Abstract The coalfield in the northwest suburbs of Xuzhou has suffered from extensive land subsidence; however, the temporal nonlinearity and corresponding spatial variation of its surface deformation has not been adequately explored. This study revealed complex surface deformation of the study area from 2015 to 2020 using time series InSAR. A general trend from sharp subsidence to moderated subsidence

Abstract This article focuses on mapping tropical deforestation using time series and machine learning algorithms. Before detecting changes in the time series, we reduced seasonality using Photosynthetic Vegetation (PV) index fractions obtained from Landsat images. Single and multi-temporal filters were used to reduce speckle noise from Synthetic Aperture Radar (SAR) images (i.e., ALOS PALSAR and Sentinel-1B)

Abstract Estimating terrestrial water storage (TWS) with high spatial resolution is crucial for hydrological and water resource management. Comparing to traditional in-situ data measurement, observation from space borne sensor such as Gravity Recovery and Climate Experiment (GRACE) satellites is quite effective to obtain a large-scale TWS data. However, the coarse resolution of the GRACE data restricts

Abstract The increasing area of Plastic-Mulched Farmland (PMF) is aggravating the conflict between agricultural development and environmental protection. The spatial distribution of PMF requires an effective and economic technique. However, most works are currently carried out on pixel-level algorithms, which leads inevitably to mixed spectral errors. In this connection, PMF has been mapped with Pléiades

Abstract Monitoring large gradient ground deformation due to temporal and spatial image decoherence has long been a challenge. We attempted an improvement using Sentinel-1A and Sentinel-1B C-band data fusion methods based on the variation law of subsidence velocity of ground leveling monitoring points. This approach improved the temporal resolution from 12 to 6 days. Using a mine in Datong, Shanxi

(2021). CJRS’ Special Issue on Deep Learning for Environmental Applications of Remote Sensing Data. Canadian Journal of Remote Sensing: Vol. 47, Deep Learning for Environmental Applications of Remote Sensing Data, pp. 159-161.

Abstract Shrub willow is considered an important dedicated energy crop in temperate climates for the production of bioenergy, biofuels, and bio-based products. A methodology to rapidly and accurately estimate above-ground biomass (AGB) is essential for understanding potential biomass supply, identifying potential growth limitations, and making management decisions. The main objective of this study

Abstract The Canadian Shield, the world’s largest exposure of glaciated crystalline bedrock, is the most lake-rich region on Earth. Recent studies using high-resolution CubeSat satellite imagery have revealed its surface water hydrology to be surprisingly dynamic at fine spatial scales. Here we test whether super-resolution (SR), the resampling of coarse imagery to a finer-than-native resolution, can

Abstract Over the past few years, Convolutional Neural Networks (CNN) have grown in popularity with the remote sensing community due to their relatively easy training process, excellent generalization capacity and state-of-the-art performance. CNN models following an encoder-decoder architecture to perform end-to-end semantic segmentation have been applied to Change Detection (CD) applications with

Abstract With the recent tremendous improvements in the spatial, spectral, and temporal resolutions of remote sensing imaging systems, there has been a dramatic increase in their applications. Amongst different applications of very high-resolution remote sensing images, damage detection for rapid emergency response is one of the most challenging ones. Recently, deep learning frameworks have enhanced

Abstract Land use and land cover (LULC) mapping is a basic research topic in geography. In deep-learning (DL)-based LULC mapping, there are primarily the following issues: training and testing samples for DL are typically annotated by indoor visual interpretation without field surveys; remotely sensed scene classification based on DL typically lacks fine geometric boundaries for ground objects; historical

Abstract In this research note, we demonstrate the applicability of interferometric analyses (InSAR) of RADARSAT 2 (RS2), SENTINEL 1 (S1) and RADARSAT Constellation Mission (RCM) datasets to characterize and monitor landslides along a high-risk section of the national railway transportation corridor traversing the Thompson River valley, British Columbia. As a geomorphically active landform, the North

Abstract The snapshot hyperspectral imaging is an emerging technique with numerous applications. However, the hyperspectral imaging reconstruction is often time-consuming, which is placing a limit on the development of snapshot hyperspectral imaging. We present an efficient reconstruction algorithm based on the tensor analysis and the low-rank constraint. The hyperspectral data cube is regarded as

Abstract Combining Dirichlet Mixture Models (DMM) with deep learning models for road extraction is an attractive study topic. Benefiting from DMM, the manually labeling work is alleviated. However, DMM suffers from high computational complexity due to pixel by pixel computations. Also, traditional constant parameter settings of DMM may not be suitable for different target images. To address the above

Abstract This paper investigates the deep neural networks for rapid and accurate detection of building rooftops in aerial orthoimages. The networks were trained using the manually labeled rooftop vector data digitized on aerial orthoimagery covering the Kitchener-Waterloo area. The performance of the three deep learning methods, U-Net, Fully Convolutional Network (FCN), and Deeplabv3+ were compared

Abstract Airborne LiDAR data allow the precise modeling of topography and are used in multiple contexts. To facilitate further analysis, the point cloud classification process allows the assignment of a class, object or feature, to each point. This research uses ConvPoint, a deep learning method, to perform airborne point cloud classification at scale, in rural and urban contexts. Specifically, our

Abstract The information-accurate road network database is greatly significant and provides essential input to many transportation-related activities. Recently, remote sensing images have been an important data source for assisting rapid road network updating tasks. However, due to the diverse challenging scenarios of roads in remote sensing images, such as occlusions, shadows, material diversities

Abstract Agricultural land abandonment is a dynamic process characterized by both significant spectral variability and spectral similarity to areas of agricultural land. The identification of abandoned agricultural land (AAL) based on remote sensing data must be preceded by field surveys that are focused on the acquisition of the physiognomic characteristics (the composition of species, height of vegetation

Abstract The landscape of post-secondary education has experienced a dramatic change in student outcomes over the past 20 years. The expectation for students in advanced education was a career in research and toward gaining employment in either academia or in government science. From our survey of university students and early career professionals, it was clear that there is an expectation gap between

Abstract Obtaining near real-time road features is very important in emergent situations like flood and geological disaster cases. Remote sensing images with very high spatial resolution usually have many details in land use and land cover, which complicate the detection and extraction of road features. In this paper, we propose a deep residual deconvolutional network (Deep ResDCLnet), to extract road

Abstract Canada’s Earth-observing RADARSAT Constellation Mission (RCM) is intended to serve operational users. The users’ main objectives were to have routinely available high-quality quantitative information about their applications, with large area coverage potential. That two-part requirement was sufficient to establish an innovative synthetic aperture radar (SAR) polarimeter’s end-to-end system

Abstract Aiming at solving inaccurate and incomplete extraction of road in remote sensing images, this paper proposes an automatic extraction algorithm based on Rectangle Marked Point Process (RMPP). First, the RMPP is designed to model the road surface, which aims to obtain the centerline and width of road correctly. Secondly, under the framework of Bayesian theory, the proposed road extraction model

Abstract The recent world-wide loss of seagrasses, which are critical components of coastal ecosystems, has ignited an effort among scientists and resource managers to develop effective monitoring tools. Although Landsat time-series is considered one of the most cost-effective options for monitoring landscapes, its application to monitor seagrasses remains scarce due to many factors including difficulties

Abstract Due to the wide distribution of crosswalks over the road nets, the finding of impaired crosswalk marks is usually long-time delayed, which may put crosswalk pedestrians into danger. To reduce the repairing cost and improve the finding speed of damaged crosswalks, this paper uses remote sensing images to automatically detect crosswalks. The detection results can be used for further examination

Abstract Railway and subway tunnels have lengthy runs, long train operation times, high detection pressures, and critical structural safety concerns that affect tunnel service life, train safety, and passenger comfort. The current method of measuring the clearance convergence requires considerable manpower and equipment to identify defects, cannot measure the entire tunnel section, has poor operation

Abstract Mid-latitude snow is understudied compared to snow in the northern high latitudes despite its importance as a source of freshwater to this economically significant region. The mid-latitudes provide opportunity to understand the influence on SWE retrievals of ice and vegetation, conditions which may encroach the north with a warming climate. Successful retrieval of SWE and snow depth was demonstrated

Abstract Landfast ice (LFI) is a prominent climatological feature in the Canadian Arctic. LFI is generally defined as immobile near-shore ice that remains fast along the coast and forms seaward from the land. It affects the coastline dynamics, is important for the near-shore ecosystems, wildlife, and human socio-economic activities. A method is proposed for mapping the LFI using time series of 10-day

Abstract Oasis ecosystems are highly vulnerable to environmental changes. To determine the state of vegetation in these ecosystems, monitoring systems must be provided with data on cultivated areas. These data can be obtained in part by using satellite observation systems with high and moderate spatial resolution and high temporal repetitiveness; these systems offer a synoptic vision that makes them

Abstract As part of the Atlantic Zone Monitoring Program two different methods were applied to merge three Level-3 AVHRR SST products into a homogenized blend covering the time period from 1982 to present over the Northwest Atlantic, providing a regionally-tuned climatological base on which to assess whether current observations are below, near or above normal. Weekly and monthly SST composites were

Abstract The analysis based on geospatial data from different measurement systems now constitutes a complex numerical and practical enterprise. The dynamic development of modern technologies enables rapid and precise acquisition of such data. Nonetheless, the diversity of reference systems is today one of the main challenges for their correct interpretation. The combined use of the processed measurement

Abstract Vernal pools are small, temporary, forested wetlands of ecological importance with a high sensitivity to changing climate and land-use patterns. These ecosystems are under considerable development pressure in southeastern Georgian Bay, where mapping techniques are required to inform wise land-use decisions. Our mapping approach combines common machine learning techniques [random forest, support

Abstract In this paper, we propose an object detection methodology applied to Global Wheat Head Detection (GWHD) Dataset. We have been through two major architectures of object detection which are Faster R-CNN, and EfficientDet, in order to design a novel and robust wheat head detection model. We emphasize on optimizing the performance of our proposed final architectures. Furthermore, we have been

Abstract Shipping constitutes the majority of the world trade, and Synthetic Aperture Radar (SAR) imagery is the primary involuntary all-condition ship monitoring and classification approach. However, large SAR datasets for deep learning are difficult to curate, usually leading to imbalanced classes. Herein, conventional methods such as weighted cost function or over-sampling are shown to be insufficient

Abstract Reindeer lichens (Cladonia spp.) are an important food source for woodland and barren ground caribou herds. In this study, we assessed Cladonia classification accuracy in a rocky, Canadian Shield landscape near Yellowknife, Northwest Territories using both Unmanned Aerial Vehicle (UAV) sensors and high-resolution satellite sensors. At the UAV scale, random forest classifications derived from

Abstract Due to the advent of powerful parallel processing tools, including modern Graphics Processing Units (GPU), new deep learning algorithms, such as Convolutional Neural Networks (CNNs), have significantly altered the state-of-the-art algorithms in satellite classification of complex environments. Recent studies have demonstrated that the generic feature maps extracted from CNNs are incredibly

Abstract The Cumberland Sound Beluga is a threatened population of belugas and the assessment of the population is done by a manual review of aerial surveys. The time-consuming and labor-intensive nature of this job motivates the need for a computer automated process to monitor beluga populations. In this paper, we investigate convolutional neural networks to detect whether a section of an aerial survey

Abstract Precise determination of vegetation type is important in remote sensing of the ecological environment. Many studies have explored ecosystem structure on explicit spatial scales using specific remote sensing data, but few studies have considered vegetation information extraction at various landscape levels using LiDAR-derived raster layers. This study determined vegetation information based

Abstract Changes in vegetation have been observed in areas of the Arctic due to changing climate. This study examines a normalized difference vegetation index (NDVI) time series (2004–2018) of high spatial resolution satellite data (i.e., IKONOS, WorldView-2, WorldView-3) to determine if vegetation abundance has changed over the Cape Bounty Arctic Watershed Observatory, Melville Island, Nunavut. Image

Abstract Wetlands have received intensive interdisciplinary attention as unique ecosystems with valuable resources. As a new technology, the airborne LiDAR system has recently been applied in wetland research. However, most of the studies have focused on one or two LiDAR observations to extract either terrain or vegetation information from wetlands. This research aims at evaluating the combination

Abstract We investigated the potential of using Synthetic Aperture Radar (SAR) imagery from three different frequencies: X-, C-, and L-band, to characterize coastal wetlands in the Great Lakes. Three sets of SAR data acquired over the Bay of Quinte, Ontario, Canada between 2016 and 2018 from Radarsat-2, 2016 from TerraSAR-X, and 2018 from ALOS-2 satellites were processed using small baseline subset

Abstract The Unmanned Aerial Vehicle (UAV) and Google Earth (GE) RGB images have ultra-high spatial resolution. But it is difficult to get a high classification accuracy due to the poor spectral resolution. In this article, the object-based wetland classification is investigated using multi-feature combination of ultra-high spatial resolution multispectral images (MSI). A Gram-Schmidt (GS) transformation

Abstract Object detection from remote sensing images serves as an important prerequisite to many applications. However, caused by scale and orientation variations, appearance and distribution diversities, occlusion and shadow contaminations, and complex environmental scenarios of the objects in remote sensing images, it brings great challenges to realize highly accurate recognition of geospatial objects

Abstract Identification of optimal pod maturity stage in Canola is key for maximizing seed yield, quality and also an important phenotypic trait in crop improvement programs. The conventional method is via visual inspection of seed color change. Alternatively, hyperspectral sensors have potential to determine physiological status of the crops. Therefore, the objective of the study is to estimate canola

Abstract Multispectral remote sensing data have proven to be useful in deriving tidal flat topography. However, limited satellite observations over a certain period have large uncertainties. In this study, we used MODIS time-series data with a high observational frequency to generate accurate tidal flat topography in Nantong, China based on the relationship between the T_Tide-derived tidal levels and

Abstract The availability of concurrently high spatiotemporal resolution remote sensing data is highly desirable as they represent a key element for effective monitoring in various environmental applications. However, due to the tradeoff between the spatial resolution and acquisition frequency of current satellites, such data are still lacking. Many studies have been undertaken trying to overcome these

Abstract The availability of concurrently high spatiotemporal resolution remote sensing data is highly desirable as they represent a key element for effective monitoring in various environmental applications. However, due to the tradeoff between the spatial resolution and acquisition frequency of current satellites, such data are still lacking. Many studies have been undertaken trying to overcome these

Abstract Conventional methods for monitoring pavement healthy states have the disadvantages of low efficiency and being time-consuming and destructive. Current studies indicate that traditional machine learning algorithms showed poor performance and low generalization capacity in identifying asphalt pavement aging and damage conditions. Further, deep learning network models have less been applied to

Abstract We investigated the potential of using Synthetic Aperture Radar (SAR) imagery from three different frequencies: X-, C-, and L-band, to characterize coastal wetlands in the Great Lakes. Three sets of SAR data acquired over the Bay of Quinte, Ontario, Canada between 2016 and 2018 from Radarsat-2, 2016 from TerraSAR-X, and 2018 from ALOS-2 satellites were processed using small baseline subset

Abstract Precise determination of vegetation type is important in remote sensing of the ecological environment. Many studies have explored ecosystem structure on explicit spatial scales using specific remote sensing data, but few studies have considered vegetation information extraction at various landscape levels using LiDAR-derived raster layers. This study determined vegetation information based

Abstract Changes in vegetation have been observed in areas of the Arctic due to changing climate. This study examines a normalized difference vegetation index (NDVI) time series (2004–2018) of high spatial resolution satellite data (i.e., IKONOS, WorldView-2, WorldView-3) to determine if vegetation abundance has changed over the Cape Bounty Arctic Watershed Observatory, Melville Island, Nunavut. Image

Abstract Historic changes in Alpine Treeline Ecotone were modeled using 21 topographic, climatic, geologic, and disturbance variables in a random forest model. Airborne LiDAR and oblique historic repeat photography were used to identify changes in canopy cover in the West Castle Watershed (WCW), Alberta, Canada (49.3° N, 114.4° W). A Random Forest model was trained on ∼30% of the watershed which was

Abstract Historic changes in Alpine Treeline Ecotone were modeled using 21 topographic, climatic, geologic, and disturbance variables in a random forest model. Airborne LiDAR and oblique historic repeat photography were used to identify changes in canopy cover in the West Castle Watershed (WCW), Alberta, Canada (49.3° N, 114.4° W). A Random Forest model was trained on ∼30% of the watershed which was

Abstract RADARSAT-2 imagery collected each winter from 2015/2016 to 2019/2020 is used to quantify and characterize the variability in the motion of, and the discharge from, the major marine-terminating ice masses of the Queen Elizabeth Islands (QEI: Devon, Ellesmere and Axel Heiberg Islands) in the Canadian High Arctic. The majority of the glaciers did not experience significant variations in flow

Abstract Detecting individual-tree crowns provides a fundamental analysis unit bridging macro ecological patterns and micro physiological functions. This study adapted an anchor-free deep learning model, CenterNet, to detect individual crown locations and regions from dense 3 D terrestrial laser scans. A total of 1181 crowns from twelve plots were manually delineated as reference, among which eight

Abstract Above-ground biomass change accumulated during four growth seasons in a hemi-boreal forest was predicted using airborne L- and P-band synthetic aperture radar (SAR) backscatter. The radar data were collected in the BioSAR 2007 and BioSAR 2010 campaigns over the Remningstorp test site in southern Sweden. Regression models for biomass change were developed from biomass maps created using airborne

Abstract Accurate prediction of crop yield before harvest is critical to food security and importation. The calculated ten explanatory factors and autumn crop yield data were used as data sources in this research. Firstly, a Redundancy Analysis (RDA) was employed to carry out explanatory factors and feature selection. The simple effects of RDA were used to evaluate the interpretation rates of the explanatory

Abstract Forest inventories in uncertain future economic and environmental conditions require the development of cost-effective measurement techniques to provide robust and accurate information on forests across regional and global scales. Digital terrestrial photogrammetry (DTP) can be used to detect and measure trees on sample plots. In this study, a method was developed which used spherical images

Abstract This paper studies the fidelity level of the extracted LiDAR (Light Detection And Ranging) building point cloud in relation to the original building. In this context, the building point cloud is compared with a reference model. This comparison allows a deep understanding of the point cloud structure with respect to both the actual building and the constructed model. Consequently, the source

Abstract Eelgrass (Zostera marina L.) is a marine angiosperm plant that grows throughout coastal areas in Atlantic Canada. Eelgrass meadows provide numerous ecosystem services while they have been acknowledged as important habitats, their location, extent, and health in Atlantic Canada are poorly understood. This study examined the effectiveness of WorldView-2 optical satellite imagery to map eelgrass

Abstract Algae blooms have been a serious problem in coastal and inland water bodies across Canada. The temporal and spatial variability of algae blooms makes it difficult to use in situ monitoring of the lakes. This study aimed to evaluate the potential of Sentinel-3 Ocean and Land Color Instrument (OLCI) and Sentinel-2 Multispectral Instrument (MSI) data for monitoring algal blooms in Lake Erie.