加拿大森林生态系统的高分辨率年度林地覆盖图(1984-2019)¶
森林土地覆盖图的年度时间序列在全国范围内(整个 6.5 亿公顷森林生态系统),代表了从 1984 年到 2019 年的逐年土地覆盖特征。这些时间序列土地覆盖图是从每年的时间制作的 - 一系列 Landsat 图像合成、森林变化信息以及辅助地形和水文数据,遵循 Hermosilla 等人描述的框架。 (2022),它建立在 Hermosilla 等人介绍的方法的基础上。 (2018)。 方法创新包括 (i) 使用森林结构的空中和太空测量从现有土地覆盖产品中导出的改进训练库; (ii) 使用距离=加权方法,选择与土地覆盖分布成比例的训练样本; (iii) 使用 150x150 公里的瓷砖系统生成区域分类模型。 使用干扰信息对地图进行后处理,以确保使用隐马尔可夫模型随时间进行逻辑类转换。 隐马尔可夫模型评估各个年级的可能性,以减少同比班级分配中的可变性和可能的噪音(例如,当班级可能性相似时)。
有关所应用的数据、图像处理和时间序列变化检测方法的概述,以及有关数据独立准确性评估的信息,请参阅 Hermosilla 等人。 (2022) 第 112780 号。DOI:https://doi.org/10.1016/j.rse.2021.112780 和 Hermosilla 等人。 (2018) https://www.tandfonline.com/doi/full/10.1080/07038992.2018.1437719
该数据代表 1984-2019 年加拿大森林生态系统的年度林地覆盖率。 8 月 1 日 -30 天的图像合成窗口用于生成最佳可用像素 (BAP) 图像合成,用作土地覆盖分类的源数据。 为产生这里显示的信息结果而开发的科学和方法,跟踪和描述加拿大森林的历史,由加拿大自然资源部加拿大林务局牵头,与不列颠哥伦比亚大学合作,并得到加拿大航天局的支持, Compute Canada 的 WestGrid 的处理能力得到增强。
引用¶
论文引用
Hermosilla, T., Wulder, M.A., White, J.C., Coops, N.C., 2022. Land cover classification in an era of big and open data: Optimizing localized implementation and training data selection to improve mapping outcomes. Remote Sensing of Environment. No. 112780. [Hermosilla et al. 2022](https://www.sciencedirect.com/science/article/pii/S0034425721005009)
When using this data, please cite as:
Hermosilla, T., Wulder, M.A., White, J.C., Coops, N.C., 2022. Land cover classification in an era of big and open data: Optimizing localized implementation and training data selection to improve mapping outcomes. Remote Sensing of Environment. No. 112780. DOI: https://doi.org/10.1016/j.rse.2022.112780 [Open Access]
Class Schema¶
#686868 | Class Code: 0 | Unclassified |
#3333ff | Class Code: 20 | Water |
#ccffff | Class Code: 31 | Snow/Ice |
#cccccc | Class Code: 32 | Rock/Rubble |
#996633 | Class Code: 33 | Exposed/Barren Land |
#ffccff | Class Code: 40 | Bryoids |
#ffff00 | Class Code: 50 | Shrubs |
#993399 | Class Code: 80 | Wetland |
#9933cc | Class Code: 81 | Wetland Treed |
#ccff33 | Class Code: 100 | Herbs |
#006600 | Class Code: 210 | Coniferous |
#00cc00 | Class Code: 220 | Broad Leaf |
#cc9900 | Class Code: 230 | Mixedwood |
Earth Engine Snippet¶
var ca_lc = ee.ImageCollection("projects/sat-io/open-datasets/CA_FOREST_LC_VLCE2"); var ca_lc_last = ee.Image(ca_lc.sort('system:time_start',false).first()); var from = [0, 20, 31, 32, 33, 40, 50, 80, 81, 100, 210, 220, 230]; var to = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 ]; ca_lc_last = ca_lc_last.remap(from, to); print("Reclassed values:"); print({"from": from, "to": to}); // Define a dictionary which will be used to make legend and visualize image on map var dict = { "names": [ "Unclassified", "Water", "Snow/Ice", "Rock/Rubble", "Exposed/Barren land", "Bryoids", "Shrubs", "Wetland", "Wetland-treed", "Herbs", "Coniferous", "Broadleaf", "Mixedwood" ], "colors": [ "#686868", "#3333ff", "#ccffff", "#cccccc", "#996633", "#ffccff", "#ffff00", "#993399", "#9933cc", "#ccff33", "#006600", "#00cc00", "#cc9900" ]}; // Create a panel to hold the legend widget var legend = ui.Panel({ style: { position: 'bottom-left', padding: '8px 15px' } }); // Function to generate the legend function addCategoricalLegend(panel, dict, title) { // Create and add the legend title. var legendTitle = ui.Label({ value: title, style: { fontWeight: 'bold', fontSize: '18px', margin: '0 0 4px 0', padding: '0' } }); panel.add(legendTitle); var loading = ui.Label('Loading legend...', {margin: '2px 0 4px 0'}); panel.add(loading); // Creates and styles 1 row of the legend. var makeRow = function(color, name) { // Create the label that is actually the colored box. var colorBox = ui.Label({ style: { backgroundColor: color, // Use padding to give the box height and width. padding: '8px', margin: '0 0 4px 0' } }); // Create the label filled with the description text. var description = ui.Label({ value: name, style: {margin: '0 0 4px 6px'} }); return ui.Panel({ widgets: [colorBox, description], layout: ui.Panel.Layout.Flow('horizontal') }); }; // Get the list of palette colors and class names from the image. var palette = dict['colors']; var names = dict['names']; loading.style().set('shown', false); for (var i = 0; i < names.length; i++) { panel.add(makeRow(palette[i], names[i])); } Map.add(panel); } /* // Display map and legend /// */ // Add the legend to the map addCategoricalLegend(legend, dict, 'CA Annual forest LC map 2019'); Map.setCenter(-97.61655457157725,55.6280720462063,4) // Add image to the map Map.addLayer(ca_lc_last.mask(ca_lc_last.neq(0)), {min:0, max:12, palette:dict['colors']}, 'CA Annual forest LC map 2019')
License¶
This work is licensed under and freely available to the public Open Government Licence - Canada (Open Government Licence - Canada | Open Government, Government of Canada).
Created by: Hermosilla et al. 2022
Curated in GEE by : Samapriya Roy
keywords: Land cover; Classification; Machine learning; Land cover change; Landsat; Lidar; ICESat-2
Last updated on GEE: 2021-11-14