当前位置: X-MOL 学术Remote Sens. Environ. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-decade, multi-sensor time-series modelling—based on geostatistical concepts—to predict broad groups of crops
Remote Sensing of Environment ( IF 13.5 ) Pub Date : 2018-10-01 , DOI: 10.1016/j.rse.2018.06.046
Matthew J. Pringle , Michael Schmidt , Daniel R. Tindall

Abstract We have mapped the broad groups of crops grown each summer and winter, from 1987 to 2017, for a 300,000-km2 region of Queensland, Australia. These maps are part of a legislated decision-making process for the protection of prime agricultural land. For summer, the two groups of crops are ‘Coarse-grain & Pulse’ and ‘Cotton’. For winter, the two groups of crops are ‘Cereal’ and ‘Pulse’. Non-crop groups, present in both summer and winter, are ‘Bare soil’ and ‘Other’ (comprising pastures, woody vegetation, and crop residues). The foundation of the maps is time-series modelling—specifically, applying the concepts of geostatistics in the temporal domain—to model the variation in land-surface phenology within a growing season. The time-series model is flexible, robust, parsimonious, parallelisable, and able to deal with irregular observations. We combined satellite imagery from the Landsat sensors, as well as, when available, Sentinel-2A and MODIS (with the last two reprojected to the 30-m grid of Landsat). We applied the time-series model pixel-wise across the study region, to three variables derived from satellite imagery gathered for an individual growing season: enhanced vegetation index, and the sub-pixel proportions of bare-ground and non-photosynthetic vegetation. Weekly-averaged predicted phenological metrics then served as explanatory variables in a tiered, tree-based classification model, for the prediction of the groups. The classification model comprised two expert rules and two random forests. Prior to fitting the classification model, geospatial object-based image analysis was used to change the scale of analysis from individual pixels to (approximately) field-based segments. From the perspective of a map-user, in any given growing season we predicted ‘Coarse-grain & Pulse’ correctly in 79% of cases; the values for ‘Cotton’, ‘Cereal’, and ‘Pulse’ were 90%, 84%, and 73%, respectively; ‘Bare soil’ was 72% in summer, and 88% in winter. ‘Other’ was the most accurately mapped group (98% correct in summer, and 99% correct in winter).

中文翻译:

数十年、多传感器时间序列建模——基于地质统计学概念——预测广泛的作物群体

摘要 我们绘制了从 1987 年到 2017 年在澳大利亚昆士兰 300,000 平方公里地区每年夏季和冬季种植的广泛作物组的地图。这些地图是保护主要农业用地的立法决策过程的一部分。对于夏季,两组作物是“粗粮和豆类”和“棉花”。对于冬季,这两组作物是“谷物”和“豆类”。夏季和冬季都存在的非作物组是“裸土”和“其他”(包括牧场、木本植被和作物残留物)。地图的基础是时间序列建模——特别是在时间域中应用地质统计学的概念——来模拟生长季节内地表物候的变化。时间序列模型灵活、稳健、简约、可并行化,并且能够处理不规则的观察。我们结合了来自 Landsat 传感器的卫星图像,以及可用的 Sentinel-2A 和 MODIS(最后两个重新投影到 Landsat 的 30 米网格)。我们将时间序列模型逐像素应用于研究区域,应用于从单个生长季节收集的卫星图像得出的三个变量:增强的植被指数,以及裸地和非光合植被的亚像素比例。然后,每周平均预测的物候指标作为分层的、基于树的分类模型中的解释变量,用于预测组。分类模型包括两个专家规则和两个随机森林。在拟合分类模型之前,基于地理空间对象的图像分析用于将分析范围从单个像素更改为(大约)基于场的片段。从地图用户的角度来看,在任何给定的生长季节,我们在 79% 的情况下正确预测了“粗粒和脉冲”;“棉花”、“谷物”和“脉冲”的值分别为 90%、84% 和 73%;“裸土”在夏季为 72%,冬季为 88%。“其他”是映射最准确的组(夏季正确率为 98%,冬季正确率为 99%)。
更新日期:2018-10-01
down
wechat
bug