Joshua Montgomery

Bio: Joshua Montgomery is an academic researcher from University of Lethbridge. The author has contributed to research in topics: Wetland classification & Wetland. The author has an hindex of 7, co-authored 9 publications receiving 195 citations. Previous affiliations of Joshua Montgomery include Alberta Environment.

Canadian Wetland Inventory using Google Earth Engine: The First Map and Preliminary Results

Abstract: Although wetlands provide valuable services to humans and the environment and cover a large portion of Canada, there is currently no Canada-wide wetland inventory based on the specifications defined by the Canadian Wetland Classification System (CWCS). The most practical approach for creating the Canadian Wetland Inventory (CWI) is to develop a remote sensing method feasible for large areas with the potential to be updated within certain time intervals to monitor dynamic wetland landscapes. Thus, this study aimed to create the first Canada-wide wetland inventory using Landsat-8 imagery and innovative image processing techniques available within Google Earth Engine (GEE). For this purpose, a large amount of field samples and approximately 30,000 Landsat-8 surface reflectance images were initially processed using several advanced algorithms within GEE. Then, the random forest (RF) algorithm was applied to classify the entire country. The final step was an original CWI map considering the five wetland classes defined by the CWCS (i.e., bog, fen, marsh, swamp, and shallow water) and providing updated and comprehensive information regarding the location and spatial extent of wetlands in Canada. The map had reasonable accuracy in terms of both visual and statistical analyses considering the large area of country that was classified (9.985 million km2). The overall classification accuracy and the average producer and user accuracies for wetland classes exclusively were 71%, 66%, and 63%, respectively. Additionally, based on the final classification map, it was estimated that 36% of Canada is covered by wetlands.

SAR and lidar temporal data fusion approaches to boreal wetland ecosystem monitoring

Abstract: The objective of this study was to develop a decision-based methodology, focused on data fusion for wetland classification based on surface water hydroperiod and associated riparian (transitional area between aquatic and upland zones) vegetation community attributes. Multi-temporal, multi-mode data were examined from airborne Lidar (Teledyne Optech, Inc., Toronto, ON, Canada, Titan), synthetic aperture radar (Radarsat-2, single and quad polarization), and optical (SPOT) sensors with near-coincident acquisition dates. Results were compared with 31 field measurement points for six wetlands at riparian transition zones and surface water extents in the Utikuma Regional Study Area (URSA). The methodology was repeated in the Peace-Athabasca Delta (PAD) to determine the transferability of the methods to other boreal environments. Water mask frequency analysis showed accuracies of 93% to 97%, and kappa values of 0.8–0.9 when compared to optical data. Concordance results comparing the semi-permanent/permanent hydroperiod between 2015 and 2016 were found to be 98% similar, suggesting little change in wetland surface water extent between these two years. The results illustrate that the decision-based methodology and data fusion could be applied to a wide range of boreal wetland types and, so far, is not geographically limited. This provides a platform for land use permitting, reclamation monitoring, and wetland regulation in a region of rapid development and uncertainty due to climate change. The methodology offers an innovative time series-based boreal wetland classification approach using data fusion of multiple remote sensing data sources.

Remote Sensing of Boreal Wetlands 2: Methods for Evaluating Boreal Wetland Ecosystem State and Drivers of Change

Abstract: The following review is the second part of a two part series on the use of remotely sensed data for quantifying wetland extent and inferring or measuring condition for monitoring drivers of change on wetland environments. In the first part, we introduce policy makers and non-users of remotely sensed data with an effective feasibility guide on how data can be used. In the current review, we explore the more technical aspects of remotely sensed data processing and analysis using case studies within the literature. Here we describe: (a) current technologies used for wetland assessment and monitoring; (b) the latest algorithmic developments for wetland assessment; (c) new technologies; and (d) a framework for wetland sampling in support of remotely sensed data collection. Results illustrate that high or fine spatial resolution pixels (≤10 m) are critical for identifying wetland boundaries and extent, and wetland class, form and type, but are not required for all wetland sizes. Average accuracies can be up to 11% better (on average) than medium resolution (11–30 m) data pixels when compared with field validation. Wetland size is also a critical factor such that large wetlands may be almost as accurately classified using medium-resolution data (average = 76% accuracy, stdev = 21%). Decision-tree and machine learning algorithms provide the most accurate wetland classification methods currently available, however, these also require sampling of all permutations of variability. Hydroperiod accuracy, which is dependent on instantaneous water extent for single time period datasets does not vary greatly with pixel resolution when compared with field data (average = 87%, 86%) for high and medium resolution pixels, respectively. The results of this review provide users with a guideline for optimal use of remotely sensed data and suggested field methods for boreal and global wetland studies.

A Physically Based Terrain Morphology and Vegetation Structural Classification for Wetlands of the Boreal Plains, Alberta, Canada

Abstract: The objective of this study is to test a cost-effective, physically based Light Detection and Ranging (LiDAR) classification methodology for wetland and upland land cover types within an area exceeding 1,000 km2 in the Boreal Plains, Alberta, Canada. Decision criteria are based on physical attributes of the landscape that influence maintenance of land cover types. Results are compared with 38 geolocated measurement plots at land cover boundaries and transition zones, manual delineation of 2,337 wetlands using photogrammetric methods and publicly available land cover classifications.Results suggest that 57% of LiDAR-based wetland classes correspond with delineated wetlands, whereas 37% occur as errors of commission due to excluded wetlands in the manual delineation and confusion with harvested areas. Comparison of classified edges with plot shows that all classifications underestimate wetland area. Residual differences of the LiDAR-based classification are −0.3 m, on average (compared with measured...

Wetland hydroperiod classification in the western prairies using multitemporal synthetic aperture radar

Abstract: Wetlands represent one of the world's most biodiverse and threatened ecosystem types and were diminished globally by about two‐thirds in the 20th century. There is continuing decline in wetland quantity and function due to infilling and other human activities. In addition, with climate change, warmer temperatures and changes in precipitation and evapotranspiration are reducing wetland surface and groundwater supplies, further altering wetland hydrology and vegetation. There is a need to automate inventory and monitoring of wetlands, and as a study system, we investigated the Shepard Slough wetlands complex, which includes numerous wetlands in urban, suburban, and agricultural zones in the prairie pothole region of southern Alberta, Canada. Here, wetlands are generally confined to depressions in the undulating terrain, challenging wetlands inventory and monitoring. This study applied threshold and frequency analysis routines for high‐resolution, single‐polarization (HH) RADARSAT‐2, synthetic aperture radar mapping. This enabled a growing season surface water extent hyroperiod‐based wetland classification, which can support water and wetland resource monitoring. This 3‐year study demonstrated synthetic aperture radar‐derived multitemporal open‐water masks provided an effective index of wetland permanence class, with overall accuracies of 89% to 95% compared with optical validation data, and RMSE between 0.2 and 0.7 m between model and field validation data. This allowed for characterizing the distribution and dynamics of 4 marsh wetlands hydroperiod classes, temporary, seasonal, semipermanent, and permanent, and mapping of the sequential vegetation bands that included emergent, obligate wetland, facultative wetland, and upland plant communities. Hydroperiod variation and surface water extent were found to be influenced by short‐term rainfall events in both wet and dry years. Seasonal hydroperiods in wetlands were particularly variable if there was a decrease in the temporary or semipermanent hydroperiod classes. In years with extreme rain events, the temporary wetlands especially increased relative to longer lasting wetlands (84% in 2015 with significant rainfall events, compared with 42% otherwise).

Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review

Abstract: Remote sensing (RS) systems have been collecting massive volumes of datasets for decades, managing and analyzing of which are not practical using common software packages and desktop computing resources. In this regard, Google has developed a cloud computing platform, called Google Earth Engine (GEE), to effectively address the challenges of big data analysis. In particular, this platform facilitates processing big geo data over large areas and monitoring the environment for long periods of time. Although this platform was launched in 2010 and has proved its high potential for different applications, it has not been fully investigated and utilized for RS applications until recent years. Therefore, this study aims to comprehensively explore different aspects of the GEE platform, including its datasets, functions, advantages/limitations, and various applications. For this purpose, 450 journal articles published in 150 journals between January 2010 and May 2020 were studied. It was observed that Landsat and Sentinel datasets were extensively utilized by GEE users. Moreover, supervised machine learning algorithms, such as Random Forest, were more widely applied to image classification tasks. GEE has also been employed in a broad range of applications, such as Land Cover/land Use classification, hydrology, urban planning, natural disaster, climate analyses, and image processing. It was generally observed that the number of GEE publications have significantly increased during the past few years, and it is expected that GEE will be utilized by more users from different fields to resolve their big data processing challenges.

Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition

Abstract: Land cover information plays a vital role in many aspects of life, from scientific and economic to political. Accurate information about land cover affects the accuracy of all subsequent applications, therefore accurate and timely land cover information is in high demand. In land cover classification studies over the past decade, higher accuracies were produced when using time series satellite images than when using single date images. Recently, the availability of the Google Earth Engine (GEE), a cloud-based computing platform, has gained the attention of remote sensing based applications where temporal aggregation methods derived from time series images are widely applied (i.e., the use the metrics such as mean or median), instead of time series images. In GEE, many studies simply select as many images as possible to fill gaps without concerning how different year/season images might affect the classification accuracy. This study aims to analyze the effect of different composition methods, as well as different input images, on the classification results. We use Landsat 8 surface reflectance (L8sr) data with eight different combination strategies to produce and evaluate land cover maps for a study area in Mongolia. We implemented the experiment on the GEE platform with a widely applied algorithm, the Random Forest (RF) classifier. Our results show that all the eight datasets produced moderately to highly accurate land cover maps, with overall accuracy over 84.31%. Among the eight datasets, two time series datasets of summer scenes (images from 1 June to 30 September) produced the highest accuracy (89.80% and 89.70%), followed by the median composite of the same input images (88.74%). The difference between these three classifications was not significant based on the McNemar test (p > 0.05). However, significant difference (p < 0.05) was observed for all other pairs involving one of these three datasets. The results indicate that temporal aggregation (e.g., median) is a promising method, which not only significantly reduces data volume (resulting in an easier and faster analysis) but also produces an equally high accuracy as time series data. The spatial consistency among the classification results was relatively low compared to the general high accuracy, showing that the selection of the dataset used in any classification on GEE is an important and crucial step, because the input images for the composition play an essential role in land cover classification, particularly with snowy, cloudy and expansive areas like Mongolia.

Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples

Abstract: Accurate information about the location, extent, and type of Land Cover (LC) is essential for various applications. The only recent available country-wide LC map of Iran was generated in 2016 by the Iranian Space Agency (ISA) using Moderate Resolution Imaging Spectroradiometer (MODIS) images with a considerably low accuracy. Therefore, the production of an up-to-date and accurate Iran-wide LC map using the most recent remote sensing, machine learning, and big data processing algorithms is required. Moreover, it is important to develop an efficient method for automatic LC generation for various time periods without the need to collect additional ground truth data from this immense country. Therefore, this study was conducted to fulfill two objectives. First, an improved Iranian LC map with 13 LC classes and a spatial resolution of 10 m was produced using multi-temporal synergy of Sentinel-1 and Sentinel-2 satellite datasets applied to an object-based Random forest (RF) algorithm. For this purpose, 2,869 Sentinel-1 and 11,994 Sentinel-2 scenes acquired in 2017 were processed and classified within the Google Earth Engine (GEE) cloud computing platform allowing big geospatial data analysis. The Overall Accuracy (OA) and Kappa Coefficient (KC) of the final Iran-wide LC map for 2017 was 95.6% and 0.95, respectively, indicating the considerable potential of the proposed big data processing method. Second, an efficient automatic method was developed based on Sentinel-2 images to migrate ground truth samples from a reference year to automatically generate an LC map for any target year. The OA and KC for the LC map produced for the target year 2019 were 91.35% and 0.91, respectively, demonstrating the efficiency of the proposed method for automatic LC mapping. Based on the obtained accuracies, this method can potentially be applied to other regions of interest for LC mapping without the need for ground truth data from the target year.

National wetland mapping in China: A new product resulting from object-based and hierarchical classification of Landsat 8 OLI images

Abstract: Spatially and thematically explicit information of wetlands is important to understanding ecosystem functions and services, as well as for establishment of management policy and implementation. However, accurate wetland mapping is limited due to lacking an operational classification system and an effective classification approach at a large scale. This study was aimed to map wetlands in China by developing a hybrid object-based and hierarchical classification approach (HOHC) and a new wetland classification system for remote sensing. Application of the hybrid approach and the wetland classification system to Landsat 8 Operational Land Imager data resulted in a wetland map of China with an overall classification accuracy of 95.1%. This national scale wetland map, so named CAS_Wetlands, reveals that China’s wetland area is estimated to be 451,084 ± 2014 km2, of which 70.5% is accounted by inland wetlands. Of the 14 sub-categories, inland marsh has the largest area (152,429 ± 373 km2), while coastal swamp has the smallest coverage (259 ± 15 km2). Geospatial variations in wetland areas at multiple scales indicate that China’s wetlands mostly present in Tibet, Qinghai, Inner Mongolia, Heilongjiang, and Xinjiang Provinces. This new map provides a new baseline data to establish multi-temporal and continuous datasets for China’s wetlands and biodiversity conservation.

Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning

Abstract: This study aimed at evaluating the synergistic use of Sentinel-1 and Sentinel-2 data combined with the Support Vector Machines (SVMs) machine learning classifier for mapping land use and land cover (LULC) with emphasis on wetlands. In this context, the added value of spectral information derived from the Principal Component Analysis (PCA), Minimum Noise Fraction (MNF) and Grey Level Co-occurrence Matrix (GLCM) to the classification accuracy was also evaluated. As a case study, the National Park of Koronia and Volvi Lakes (NPKV) located in Greece was selected. LULC accuracy assessment was based on the computation of the classification error statistics and kappa coefficient. Findings of our study exemplified the appropriateness of the spatial and spectral resolution of Sentinel data in obtaining a rapid and cost-effective LULC cartography, and for wetlands in particular. The most accurate classification results were obtained when the additional spectral information was included to assist the classification implementation, increasing overall accuracy from 90.83% to 93.85% and kappa from 0.894 to 0.928. A post-classification correction (PCC) using knowledge-based logic rules further improved the overall accuracy to 94.82% and kappa to 0.936. This study provides further supporting evidence on the suitability of the Sentinels 1 and 2 data for improving our ability to map a complex area containing wetland and non-wetland LULC classes.