While satellite remote sensing of ocean color is a viable tool for estimating large-scale patterns of chlorophyll-a (Chl-a) and global ocean primary production, its application in coastal waters is limited by the complex optical properties. An exploratory study was conducted in the Gulf of Trieste (Adriatic Sea) to assess the usefulness of Sentinel-3 satellite data in the Slovenian national waters. OLCI (Ocean and Land Colour Instrument) Chl-a level 2 products (OC4Me and NN) were compared to monthly Chl-a in-situ measurements at fixed sites from 2017 to 2019. In addition, eight other methods for estimating Chl-a concentration based on reflectance in different spectral bands were tested (OC3M, OC4E, MedOC4, ADOC4, AD4, 3B-OLCI, 2B-OLCI and G2B). For some of these methods, calibration was performed on in-situ data to achieve a better agreement. Finally, L1-regularized regression and random forest were trained on the available dataset to test the capabilities of the machine learning approach. The results show rather poor performance of the two originally available products. The same is true for the other eight methods and the fits to the measured values also show only marginal improvement. The best results are obtained with the blue-green methods (OC3, OC4 and AD4), especially the AD4SI (a designated fit of AD4) with R = 0.56 and RMSE = 0.4 mg/m³, while the near infrared (NIR) methods show underwhelming performance. The machine learning approach can only explain 30% of the variability and the RMSE is of the same order as for the blue-green methods. We conclude that due to the low Chl-a concentration and the moderate turbidity of the seawater, the reflectance provided by the Sentinel-3 OLCI spectrometer carries little information about Chl-a in the Slovenian national waters within the Gulf of Trieste and is therefore of limited use for our purposes. This requires that we continue to improve satellite products for use in those marine waters that have not yet proven suitable. In this way, satellite data could be effectively integrated into a comprehensive network that would allow a reliable assessment of ecological status, taking into account environmental regulations.
20 March 2018 in Knowledge and Information Systems
One of the biggest challenges in continual learning domains is the tendency of machine learning models to forget previously learned information over time. While overcoming this issue, the existing approaches often exploit large amounts of additional memory and apply model forgetting mitigation mechanisms which substantially prolong the training process. Therefore, we propose a novel SuperFormer method that alleviates model forgetting, while spending negligible additional memory and time. We tackle the continual learning challenges in a learning scenario, where we learn different tasks in a sequential order. We compare our method against several prominent continual learning methods, i.e., EWC, SI, MAS, GEM, PSP, etc. on a set of text classification tasks. We achieve the best average performance in terms of AUROC and AUPRC (0.7% and 0.9% gain on average, respectively) and the lowest training time among all the methods of comparison. On average, our method reduces the total training time by a factor of 5.4-8.5 in comparison to similarly performing methods. In terms of the additional memory, our method is on par with the most memory-efficient approaches.
The reference method for \({\hbox {PM}}_{{10}}\) and \({\hbox {PM}}_{2.5}\) measurement in Europe is active sampling with subsequent gravimetric analysis. Also tapered element oscillating microbalance (TEOM) monitors are widely used across Europe for the assessment of particulate matter (PM), even though they are known to be biased due to the loss of semi-volatile materials attributed to sample heating. In our work we correct TEOM \({\hbox {PM}}_{{10}}\) measurements at eight different monitoring sites located in different surroundings and different climates across Slovenia to replicate reference measurements. We use simultaneous reference and TEOM measurements from a period of seven years (2011–2017) and assess the advantage of custom defined correction factors (with linear and orthogonal regression) compared to default correction factors. We further try to improve the corrections by adding meteorological parameters as inputs and training a linear model (lasso) and nonlinear model (random forest). Random forest and lasso models also enable us to evaluate the impact of different meteorological parameters or chemical compounds on TEOM measurements. Our results show that TEOM measurements can be efficiently corrected using correction factors defined with two linear regressions (for summer and winter) at most locations across continental Slovenia. Koper, which lies at the sea side, was the most problematic measurement site. There the measurements were the most affected by the meteorological situation, and they could not be successfully corrected. When examining the effect of the chemical composition at two different locations, levels of \({\hbox {NH}}_4^+\), \({\hbox {NO}}_3^{-}\), and organic carbon exhibited major impact on the discrepancies between reference and TEOM measurements.