The Quality of Detailed Land Cover Maps in Highly Bio-Diverse Areas: Lessons Learned from the Mexican Experience

The simplest way to interpret polarimetric imagery for land cover classification is to use visualinterpretation methods. The existence of interpretations key as a tool for visual interpretation becomesimportant when different interpreters can produce different results. The quality of the results of theinterpretation of land cover is then determined by the quality of the interpretation tool, in this case, thekey to the interpretation of land cover. The purpose of this study was to make the key to land coverclass interpretation in the Full Polarimetric ALOS PALSAR image, then the interpretation key wasused for reference in making land cover maps and measuring the accuracy of the results of the visualinterpretation. The image used in this study consisted of HH, VV, HV and VH bands. The location ofthe study was in parts of Sleman District. The analysis is done visually by on-screen digitizing onALOS Palsar composite HH + VV HV + VH HH-HV image, which is then interpreted key. The truetest is done by means of the overall accuracy test and Kappa. Visually, ALOS PALSAR imagery isable to distinguish 12 land cover classes in the research area, namely built land, rice fields, mixedgardens, moorlands, salak garden, grass, forest, shrubs, open land, airports, water bodies and lavawith 83% Overall accuracy, and 78% Kappa accuracy.

Download Full-text

Imbalanced Learning in Land Cover Classification: Improving Minority Classes’ Prediction Accuracy Using the Geometric SMOTE Algorithm

Remote Sensing ◽

10.3390/rs11243040 ◽

2019 ◽

Vol 11 (24) ◽

pp. 3040 ◽

Cited By ~ 7

Author(s):

Georgios Douzas ◽

Fernando Bacao ◽

Joao Fonseca ◽

Manvel Khudinyan

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Imbalanced Learning ◽

Learning Problem ◽

Automatic Production ◽

Good Resource ◽

New Generation ◽

Land Cover Maps

The automatic production of land use/land cover maps continues to be a challenging problem, with important impacts on the ability to promote sustainability and good resource management. The ability to build robust automatic classifiers and produce accurate maps can have a significant impact on the way we manage and optimize natural resources. The difficulty in achieving these results comes from many different factors, such as data quality and uncertainty. In this paper, we address the imbalanced learning problem, a common and difficult conundrum in remote sensing that affects the quality of classification results, by proposing Geometric-SMOTE, a novel oversampling method, as a tool for addressing the imbalanced learning problem in remote sensing. Geometric-SMOTE is a sophisticated oversampling algorithm which increases the quality of the instances generated in previous methods, such as the synthetic minority oversampling technique. The performance of Geometric- SMOTE, in the LUCAS (Land Use/Cover Area Frame Survey) dataset, is compared to other oversamplers using a variety of classifiers. The results show that Geometric-SMOTE significantly outperforms all the other oversamplers and improves the robustness of the classifiers. These results indicate that, when using imbalanced datasets, remote sensing researchers should consider the use of these new generation oversamplers to increase the quality of the classification results.

Download Full-text

A Metric for Evaluating the Geometric Quality of Land Cover Maps Generated with Contextual Features from High-Dimensional Satellite Image Time Series without Dense Reference Data

Remote Sensing ◽

10.3390/rs11161929 ◽

2019 ◽

Vol 11 (16) ◽

pp. 1929 ◽

Cited By ~ 1

Author(s):

Dawa Derksen ◽

Jordi Inglada ◽

Julien Michel

Keyword(s):

Time Series ◽

Land Cover ◽

Classification Model ◽

Classification Result ◽

Contextual Features ◽

Geometric Precision ◽

Context Dependent ◽

Land Cover Maps ◽

Sentinel 2

Land cover maps are a key resource for many studies in Earth Observation, and thanks to the high temporal, spatial, and spectral resolutions of systems like Sentinel-2, maps with a wide variety of land cover classes can now be automatically produced over vast areas. However, certain context-dependent classes, such as urban areas, remain challenging to classify correctly with pixel-based methods. Including contextual information into the classification can either be done at the feature level with texture descriptors or object-based approaches, or in the classification model itself, as is done in Convolutional Neural Networks. This improves recognition rates of these classes, but sometimes deteriorates the fine-resolution geometry of the output map, particularly in sharp corners and in fine elements such as rivers and roads. However, the quality of the geometry is difficult to assess in the absence of dense training data, which is usually the case in land cover mapping, especially over wide areas. This work presents a framework for measuring the geometric precision of a classification map, in order to provide deeper insight into the consequences of the use of various contextual features, when dense validation data is not available. This quantitative metric, named the Pixel Based Corner Match (PBCM), is based on corner detection and corner matching between a pixel-based classification result, and a contextual classification result. The selected case study is the classification of Sentinel-2 multi-spectral image time series, with a rich nomenclature containing context-dependent classes. To demonstrate the added value of the proposed metric, three spatial support shapes (window, object, superpixel) are compared according to their ability to improve the classification performance on this challenging problem, while paying attention to the geometric precision of the result. The results show that superpixels are the best candidate for the local statistics features, as they modestly improve the classification accuracy, while preserving the geometric elements in the image. Furthermore, the density of edges in a sliding window provides a significant boost in accuracy, and maintains a high geometric precision.

Download Full-text

Finer-Resolution Mapping of Global Land Cover: Recent Developments, Consistency Analysis, and Prospects

Journal of Remote Sensing ◽

10.34133/2021/5289697 ◽

2021 ◽

Vol 2021 ◽

pp. 1-38

Author(s):

Liangyun Liu ◽

Xiao Zhang ◽

Yuan Gao ◽

Xidong Chen ◽

Xie Shuai ◽

...

Keyword(s):

Cloud Computing ◽

Land Cover ◽

Impervious Surface ◽

Global Land Cover ◽

Global Land ◽

Recent Developments ◽

Computing Platforms ◽

Fine Resolution ◽

Land Cover Maps

Land-cover mapping is one of the foundations of Earth science. As a result of the combined efforts of many scientists, numerous global land-cover (GLC) products with a resolution of 30 m have so far been generated. However, the increasing number of fine-resolution GLC datasets is imposing additional workloads as it is necessary to confirm the quality of these datasets and check their suitability for user applications. To provide guidelines for users, in this study, the recent developments in currently available 30 m GLC products (including three GLC products and thematic products for four different land-cover types, i.e., impervious surface, forest, cropland, and inland water) were first reviewed. Despite the great efforts toward improving mapping accuracy that there have been in recent decades, the current 30 m GLC products still suffer from having relatively low accuracies of between 46.0% and 88.9% for GlobeLand30-2010, 57.71% and 80.36% for FROM_GLC-2015, and 65.59% and 84.33% for GLC_FCS30-2015. The reported accuracies for the global 30 m thematic maps vary from 67.86% to 95.1% for the eight impervious surface products that were reviewed, 56.72% to 97.36% for the seven forest products, 32.73% to 98.3% for the six cropland products, and 15.67% to 99.7% for the six inland water products. The consistency between the current GLC products was then examined. The GLC maps showed a good overall agreement in terms of spatial patterns but a limited agreement for some vegetation classes (such as shrub, tree, and grassland) in specific areas such as transition zones. Finally, the prospects for fine-resolution GLC mapping were also considered. With the rapid development of cloud computing platforms and big data, the Google Earth Engine (GEE) greatly facilitates the production of global fine-resolution land-cover maps by integrating multisource remote sensing datasets with advanced image processing and classification algorithms and powerful computing capability. The synergy between the spectral, spatial, and temporal features derived from multisource satellite datasets and stored in cloud computing platforms will definitely improve the classification accuracy and spatiotemporal resolution of fine-resolution GLC products. In general, up to now, most land-cover maps have not been able to achieve the maximum (per class or overall) error of 5%–15% required by many applications. Therefore, more efforts are needed toward improving the accuracy of these GLC products, especially for classes for which the accuracy has so far been low (such as shrub, wetland, tundra, and grassland) and in terms of the overall quality of the maps.

Download Full-text

A PRELIMINARY QUALITY ANALYSIS OF THE CLIMATE CHANGE INITIATIVE LAND COVER PRODUCTS FOR CONTINENTAL PORTUGAL

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w13-1213-2019 ◽

2019 ◽

Vol XLII-2/W13 ◽

pp. 1213-1220

Author(s):

C. C. Fonte ◽

L. See ◽

M. Lesiv ◽

S. Fritz

Keyword(s):

Climate Change ◽

Land Cover ◽

Quality Analysis ◽

Data Sets ◽

Change Initiative ◽

Small Areas ◽

Land Cover Data ◽

Vegetation Class ◽

Land Cover Maps

<p><strong>Abstract.</strong> The aim of this paper is to perform a preliminary analysis of the compatibility and quality of the available time series of land cover data available for continental Portugal, in particular, Climate Change Initiative Land Cover maps, which are available annually from 1992 to 2015; CORINE Land Cover and the Urban Atlas for 2006 and 2012; and the Portuguese Carta de Ocupação do Solo for 2007 and 2010. Changes were first identified per product between the different data sets for consecutive dates and then a comparison was made between products. This was followed by validation of two study areas using the COS and UA as reference products. The results show that increases in urbanization are visible in all pairs of products but that the amount of change varies. Moreover, some changes are not in the same direction but may be attributable to classes with small areas and the coarser resolution of the CCI LC maps compared to the other products. The CCI LC maps also overestimate the forest/natural vegetation class by 11&ndash;13%, which is also the largest class in Portugal.</p>

Download Full-text

Mires in Europe—Regional Diversity, Condition and Protection

Diversity ◽

10.3390/d13080381 ◽

2021 ◽

Vol 13 (8) ◽

pp. 381

Author(s):

Franziska Tanneberger ◽

Asbjørn Moen ◽

Alexandra Barthelmes ◽

Edward Lewis ◽

Lera Miles ◽

...

Keyword(s):

Land Cover ◽

Data Quality ◽

Protected Areas ◽

Lessons Learned ◽

Distribution Data ◽

The World ◽

Total Proportion ◽

Monitoring Service ◽

Land Cover Maps ◽

The Eu

In spite of the worldwide largest proportional loss of mires, Europe is a continent with important mire diversity. This article analyses the condition and protection status of European mire ecosystems. The overview is based on the system of European mire regions, representing regional variety and ecosystem biodiversity. We combined peatland distribution data with land cover maps of the Copernicus Land Monitoring Service as well as with the World Database on Protected Areas to assess the extent of degraded peatlands and the proportion of peatlands located in protected areas in each European mire region. The total proportion of degraded peatlands in Europe is 25%; within the EU it is 50% (120,000 km2). The proportion of degradation clearly increases from north to south, as does the proportion of peatlands located within protected areas. In more than half of Europe’s mire regions, the target of at least 17% of the area located in protected areas is not met with respect to peatlands. Data quality is discussed and the lessons learned from Europe for peatland conservation are presented.

Download Full-text