ColorMap type="ramp">' + '<ColorMapEntry color="#000004" label="0-21.2" opacity="1" quantity="31"/>' + '<ColorMapEntry color="#0C0927" label="21.2-35.6" opacity="1" quantity="36"/>' + '<ColorMapEntry color="#231151" label="35.6-53.6" opacity="1" quantity="40"/>' + '<ColorMapEntry color="#410F75" label="53.6-65.7" opacity="1" quantity="42"/>' + '<ColorMapEntry color="#5F187F" label="65.7-72.7" opacity="1" quantity="43"/>' + '<ColorMapEntry color="#7B2382" label="72.7-80.5" opacity="1" quantity="44"/>' + '<ColorMapEntry color="#982D80" label="80.5-89" opacity="1" quantity="45"/>' + '<ColorMapEntry color="#B63679" label="89-98.5" opacity="1" quantity="46"/>' + '<ColorMapEntry color="#D3436E" label="98.5-108.9" opacity="1" quantity="47"/>' + '<ColorMapEntry color="#EB5760" label="108.9-120.5" opacity="1" quantity="48"/>' + '<ColorMapEntry color="#F8765C" label="120.5-133.3" opacity="1" quantity="49"/>' + '<ColorMapEntry color="#FD9969" label="133.3-147.4" opacity="1" quantity="50"/>' + '<ColorMapEntry color="#FEBA80" label="147.4-163" opacity="1" quantity="51"/>' + '<ColorMapEntry color="#FDDC9E" label="163-199.3" opacity="1" quantity="53"/>' + '<ColorMapEntry color="#FCFDBF" label="199.3-1800" opacity="1" quantity="55"/>' + '</ColorMap>' + '<ContrastEnhancement/>' + '</RasterSymbolizer>'; var mean_20_50 = '<RasterSymbolizer>' + '<ColorMap type="ramp">' + '<ColorMapEntry color="#000004" label="0-21.2" opacity="1" quantity="31"/>' + '<ColorMapEntry color="#0C0927" label="21.2-35.6" opacity="1" quantity="36"/>' + '<ColorMapEntry color="#231151" label="35.6-53.6" opacity="1" quantity="40"/>' + '<ColorMapEntry color="#410F75" label="53.6-65.7" opacity="1" quantity="42"/>' + '<ColorMapEntry color="#5F187F" label="65.7-72.7" opacity="1" quantity="43"/>' + '<ColorMapEntry color="#7B2382" label="72.7-80.5" opacity="1" quantity="44"/>' + '<ColorMapEntry color="#982D80" label="80.5-89" opacity="1" quantity="45"/>' + '<ColorMapEntry color="#B63679" label="89-98.5" opacity="1" quantity="46"/>' + '<ColorMapEntry color="#D3436E" label="98.5-108.9" opacity="1" quantity="47"/>' + '<ColorMapEntry color="#EB5760" label="108.9-120.5" opacity="1" quantity="48"/>' + '<ColorMapEntry color="#F8765C" label="120.5-133.3" opacity="1" quantity="49"/>' + '<ColorMapEntry color="#FD9969" label="133.3-147.4" opacity="1" quantity="50"/>' + '<ColorMapEntry color="#FEBA80" label="147.4-163" opacity="1" quantity="51"/>' + '<ColorMapEntry color="#FDDC9E" label="163-199.3" opacity="1" quantity="53"/>' + '<ColorMapEntry color="#FCFDBF" label="199.3-1800" opacity="1" quantity="55"/>' + '</ColorMap>' + '<ContrastEnhancement/>' + '</RasterSymbolizer>'; var stdev_0_20 = '<RasterSymbolizer>' + '<ColorMap type="ramp">' + '<ColorMapEntry color="#fde725" label="low" opacity="1" quantity="5"/>' + '<ColorMapEntry color="#5dc962" label=" " opacity="1" quantity="9"/>' + '<ColorMapEntry color="#20908d" label=" " opacity="1" quantity="10"/>' + '<ColorMapEntry color="#3a528b" label=" " opacity="1" quantity="12"/>' + '<ColorMapEntry color="#440154" label="high" opacity="1" quantity="14"/>' + '</ColorMap>' + '<ContrastEnhancement/>' + '</RasterSymbolizer>'; var stdev_20_50 = '<RasterSymbolizer>' + '<ColorMap type="ramp">' + '<ColorMapEntry color="#fde725" label="low" opacity="1" quantity="5"/>' + '<ColorMapEntry color="#5dc962" label=" " opacity="1" quantity="9"/>' + '<ColorMapEntry color="#20908d" label=" " opacity="1" quantity="10"/>' + '<ColorMapEntry color="#3a528b" label=" " opacity="1" quantity="12"/>' + '<ColorMapEntry color="#440154" label="high" opacity="1" quantity="14"/>' + '</ColorMap>' + '<ContrastEnhancement/>' + '</RasterSymbolizer>'; Map.setCenter(25, -3, 2); var raw = ee.Image("ISDASOIL/Africa/v1/aluminium_extractable"); Map.addLayer( raw.select(0).sldStyle(mean_0_20), {}, "Aluminium, extractable, mean visualization, 0-20 cm"); Map.addLayer( raw.select(1).sldStyle(mean_20_50), {}, "Aluminium, extractable, mean visualization, 20-50 cm"); Map.addLayer( raw.select(2).sldStyle(stdev_0_20), {}, "Aluminium, extractable, stdev visualization, 0-20 cm"); Map.addLayer( raw.select(3).sldStyle(stdev_20_50), {}, "Aluminium, extractable, stdev visualization, 20-50 cm"); var converted = raw.divide(10).exp().subtract(1); Map.addLayer( converted.select(0), {min: 0, max: 100}, "Aluminium, extractable, mean, 0-20 cm");