scholarly journals INTER-COMPARISON OF THE GLOBAL LAND COVER MAPS IN AFRICA SUPPLEMENTED BY SPATIAL ASSOCIATION OF ERRORS

2019 ◽  
Vol XLII-4/W14 ◽  
pp. 11-16
Author(s):  
G. Bratic ◽  
D. Oxoli ◽  
M. A. Brovelli
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Confusion Matrix ◽  
Spatial Association ◽  
Probability Of Error ◽  
Earth Observations ◽  
Area Of Interest ◽  
Global Land Cover ◽  
Land Cover Maps ◽  
Single Pixel

<p><strong>Abstract.</strong> Recent advances in Earth Observations supported development of high-resolution land cover (LC) maps on a large-scale. This is an important step forward, especially for developing countries, which experienced problems in the past due to absence of reliable LC information. Nevertheless, increasing number of LC products is imposing additional validation workload to confirm their quality. In this paper inter-comparison of two recent LC products (GlobeLand30 and S2 prototype LC 20m map of Africa) for country of Rwanda in Africa was done. It is a way to facilitate validation by identifying the areas with higher probability of error. Specific approach of comparison of single pixel of one map with multiple pixels of another map provided confusion matrix and sub-pixel agreement table. In this work, accuracy indexes based on the confusion matrix were computed as a measure of similarity between the two maps. Furthermore, Moran’s I index was computed for estimation of spatial association of the pixels in disagreement. Also, total disagreement, as well as disagreement of particularly confused classes was visualised to analyse their spatial distribution. The results are showing that similarity of the two maps is about 66%. Disagreements are spatially associated and the most evident in the eastern and north-western part of the area of interest. This coincides also with the distribution of the two most confused classes Wetland and Shrubland. The results delineate areas of inconsistency between the two maps, and therefore areas where careful accuracy analysis are needed.</p>

scholarly journals EXTENDING ACCURACY ASSESSMENT PROCEDURES OF GLOBAL COVERAGE LAND COVER MAPS THROUGH SPATIAL ASSOCIATION ANALYSIS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1601-1607
Author(s):  
D. Oxoli ◽  
G. Bratic ◽  
H. Wu ◽  
M. A. Brovelli
Keyword(s):  
Land Cover ◽  
Spatial Patterns ◽  
Accuracy Assessment ◽  
Confusion Matrix ◽  
Spatial Association ◽  
Visual Exploration ◽  
Assessment Procedure ◽  
Lombardy Region ◽  
Land Cover Map ◽  
Land Cover Maps

<p><strong>Abstract.</strong> High-resolution land cover maps are in high demand for many environmental applications. Yet, the information they provide is uncertain unless the accuracy of these maps is known. Therefore, accuracy assessment should be an integral part of land cover map production as a way of ensuring reliable products. The traditional accuracy metrics like Overall Accuracy and Producer’s and User’s accuracies &amp;ndash; based on the confusion matrix &amp;ndash; are useful to understand global accuracy of the map, but they do not provide insight into the possible nature or source of the errors. The idea behind this work is to complement traditional accuracy metrics with the analysis of error spatial patterns. The aim is to discover errors underlying features which can be later employed to improve the traditional accuracy assessment. The designed procedure is applied to the accuracy assessment of the GlobeLand30 global land cover map for the Lombardy Region (Northern Italy) by means of comparison with the DUSAF regional land cover map. Traditional accuracy assessment quantified the classification accuracies of the map. Indeed, critical errors were pointed out and further analyses on their spatial patterns were performed by means of the Moran’s I indicator. Additionally, visual exploration of the spatial patterns was performed. This allowed describing possible sources of errors. Both software and analysis strategies were described in detail to facilitate future improvement and replication of the procedure. The results of the exploratory experiments are critically discussed in relation to the benefits that they potentially introduce into the traditional accuracy assessment procedure.</p>

scholarly journals Domain-Adversarial Training of Self-Attention-Based Networks for Land Cover Classification Using Multi-Temporal Sentinel-2 Satellite Imagery

2021 ◽  
Vol 13 (13) ◽  
pp. 2564
Author(s):  
Mauro Martini ◽  
Vittorio Mazzia ◽  
Aleem Khaliq ◽  
Marcello Chiaberge
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Domain Adaptation ◽  
Learning Approaches ◽  
Atmospheric Conditions ◽  
Practical Applications ◽  
Area Of Interest ◽  
Multi Temporal ◽  
Significant Performance ◽  
Adversarial Training

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time-consuming solution that pose strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention-based models for LC&CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

scholarly journals A National Assessment of Wetland Status and Trends for Canada’s Forested Ecosystems Using 33 Years of Earth Observation Satellite Data

2018 ◽  
Vol 10 (10) ◽  
pp. 1623 ◽  
Author(s):  
Michael Wulder ◽  
Zhan Li ◽  
Elizabeth Campbell ◽  
Joanne White ◽  
Geordie Hobart ◽  
...  
Keyword(s):  
Land Cover ◽  
Satellite Data ◽  
Regional Variability ◽  
National Assessment ◽  
Wetland Dynamics ◽  
Earth Observations ◽  
Land Condition ◽  
Earth Observation Satellite ◽  
Forested Ecosystems ◽  
Land Cover Maps

Wetlands are important globally for supplying clean water and unique habitat, and for storing vast amounts of carbon and nutrients. The geographic extent and state of wetlands vary over time and represent a dynamic land condition rather than a permanent land cover state. Herein, we combined a time series of land cover maps derived from Landsat data at 30-m resolution to inform on spatial and temporal changes to non-treed and treed wetland extents over Canada’s forested ecosystems (>650 million ha) from 1984 to 2016. Overall, for the period, 1984 to 2016, we found the extent of wetlands (non-treed and treed combined) in Canada’s forested ecosystems to be stable, with some regional variability, often resulting from offsetting decreases and increases within a given ecozone. Notwithstanding difficulties in using optical satellite data for mapping a land condition, by accumulating wetland evidence via earth observations consistently through multiple decades, our results capture the trends in wetland cover over a previously unmapped, national extent at a level of spatial detail and temporal reach suitable for further focused interpretations of wetlands and drivers and projections of wetland dynamics.

scholarly journals Utilizing the Global Land Cover 2000 reference dataset for a comparative accuracy assessment of 1 km global land cover maps

2015 ◽  
Vol XL-7/W3 ◽  
pp. 503-510 ◽  
Author(s):  
M. Schultz ◽  
N. E. Tsendbazazr ◽  
M. Herold ◽  
M. Jung ◽  
P. Mayaux ◽  
...  
Keyword(s):  
Land Cover ◽  
Climate Models ◽  
Accuracy Assessment ◽  
Careful Consideration ◽  
Global Climate Models ◽  
Reference Dataset ◽  
Heterogeneous Landscape ◽  
Global Land Cover ◽  
Global Land ◽  
Land Cover Maps

Many investigators use global land cover (GLC) maps for different purposes, such as an input for global climate models. The current GLC maps used for such purposes are based on different remote sensing data, methodologies and legends. Consequently, comparison of GLC maps is difficult and information about their relative utility is limited. The objective of this study is to analyse and compare the thematic accuracies of GLC maps (i.e., IGBP-DISCover, UMD, MODIS, GLC2000 and SYNMAP) at 1 km resolutions by (a) re-analysing the GLC2000 reference dataset, (b) applying a generalized GLC legend and (c) comparing their thematic accuracies at different homogeneity levels. The accuracy assessment was based on the GLC2000 reference dataset with 1253 samples that were visually interpreted. The legends of the GLC maps and the reference datasets were harmonized into 11 general land cover classes. There results show that the map accuracy estimates vary up to 10-16% depending on the homogeneity of the reference point (HRP) for all the GLC maps. An increase of the HRP resulted in higher overall accuracies but reduced accuracy confidence for the GLC maps due to less number of accountable samples. The overall accuracy of the SYNMAP was the highest at any HRP level followed by the GLC2000. The overall accuracies of the maps also varied by up to 10% depending on the definition of agreement between the reference and map categories in heterogeneous landscape. A careful consideration of heterogeneous landscape is therefore recommended for future accuracy assessments of land cover maps.

scholarly journals Analyzing the Uncertainty of Degree Confluence Project for Validating Global Land-Cover Maps Using Reference Data-Based Classification Schemes

2020 ◽  
Vol 12 (16) ◽  
pp. 2589
Author(s):  
Tana Qian ◽  
Tsuguki Kinoshita ◽  
Minoru Fujii ◽  
Yuhai Bao
Keyword(s):  
Land Cover ◽  
Reference Data ◽  
Data Uncertainty ◽  
Validation Data ◽  
Classification Schemes ◽  
Reference Information ◽  
Global Land Cover ◽  
Global Land ◽  
Land Cover Maps ◽  
The Impact

Global land-cover products play an important role in assisting the understanding of climate-related changes and the assessment of progress in the implementation of international initiatives for the mitigation of, and adaption to, climate change. However, concerns over the accuracies of land-cover products remain, due to the issue of validation data uncertainty. The volunteer-based Degree Confluence Project (DCP) was created in 1996, and it has been used to provide useful ground-reference information. This study aims to investigate the impact of DCP-based validation data uncertainty and the thematic issues on map accuracies. We built a reference dataset based on the DCP-interpreted dataset and applied a comparison for three existing global land-cover maps and DCP dataset-based probability maps under different classification schemes. The results of the obtained confusion matrices indicate that the uncertainty, including the number of classes and the confusion in mosaic classes, leads to a decrease in map accuracy. This paper proposes an informative classification scheme that uses a matrix structure of unaggregated land-cover and land-use classes, and has the potential to assist in the land-cover interpretation and validation processes. The findings of this study can potentially serve as a guide to select reference data and choose/define appropriate classification schemes.

scholarly journals REVIEW OF HIGH-RESOLUTION GLOBAL LAND COVER

2021 ◽  
Vol XLIII-B4-2021 ◽  
pp. 175-182
Author(s):  
G. Bratic ◽  
A. Vavassori ◽  
M. A. Brovelli
Keyword(s):  
High Resolution ◽  
Land Cover ◽  
Spatial Resolution ◽  
Accuracy Assessment ◽  
General Information ◽  
Tree Canopy ◽  
Global Land Cover ◽  
Tree Canopy Cover ◽  
Global Land ◽  
Land Cover Maps

Abstract. The land cover detection on our planet at high spatial resolution has a key role in many scientific and operational applications, such as climate modeling, natural resources management, biodiversity studies, urbanization analyses and spatial demography. Thanks to the progresses in Remote Sensing, accurate and high-resolution land cover maps have been developed over the last years, aiming at detecting the spatial resolution of different types of surfaces. In this paper we propose a review of the high-resolution global land cover products developed through Earth Observation technologies. A series of general information regarding imagery and data used to produce the map, the procedures employed for the map development and for the map accuracy assessment have been provided for every dataset. The land cover maps described in this paper concern the global distribution of settlements (Global Urban Footprint, Global Human Settlement Built-Up, World Settlement Footprint), water (Global Surface Water), forests (Forest/Non-forest, Tree canopy cover), and a two land cover maps describing world in 10 generic classes (GlobeLand30 and Finer Resolution Observation and Monitoring of Global Land Cover). The advantages and shortcomings of these maps and of the methods employed to produce them are summarized and compared in the conclusions.

scholarly journals Towards an open and synergistic framework for mapping global land cover

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11877
Author(s):  
Jiyao Zhao ◽  
Le Yu ◽  
Han Liu ◽  
Huabing Huang ◽  
Jie Wang ◽  
...  
Keyword(s):  
Land Cover ◽  
Google Earth ◽  
Single Type ◽  
Impervious Surfaces ◽  
Sources Of Information ◽  
Computing Platform ◽  
Global Land Cover ◽  
Global Land ◽  
Cloud Computing Platform ◽  
Land Cover Maps

Global land-cover datasets are key sources of information for understanding the complex inter-actions between human activities and global change. They are also among the most critical variables for climate change studies. Over time, the spatial resolution of land cover maps has increased from the kilometer scale to 10-m scale. Single-type historical land cover datasets, including for forests, water, and impervious surfaces, have also been developed in recent years. In this study, we present an open and synergy framework to produce a global land cover dataset that combines supervised land cover classification and aggregation of existing multiple thematic land cover maps with the Google Earth Engine (GEE) cloud computing platform. On the basis of this method of classification and mosaicking, we derived a global land cover dataset for 6 years over a time span of 25 years. The overall accuracies of the six maps were around 75% and the accuracy for change area detection was over 70%. Our product also showed good similarity with the FAO and existing land cover maps.

Sign in / Sign up

Export Citation Format

Share Document