当前位置: X-MOL 学术Remote Sens. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Basin-scale and seasonal evaluation of automated threshold methods for surface water detection
Remote Sensing Letters ( IF 1.4 ) Pub Date : 2021-04-20 , DOI: 10.1080/2150704x.2021.1918788
Joni Storie 1 , C. D. Storie 1 , C.J. Henry 2 , M. Sokolov 2 , B. Murray 1 , J. Cameron 1 , R-M Tsenov 2
Affiliation  

ABSTRACT

Estimating surface water using satellite data can improve estimates and predictions for hydroelectric energy generation. The goal of this research is to identify the best threshold method and image band combination to detect seasonal surface water at the basin scale. This paper explores Otsu, Minimum Entropy, and average of Otsu-Minimum Entropy threshold algorithms using Sentinel-2 narrow near-infrared band 8A (N-NIR), shortwave infrared bands 11 and 12 (SWIR-11 or SWIR-12) images for the Assiniboine River Basin (ARB). The highest precision (0.87) of surface water detection was obtained in autumn using Minimum Entropy (N-NIR & SWIR-11) threshold values for the ARB, however, the Minimum Entropy also had poor detection of surface water (low recall). Use of the naïve Bayesian classifier did not improve detection of surface water compared to using threshold values alone, and the use of threshold values generated for one basin was not transferable to another basin. We concluded that threshold methods should be assessed seasonally, at a per-tile scale before combining surface water products at a watershed scale, and products should be evaluated using non-balanced statistical measures for watersheds with high land-to-water ratios. Accuracy assessment is hampered by validation data which represents static hydrologic conditions, not contemporary, seasonal conditions.



中文翻译:

流域规模和季节评估的地表水自动检测阈值方法

摘要

使用卫星数据估算地表水可以改善水力发电的估算和预测。这项研究的目的是确定最佳阈值方法和图像带组合,以检测流域尺度的季节性地表水。本文使用Sentinel-2窄近红外波段8A(N-NIR),短波红外波段11和12(SWIR-11或SWIR-12)图像探索Otsu,最小熵和Otsu-最小熵阈值算法的平均值,以用于阿西尼博因河流域(ARB)。在秋季,使用ARB的最小熵(N-NIR&SWIR-11)阈值获得了最高精度(0.87)的地表水,但是,最小熵对地表水的检测也很差(召回率低)。与仅使用阈值相比,使用朴素的贝叶斯分类器并没有改善地表水的检测,并且一个盆地生成的阈值的使用无法转移到另一个盆地。我们得出的结论是,应在分水岭规模合并地表水产品之前按季,以小块规模对阈值方法进行评估,并且对于水陆比高的分水岭,应使用非平衡统计方法对产品进行评估。验证数据妨碍了准确性评估,验证数据代表静态水文状况,而不是当代的季节性状况。在分水岭规模合并地表水产品之前,以每分位数规模为单位,对于具有高水土比的分水岭,应使用非平衡统计量度对产品进行评估。验证数据妨碍了准确性评估,验证数据代表静态水文状况,而不是当代的季节性状况。在分水岭规模合并地表水产品之前,以每分位数规模为单位,对于具有高水土比的分水岭,应使用非平衡统计量度对产品进行评估。验证数据妨碍了准确性评估,验证数据代表静态水文状况,而不是当代的季节性状况。

更新日期:2021-05-05
down
wechat
bug