Belda Santiago, Pipia Luca, Morcillo-Pallarés Pablo, Verrelst Jochem
Image Processing Laboratory (IPL), Parc Científic, University of Valencia, Paterna, 46980 Valencia, Spain.
Agronomy (Basel). 2020 Apr 27;10(5):618. doi: 10.3390/agronomy10050618.
Image processing entered the era of artificial intelligence, and machine learning algorithms emerged as attractive alternatives for time series data processing. Satellite image time series processing enables crop phenology monitoring, such as the calculation of start and end of season. Among the promising algorithms, Gaussian process regression (GPR) proved to be a competitive time series gap-filling algorithm with the advantage of, as developed within a Bayesian framework, providing associated uncertainty estimates. Nevertheless, the processing of time series images becomes computationally inefficient in its standard per-pixel usage, mainly for GPR training rather than the fitting step. To mitigate this computational burden, we propose to substitute the per-pixel optimization step with the creation of a cropland-based precalculations for the GPR hyperparameters . To demonstrate our approach hardly affects the accuracy in fitting, we used Sentinel-2 LAI time series over an agricultural region in Castile and Leon, North-West Spain. The performance of image reconstructions were compared against the standard per-pixel GPR time series processing. Results showed that accuracies were on the same order (RMSE 0.1767 vs. 0.1564 [m/m], 12% RMSE degradation) whereas processing time accelerated about 90 times. We further evaluated the alternative option of using the same hyperparameters for all the pixels within the complete scene. It led to similar overall accuracies over crop areas and computational performance. Crop phenology indicators were also calculated for the three different approaches and compared. Results showed analogous crop temporal patterns, with differences in start and end of growing season of no more than five days. To the benefit of crop monitoring applications, all the gap-filling and phenology indicators retrieval techniques have been implemented into the freely downloadable GUI toolbox DATimeS.
图像处理进入了人工智能时代，机器学习算法成为时间序列数据处理的有吸引力的替代方法。卫星图像时间序列处理能够进行作物物候监测，例如计算季节的开始和结束。在有前景的算法中，高斯过程回归（GPR）被证明是一种有竞争力的时间序列填补缺口算法，其优势在于在贝叶斯框架内开发，能够提供相关的不确定性估计。然而，时间序列图像的处理在其标准的逐像素使用中计算效率低下，主要是在GPR训练而非拟合步骤中。为了减轻这种计算负担，我们建议用基于农田的GPR超参数预计算来替代逐像素优化步骤。为了证明我们的方法几乎不影响拟合精度，我们使用了西班牙西北部卡斯蒂利亚-莱昂一个农业地区的哨兵-2叶面积指数（LAI）时间序列。将图像重建的性能与标准的逐像素GPR时间序列处理进行了比较。结果表明，精度处于同一水平（均方根误差分别为0.1767和0.1564 [m/m]，RMSE下降12%），而处理时间加快了约90倍。我们进一步评估了在整个场景中对所有像素使用相同超参数的替代选项。它在作物区域导致了相似的总体精度和计算性能。还针对三种不同方法计算并比较了作物物候指标。结果显示了类似的作物时间模式，生长季节开始和结束的差异不超过五天。为了便于作物监测应用，所有的缺口填补和物候指标检索技术都已在可免费下载的GUI工具箱DATimeS中实现。
