ABSTRACT The South Asia (India, Pakistan, Bangladesh, Nepal, Sri Lanka and Bhutan) has a staggering 900 million people (~43% of the population) who face food insecurity or severe food insecurity as per United Nations, Food and Agriculture Organization’s (FAO) the Food Insecurity Experience Scale (FIES). The existing coarse-resolution (≥250-m) cropland maps lack precision in geo-location of individual farms and have low map accuracies. This also results in uncertainties in cropland areas calculated from such products. Thereby, the overarching goal of this study was to develop a high spatial resolution (30-m or better) baseline cropland extent product of South Asia for the year 2015 using Landsat satellite time-series big-data and machine learning algorithms (MLAs) on the Google Earth Engine (GEE) cloud computing platform. To eliminate the impact of clouds, 10 time-composited Landsat bands (blue, green, red, NIR, SWIR1, SWIR2, Thermal, EVI, NDVI, NDWI) were derived for each of the three time-periods over 12 months (monsoon: Days of the Year (DOY) 151–300; winter: DOY 301–365 plus 1–60; and summer: DOY 61–150), taking the every 8-day data from Landsat-8 and 7 for the years 2013–2015, for a total of 30-bands plus global digital elevation model (GDEM) derived slope band. This 31-band mega-file big data-cube was composed for each of the five agro-ecological zones (AEZ’s) of South Asia and formed a baseline data for image classification and analysis. Knowledge-base for the Random Forest (RF) MLAs were developed using spatially well spread-out reference training data (N = 2179) in five AEZs. The classification was performed on GEE for each of the five AEZs using well-established knowledge-base and RF MLAs on the cloud. Map accuracies were measured using independent validation data (N = 1185). The survey showed that the South Asia cropland product had a producer’s accuracy of 89.9% (errors of omissions of 10.1%), user’s accuracy of 95.3% (errors of commission of 4.7%) and an overall accuracy of 88.7%. The National and sub-national (districts) areas computed from this cropland extent product explained 80-96% variability when compared with the National statistics of the South Asian Countries. The full-resolution imagery can be viewed at full-resolution, by zooming-in to any location in South Asia or the world, at www.croplands.org and the cropland products of South Asia downloaded from The Land Processes Distributed Active Archive Center (LP DAAC) of National Aeronautics and Space Administration (NASA) and the United States Geological Survey (USGS): https://lpdaac.usgs.gov/products/gfsad30saafgircev001/.

中文翻译：

---

农田范围和南亚地区使用 Landsat 卫星 30 米时间序列大数据，使用谷歌地球引擎云上的随机森林机器学习算法

摘要南亚（印度、巴基斯坦、孟加拉国、尼泊尔、斯里兰卡和不丹）有惊人的 9 亿人（约占总人口的 43%）面临粮食不安全或严重粮食不安全，联合国、粮食及农业组织（粮农组织）粮食不安全经验量表（FIES）。现有的粗分辨率（≥250 米）农田地图缺乏单个农场的地理定位精度，地图精度低。这也导致根据此类产品计算的耕地面积存在不确定性。因此，本研究的首要目标是使用 Landsat 卫星时间序列大数据和机器学习算法 (MLA) 开发 2015 年南亚的高空间分辨率（30 米或更高）基线农田范围产品Google Earth Engine (GEE) 云计算平台。为消除云的影响，针对 12 个月内的三个时间段（季风：一年中的天数 (DOY) 151–300；冬季：DOY 301–365 加 1–60；夏季：DOY 61–150），从 Landsat-8 和 7 获取 2013–2015 年每 8 天的数据，总共 30 个波段加上全球数字高程模型 (GDEM) 导出的斜坡带。这个 31 波段的巨型文件大数据立方体由南亚五个农业生态区 (AEZ) 中的每一个组成，并形成了用于图像分类和分析的基线数据。随机森林 (RF) MLA 的知识库是使用五个 AEZ 中空间分布良好的参考训练数据 (N = 2179) 开发的。使用完善的知识库和云上的 RF MLA 在 GEE 上对五个 AEZ 中的每一个进行分类。使用独立的验证数据（N = 1185）测量地图精度。调查显示，南亚农田产品生产者准确率为89.9%（遗漏错误10.1%），用户准确率为95.3%（委托错误4.7%），综合准确率为88.7%。与南亚国家的国家统计数据相比，根据该农田范围产品计算的国家和次国家（地区）面积解释了 80-96% 的可变性。可以在 www.croplands 上放大到南亚或世界上的任何位置，以全分辨率查看全分辨率图像。