ABSTRACT

The increased open-access availability of radar and optical satellite imagery has engendered numerous land use and land cover (LULC) analyses combining these data sources. In parallel, cloud computing platforms have enabled a wider community to perform LULC classifications over long periods and large areas. However, an assessment of how the performance of classifiers available on these cloud platforms can be optimized for the use of multi-imagery data has been lacking for multi-temporal LULC approaches. This study provides such an assessment for the supervised classifiers available on the open-access Google Earth Engine platform: Naïve Bayes (NB), Classification and Regression Trees (CART), Random Forest (RF), Gradient Tree Boosting (GTB), and Support Vector Machines (SVM). A multi-temporal LULC analysis using Sentinel-1 and 2 is implemented for a study area in the Mekong Delta. Classifier performance is compared for different combinations of input imagery, band sets, and training datasets. The results show that GTB and RF yield the highest overall accuracies, at 94% and 93%. Combining optical and radar imagery boosts classification accuracy for CART, RF, GTB, and SVM by 10–15 percentage points. Furthermore, it reduces the impact of limited training dataset quality for RF, GTB, and SVM.

摘要

雷达和光学卫星图像的开放获取可用性增加，产生了大量结合这些数据源的土地利用和土地覆盖 (LULC) 分析。同时，云计算平台使更广泛的社区能够在长期和大范围内执行 LULC 分类。然而，对于多时态 LULC 方法，缺乏对如何优化这些云平台上可用分类器的性能以使用多图像数据的评估。本研究为开放访问 Google Earth Engine 平台上可用的监督分类器提供了这样的评估：朴素贝叶斯 (NB)、分类和回归树 (CART)、随机森林 (RF)、梯度树提升 (GTB) 和支持向量机 (SVM)。使用 Sentinel-1 和 2 对湄公河三角洲的一个研究区域进行了多时相 LULC 分析。针对输入图像、波段集和训练数据集的不同组合，比较分类器性能。结果表明，GTB 和 RF 的总体准确度最高，分别为 94% 和 93%。结合光学和雷达图像将 CART、RF、GTB 和 SVM 的分类精度提高 10-15 个百分点。此外，它还减少了有限的训练数据集质量对 RF、GTB 和 SVM 的影响。和 SVM 提高 10-15 个百分点。此外，它还减少了有限的训练数据集质量对 RF、GTB 和 SVM 的影响。和 SVM 提高 10-15 个百分点。此外，它还减少了有限的训练数据集质量对 RF、GTB 和 SVM 的影响。