Wetland Classification Research Articles

Which regionalization scheme is the best to predict wetland plant distribution in Western Patagonia?

AbstractQuestionsGiven the current multiplicity of threats to pond biodiversity, there is a clear need to examine which environmental drivers determine the composition and distribution of species. Using wetland plants as pond biodiversity surrogates, two questions led to this work: How do wetland plant species assemblages and abundance vary across local‐ and regional‐scale classification schemes in wetlands? How does wetland plant beta‐diversity vary within these wetland classification schemes?LocationWestern Patagonia, Argentina, from 36°S to 56°S and from 73°W to 65°W.MethodsWetland plant distribution constrained by water and climatic factors was analyzed using canonical correspondence analysis. Variance partitioning analysis was performed to assess which classification scheme (phytogeographical units, wetland regions, wetland genesis and hydrogeomorphological types) better explained variation in plant composition. An IndVal analysis was also carried out to detect taxa with the highest association values (indicator taxa) for the different categories of wetland classification. Beta‐diversity was calculated to evaluate variation patterns within classification schemes.ResultsPlant distribution was mainly related to site location across the latitudinal gradient, following a decreasing pattern of air temperature from northern to southern wetlands. Variance partitioning analysis confirmed the effectiveness of a regional‐scale classification (wetland regions) in predicting plant associations, and the IndVal analysis also highlighted this classification scheme above the remainder, sustaining the highest number of indicator taxa. Wetland plant beta‐diversity patterns were explained by relatively high species turnover, with species composition showing low nestedness values.ConclusionClimate factors rather than local characteristics were the main drivers of plant distribution at the wide regional scale analyzed. Wetland region (classification based on climatic criteria) was the most effective scheme in predicting plant associations and sustaining the highest number of indicator taxa. Also, ponds located in the Patagonian Andes and those with a glacigenic origin contribute most to the regional wetland plant diversity. Therefore, these aspects should be taken directly into account in the future delineation of protected areas to increase the resilience of Patagonian wetland habitats and their associated biota, and to maintain the ecosystem services that they provide.

Poyang Lake Wetland Classification Using Time-Series ENVISAT ASAR Data and Beijing-1 Imagery

Beijing-1 and ENVISAT ASAR images were used to classify wetland aquatic macrophytes in terms of their plant functional types (PFTs) over the Poyang Lake region, China. Speckle noise filtering, systematic sensor calibration within the same polarization or between different polarizations, and accurate geo-registration were applied to the time-series SAR data. As a result, time-series backscattering data, which is described as permittivity curves in this paper, were obtained. In addition, time-series indices, described as phenological curves, were derived from Beijing-1 time-series images in the classification experiment. Based on these two curves, a rule-based classification strategy was developed to extract wetland information from the combined SAR and optical data. In the rule-based wetland classification method, DEM data, submersion time index, temporal Beijing-1 images, time-series normalized difference vegetation index (TSNDVI) images, principal component analysis (PCA), and temporal ratio of ASAR time-series images were used. In addition, a decision tree-based method was used to map the wetlands. Conclusions include the following: (1) after the preprocessing of ASAR data, it was possible to satisfactorily separate different aquatic plant functional types; (2) hydrophytes from different PFTs exhibited distinct phenological, structural, moisture, and roughness characteristics due to the impact of the annual inundation of Poyang Lake wetland; and (3) more accurate results were obtained with the rule-based method than the decision tree (DT) method. Producer’s and user’s accuracy calculated from test samples in the classification results indicate that the DT method can potentially be used for mapping aquatic PFTs, with overall producer’s accuracy exceeding 80% and higher user’s accuracy for aquatic bed wetland PFTs. A comparison of producer’s and user’s accuracy from the rule-based classification increased from 3 to 12% and 7 to 26%, respectively, for different aquatic PFTs.

Wetlands Classification Using Quad-Polarimetric Synthetic Aperture Radar through Convolutional Neural Networks Based on Polarimetric Features

Wetlands are the “kidneys” of the earth and are crucial to the ecological environment. In this study, we utilized GF-3 quad-polarimetric synthetic aperture radar (QP) images to classify the ground objects (nearshore water, seawater, spartina alterniflora, tamarix, reed, tidal flat, and suaeda salsa) in the Yellow River Delta through convolutional neural networks (CNNs) based on polarimetric features. In this case, four schemes were proposed based on the extracted polarimetric features from the polarization coherency matrix and reflection symmetry decomposition (RSD). Through the well-known CNNs: AlexNet and VGG16 as backbone networks to classify GF-3 QP images. After testing and analysis, 21 total polarimetric features from RSD and the polarization coherency matrix for QP image classification contributed to the highest overall accuracy (OA) of 96.54% and 94.93% on AlexNet and VGG16, respectively. The performance of the polarization coherency matrix and polarimetric power features was similar but better than just using three main diagonals of the polarization coherency matrix. We also conducted noise test experiments. The results indicated that OAs and kappa coefficients decreased in varying degrees after we added 1 to 3 channels of Gaussian random noise, which proved that the polarimetric features are helpful for classification. Thus, higher OAs and kappa coefficients can be acquired when more informative polarimetric features are input CNNs. In addition, the performance of RSD was slightly better than obtained using the polarimetric coherence matrix. Therefore, RSD can help improve the accuracy of polarimetric SAR image classification of wetland objects using CNNs.

Mapping African wetlands for 2020 using multiple spectral, geo-ecological features and Google Earth Engine

Wetlands provide numerous ecosystem services essential for biodiversity conservation, climate change mitigation, and human well-being. Nevertheless, there are still no complete and uniform wetland maps providing information on the location, distribution, size, and changing status of wetlands in Africa. In this study, we used 130,000 Landsat satellite images and 270,000 sampling points evenly distributed across Africa to classify wetlands with a random forest classifier based on the Google Earth Engine (GEE) cloud platform. This resulted in the first systematic and comprehensive map of existing wetlands in Africa that quantified the area and distribution of these wetlands at a spatial resolution of 30 m, with an overall wetland producer accuracy of 90.22 % and user accuracy of 95.74 %. To address the seasonal variation in African wetlands, we used a dynamic threshold segmentation method based on the Otsu method, which can extract the extent of wetlands under different periods more accurately based on Landsat time series and African phenology data. Our results show that the total African existing wetlands extent from 2019 to 2021 (here in 2020), was approximately 1,341,500 km2, excluding shallow marine waters, comprises 3.98 % of Africa's total land area. Of these wetlands, inland wetlands account for 81 %, and coastal wetlands account for 19 %. The wetlands in Africa were symmetrically distributed around the equator and decreased with increasing latitude, accounting for 97 % of the total wetland area being within the 20°N and 20°S latitudes. African marshes were highly dynamic, expanding by 92.22 % from the dry to wet season. Our study demonstrates the substantial potential of large data samples, multiple wetland classification features (spectral-temporal, topographic, and hydrological features), and random forest classification in GEE for large-scale wetland mapping. The resulting wetland maps provide new baseline data for large-scale monitoring of seasonal dynamics and long-term trends in African wetlands.

UAS Hyperspatial LiDAR Data Performance in Delineation and Classification across a Gradient of Wetland Types

Wetlands play a critical role in maintaining stable and productive ecosystems, and they continue to be at heightened risk from anthropogenic and natural degradation, especially along the rapidly developing Atlantic Coastal Plain of North America. As such, strategies to develop up-to-date and high-resolution wetland inventories and classifications remain highly relevant in the context of accelerating sea-level rise and coastal changes. Historically, satellite and airborne remote sensing data along with traditional field-based methods have been used for wetland delineation, yet, more recently, the advent of Uncrewed Aerial Systems (UAS) platforms and sensors is opening new avenues of performing rapid and accurate wetland classifications. To test the relative advantages and limitations of UAS technologies for wetland mapping and classification, we developed wetland classification models using UAS-collected multispectral and UAS-collected light detection and ranging (LiDAR) data relative to airborne-derived LiDAR models of wetland types ranging from palustrine to estuarine. The models were parameterized through a pixel-based random forest algorithm to evaluate model performance systematically and establish variable importance for a suite of variables including topographic, hydrologic, and vegetation-based indices. Based on our experimental results, the average overall classification accuracy and kappa coefficients for the UAS LiDAR-derived models are 75.29% and 0.74, respectively, compared to 79.80% and 0.75 for the airborne LiDAR-derived models, with significant differences in the spatial representation of final wetland classes. The resulting classification maps for the UAS models capture more precise wetland delineations than those of airborne models when trained with ground reference data collected at the same time as the UAS flights. The similar accuracy between the airborne and UAS models suggest that the UAS LiDAR is comparable to the airborne LiDAR. However, given poor revisit time of the airborne surveys and the high spatial resolution and precision of the UAS data, UAS-collected LiDAR provides excellent complementary data to statewide airborne missions or for specific applications that require hyperspatial data. For more structurally complex wetland types (such as the palustrine scrub shrub), UAS hyperspatial LiDAR data performs better and is much more advantageous to use in delineation and classification models. The results of this study contribute towards enhancing wetland delineation and classification models using data collected from multiple UAS platforms.

AMM-FuseNet: Attention-Based Multi-Modal Image Fusion Network for Land Cover Mapping

Land cover mapping provides spatial information on the physical properties of the Earth’s surface for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems, such as the destruction of important wetlands/forests, and loss of fish and wildlife habitats. This has made land cover mapping become one of the most widespread applications in remote sensing computational imaging. However, due to the differences between modalities in terms of resolutions, content, and sensors, integrating complementary information that multi-modal remote sensing imagery exhibits into a robust and accurate system still remains challenging, and classical segmentation approaches generally do not give satisfactory results for land cover mapping. In this paper, we propose a novel dynamic deep network architecture, AMM-FuseNet that promotes the use of multi-modal remote sensing images for the purpose of land cover mapping. The proposed network exploits the hybrid approach of the channel attention mechanism and densely connected atrous spatial pyramid pooling (DenseASPP). In the experimental analysis, in order to verify the validity of the proposed method, we test AMM-FuseNet with three datasets whilst comparing it to the six state-of-the-art models of DeepLabV3+, PSPNet, UNet, SegNet, DenseASPP, and DANet. In addition, we demonstrate the capability of AMM-FuseNet under minimal training supervision (reduced number of training samples) compared to the state of the art, achieving less accuracy loss, even for the case with 1/20 of the training samples.

Centennial-scale study on the spatial-temporal evolution of riparian wetlands in the Yangtze River of China

• A classification system for riparian wetlands in the Yangtze River was build. • Spatial-temporal changes of riparian wetlands at centennial-scale was analyzed. • Riparian wetlands in the Yangtze River generally showed a decreasing trend. • Spatial-temporal changes of riparian wetlands can be divided into three stages. • Wetland protection policies have significant impacts, especially since 1998. Wetlands play a crucial role in maintaining the ecosystem function and ecological security of the Yangtze River. This study collected multi-source remote sensing image data, including historical topographic maps, Landsat, and Gaofen-2, and established a set of classification and interpretation standards for riparian wetlands in the Yangtze River. The artificial visual interpretation was used to reconstruct the spatial–temporal evolution process of riparian wetlands in the Yangtze River over the past century, clarified its characteristics, and analyzed the impact of climate change, damming, and land development and wetland policies. The results showed that: (1) Riparian wetlands in the Yangtze River generally showed a decreasing trend. Among them, those in the upper reaches showed a decreasing trend, those in the middle reaches increased during 1930–1980 s and decreased since the 1980 s, and those in the lower reaches fluctuated. (2) The spatial–temporal evolution can be divided into three characteristic areas. In the estuary (Shanghai and the coastal), riparian wetlands first decreased and then increased, and changed significantly. The three provinces in the downstream (Jiangsu, Anhui, and Jiangxi) and Chongqing showed a decreasing trend with great changes. The three provinces in the middle and upstream first increased and then decreased with little change. (3) The impact of wetland exploitation and protection policies can be divided into three stages: no wetland protection policies (before 1986), wetland protection policy development (1986–1998), and strict protection (1998–present). This study provides an important scientific foundation for the implementation of coordinated protection of the Yangtze River.

Dynamic Changes and Driving Forces of Alpine Wetlands on the Qinghai–Tibetan Plateau Based on Long-Term Time Series Satellite Data: A Case Study in the Gansu Maqu Wetlands

The Qinghai–Tibet Plateau (QTP), also known as the Third Pole of the Earth, is sensitive to climate change, and it has become a hotspot area for research. As a typical natural ecosystem on the QTP, alpine wetlands are particularly sensitive to climate change. The identification of different types of alpine wetland and analysis of changes in their distributions and areas are the most direct indicators for characterizing the impact of climate change on wetlands. To understand the dynamic change process of the alpine wetlands in the QTP and their responses to climate change, the Maqu wetlands, located at the source of the Three Rivers in the eastern part of the QTP, was taken as an example; the Google Earth Engine (GEE) remote sensing cloud platform and long-term dense Landsat time series data from 1990 to 2020 were used to map the annual wetland classification and to analyze the evolution characteristics of the wetlands and their driving forces. The results revealed that (1) based on dense Landsat time series data, different alpine wetland types can be effectively distinguished, including swamp, swamp meadow, and wet meadow. (2) From 1990 to 2020, the area of the Maqu wetlands exhibited an overall fluctuating decrease, with the total area decreasing by about 23.35%, among which the swamp area decreased the most (by 27.15%). The overall type of change was from wet to dry. All of the types of wetlands were concentrated between 3400 and 3600 m above sea level, and the reduction in the wetland area was concentrated on slopes < 3°, with the greatest loss of wetland area occurring on shady slopes. (3) The driving forces of the changes in the wetlands were predominantly temperature and precipitation, and the greatest correlation was between the total wetland area and the growing season temperature. The results of this study provide valuable information for the conservation of alpine wetlands.

Identifying Coastal Wetlands Changes Using a High-Resolution Optical Images Feature Hierarchical Selection Method

Coastal wetlands are dynamic and fragile ecosystems where complex changes have taken place. As they are affected by environmental changes and human activities, it is of great practical significance to monitor coastal wetlands changes regularly. High-resolution optical data can observe changes in coastal wetlands, however, the impact of different optical features on the identification of changes in coastal wetlands is not clear. Simultaneously, the combination of many features could cause the “dimension disaster” problem. In addition, only small amounts of training samples are accessible at pre- or post-changed time. In order to solve the above problems, the feature hierarchical selection method is proposed, taking into account the jumping degree of different image features. The influence of different optical features on wetland classification was analyzed. In addition, a training samples transfer learning strategy was designed for wetland classification, and the classification result at pre- and post-changed times were compared to identify the “from-to” coastal wetlands changes. The southeastern coastal wetlands located in Jiangsu Province were used as a study area, and ZY-3 images in 2013 and 2018 were used to verify the proposed methods. The results show that the feature hierarchical selection method can provide a quantitative reference for optimal subset feature selection. A training samples transfer learning strategy was used to classify post-changed optical data, the overall accuracy of transferred training samples was 91.16%, and it ensures the accuracy requirements for change identification. In the study area, the salt marsh increased mainly from the sea area, because salt marshes expand rapidly throughout coastal areas, and aquaculture ponds increased from the sea area and salt marshes, because of the considerable economic benefits of the aquacultural industry.

Deep and Machine Learning Image Classification of Coastal Wetlands Using Unpiloted Aircraft System Multispectral Images and Lidar Datasets

The recent developments of new deep learning architectures create opportunities to accurately classify high-resolution unoccupied aerial system (UAS) images of natural coastal systems and mandate continuous evaluation of algorithm performance. We evaluated the performance of the U-Net and DeepLabv3 deep convolutional network architectures and two traditional machine learning techniques (support vector machine (SVM) and random forest (RF)) applied to seventeen coastal land cover types in west Florida using UAS multispectral aerial imagery and canopy height models (CHM). Twelve combinations of spectral bands and CHMs were used. Our results using the spectral bands showed that the U-Net (83.80–85.27% overall accuracy) and the DeepLabV3 (75.20–83.50% overall accuracy) deep learning techniques outperformed the SVM (60.50–71.10% overall accuracy) and the RF (57.40–71.0%) machine learning algorithms. The addition of the CHM to the spectral bands slightly increased the overall accuracy as a whole in the deep learning models, while the addition of a CHM notably improved the SVM and RF results. Similarly, using bands outside the three spectral bands, namely, near-infrared and red edge, increased the performance of the machine learning classifiers but had minimal impact on the deep learning classification results. The difference in the overall accuracies produced by using UAS-based lidar and SfM point clouds, as supplementary geometrical information, in the classification process was minimal across all classification techniques. Our results highlight the advantage of using deep learning networks to classify high-resolution UAS images in highly diverse coastal landscapes. We also found that low-cost, three-visible-band imagery produces results comparable to multispectral imagery that do not risk a significant reduction in classification accuracy when adopting deep learning models.

Creating a Detailed Wetland Inventory with Sentinel-2 Time-Series Data and Google Earth Engine in the Prairie Pothole Region of Canada

Wetlands in the Prairie Pothole Region (PPR) of Canada and the United States represent a unique mapping challenge. They are dynamic both seasonally and year-to-year, are very small, and frequently altered by human activity. Many efforts have been made to estimate the loss of these important habitats but a high-quality inventory of pothole wetlands is needed for data-driven conservation and management of these resources. Typical landcover classifications using one or two image dates from optical or Synthetic Aperture Radar (SAR) Earth Observation (EO) systems often produce reasonable wetland inventories for less dynamic, forested landscapes, but will miss many of the temporary and seasonal wetlands in the PPR. Past studies have attempted to capture PPR wetland dynamics by using dense image stacks of optical or SAR data. We build upon previous work, using 2017–2020 Sentinel-2 imagery processed through the Google Earth Engine (GEE) cloud computing platform to capture seasonal flooding dynamics of wetlands in a prairie pothole wetland landscape in Alberta, Canada. Using 36 different image dates, wetland flood frequency (hydroperiod) was calculated by classifying water/flooding in each image date. This product along with the Global Ecosystem Dynamics Investigation (GEDI) Canopy Height Model (CHM) was then used to generate a seven-class wetland inventory with wetlands classified as areas with seasonal but not permanent water/flooding. Overall accuracies of the resulting inventory were between 95% and 96% based on comparisons with local photo-interpreted inventories at the Canadian Wetland Classification System class level, while wetlands themselves were classified with approximately 70% accuracy. The high overall accuracy is due, in part, to a dominance of uplands in the PPR. This relatively simple method of classifying water through time generates reliable wetland maps but is only applicable to ecosystems with open/non-complex wetland types and may be highly sensitive to the timing of cloud-free optical imagery that captures peak wetland flooding (usually post snow melt). Based on this work, we suggest that expensive field or photo-interpretation training data may not be needed to map wetlands in the PPR as self-labeling of flooded and non-flooded areas in a few Sentinel-2 images is sufficient to classify water through time. Our approach demonstrates a framework for the operational mapping of small, dynamic PPR wetlands that relies on open-access EO data and does not require costly, independent training data. It is an important step towards the effective conservation and management of PPR wetlands, providing an efficient method for baseline and ongoing mapping in these dynamic environments.

Mapping, Inventory and Change Detection of Wetlands of Thavanur Grama Panchayath using Multispectral Satellite Imagery

Wetlands are the submerged or waters saturated lands, both natural and man-made, permanent or temporary, with water that is static or flowing, fresh, brackish or salt, including areas of marine water, the depth of which at low tide does not exceed 6 meters. Effective wetlands management and protection are critical. Accurate and comprehensive wetland classification maps as well as spatiotemporal change information are essential for ecological protection and local government decisions. Wetland mapping and classification help to preserve and improve wetland quality.
 A study was conducted on wetland mapping, inventory and change detection wetlands of Thavanur Grama Panchayath in Malappuram district of Kerala using multispectral satellite imageries of high resolution (2.4x2.4m) during the year 2020-2021. The image processing was carried out by Visual Interpretation Technique. The accuracy of mapping was assessed by kappa coefficient.
 The various wetland classes found in Thavanur Grama Panchayath were Aquaculture, Marshy land, River and other ponds and small waterbodies. The major wetlands identified in the Panchayath were Ayankalam kayal, Maravanchery kaayal, Varo kaayal, Thavanur kaayal (marshy type wetlands), Bharathapuzha River, Ayankalam aquaculture, Mathur aquaculture and several other ponds. The change detection analysis showed that the percentage change in wetland during the decade was found maximum for pond and well (-33.18%). The major land use changes during the period 2008 and 2018 were that coconut plantation increased by 70.79 ha, paddy land decreased by 61.62 ha and marshy land decreased by 7.04 ha. The kappa coefficient of mapping was obtained as 0.93 which indicted good accuracy.

Classification and Evolutionary Analysis of Yellow River Delta Wetlands Using Decision Tree Based on Time Series SAR Backscattering Coefficient and Coherence

In recent years, the Yellow River Delta has been affected by invasive species Spartina alterniflora (S. alterniflora), resulting in a fragile ecological environment. It is of great significance to monitor the ground object types in the Yellow River Delta wetlands. The classification accuracy based on Synthetic Aperture Radar (SAR) backscattering coefficient is limited by the small difference between some ground objects. To solve this problem, a decision tree classification method for extracting the ground object types in wetland combined time series SAR backscattering and coherence characteristics was proposed. The Yellow River Delta was taken as the study area and the 112 Sentinel-1A GRD data with VV/VH dual-polarization and 64 Sentinel-1A SLC data with VH polarization were used. The decision tree method was established, based on the annual mean VH and VV backscattering characteristics, the new constructed radar backscattering indices, and the annual mean VH coherence characteristics were suitable for extracting the wetlands in the Yellow River Delta. Then the classification results in the Yellow River Delta wetlands from 2018 to 2021 were obtained using the new method proposed in this paper. The results show that the overall accuracy and Kappa coefficient of the proposed method w5ere 89.504% and 0.860, which were 9.992% and 0.127 higher than multi-temporal classification by Support Vector Machine classifier. Compared with the decision tree without coherence, the overall accuracy and Kappa coefficient were improved by 8.854% and 0.108. The spatial distributions of wetland types in the Yellow River Delta from 2018 to 2021 were obtained using the constructed decision tree. The spatio-temporal evolution analysis was conducted. The results showed that the area ofS. alternifloradecreased significantly in 2020 but it increased to the area of 2018 in 2021. In addition,S. alternifloraseriously affected the living space of Phragmites australis (P. australis) and in 4 years, 10.485 km2living space ofP. australiswas occupied byS. alterniflora. The proposed method can provide a theoretical basis for higher accuracy SAR wetland classification and the monitoring results can provide an effective reference for local wetland protection.

THE IMPORTANCE OF SEASONAL TEXTURAL FEATURES FOR OBJECT-BASED CLASSIFICATION OF WETLANDS: NEW YORK STATE CASE STUDY

Abstract. Seasonal variations result in hydrophytes and undrained hydric soil changes in wetland areas, which lead to a dynamic environment that makes wetland classification challenging. This study aims to explore the applicability of multi-seasonal Gray-Level Co-Occurrence Matrix (GLCM) texture-derived features for object-based wetland classification over large-extent for the first time. We attempted to enhance the performance of the random forest classifier by incorporating multi-source remote sensing data, including Sentinel-2, Sentinel-1, Alos-Palsar, and topographic features. A total of 47 features were extracted from multi-source remote sensing data. In this context, we assessed the applicability of multi- versus mono-seasonal derived features for the wetland's classes with low within-class separability. We investigated the mean decrease in the Gini impurity index for each GLCM feature. We observed that including GLCM features enhanced overall accuracy by 7.38% when using imagery from one season and 4.21% for multi-season imagery. The multi-season scenario that included GLCM measures (93.49%) attained the highest overall accuracy. For this scenario, the means of decrease in Gini impurity index suggested that Soil Adjusted Vegetation Index, Modified Normalized Difference Water Index, slope, correlation in summer (GLCM feature), and Sentinel-1 VH are the most important features in increasing the random forest's classifier performance. In looking at the GLCM features, the separability analysis suggested that Entropy, Sum of Average, and Variance calculated from the summer imagery improve the classifier's performance while other textural features from spring imagery better contributed to classifier accuracy.

Spatiotemporal Change Detection of Coastal Wetlands Using Multi-Band SAR Coherence and Synergetic Classification

Synthetic aperture radar (SAR) signal can penetrate clouds and some vegetation canopies in all weather, and therefore, provides an important measurement tool for change detection and sustainable development of coastal wetland environments and ecosystems. However, there are a few quantitative estimations about the spatiotemporal coherence change with multi-band SAR images in complex coastal wetland ecosystems of the Yellow River Delta (YRD). In this study, C-band Sentinel-1 and L-band ALOS-2 PALSAR data were used to detect the spatiotemporal distribution and change pattern of interferometric coherence in the coastal wetlands of the YRD. The results show that the temporal baseline has a greater impact on the interferometric coherence than the perpendicular baseline, especially for short wavelength C-band SAR. Furthermore, the OTSU algorithm was proven to be able to distinguish the changing regions. The coherence mean and standard deviation values of different land cover types varied significantly in different seasons, while the minimum and maximum coherence changes occurred in February and August, respectively. In addition, considering three classical machine learning algorithms, namely naive Bayes (NB), random forest (RF), and multilayer perceptron (MLP), we proposed a method of synergetic classification with SAR coherence, backscatter intensity, and optical images for coastal wetland classification. The multilayer perceptron algorithm performs the best in synergetic classification with an overall accuracy of 98.3%, which is superior to a single data source or the other two algorithms. In this article, we provide an alternative cost-effective method for coastal wetland change detection, which contributes to more accurate dynamic land cover classification and to an understanding of the response mechanism of land features to climate change and human activities.

Global coastal geomorphology – integrating earth observation and geospatial data

Coastal geomorphic classification identifying the type of depositional environment, is an important indicator for coastal state and vulnerability, e.g., beach, bedrock and wetland (tidal flat and estuarine/delta/back-barrier depression). Accurate and current maps of these geomorphology classes from local (100 m-1 km) to global (105 km) scales are important for a range of objectives in the coastal zone. Previous methods to create coastal geomorphic maps relied heavily on manual efforts and expert opinions. However, these approaches are labour intensive and impractical for consistent application at a global scale, while still including local details. Existing global coastal geomorphology datasets are a compilation of different local-scale datasets, with varying spatial, categorical resolutions and accuracies. The recent availability of “big” and “open” data as well as increased processing capabilities resulted in the use of satellite images and digital elevation models to identify sandy beach and cliff separately. In our work, these raster data were processed on Google Earth Engine, combined with shape descriptors of coastline vectors and then fitted into machine learning models to classify the intertidal coastal geomorphology into bedrock, beach or wetland classes on the global scale (from 56° S to 60° N, excluding coral reef/fringing reef and fjord dominated coasts). A unique attribute of this new method was the incorporation of shape descriptors extracted from shoreline vector data, which substantially improved the classification accuracy. Using existing data from European Union (EU), the United States of America (US) and Australia for training and testing, the model achieved averaged 85% accuracy for testing datasets in these continents and 84% accuracy for 10,000 independent global validation samples beyond these continents. Successful classification was achieved for coasts dominated by a single geomorphology class, as well as more complex environments, such as headland bay and barrier island systems, where multiple classes appear next to each other. The model had relatively less confidence in coasts with sandy cliffs, tall canopy cover and engineered structures. Complete statistics from this study covering 56° S to 60° N showed 36.8% (142,845 km) wetland, 26.7% (103,762 km) beach and 36.5% (141,579 km) bedrock. Beach and bedrock geomorphic classes were commonly detected at mid-latitudes (30o to 60o N/S), while wetland dominated tropical latitudes (0o to 30o N/S). The output dataset can be used for different coastal management purposes. The accuracy and categorical resolution of the classification can be further improved with the development of Earth Observation Big Data in the future.

STATE-WIDE WETLAND INVENTORY MAP OF MINNESOTA USING MULTI-SOURCE AND MULTI-TEMPORALREMOTE SENSING DATA

Abstract. Carbon sequestration coupled with flood mitigation and other functions of wetlands, such as water filtration, coastal protection, biodiversity, and providing recreational spots, make wetland mapping and monitoring important for different countries. Google Earth Engine (GEE) cloud computing platform is becoming a very important tool for lots of environmental studies as it provides a suite of tools and access to data that facilitate large-scale environmental monitoring projects through its powerful parallel processing capabilities. In this study, we use GEE to access multi-source remote sensing datasets and implement an object-based image analysis, and random forest algorithm for the classification of wetlands in the state of Minnesota. Emergent, forested, and scrub-shrub wetland classes, water, as well as urban, forest, and agriculture land cover types were classified using Sentinel-2, Sentinel-1, USGS 3D Elevation Program 10-meter DEM, and gridded soil data. NDVI, EVI, BSI, NDBI, and NDWI spectral indices were calculated from Sentinel-2 imagery, VV and VH polarization channels, and their ratio, as well as span parameters, were calculated from Sentinel-1 imagery, and slope and aspect features were extracted from DEM. Simple Non-Iterative Clustering (SNIC), Gray-Level Co-occurrence Matrix (GLCM), Principal Components Analysis (PCA), and random forest algorithms were implemented to classify wetlands from the GEE platform. Emergent wetlands, water, urban, and agriculture classes performed well with producer accuracies greater than 90%. Sentinel-1, DEM, and soil datasets improve the identification of wetland classes and highlight the importance of multi-source approaches for wetland mapping.

META-LEARNING FOR WETLAND CLASSIFICATION USING A COMBINATION OF SENTINEL-1 AND SENTINEL-2 IMAGERY

Abstract. In wetland mapping, a lot of uncertainty is related to the task of selecting an appropriate classification approach. Although the individual models are available and well-established in the literature for the classification task, the combination approaches have become popular recently. Hence, selecting an appropriate method is challenging, whether an individual approach or combination. In this work, a meta-learning study is performed to prove that combining the result of individual machine learning models could be better than using the best single model. This study investigates the applicability of the meta-learning method for wetland classification. We will first explore the importance of extracted features for each model. Then, the essential features are fed to the model with the well-tuned hyper-parameters. Finally, the voting classifier as a meta-learning approach is adopted to improve the classification result. The classification map of the study area reached the highest accuracy (Overall Accuracy = 93.9% and Kappa = 0.92) when the proposed ensemble classifier was employed. The results show the superiority of a combination of methods over simple model selection approaches. The results of this study can provide new insights for researchers to find new combination strategies to improve the classification results.

Coastal Wetland Responses to Sea Level Rise: The Losers and Winners Based on Hydro-Geomorphological Settings

Many coastal wetlands are under pressure due to climate change and the associated sea level rise (SLR). Many previous studies suggest that upslope lateral migration is the key adaptive mechanism for saline wetlands, such as mangroves and saltmarshes. However, few studies have explored the long-term fate of other wetland types, such as brackish swamps and freshwater forests. Using the current wetland map of a micro-tidal estuary, the Manning River in New South Wales, Australia, this study built a machine learning model based on the hydro-geomorphological settings of four broad wetland types. The model was then used to predict the future wetland distribution under three sea level rise scenarios. The predictions were compared to compute the persistence, net, swap, and total changes in the wetlands to investigate the loss and gain potential of different wetland classes. Our results for the study area show extensive gains by mangroves under low (0.5 m), moderate (1.0 m), and high (1.5 m) sea level rise scenarios, whereas the other wetland classes could suffer substantial losses. Our findings suggest that the accommodation spaces might only be beneficial to mangroves, and their availability to saltmarshes might be limited by coastal squeeze at saline–freshwater ecotones. Furthermore, the accommodation spaces for freshwater wetlands were also restrained by coastal squeeze at the wetland-upland ecotones. As sea level rises, coastal wetlands other than mangroves could be lost due to barriers at the transitional ecotones. In our study, these are largely manifested by slope impacts on hydrology at a higher sea level. Our approach provides a framework to systematically assess the vulnerability of all coastal wetland types.

Obligations of Researchers and Managers to Respect Wetlands: Practical Solutions to Minimizing Field Monitoring Impacts

Research and field monitoring can disturb wetland integrity. Adoption of ethical field practices is needed to limit monitoring induced stressors such as trampling, non-native seed and invertebrate dispersal, and disease and fungal spread. We identify a linear pathway of deterioration highlighting stressors that can progress to cumulative impacts, consequences, and losses at the site scale. The first step to minimize disturbance is to assess and classify the current ecosystem quality. We present a tiered framework for wetland classification and link preventative measures to the wetland tier. Preventative measures are recommended at various intensities respective to the wetland tier, with higher tiered wetlands requiring more intense preventative measures. In addition, preventative measures vary by time of implementation (before, during, and after the wetland visit) to mitigate impacts at various temporal scales. The framework is designed to increase transparency of field monitoring impacts and to promote the adoption of preventative measures. Implementing preventative measures can build accountability and foster a greater appreciation for our roles as researchers and managers in protecting wetlands.