Rufin Philippe, Bey Adia, Picoli Michelle, Meyfroidt Patrick
Earth and Life Institute, UCLouvain, 1348 Louvain-la-Neuve, Belgium.
Geography Department, Humboldt-Universität zu Berlin, 10117 Berlin, Germany.
Int J Appl Earth Obs Geoinf. 2022 Aug;112:102937. doi: 10.1016/j.jag.2022.102937.
Cropland mapping in smallholder landscapes is challenged by complex and fragmented landscapes, labor-intensive and unmechanized land management causing high within-field variability, rapid dynamics in shifting cultivation systems, and substantial proportions of short-term fallows. To overcome these challenges, we here present a large-area mapping framework to identify active cropland and short-term fallows in smallholder landscapes for the 2020/2021 growing season at 4.77 m spatial resolution. Our study focuses on Northern Mozambique, an area comprising 381,698 km. The approach is based on Google Earth Engine and time series of PlanetScope mosaics made openly available through Norwaýs International Climate and Forest Initiative (NICFI) data program. We conducted multi-temporal coregistration of the PlanetScope data using seasonal Sentinel-2 base images and derived consistent and gap-free seasonal time series metrics to classify active cropland and short-term fallows. An iterative active learning framework based on Random Forest class probabilities was used for training rare classes and uncertain regions. The map was accurate (area-adjusted overall accuracy 88.6% ± 1.5%), with the main error type being the commission of active cropland. Error-adjusted area estimates of active cropland extent (61,799.5 km ± 4,252.5 km) revealed that existing global and regional land cover products tend to under-, or over-estimate active cropland extent, respectively. Short-term fallows occupied 28.9% of the cropland in our reference sample (13% of the mapped cropland), with consolidated agricultural regions showing the highest shares of short-term fallows. Our approach relies on openly available PlanetScope data and cloud-based processing in Google Earth Engine, which minimizes financial constraints and maximizes replicability of the methods. All code and maps were made available for further use.
小农户景观中的农田测绘面临诸多挑战，包括景观复杂破碎、土地管理劳动密集且未机械化导致田间差异大、轮作系统动态变化快以及大量短期休耕地。为克服这些挑战，我们在此提出一个大面积测绘框架，用于在4.77米空间分辨率下识别2020/2021生长季小农户景观中的活跃农田和短期休耕地。我们的研究聚焦于莫桑比克北部，该地区面积为381,698平方千米。该方法基于谷歌地球引擎以及通过挪威国际气候与森林倡议（NICFI）数据项目公开提供的PlanetScope镶嵌图时间序列。我们使用季节性哨兵-2基础图像对PlanetScope数据进行多时间序列配准，并得出一致且无间隙的季节性时间序列指标，以对活跃农田和短期休耕地进行分类。基于随机森林分类概率的迭代主动学习框架用于训练稀有类别和不确定区域。该地图准确（面积调整后的总体准确率为88.6%±1.5%），主要误差类型是将非农田误判为活跃农田。活跃农田范围的误差调整面积估计值（61,799.5平方千米±4,252.5平方千米）表明，现有的全球和区域土地覆盖产品往往分别低估或高估活跃农田范围。在我们的参考样本中，短期休耕地占农田的28.9%（占测绘农田的13%），农业集中区域的短期休耕地比例最高。我们的方法依赖于公开可用的PlanetScope数据和谷歌地球引擎中的基于云的处理，这最大限度地减少了资金限制并提高了方法的可复制性。所有代码和地图均可供进一步使用。
