On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies

Subpixel classification (SPC) extracts meaningful information on land-cover classes from the mixed pixels.However, the major challenges for SPC are to obtain reliable soft reference data (RD), use apt input data, and achieve maximum accuracy. This article addresses these issues and applies the support vector machine (SVM) to retrieve the subpixel estimates of glacier facies (GF) using high radiometric-resolution Advanced Wide Field Sensor (AWiFS) data. Precise quantification of GF has fundamental importance in the glaciological research. Efficacy of the approach was first tested on the synthetic data followed by the input AWiFS and reference MultiSpectral Instrument data, including ancillary data. SPC of synthetic data resulted in overall accuracy (OA) of 95%, proving the merit of SVM. Classification accuracy is inversely related to the glacier’s surface heterogeneity. Reducing the number of classes enhanced the OA by ∼18%. Source and timing of RD invariably controls the SPC accuracy. OA improved by ∼5% on addressing the issue of temporal gap between input and RD. ∼11% increase in OA with the inclusion of ancillary data confirmed their positive effect on the accuracy. Input and reference fractional area of GF were strongly correlated (r > 0.9) with each other substantiating the results.

亚像素分类（Subpixel classification，SPC）可从混合像元中提取土地覆盖类别的有效信息。然而，SPC面临的核心挑战在于获取可靠的软参考数据（soft reference data，RD）、选用适配的输入数据以及实现最优分类精度。本文针对上述问题展开研究，采用支持向量机（Support Vector Machine，SVM），利用高辐射分辨率先进宽视场传感器（Advanced Wide Field Sensor，AWiFS）数据反演冰川相（Glacier Facies，GF）的亚像素估计值。冰川相的精准量化在冰川学研究中具有基础性重要意义。本研究首先在合成数据集上验证所提方法的有效性，随后分别基于输入AWiFS数据、参考多光谱仪器（MultiSpectral Instrument）数据并辅以辅助数据开展实验。合成数据的SPC实验获得了95%的总体精度（Overall Accuracy，OA），证实了SVM方法的应用价值。分类精度与冰川表面异质性呈负相关关系。减少分类类别数量可使OA提升约18%。参考数据的来源与时间节点始终是影响SPC精度的关键因素。通过弥补输入数据与参考数据间的时间间隙，OA提升约5%。加入辅助数据后OA提升约11%，证实了辅助数据对分类精度的积极作用。冰川相的输入分数面积与参考分数面积呈现极强的相关性（相关系数r>0.9），验证了实验结果的可靠性。