一种基于光谱成像和人工神经网络确定水体中总悬浮固体与溶解有机物之间相关性的方法提案。

Proposal of a Method to Determine the Correlation between Total Suspended Solids and Dissolved Organic Matter in Water Bodies from Spectral Imaging and Artificial Neural Networks.

作者信息

R Veronez Maurício, Kupssinskü Lucas S, T Guimarães Tainá, Koste Emilie C, da Silva Juarez M, de Souza Laís V, Oliverio William F M, Jardim Rogélio S, Koch Ismael É, de Souza Jonas G, Gonzaga Luiz, Mauad Frederico F, Inocencio Leonardo C, Bordin Fabiane

机构信息

Advanced Visualization & Geoinformatics Lab-VizLab, Unisinos University, São Leopoldo 93022-750, Brazil.

Graduate Programme in Geology, Unisinos University, São Leopoldo 93022-750, Brazil.

出版信息

Sensors (Basel). 2018 Jan 9;18(1):159. doi: 10.3390/s18010159.

DOI:10.3390/s18010159

PMID:29315219

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5795905/

Abstract

Water quality monitoring through remote sensing with UAVs is best conducted using multispectral sensors; however, these sensors are expensive. We aimed to predict multispectral bands from a low-cost sensor (R, G, B bands) using artificial neural networks (ANN). We studied a lake located on the campus of Unisinos University, Brazil, using a low-cost sensor mounted on a UAV. Simultaneously, we collected water samples during the UAV flight to determine total suspended solids (TSS) and dissolved organic matter (DOM). We correlated the three bands predicted with TSS and DOM. The results show that the ANN validation process predicted the three bands of the multispectral sensor using the three bands of the low-cost sensor with a low average error of 19%. The correlations with TSS and DOM resulted in R² values of greater than 0.60, consistent with literature values.

摘要

利用无人机进行水质遥感监测时，最好使用多光谱传感器；然而，这些传感器价格昂贵。我们旨在使用人工神经网络（ANN）从低成本传感器（红、绿、蓝波段）预测多光谱波段。我们使用安装在无人机上的低成本传感器，对巴西南大河州联邦大学（Unisinos University）校园内的一个湖泊进行了研究。同时，我们在无人机飞行期间采集了水样，以测定总悬浮固体（TSS）和溶解有机物（DOM）。我们将预测的三个波段与TSS和DOM进行了关联。结果表明，人工神经网络验证过程使用低成本传感器的三个波段预测了多光谱传感器的三个波段，平均误差低至19%。与TSS和DOM的相关性导致R²值大于0.60，与文献值一致。