Remote Sensing of Turbidity in the Tennessee River Using Landsat 8 Satellite

The Tennessee River in the United States is one of the most ecologically distinct rivers in the world and serves as a great resource for local residents. However, it is also one of the most polluted rivers in the world, and a leading cause of this pollution is storm water runoff. Satellite remote sensing technology, which has been used successfully to study surface water quality parameters for many years, could be very useful to study and monitor the quality of water in the Tennessee River. This study developed a numerical turbidity estimation model for the Tennessee River and its tributaries in Southeast Tennessee using Landsat 8 satellite imagery coupled with near real-time in situ measurements. The obtained results suggest that a nonlinear regression-based numerical model can be developed using Band 4 (red) surface reflectance values of the Landsat 8 OLI sensor to estimate turbidity in these water bodies with the potential of high accuracy. The accuracy assessment of the estimated turbidity achieved a coefficient of determination (R2) value and root mean square error (RMSE) as high as 0.97 and 1.41 NTU, respectively. The model was also tested on imagery acquired on a different date to assess its potential for routine remote estimation of turbidity and produced encouraging results with R2 value of 0.94 and relatively high RMSE.

Inferring Grassland Drought Stress with Unsupervised Learning from Airborne Hyperspectral VNIR Imagery

The 2018–2019 Central European drought had a grave impact on natural and managed ecosystems, affecting their health and productivity. We examined patterns in hyperspectral VNIR imagery using an unsupervised learning approach to improve ecosystem monitoring and the understanding of grassland drought responses. The main objectives of this study were (1) to evaluate the application of simplex volume maximisation (SiVM), an unsupervised learning method, for the detection of grassland drought stress in high-dimensional remote sensing data at the ecosystem scale and (2) to analyse the contributions of different spectral plant and soil traits to the computed stress signal. The drought status of the research site was assessed with a non-parametric standardised precipitation–evapotranspiration index (SPEI) and soil moisture measurements. We used airborne HySpex VNIR-1800 data from spring 2018 and 2019 to compare vegetation condition at the onset of the drought with the state after one year. SiVM, an interpretable matrix factorisation technique, was used to derive typical extreme spectra (archetypes) from the hyperspectral data. The classification of archetypes allowed for the inference of qualitative drought stress levels. The results were evaluated using a set of geophysical measurements and vegetation indices as proxy variables for drought-inhibited vegetation growth. The successful application of SiVM for grassland stress detection at the ecosystem canopy scale was verified in a correlation analysis. The predictor importance was assessed with boosted beta regression. In the resulting interannual stress model, carotenoid-related variables had among the highest coefficient values. The significance of the photochemical reflectance index that uses 512 nm as reference wavelength (PRI512) demonstrates the value of combining imaging spectrometry and unsupervised learning for the monitoring of vegetation stress. It also shows the potential of archetypical reflectance spectra to be used for the remote estimation of photosynthetic efficiency. More conclusive results could be achieved by using vegetation measurements instead of proxy variables for evaluation. It must also be investigated how the method can be generalised across ecosystems.