Resolving phytoplankton pigments from spectral images using convolutional neural networks
Resolving phytoplankton pigments from spectral images using convolutional neural networks
复制标题
DOI：
10.1002/lom3.10588
复制
发表时间：
2023-11-06
影响因子：
2.7
通讯作者：
Hunter，Peter
中科院分区：
文献类型：
--
作者：
Salmi，Pauliina;Poeloenen，Ilkka;Hunter，Peter
出于对内陆水域浮游植物进行快速、可靠监测的需求，本文介绍了一种基于移动光谱成像仪的协议，用于评估水样中的浮游植物色素。该方案包括（1）样品浓缩； (2)光谱成像； (3) 卷积神经网络 (CNN) 解析叶绿素 (Chla)、类胡萝卜素和藻蓝蛋白的浓度。该协议通过来自苏格兰 20 个湖泊的样本进行了验证，特别是蓝藻频繁繁殖的利文湖。同时，制备样品用于通过高效液相色谱法对 Chla 和类胡萝卜素进行参考观察，并通过分光光度法对藻蓝蛋白进行参考观察。通过每次从模型训练中排除每个湖并将排除的数据用作独立的测试数据来研究 CNN 的鲁棒性。对于利文湖，Chla 的中位绝对百分比差异 (MAPD) 为 15%，类胡萝卜素为 36%。 MAPD 估计的藻蓝蛋白浓度较高（102%）；然而，该系统能够表明蓝藻爆发的可能性。在其他湖泊的留一法测试中，叶绿素的 MAPD 为 26%，类胡萝卜素为 27%，藻蓝蛋白为 75%。藻蓝蛋白的较高误差可能是由于数据分布和参考观察的变化造成的。结论是，该协议可以通过使用 Chla 和类胡萝卜素作为生物量的代理来支持浮游植物监测。更多地关注训练数据的分布和数量将改善藻蓝蛋白的估计。
Motivated by the need for rapid and robust monitoring of phytoplankton in inland waters, this article introduces a protocol based on a mobile spectral imager for assessing phytoplankton pigments from water samples. The protocol includes (1) sample concentrating; (2) spectral imaging; and (3) convolutional neural networks (CNNs) to resolve concentrations of chlorophylla(Chla), carotenoids, and phycocyanin. The protocol was demonstrated with samples from 20 lakes across Scotland, with special emphasis on Loch Leven where blooms of cyanobacteria are frequent. In parallel, samples were prepared for reference observations of Chlaand carotenoids by high‐performance liquid chromatography and of phycocyanin by spectrophotometry. Robustness of the CNNs were investigated by excluding each lake from model trainings one at a time and using the excluded data as independent test data. For Loch Leven, median absolute percentage difference (MAPD) was 15% for Chlaand 36% for carotenoids. MAPD in estimated phycocyanin concentration was high (102%); however, the system was able to indicate the possibility of a cyanobacteria bloom. In the leave‐one‐out tests with the other lakes, MAPD was 26% for Chla, 27% for carotenoids, and 75% for phycocyanin. The higher error for phycocyanin was likely due to variation in the data distribution and reference observations. It was concluded that this protocol could support phytoplankton monitoring by using Chlaand carotenoids as proxies for biomass. Greater focus on the distribution and volume of the training data would improve the phycocyanin estimates.