Vizlab | X-Reality and Geoinformatics Lab, Graduate Programme in Applied Computing, Unisinos University, São Leopoldo 93022-750, Brazil.
Department of Statistics, State University of Maringá-PR, Maringá 87020-900, Brazil.
Sensors (Basel). 2020 Apr 9;20(7):2125. doi: 10.3390/s20072125.
Total Suspended Solids (TSS) and chlorophyll-a concentration are two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, this paper presents a methodology to estimate this information through remote sensing and Machine Learning (ML) techniques. TSS and chlorophyll-a are optically active components, therefore enabling measurement by remote sensing. Two study cases in distinct water bodies are performed, and those cases use different spatial resolution data from Sentinel-2 spectral images and unmanned aerial vehicles together with laboratory analysis data. In consonance with the methodology, supervised ML algorithms are trained to predict the concentration of TSS and chlorophyll-a. The predictions are evaluated separately in both study areas, where both TSS and chlorophyll-a models achieved R-squared values above 0.8.
总悬浮固体（TSS）和叶绿素 a 浓度是监测水质的两个关键参数。由于直接采集样本进行实验室分析可能很昂贵，因此本文提出了一种通过遥感和机器学习（ML）技术估算这些信息的方法。TSS 和叶绿素 a 是光活性成分，因此可以通过遥感进行测量。本文在两个不同的水体中进行了两个案例研究，这些案例使用了来自 Sentinel-2 光谱图像和无人机的不同空间分辨率数据以及实验室分析数据。根据该方法，对监督机器学习算法进行了训练，以预测 TSS 和叶绿素 a 的浓度。在这两个研究区域中分别对预测结果进行了评估，其中 TSS 和叶绿素 a 模型的 R 平方值均高于 0.8。
Zotero 插件
