Evaluation of multi-temporal landsat 8 data for wetland classification in newfoundland, Canada

Amani, Meisam; Salehi, Bahram; Mahdavi, Sahel; Granger, Jean; Brisco, Brian

doi:10.1109/igarss.2017.8128432

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For mapping natural features over large areas such as the Province of New Brunswick, Earth's observation satellite images can be a good alternative to aerial photographs. Indeed, current satellite imagery provides multi-temporal data at a lower cost over large areas at a suitable spatial and temporal resolution that allows frequent updating of wetland cover maps [17][18][19]. In particular, multi-date satellite images can incorporate water level and seasonal effects on vegetation, both of which can influence mapping accuracy [20].…”

Section: Introductionmentioning

confidence: 99%

Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada

et al. 2020

View full text Add to dashboard Cite

Mapping wetlands with high spatial and thematic accuracy is crucial for the management and monitoring of these important ecosystems. Wetland maps in New Brunswick (NB) have traditionally been produced by the visual interpretation of aerial photographs. In this study, we used an alternative method to produce a wetland map for southern New Brunswick, Canada, by classifying a combination of Landsat 8 OLI, ALOS-1 PALSAR, Sentinel-1, and LiDAR-derived topographic metrics with the Random Forests (RF) classifier. The images were acquired in three seasons (spring, summer, and fall) with different water levels and during leaf-off/on periods. The resulting map has eleven wetland classes (open bog, shrub bog, treed bog, open fen, shrub fen, freshwater marsh, coastal marsh, shrub marsh, shrub wetland, forested wetland, and aquatic bed) plus various non-wetland classes. We achieved an overall accuracy classification of 97.67%. We compared 951 in-situ validation sites to the classified image and both the 2106 and 2019 reference maps available through Service New Brunswick. Both reference maps were produced by photo-interpretation of RGB-NIR digital aerial photographs, but the 2019 NB reference also included information from LiDAR-derived surface and ecological metrics. Of these 951 sites, 94.95% were correctly identified on the classified image, while only 63.30% and 80.02% of these sites were correctly identified on the 2016 and 2019 NB reference maps, respectively. If only the 489 wetland validation sites were considered, 96.93% of the sites were correctly identified as a wetland on the classified image, while only 58.69% and 62.17% of the sites were correctly identified as a wetland on the 2016 and 2019 NB reference maps, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It appears SAR data are most useful for monitoring the dynamics of wetlands. Other studies and projects have used moderate resolution optical data such as Landsat or Sentinel-2 to generate wetland inventories [30,46,47]. Most modern approaches to large-scale wetland inventories utilize a fusion of data such as SAR and optical [34,39,48] and, ideally, SAR, optical, plus topographic information [6,7,49].…”

Section: Introductionmentioning

confidence: 99%

Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada

Simms²,

et al. 2019

Self Cite

View full text Add to dashboard Cite

Advances in machine learning have changed many fields of study and it has also drawn attention in a variety of remote sensing applications. In particular, deep convolutional neural networks (CNNs) have proven very useful in fields such as image recognition; however, the use of CNNs in large-scale remote sensing landcover classifications still needs further investigation. We set out to test CNN-based landcover classification against a more conventional XGBoost shallow learning algorithm for mapping a notoriously difficult group of landcover classes, wetland class as defined by the Canadian Wetland Classification System. We developed two wetland inventory style products for a large (397,958 km2) area in the Boreal Forest region of Alberta, Canada, using Sentinel-1, Sentinel-2, and ALOS DEM data acquired in Google Earth Engine. We then tested the accuracy of these two products against three validation data sets (two photo-interpreted and one field). The CNN-generated wetland product proved to be more accurate than the shallow learning XGBoost wetland product by 5%. The overall accuracy of the CNN product was 80.2% with a mean F1-score of 0.58. We believe that CNNs are better able to capture natural complexities within wetland classes, and thus may be very useful for complex landcover classifications. Overall, this CNN framework shows great promise for generating large-scale wetland inventory data and may prove useful for other landcover mapping applications.

show abstract

“…A major reason for this difficulty is that although each of the wetland species has several distinctive characteristics, they share some ecological and phenological similarities (Boon et al 2016), with non-wetland plant species (Henderson & Lewis 2008). Therefore, this makes it difficult to spectrally distinguish some of the wetland plants from non-wetland plant species using remote sensing imagery (Amani et al 2017). Furthermore, the accuracy of monitoring and assessing LULC change impacts on wetland ecosystems is mainly limited by the imaging characteristics of remotely sensed data as well as the algorithms used, which have been developed by different studies or for a specific application scale.…”

Section: Implications Of Remote Sensing Of Wetland Vegetation and Pro...mentioning

confidence: 99%

Advances in satellite remote sensing of the wetland ecosystems in Sub-Saharan Africa

Thamaga

Dube

Shoko

2021

Geocarto International

View full text Add to dashboard Cite

Wetlands are highly productive systems that act as habitats for a variety of fauna and flora. Despite their ecohydrological significance, wetland ecosystems are severely under threat from global environmental changes as well as pressure from anthropogenic activities. Such changes results in severe disturbances of plant species composition, spatial distribution, productivity, diversity, and their ability to offer critical ecosystem goods and services . However, wetland degradation varies considerably from place to place with severe degradation in developing countries, especially in sub-Saharan Africa due to poor management practices that leads to underutilization and over reliance on them for livelihoods. The lack of monitoring and assessment in this region has therefore led to the lack of consolidated detailed understanding on the rate of wetland loss. For example, the lack of up-to-date and reliable spatial explicit information further complicates the management of wetland ecosystems in semi-arid tropical environments. To monitor, understand and document wetland degradation rate, the use of remote sensing for accurate estimation and precise mapping of present and historic information remains imperative. Similarly, there is a need to develop robust methodologies to precisely assess and monitor wetland degradation, ecohydrological processes and wetland condition over space and time. This work thereof, provides a comprehensive overview of remote sensing applications in monitoring and mapping the wetland ecosystem. It also highlights the strength and challenges associated with the use of satellite data for purposes of wetland monitoring. Spatial explicit and periodic information offered by satellite remote sensing demonstrate a unique opportunity for documenting and understanding of wetlands, their ecohydrological processes, and environmental conditions.

show abstract

Evaluation of multi-temporal landsat 8 data for wetland classification in newfoundland, Canada

Cited by 5 publications

References 4 publications

Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada

Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada

Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada

Advances in satellite remote sensing of the wetland ecosystems in Sub-Saharan Africa

Contact Info

Product

Resources

About