Crop type mapping without field-level labels: Random forest transfer and unsupervised clustering techniques
Crop type mapping without field-level labels: Random forest transfer and unsupervised clustering techniques
复制标题
DOI：
10.1016/j.rse.2018.12.026
复制
发表时间：
2019-03-01
影响因子：
13.5
通讯作者：
Lobell, David B.
中科院分区：
文献类型：
--
作者：
Wang, Sherrie;Azzari, George;Lobell, David B.
田间作物类型测绘对于农业监测和粮食安全的各种应用是必要的。随着遥感图像的空间和时间分辨率不断提高，它正成为创建作物类型地图的日益强大的原始输入。尽管如此，自动作物类型映射仍然受到缺乏用于训练监督分类模型的田间作物标签的限制，在这项研究中，我们探索了使用跨越地理距离和时间转移的随机森林和无监督方法，结合作物类型映射的总体作物统计数据，我们通过剥夺不同州和年份的标签模型来模拟标签贫乏的环境。我们使用美国农业部农田数据层 (CDL) 提供的 30 m 空间分辨率作物类型标签验证了我们的方法。使用 Google Earth Engine，我们计算了陆地卫星表面反射率时间序列和导出的植被指数的傅里叶变换（或调和回归），并提取系数作为机器学习模型的特征。我们发现，在生长度日 (ODD) 相似的地区和年份上训练的随机森林转移到目标地区的准确率始终超过 80%。随着 GDD 差异的扩大，准确度会降低。无监督高斯混合模型 (GMM) 具有使用县级农作物统计数据得出的类标签，对农作物的分类不太一致，但不需要进行田间级标签进行训练。 GMM 在作物多样性较低的州（伊利诺伊州、爱荷华州、印第安纳州、内布拉斯加州）实现了超过 85% 的准确率，但当作物多样性较高干扰聚类时（北达科他州、南达科他州、威斯康星州、密歇根州），其表现有时并不比随机模型更好。在适当的条件下，这些方法为世界各地很少或没有地面标签的地区提供田间分辨率作物类型绘图的选择。
Crop type mapping at the field level is necessary for a variety of applications in agricultural monitoring and food security. As remote sensing imagery continues to increase in spatial and temporal resolution, it is becoming an increasingly powerful raw input from which to create crop type maps. Still, automated crop type mapping remains constrained by a lack of field-level crop labels for training supervised classification models, in this study, we explore the use of random forests transferred across geographic distance and time and unsupervised methods in conjunction with aggregate crop statistics for crop type mapping in the US Midwest, where we simulated the label-poor setting by depriving the models of labels in various states and years. We validated our methodology using available 30 m spatial resolution crop type labels from the US Department of Agriculture's Cropland Data Layer (CDL). Using Google Earth Engine, we computed Fourier transforms (or harmonic regressions) on the time series of Landsat Surface Reflectance and derived vegetation indices, and extracted the coefficients as features for machine learning models. We found that random forests trained on regions and years similar in growing degree days (ODD) transfer to the target region with accuracies consistently exceeding 80%. Accuracies decrease as differences in GDD expand. Unsupervised Gaussian mixture models (GMM) with class labels derived using county-level crop statistics classify crops less consistently but require no field-level labels for training. GMM achieves over 85% accuracy in states with low crop diversity (Illinois, Iowa, Indiana, Nebraska), but performs sometimes no better than random when high crop diversity interferes with clustering (North Dakota, South Dakota, Wisconsin, Michigan). Under the appropriate conditions, these methods offer options for field-resolution crop type mapping in regions around the world with few or no ground labels.