32_geemap学习笔记 | 监督分类

断了学习geemap很久了，今天继续
1月11号迎来了吴秋生老师geemap的更新，所以咱们先更新一波

pip install -U geemap

import ee
import geemap
geemap.set_proxy(port=10809)

Map = geemap.Map()
Map

#Add data to the map
point = ee.Geometry.Point([-122.4439, 37.7538])

image = ee.ImageCollection('LANDSAT/LC08/C01/T1_SR') \
                    .filterBounds(point) \
                    .filterDate('2016-01-01', '2016-12-31') \
                    .sort('CLOUD_COVER') \
                    .first() \
                    .select('B[1-7]')

vis_params = {
    'min': 0,
    'max': 3000,
    'bands': ['B5', 'B4', 'B3']
}

Map.centerObject(point, 8)
Map.addLayer(image, vis_params, "Landsat-8")

#查看图片属性
ee.Date(image.get('system:time_start')).format('YYYY-MM-dd').getInfo()
# '2016-11-18'

image.get('CLOUD_COVER').getInfo()
# 0.08

#有以下几种方式可以产生训练集
#region = map.user_roi
#region = ee.Geometry.Rectangle([-122.6003, 37.4831, -121.8036, 37.8288])
#region = ee.Geometry.Point([-122.4439, 37.7538]).buffer(10000)

nlcd = ee.Image('USGS/NLCD/NLCD2016').select('landcover').clip(image.geometry())
Map.addLayer(nlcd, {}, 'NLCD')
Map

#制作训练样本
points = nlcd.sample(**{
    'region':image.geometry(),
    'scale':30,
    'numPixels':5000,
    'seed':0,
    'geometries':True  #set this to False to ignore geometries
})

Map.addLayer(points, {}, 'training', False)

print(points.size().getInfo())
# 3583

print(points.first().getInfo())
# {'type': 'Feature', 'geometry': {'type': 'Point', 'coordinates': [-122.25798986874739, 38.2706212827936]}, 'id': '0', 'properties': {'landcover': 31}}

Train the classifier

#使用下述波段去预测
bands = ['B1','B2','B3','B4','B5','B6','B7']
label = 'landcover'
training = image.select(bands).sampleRegions(**{
    'collection':points,
    'properties':[label],
    'scale':30
})

trained = ee.Classifier.smileCart().train(training, label, bands)

print(training.first().getInfo())
# {'type': 'Feature', 'geometry': None, 'id': '0_0', 'properties': {'B1': 575, 'B2': 814, 'B3': 1312, 'B4': 1638, 'B5': 1980, 'B6': 2091, 'B7': 1967, 'landcover': 31}}

Classify the image

# Classify the image with the same bands used for training 
result = image.select(bands).classify(trained)

# Display the clusters with random colors
Map.addLayer(result.randomVisualizer(),{}, 'classfied')
Map

class_values = nlcd.get('landcover_class_values').getInfo()
class_values
# [11,
#  12,
#  21,
#  22,
#  23,
#  24,
#  31,
#  41,
#  42,
#  43,
#  51,
#  52,
#  71,
#  72,
#  73,
#  74,
#  81,
#  82,
#  90,
#  95]

class_palette = nlcd.get('landcover_class_palette').getInfo()
class_palette
# ['476ba1',
#  'd1defa',
#  'decaca',
#  'd99482',
#  'ee0000',
#  'ab0000',
#  'b3aea3',
#  '68ab63',
#  '1c6330',
#  'b5ca8f',
#  'a68c30',
#  'ccba7d',
#  'e3e3c2',
#  'caca78',
#  '99c247',
#  '78ae94',
#  'dcd93d',
#  'ab7028',
#  'bad9eb',
#  '70a3ba']

landcover = result.set('classification_class_values', class_values)
landcover = landcover.set('classification_class_palette', class_palette)

Map.addLayer(landcover, {}, 'land cover')
Map

print("Change layer opacity")
cluster_layer = Map.layers[-1]
cluster_layer.interact(opacity=(0, 1, 0.1))

Map.add_legend(builtin_legend='NLCD')
Map

#导出到本地
import os
out_dir = os.path.join(os.path.expanduser('~'), 'Downloads')
out_file = os.path.join(out_dir, 'landcover.tif')

geemap.ee_export_image(landcover, filename=out_file, scale=900)

#导出数据到谷歌网盘
geemap.ee_export_image_to_drive(landcover, description='landcover', folder='eeexport', scale=90)