0000000001122891
AUTHOR
Kari Kallio
Machine Learning Regression Approaches for Colored Dissolved Organic Matter (CDOM) Retrieval with S2-MSI and S3-OLCI Simulated Data
The colored dissolved organic matter (CDOM) variable is the standard measure of humic substance in waters optics. CDOM is optically characterized by its spectral absorption coefficient, a C D O M at at reference wavelength (e.g., ≈ 440 nm). Retrieval of CDOM is traditionally done using bio-optical models. As an alternative, this paper presents a comparison of five machine learning methods applied to Sentinel-2 and Sentinel-3 simulated reflectance ( R r s ) data for the retrieval of CDOM: regularized linear regression (RLR), random forest regression (RFR), kernel ridge regression (KRR), Gaussian process regression (GPR) and support vector machines (SVR). Two different datasets of radiative t…
Geographic and temporal variations in turbulent heat loss from lakes : A global analysis across 45 lakes
Heat fluxes at the lake surface play an integral part in determining the energy budget and thermal structure in lakes, including regulating how lakes respond to climate change. We explore patterns in turbulent heat fluxes, which vary across temporal and spatial scales, using in situ high-frequency monitoring data from 45 glob- ally distributed lakes. Our analysis demonstrates that some of the lakes studied follow a marked seasonal cycle in their turbulent surface fluxes and that turbulent heat loss is highest in larger lakes and those situated at low latitude. The Bowen ratio, which is the ratio of mean sensible to mean latent heat fluxes, is smaller at low lati- tudes and, in turn, the rel…
Retrieval of coloured dissolved organic matter with machine learning methods
The coloured dissolved organic matter (CDOM) concentration is the standard measure of humic substance in natural waters. CDOM measurements by remote sensing is calculated using the absorption coefficient (a) at a certain wavelength (e.g. 440nm). This paper presents a comparison of four machine learning methods for the retrieval of CDOM from remote sensing signals: regularized linear regression (RLR), random forest (RF), kernel ridge regression (KRR) and Gaussian process regression (GPR). Results are compared with the established polynomial regression algorithms. RLR is revealed as the simplest and most efficient method, followed closely by its nonlinear counterpart KRR.