Search

A large portion of Canada is covered by wetlands; mapping and monitoring them is of great importance for various applications. In this regard, Remote Sensing (RS) technology has been widely employed for wetland studies in Canada over the past 45 years. This study evaluates meta-data to investigate the status and trends of wetland studies in Canada using RS technology by reviewing the scientific papers published between 1976 and the end of 2020 (300 papers in total). Initially, a meta-analysis was conducted to analyze the status of RS-based wetland studies in terms of the wetland classification systems, methods, classes, RS data usage, publication details (e.g., authors, keywords, citations, and publications time), geographic information, and level of classification accuracies. The deep systematic review of 128 peer-reviewed articles illustrated the rising trend in using multi-source RS datasets along with advanced machine learning algorithms for wetland mapping in Canada. It was also observed that most of the studies were implemented over the province of Ontario. Pixel-based supervised classifiers were the most popular wetland classification algorithms. This review summarizes different RS systems and methodologies for wetland mapping in Canada to outline how RS has been utilized for the generation of wetland inventories. The results of this review paper provide the current state-of-the-art methods and datasets for wetland studies in Canada and will provide direction for future wetland mapping research. [ABSTRACT FROM AUTHOR]

This study examines the response of a cold-regions deltaic wetland ecosystem in northwestern Canada to two separate and differing seasonal wetting cycles. The goal of this paper was to examine the nature of reflected electromagnetic energy measured by earth observation (EO) satellites, and to assess whether seasonal wetland hydroperiod and episodic flooding events impact the information retrieved by the Sentinel-2 sensors. The year 2018 represents a year characterized by a large spring freshet and ice-jam flooding, while 2019 represents a year characterized more by summer open-water flooding. We applied the Modified Normalized Difference Wetness Index (MNDWI) to address the effects of the wetting cycles. The response of the vegetative cover was tracked using the fraction of the absorbed photosynthetically active radiation (fAPAR) and the Leaf Area Index (LAI). All three indices were viewed through the lens of cover classes as derived through a previously published study by the authors. The study provides a framework for designing longer-term studies where multiple intra- and inter-annual hydrological cycles can be accessed via EO data. Future studies will enable the examination of lag times inherent in the response to the various water sources applied to spectral response and incorporate this EO approach into a monitoring framework. [ABSTRACT FROM AUTHOR]

Wetlands are important ecosystems that are linked to climate change mitigation. As 25% of global wetlands are located in Canada, accurate and up-to-date wetland classification is of high importance, nationally and internationally. The advent of deep learning techniques has revolutionized the current use of machine learning algorithms to classify complex environments, specifically in remote sensing. In this paper, we explore the potential and possible limitations to be overcome regarding the use of ensemble deep learning techniques for complex wetland classification and discusses the potential and limitation of various solo convolutional neural networks (CNNs), including DenseNet, GoogLeNet, ShuffleNet, MobileNet, Xception, Inception-ResNet, ResNet18, and ResNet101 in three different study areas located in Newfoundland and Labrador, Canada (i.e., Avalon, Gros Morne, and Grand Falls). Moreover, to improve the classification accuracies of wetland classes of bog, fen, marsh, swamp, and shallow water, the results of the three best CNNs in each study area is fused using three supervised classifiers of random forest (RF), bagged tree (BTree), Bayesian optimized tree (BOT), and one unsupervised majority voting classifier. The results suggest that the ensemble models, in particular BTree, have a valuable role to play in the classification of wetland classes of bog, fen, marsh, swamp, and shallow water. The ensemble CNNs show an improvement of 9.63–19.04% in terms of mean producer's accuracy compared to the solo CNNs, to recognize wetland classes in three different study areas. This research indicates a promising potential for integrating ensemble-based learning and deep learning for operational large area land cover, particularly complex wetland type classification. [ABSTRACT FROM AUTHOR]

When severe flooding occurs in Canada, the Emergency Geomatics Service (EGS) is tasked with creating and disseminating maps that depict flood extents in near real time. EGS flood mapping methods were created with efficiency and robustness in mind, to allow maps to be published quickly, and therefore have the potential to generate high-repeat water products that can enhance frequent wetland monitoring. The predominant imagery currently used is synthetic aperture radar (SAR) from RADARSAT-2 (R2). With the commissioning phase of the RADARSAT Constellation Mission (RCM) complete, the EGS is adapting its methods for use with this new source of SAR data. The introduction of RCM's circular-transmit linear-receive (CTLR) beam mode provides the option to exploit compact polarimetric (CP) information not previously available with R2. The aim of this study was to determine the most effective CP parameters for use in mapping open water and flooded vegetation, using current EGS methodologies, and compare these products to those created by using R2 data. Nineteen quad-polarization R2 scenes selected from three regions containing wetlands prone to springtime flooding were used to create reference flood maps, using existing EGS tools. These scenes were then used to simulate 22 RCM CP parameters at different noise floors and spatial resolutions representative of the three RCM beam modes. Using multiple criteria, CP parameters were ranked in order of importance and entered into a stepwise classification procedure, for evaluation against reference R2 products. The top four CP parameters —m-chi-volume or m-delta-volume, RR intensity, Shannon Entropy intensity (SEi), and RV intensity—achieved a maximum agreement with baseline R2 products of upward of 98% across all 19 scenes and three beam modes. Separability analyses between flooded vegetation and other land-cover classes identified four candidate CP parameters—RH intensity, RR intensity, SEi, and the first Stokes parameter (SV0)—suitable for flooded-vegetation-region growing. Flooded-vegetation-region-growing CP thresholds were found to be dependent on incidence angle for each of these four parameters. After region growing using each of the four candidate CP parameters, RH intensity was deemed best to map flooded vegetation, based on our evaluations. The results of the study suggest a set of suitable CP parameters to generate flood maps from RCM data, using current EGS methodologies that must be validated further as real RCM data become available. [ABSTRACT FROM AUTHOR]

Wetlands play a key role in regional and global environments, and are critically linked to major issues such as climate change, wildlife habitat, biodiversity, water quality protection, and global carbon and methane cycles. Remotely-sensed imagery provides a means to detect and monitor wetlands on large scales and with regular frequency. In this project, methodologies were developed to classify wetlands (Open Bog, Treed Bog, Open Fen, Treed Fen, and Swamps) from multi-source remotely sensed data using advanced classification algorithms. The data utilized included multispectral optical and thermal data (Landsat-5) and Radar imagery from RADARSAT-2 and Sentinel-1. The goals were to determine the best way to combine the aforementioned imagery to classify wetlands, and determine the most significant image features. Classification algorithms investigated in this study were Naive Bayes, K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Random Forest (RF). Based on the test results in the study area in Northern Ontario, Canada (49°31′.34N, 80°43′37.04W), a RF based classification methodology produced the most accurate classification result (87.51%). SVM, in some cases, produced results of comparable or better accuracy than RF. Our work also showed that the use of surface temperature (an untraditional feature choice) could aid in the classification process if the image is from an abnormally warm spring. This study found that wetlands were best classified using the NDVI (Normalized Difference Vegetative Index) calculated from optical imagery obtained in the spring months, radar backscatter coefficients, surface temperature, and ancillary data such as surface slope, computed through either an RF or SVM classifier. It was also found that preselection of features using Log-normal or RF variable importance analysis was an effective way of identifying low quality features and to a lesser extent features which were of higher quality. [ABSTRACT FROM AUTHOR]