IrrMapper는 Landsat 규모 (즉, 30m)을 사용하여 1986년부터 현재까지의 기간을 다룹니다.
IrrMapper 논문에서는 4가지 클래스 (즉, 관개, 건지, 미경작지, 습지)의 분류를 설명하지만 데이터 세트는 관개 및 비관개의 이진 분류로 변환됩니다.
'관개'는 연중 관개 여부를 감지한 것을 의미합니다.
IrrMapper 랜덤 포레스트 모델은 50,000개가 넘는 인적 검증된 관개 농지, 38,000개의 건조지 농지, 500,000km²가 넘는 미경작지를 포함하여 관개 및 비관개 클래스 각각의 광범위한 지리 공간적 토지 피복 데이터베이스를 사용하여 학습되었습니다.
버전 1.2에서는 원래 학습 데이터가 크게 확장되었고, 각 주에 대해 RF 모델이 빌드되었으며, 더 철저한 검증 및 불확실성 분석이 수행되었습니다. 관개가 하천 유량에 미치는 영향에 관한 논문의 보충 자료를 참고하세요.
Ketchum, D.; Jencso, K.; Maneta, M.P.; Melton, F.; Jones, M.O.; Huntington, J.
IrrMapper: 미국 서부 전역의 관개 농업을 고해상도로 매핑하기 위한 머신러닝 접근 방식
Remote Sens. 2020, 12, 2328. doi:10.3390/rs12142328
Ketchum, D., Hoylman, Z.H., Huntington, J. 외. Irrigation intensification impacts sustainability
of streamflow in the Western United States. Commun Earth Environ 4, 479 (2023). doi:10.1038/s43247-023-01152-2
[null,null,[],[[["\u003cp\u003eIrrMapper is an annual dataset that classifies irrigated and non-irrigated land in the Western US from 1986 to present.\u003c/p\u003e\n"],["\u003cp\u003eThe dataset uses a Random Forest algorithm and Landsat data for 30m resolution mapping of irrigation status.\u003c/p\u003e\n"],["\u003cp\u003eIt provides a binary classification: irrigated areas are marked with a value of 1, while non-irrigated areas are masked out.\u003c/p\u003e\n"],["\u003cp\u003eDeveloped by the University of Montana, IrrMapper is available for research, education, and non-profit use under the CC-BY-4.0 license.\u003c/p\u003e\n"],["\u003cp\u003eUsers can explore and analyze the dataset using Google Earth Engine.\u003c/p\u003e\n"]]],[],null,["# IrrMapper Irrigated Lands, Version 1.2\n\nDataset Availability\n: 1986-01-01T00:00:00Z--2024-01-01T00:00:00Z\n\nDataset Provider\n:\n\n\n [University of Montana / Montana Climate Office](https://climate.umt.edu/research/irrmapper/)\n\nTags\n:\n[agriculture](/earth-engine/datasets/tags/agriculture) [landsat-derived](/earth-engine/datasets/tags/landsat-derived) \n\n#### Description\n\nIrrMapper is an annual classification of irrigation status in the 11\nWestern United States made at Landsat scale (i.e., 30 m) using the\nRandom Forest algorithm, covering years 1986 - present.\n\nWhile the [IrrMapper paper](https://www.mdpi.com/2072-4292/12/14/2328)\ndescribes classification of four classes (i.e., irrigated, dryland,\nuncultivated, wetland), the dataset is converted to a binary\nclassification of irrigated and non-irrigated.\n\n'Irrigated' refers to the detection of any irrigation during the year.\nThe IrrMapper random forest model was trained using an extensive\ngeospatial database of land cover from each of four irrigated- and\nnon-irrigated classes, including over 50,000 human-verified irrigated\nfields, 38,000 dryland fields, and over 500,000 square kilometers of\nuncultivated lands.\n\nFor version 1.2, the original training data was greatly expanded,\na RF model built for each state, and a more thorough validation and uncertainty\nanalysis undertaken. See the [supplement](https://static-content.springer.com/esm/art%3A10.1038%2Fs43247-023-01152-2/MediaObjects/43247_2023_1152_MOESM3_ESM.docx)\nto our [paper](https://www.nature.com/articles/s43247-023-01152-2) on the impacts of irrigation on streamflow.\n\n### Bands\n\n\n**Pixel Size**\n\n30 meters\n\n**Bands**\n\n| Name | Pixel Size | Description |\n|------------------|------------|------------------------------------------------------------------------|\n| `classification` | meters | Irrigated pixels have the value of 1, the other pixels are masked out. |\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- Ketchum, D.; Jencso, K.; Maneta, M.P.; Melton, F.; Jones, M.O.; Huntington, J.\n IrrMapper: A Machine Learning Approach for High Resolution Mapping of\n Irrigated Agriculture Across the Western U.S.,\n Remote Sens. 2020, 12, 2328. [doi:10.3390/rs12142328](https://doi.org/10.3390/rs12142328)\n\n Ketchum, D., Hoylman, Z.H., Huntington, J. et al. Irrigation intensification impacts sustainability\n of streamflow in the Western United States. Commun Earth Environ 4, 479 (2023). [doi:10.1038/s43247-023-01152-2](https://doi.org/10.1038/s43247-023-01152-2)\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 dataset = ee.ImageCollection('UMT/Climate/IrrMapper_RF/v1_2');\nvar irr = dataset.filterDate('2023-01-01', '2023-12-31').mosaic();\n\nvar visualization = {\n min: 0.0,\n max: 1.0,\n palette: ['blue']\n};\nMap.addLayer(irr, visualization, 'IrrMapper 2023');\nMap.setCenter(-112.516, 45.262, 10);\n```\n[Open in Code Editor](https://code.earthengine.google.com/?scriptPath=Examples:Datasets/UMT/UMT_Climate_IrrMapper_RF_v1_2) \n[IrrMapper Irrigated Lands, Version 1.2](/earth-engine/datasets/catalog/UMT_Climate_IrrMapper_RF_v1_2) \nIrrMapper is an annual classification of irrigation status in the 11 Western United States made at Landsat scale (i.e., 30 m) using the Random Forest algorithm, covering years 1986 - present. While the IrrMapper paper describes classification of four classes (i.e., irrigated, dryland, uncultivated, wetland), the dataset is converted to ... \nUMT/Climate/IrrMapper_RF/v1_2, agriculture,landsat-derived \n1986-01-01T00:00:00Z/2024-01-01T00:00:00Z \n31.3 -124.5 49 -99 \nGoogle Earth Engine \nhttps://developers.google.com/earth-engine/datasets\n\n- [](https://doi.org/https://climate.umt.edu/research/irrmapper/)\n- [](https://doi.org/https://developers.google.com/earth-engine/datasets/catalog/UMT_Climate_IrrMapper_RF_v1_2)"]]
