Hengl, T., Miller, M.A.E., קריז'אן, ג'., ואחרים. מיפוי של תכונות ורכיבי תזונה בקרקע באפריקה ברזולוציה מרחבית של 30 מ' באמצעות למידת מכונה בהרכב דו-קנה מידה.
Sci Rep 11, 6130 (2021).
doi:10.1038/s41598-021-85639-y
זרחן שניתן להפקה בעומקי קרקע של 0-20 ס"מ ו-20-50 ס"מ, ממוצע צפוי וסטיית תקן. צריך לבצע טרנספורמציה הפוכה של ערכי הפיקסלים באמצעות הנוסחה exp(x/10)-1. באזורים של ג'ונגל צפוף (בדרך כלל מעל מרכז אפריקה), רמת הדיוק של המודל נמוכה ולכן יכול להיות שיוצגו ארטיפקטים כמו פסים. תחזיות לגבי תכונות הקרקע היו …
[null,null,[],[[["\u003cp\u003eThis dataset provides the predicted mean and standard deviation of extractable phosphorus in African soil at two depths (0-20 cm and 20-50 cm).\u003c/p\u003e\n"],["\u003cp\u003eThe data covers the period from 2001 to 2017 and was produced by iSDA using machine learning and remote sensing data.\u003c/p\u003e\n"],["\u003cp\u003ePixel values require back-transformation using the formula \u003ccode\u003eexp(x/10)-1\u003c/code\u003e to represent actual phosphorus levels in ppm.\u003c/p\u003e\n"],["\u003cp\u003eModel accuracy is reduced in dense jungle areas, potentially leading to visual artifacts like banding.\u003c/p\u003e\n"],["\u003cp\u003eThe dataset is available under the CC-BY-4.0 license.\u003c/p\u003e\n"]]],["The dataset, provided by iSDA, offers predicted mean and standard deviation of extractable phosphorus in African soil at depths of 0-20 cm and 20-50 cm from 2001-01-01T00:00:00Z to 2017-01-01T00:00:00Z. Soil data is at 30-meter pixel resolution, using machine learning and over 100,000 soil samples. Users must apply the `exp(x/10)-1` formula to back-transform pixel values. Model accuracy is low in dense jungle areas. The dataset is accessible via Earth Engine.\n"],null,["# iSDAsoil Extractable Phosphorus\n\nDataset Availability\n: 2001-01-01T00:00:00Z--2017-01-01T00:00:00Z\n\nDataset Provider\n:\n\n\n [iSDA](https://isda-africa.com/)\n\nTags\n:\n [africa](/earth-engine/datasets/tags/africa) [isda](/earth-engine/datasets/tags/isda) [soil](/earth-engine/datasets/tags/soil) \nphosphorus \n\n#### Description\n\nExtractable phosphorus at soil depths of 0-20 cm and 20-50 cm,\npredicted mean and standard deviation.\n\nPixel values must be back-transformed with `exp(x/10)-1`.\n\nIn areas of dense jungle (generally over central Africa), model accuracy is\nlow and therefore artifacts such as banding (striping) might be seen.\n\nSoil property predictions were made by\n[Innovative Solutions for Decision Agriculture Ltd. (iSDA)](https://isda-africa.com/)\nat 30 m pixel size using machine learning coupled with remote sensing data\nand a training set of over 100,000 analyzed soil samples.\n\nFurther information can be found in the\n[FAQ](https://www.isda-africa.com/isdasoil/faq/) and\n[technical information documentation](https://www.isda-africa.com/isdasoil/technical-information/). To submit an issue or request support, please visit\n[the iSDAsoil site](https://isda-africa.com/isdasoil).\n\n### Bands\n\n\n**Pixel Size**\n\n30 meters\n\n**Bands**\n\n| Name | Units | Min | Max | Pixel Size | Description |\n|---------------|-------|-----|-----|------------|---------------------------------------------------------------|\n| `mean_0_20` | ppm | 1 | 55 | meters | Phosphorus, extractable, predicted mean at 0-20 cm depth |\n| `mean_20_50` | ppm | 0 | 52 | meters | Phosphorus, extractable, predicted mean at 20-50 cm depth |\n| `stdev_0_20` | ppm | 0 | 19 | meters | Phosphorus, extractable, standard deviation at 0-20 cm depth |\n| `stdev_20_50` | ppm | 0 | 20 | meters | Phosphorus, extractable, standard deviation at 20-50 cm depth |\n\n### Terms of Use\n\n**Terms of Use**\n\n[CC-BY-4.0](https://spdx.org/licenses/CC-BY-4.0.html)\n\n### Citations\n\nCitations:\n\n- Hengl, T., Miller, M.A.E., Križan, J., et al. African soil properties and nutrients\n mapped at 30 m spatial resolution using two-scale ensemble machine learning.\n Sci Rep 11, 6130 (2021).\n [doi:10.1038/s41598-021-85639-y](https://doi.org/10.1038/s41598-021-85639-y)\n\n### Explore with Earth Engine\n\n| **Important:** Earth Engine is a platform for petabyte-scale scientific analysis and visualization of geospatial datasets, both for public benefit and for business and government users. Earth Engine is free to use for research, education, and nonprofit use. To get started, please [register for Earth Engine access.](https://console.cloud.google.com/earth-engine)\n\n### Code Editor (JavaScript)\n\n```javascript\nvar mean_0_20 =\n'\u003cRasterSymbolizer\u003e' +\n '\u003cColorMap type=\"ramp\"\u003e' +\n '\u003cColorMapEntry color=\"#0D0887\" label=\"0-2.7\" opacity=\"1\" quantity=\"13\"/\u003e' +\n '\u003cColorMapEntry color=\"#350498\" label=\"2.7-3\" opacity=\"1\" quantity=\"14\"/\u003e' +\n '\u003cColorMapEntry color=\"#5402A3\" label=\"3-3.5\" opacity=\"1\" quantity=\"15\"/\u003e' +\n '\u003cColorMapEntry color=\"#7000A8\" label=\"3.5-4\" opacity=\"1\" quantity=\"16\"/\u003e' +\n '\u003cColorMapEntry color=\"#8B0AA5\" label=\"4-4.5\" opacity=\"1\" quantity=\"17\"/\u003e' +\n '\u003cColorMapEntry color=\"#A31E9A\" label=\"4.5-5\" opacity=\"1\" quantity=\"18\"/\u003e' +\n '\u003cColorMapEntry color=\"#B93289\" label=\"5-5.7\" opacity=\"1\" quantity=\"19\"/\u003e' +\n '\u003cColorMapEntry color=\"#CC4678\" label=\"5.7-6.4\" opacity=\"1\" quantity=\"20\"/\u003e' +\n '\u003cColorMapEntry color=\"#DB5C68\" label=\"6.4-7.2\" opacity=\"1\" quantity=\"21\"/\u003e' +\n '\u003cColorMapEntry color=\"#E97158\" label=\"7.2-8\" opacity=\"1\" quantity=\"22\"/\u003e' +\n '\u003cColorMapEntry color=\"#F48849\" label=\"8-9\" opacity=\"1\" quantity=\"23\"/\u003e' +\n '\u003cColorMapEntry color=\"#FBA139\" label=\"9-10\" opacity=\"1\" quantity=\"24\"/\u003e' +\n '\u003cColorMapEntry color=\"#FEBC2A\" label=\"10-11.2\" opacity=\"1\" quantity=\"25\"/\u003e' +\n '\u003cColorMapEntry color=\"#FADA24\" label=\"11.2-12.5\" opacity=\"1\" quantity=\"26\"/\u003e' +\n '\u003cColorMapEntry color=\"#F0F921\" label=\"12.5-125\" opacity=\"1\" quantity=\"27\"/\u003e' +\n '\u003c/ColorMap\u003e' +\n '\u003cContrastEnhancement/\u003e' +\n'\u003c/RasterSymbolizer\u003e';\n\nvar mean_20_50 =\n'\u003cRasterSymbolizer\u003e' +\n '\u003cColorMap type=\"ramp\"\u003e' +\n '\u003cColorMapEntry color=\"#0D0887\" label=\"0-2.7\" opacity=\"1\" quantity=\"13\"/\u003e' +\n '\u003cColorMapEntry color=\"#350498\" label=\"2.7-3\" opacity=\"1\" quantity=\"14\"/\u003e' +\n '\u003cColorMapEntry color=\"#5402A3\" label=\"3-3.5\" opacity=\"1\" quantity=\"15\"/\u003e' +\n '\u003cColorMapEntry color=\"#7000A8\" label=\"3.5-4\" opacity=\"1\" quantity=\"16\"/\u003e' +\n '\u003cColorMapEntry color=\"#8B0AA5\" label=\"4-4.5\" opacity=\"1\" quantity=\"17\"/\u003e' +\n '\u003cColorMapEntry color=\"#A31E9A\" label=\"4.5-5\" opacity=\"1\" quantity=\"18\"/\u003e' +\n '\u003cColorMapEntry color=\"#B93289\" label=\"5-5.7\" opacity=\"1\" quantity=\"19\"/\u003e' +\n '\u003cColorMapEntry color=\"#CC4678\" label=\"5.7-6.4\" opacity=\"1\" quantity=\"20\"/\u003e' +\n '\u003cColorMapEntry color=\"#DB5C68\" label=\"6.4-7.2\" opacity=\"1\" quantity=\"21\"/\u003e' +\n '\u003cColorMapEntry color=\"#E97158\" label=\"7.2-8\" opacity=\"1\" quantity=\"22\"/\u003e' +\n '\u003cColorMapEntry color=\"#F48849\" label=\"8-9\" opacity=\"1\" quantity=\"23\"/\u003e' +\n '\u003cColorMapEntry color=\"#FBA139\" label=\"9-10\" opacity=\"1\" quantity=\"24\"/\u003e' +\n '\u003cColorMapEntry color=\"#FEBC2A\" label=\"10-11.2\" opacity=\"1\" quantity=\"25\"/\u003e' +\n '\u003cColorMapEntry color=\"#FADA24\" label=\"11.2-12.5\" opacity=\"1\" quantity=\"26\"/\u003e' +\n '\u003cColorMapEntry color=\"#F0F921\" label=\"12.5-125\" opacity=\"1\" quantity=\"27\"/\u003e' +\n '\u003c/ColorMap\u003e' +\n '\u003cContrastEnhancement/\u003e' +\n'\u003c/RasterSymbolizer\u003e';\n\nvar stdev_0_20 =\n'\u003cRasterSymbolizer\u003e' +\n '\u003cColorMap type=\"ramp\"\u003e' +\n '\u003cColorMapEntry color=\"#fde725\" label=\"low\" opacity=\"1\" quantity=\"1\"/\u003e' +\n '\u003cColorMapEntry color=\"#5dc962\" label=\" \" opacity=\"1\" quantity=\"2\"/\u003e' +\n '\u003cColorMapEntry color=\"#20908d\" label=\" \" opacity=\"1\" quantity=\"3\"/\u003e' +\n '\u003cColorMapEntry color=\"#3a528b\" label=\" \" opacity=\"1\" quantity=\"4\"/\u003e' +\n '\u003cColorMapEntry color=\"#440154\" label=\"high\" opacity=\"1\" quantity=\"5\"/\u003e' +\n '\u003c/ColorMap\u003e' +\n '\u003cContrastEnhancement/\u003e' +\n'\u003c/RasterSymbolizer\u003e';\n\nvar stdev_20_50 =\n'\u003cRasterSymbolizer\u003e' +\n '\u003cColorMap type=\"ramp\"\u003e' +\n '\u003cColorMapEntry color=\"#fde725\" label=\"low\" opacity=\"1\" quantity=\"1\"/\u003e' +\n '\u003cColorMapEntry color=\"#5dc962\" label=\" \" opacity=\"1\" quantity=\"2\"/\u003e' +\n '\u003cColorMapEntry color=\"#20908d\" label=\" \" opacity=\"1\" quantity=\"3\"/\u003e' +\n '\u003cColorMapEntry color=\"#3a528b\" label=\" \" opacity=\"1\" quantity=\"4\"/\u003e' +\n '\u003cColorMapEntry color=\"#440154\" label=\"high\" opacity=\"1\" quantity=\"5\"/\u003e' +\n '\u003c/ColorMap\u003e' +\n '\u003cContrastEnhancement/\u003e' +\n'\u003c/RasterSymbolizer\u003e';\n\nvar raw = ee.Image(\"ISDASOIL/Africa/v1/phosphorus_extractable\");\nMap.addLayer(\n raw.select(0).sldStyle(mean_0_20), {},\n \"Phosphorus extractable, mean visualization, 0-20 cm\");\nMap.addLayer(\n raw.select(1).sldStyle(mean_20_50), {},\n \"Phosphorus extractable, mean visualization, 20-50 cm\");\nMap.addLayer(\n raw.select(2).sldStyle(stdev_0_20), {},\n \"Phosphorus extractable, stdev visualization, 0-20 cm\");\nMap.addLayer(\n raw.select(3).sldStyle(stdev_20_50), {},\n \"Phosphorus extractable, stdev visualization, 20-50 cm\");\n\nvar converted = raw.divide(10).exp().subtract(1);\n\nvar visualization = {min: 0, max: 15};\n\nMap.setCenter(25, -3, 2);\n\nMap.addLayer(converted.select(0), visualization, \"Phosphorus extractable, mean, 0-20 cm\");\n```\n[Open in Code Editor](https://code.earthengine.google.com/?scriptPath=Examples:Datasets/ISDASOIL/ISDASOIL_Africa_v1_phosphorus_extractable) \n[iSDAsoil Extractable Phosphorus](/earth-engine/datasets/catalog/ISDASOIL_Africa_v1_phosphorus_extractable) \nExtractable phosphorus at soil depths of 0-20 cm and 20-50 cm, predicted mean and standard deviation. Pixel values must be back-transformed with exp(x/10)-1. In areas of dense jungle (generally over central Africa), model accuracy is low and therefore artifacts such as banding (striping) might be seen. Soil property predictions were ... \nISDASOIL/Africa/v1/phosphorus_extractable, africa,isda,soil \n2001-01-01T00:00:00Z/2017-01-01T00:00:00Z \n-35.22 -31.46 37.98 57.08 \nGoogle Earth Engine \nhttps://developers.google.com/earth-engine/datasets\n\n- [](https://doi.org/https://isda-africa.com/)\n- [](https://doi.org/https://developers.google.com/earth-engine/datasets/catalog/ISDASOIL_Africa_v1_phosphorus_extractable)"]]