Hyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning
Open Access
- 24 August 2019
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 11 (17) , 2001
Abstract
Phytoplankton species composition research is key to understanding phytoplankton ecological and biogeochemical functions. Hyperspectral optical sensor technology allows us to obtain detailed information about phytoplankton species composition. In the present study, a transfer learning method to inverse phytoplankton species composition using in situ hyperspectral remote sensing reflectance and hyperspectral satellite imagery was presented. By transferring the general knowledge learned from the first few layers of a deep neural network (DNN) trained by a general simulation dataset, and updating the last few layers with an in situ dataset, the requirement for large numbers of in situ samples for training the DNN to predict phytoplankton species composition in natural waters was lowered. This method was established from in situ datasets and validated with datasets collected in different ocean regions in China with considerable accuracy (R2 = 0.88, mean absolute percentage error (MAPE) = 26.08%). Application of the method to Hyperspectral Imager for the Coastal Ocean (HICO) imagery showed that spatial distributions of dominant phytoplankton species and associated compositions could be derived. These results indicated the feasibility of species composition inversion from hyperspectral remote sensing, highlighting the advantages of transfer learning algorithms, which can bring broader application prospects for phytoplankton species composition and phytoplankton functional type research.Keywords
Funding Information
- National Natural Science Foundation of China (41771378, 51739005)
- National Key Research and Development Program of China (2016YFE0103200)
This publication has 70 references indexed in Scilit:
- Distinguishing Cyanobacterial Bloom From Floating Leaf Vegetation in Lake Taihu Based on Medium-Resolution Imaging Spectrometer (MERIS) DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017
- Obtaining Phytoplankton Diversity from Ocean Color: A Scientific Roadmap for Future DevelopmentFrontiers in Marine Science, 2017
- A Consumer's Guide to Satellite Remote Sensing of Multiple Phytoplankton Groups in the Global OceanFrontiers in Marine Science, 2017
- Temporal and spatial dynamics of phytoplankton diversity in the East China Sea near Jeju Island (Korea): A pyrosequencing-based studyBiochemical Systematics and Ecology, 2015
- Global phytoplankton decline over the past centuryNature, 2010
- Spectral backscattering properties of marine phytoplankton culturesOptics Express, 2010
- The life of diatoms in the world's oceansNature, 2009
- On Phytoplankton TrendsScience, 2008
- Spring algal bloom and larval fish survivalNature, 2003
- Stable phytoplankton community structure in the Arabian Sea over the past 200,000 yearsNature, 1998