Search

Tide refers to a phenomenon that causes the change of water level in oceans. Tidal level forecasting plays an important role in many real-world applications especially those related to oceanic and coastal areas. For instance, accurate forecasting of tidal level can significantly increase the vessels’ safety as an excessive level of tidal makes serious problems in the movement of vessels. In this work, we propose a deep learning-based prediction interval framework in order to model the forecasting uncertainties of tidal current datasets. The proposed model develops optimum prediction intervals (PIs) focused on the deep learning-based CNN-LSTM model (CLSTM), and nonparametric approach termed as the lower upper bound estimation (LUBE) model. Moreover, we develop a novel deep neuroevolution algorithm based on a two-stage modification of the gaining-sharing knowledge optimization algorithm to optimize the architecture of the CLSTM automatically without the procedure of trial and error. This leads to a decline in the complexity raises in designing manually the deep learning architectures, as well as an enhancement in the performance of the PIs. We also utilize coverage width criterion to establish an excellent correlation appropriately between both the PI coverage probability and PI normalized average width. We indicate the searching efficiency and high accuracy of our proposed framework named as MGSK-CLSTM-LUBE by examining over the practical collected tidal current datasets from the Bay of Fundy, NS, Canada. [ABSTRACT FROM AUTHOR]

To deal with the large volume of data produced by hyperspectral sensors, the Canadian Space Agency (CSA) has developed and patented two near lossless data compression algorithms for use onboard a hyperspectral satellite: successive approximation multi-stage vector quantization (SAMVQ) and hierarchical self-organizing cluster vector quantization (HSOCVQ). This paper describes the two compression algorithms and demonstrates their near lossless feature. The compression error introduced by the two compression algorithms was compared with the intrinsic noise of the original data that is caused by the instrument noise and other noise sources such as calibration and atmospheric correction errors. The experimental results showed that the compression error was not larger than the intrinsic noise of the original data when a test data set was compressed at a compression ratio of 20:1. The overall noise in the reconstructed data that contains both the intrinsic noise and the compression error is even smaller than the intrinsic noise when the data is compressed using SAMVQ. A multi-disciplinary user acceptability study has been carried out in order to evaluate the impact of the two compression algorithms on hyperspectral data applications. This paper briefly summarizes the evaluation results of the user acceptability study. A prototype hardware compressor that implements the two compression algorithms has been built using field programmable gate arrays (FPGAs) and benchmarked. The compression ratio and fidelity achieved by the hardware compressor are similar to those obtained by software simulation. [ABSTRACT FROM AUTHOR]

The recently observed reduction in perennial ice in the Arctic has given rise to a corresponding increase in seasonal ice, which includes young ice (YI). This type of ice has a major impact on the weather and climate systems. However, only a limited number of studies have been dedicated to explore its spatial coverage and duration. This is mainly due to the lack of remote sensing tools that can identify it. This study uses an ice type and concentration retrieval algorithm, namely, Environment Canada's Ice Concentration Extractor, to study YI distribution and duration in the Arctic during seven ice formation seasons: 2002–03 to 2008–09. Results on the YI area, peak period, duration, and its interannual variability are presented in six regions covering the Arctic Basin. Duration is presented in terms of two parameters that describe the peak period and the number of days when YI concentration exceeds 50%. Probability distribution of the latter parameter shows that YI survives very few days before it grows into first-year ice. The summer of the minimum ice record in 2007 did not leave a remarkable impact on the subsequent YI area or its duration, although a delay in ice formation is observed. YI in the North Water polynya is also studied and shows no particular trend, although it varies between years. Anomalies are explained in terms of modeled surface temperature and wind. [ABSTRACT FROM AUTHOR]

A new algorithm, called Environment Canada's Ice Concentration Extractor (ECICE), has been developed to calculate total ice concentration and partial concentration of each ice type from remote-sensing observations. It employs two new concepts. First, it obtains a best estimate of ice concentrations by minimizing the sum of squared difference between observed and estimated radiometric values based on a linear radiometric model for each ice type. Second, instead of employing a single radiometric value (tie point) for each ice type, it utilizes the probability density distribution of the radiometric values for each ice type. Then, in a Monte Carlo simulation, 1000 radiometric values are randomly selected, total and ice-type concentrations are calculated by solving the minimization problem, and finally, median values from the 1000 simulations are chosen. The algorithm was applied to the winter sea ice in the Gulf of St. Lawrence, Canada, us- ing observations from Special Sensor Microwave Imager (SSM/I) 85-GHz channel. Results were evaluated against ice concentration estimates from the operational analysis of Radarsat images at the Canadian Ice Service (CIS). Statistics of the differences between the output concentration and CIS estimates show that ECICE can successfully identify open water and consolidated pack ice pixels better than the Enhanced NASA Team algorithm. However, in areas of ice concentrations between 20% and 70%, the algorithm's performance could not be precisely evaluated because the typical size of the CIS's analysis polygon is much larger than the footprint of the 85-GHz SSM/I channel. Hence, the algorithm captures information at a finer spatial scale. Examples of using one, two, and three radiometric parameters to calculate the concentrations are presented. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI) is an important surface variable for monitoring the status of vegetation and as input in a number of ecosystem process models. There are currently several coarse-resolution LAI maps over Canada, including a Canada Centre for Remote Sensing ten-day, 1-km resolution, Canada-wide product based on SPOT-4 VEGETATION (VGT), a MODIS eight-day, 1-km resolution, global product and a monthly, 7-km resolution, global map produced using POLDER-1. These products are difficult to validate because of their large spatial extent and coarse resolution. In this study we use in situ LAI measurements collected over a wide range of forest types and ecological zones in Canada to derive 30-m resolution reference LAI maps based on robust error-in-measurement regressions to Landsat Enhanced Thematic Mapper Plus vegetation indices. The reference maps and LAI products were aggregated to a coarser resolution (3 km for MODIS and VGT and 7 km for POLDER) before comparison to account for registration errors, and variability in sensor projected point spread functions. Spatially corresponding aggregated pixels with both high-quality reference and coarse scale LAI retrievals were compared. The comparison shows reasonable agreement (biases less than 25% or one LAI) between the VGT and reference LAI. The MODIS LAI product showed weak correlations (R² < 0.25) over all sites at the scale of comparison and typically overestimated reference LAI in mixed forests by approximately 200%. The POLDER LAI product, only available in June 1997, showed almost no correlation to the summer reference LAI datasets. It underestimated reference LAI for an early growing season with an extent, in some cases, greater than the seasonal differences in LAI. This independent validation of three large area LAI products suggests that there may be substantial biases due to the lack of regional tuning of retrieval algorithms. These biases are far larger than the uncertainties in the reference-based LAI scenes in the case of the MODIS product. This suggests that reliable LAI maps may require regional calibration to meet the Global Terrestrial Observing System mapping requirements of ± 15 % uncertainties. [ABSTRACT FROM AUTHOR]