scholarly journals Assessment of Optimal Transport for Operational Land-Cover Mapping Using High-Resolution Satellite Images Time Series without Reference Data of the Mapping Period

2019 ◽  
Vol 11 (9) ◽  
pp. 1047 ◽  
Author(s):  
Benjamin Tardy ◽  
Jordi Inglada ◽  
Julien Michel
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Reference Data ◽  
Optimal Transport ◽  
Majority Voting ◽  
Data Availability ◽  
Optical Data ◽  
High Resolution Satellite Images ◽  
Land Cover Map ◽  
Number Of Classes

Land-cover map production using remote-sensing imagery is governed by data availability. In our case, data sources are two-fold: on one hand, optical data provided regularly by satellites such as Sentinel-2, and on the other hand, reference data which allow calibrating mapping methods or validating the results. The lengthy delays due to reference data collection and cleansing are one of the main issues for applications. In this work, the use of Optimal Transport (OT) is proposed. OT is a Domain Adaptation method that uses past data, both images and reference data, to produce the land-cover map of the current period without updated reference data. Seven years of Formosat-2 image time series and the corresponding reference data are used to evaluate two OT algorithms: conventional EMD transport and regularized transport based on the Sinkhorn distance. The contribution of OT to a classification fusion strategy is also evaluated. The results show that with a 17-class nomenclature the problem is too complex for the Sinkhorn algorithm, which provides maps with an Overall Accuracy (OA) of 30%. In contrast, with the EMD algorithm, an OA close to 70% is obtained. One limitation of OT is the number of classes that can be considered at the same time. Simplification schemes are proposed to reduce the number of classes to be transported. Cases of improvement are shown when the problem is simplified, with an improvement in OA varying from 5% and 20%, producing maps with an OA near 79%. As several years are available, the OT approaches are compared to standard fusion schemes, like majority voting. The gain in voting strategies with OT use is lower than the gain obtained with standard majority voting (around 5%).

scholarly journals Combined Use of Optical and Synthetic Aperture Radar Data for REDD+ Applications in Malawi

Land ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 116 ◽  
Author(s):  
Manuela Hirschmugl ◽  
Carina Sobe ◽  
Janik Deutscher ◽  
Mathias Schardt
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Synthetic Aperture Radar ◽  
Data Availability ◽  
Synthetic Aperture ◽  
Optical Data ◽  
Series Data ◽  
Forest Mapping ◽  
Sar Data ◽  
Aperture Radar

Recent developments in satellite data availability allow tropical forest monitoring to expand in two ways: (1) dense time series foster the development of new methods for mapping and monitoring dry tropical forests and (2) the combination of optical data and synthetic aperture radar (SAR) data reduces the problems resulting from frequent cloud cover and yields additional information. This paper covers both issues by analyzing the possibilities of using optical (Sentinel-2) and SAR (Sentinel-1) time series data for forest and land cover mapping for REDD+ (Reducing Emissions from Deforestation and Forest Degradation) applications in Malawi. The challenge is to combine these different data sources in order to make optimal use of their complementary information content. We compare the results of using different input data sets as well as of two methods for data combination. Results show that time-series of optical data lead to better results than mono-temporal optical data (+8% overall accuracy for forest mapping). Combination of optical and SAR data leads to further improvements: +5% in overall accuracy for land cover and +1.5% for forest mapping. With respect to the tested combination methods, the data-based combination performs slightly better (+1% overall accuracy) than the result-based Bayesian combination.

scholarly journals Characterizing Land Use/Land Cover Using Multi-Sensor Time Series from the Perspective of Land Surface Phenology

2019 ◽  
Vol 11 (14) ◽  
pp. 1677 ◽  
Author(s):  
Lan H. Nguyen ◽  
Geoffrey M. Henebry
Keyword(s):  
Land Use ◽  
Time Series ◽  
Land Cover ◽  
Land Surface ◽  
Quadratic Model ◽  
Observation Data ◽  
Land Use Land Cover ◽  
Land Surface Phenology ◽  
Land Cover Map ◽  
Phenological Metrics

Due to a rapid increase in accessible Earth observation data coupled with high computing and storage capabilities, multiple efforts over the past few years have aimed to map land use/land cover using image time series with promising outcomes. Here, we evaluate the comparative performance of alternative land cover classifications generated by using only (1) phenological metrics derived from either of two land surface phenology models, or (2) a suite of spectral band percentiles and normalized ratios (spectral variables), or (3) a combination of phenological metrics and spectral variables. First, several annual time series of remotely sensed data were assembled: Accumulated growing degree-days (AGDD) from the MODerate resolution Imaging Spectroradiometer (MODIS) 8-day land surface temperature products, 2-band Enhanced Vegetation Index (EVI2), and the spectral variables from the Harmonized Landsat Sentinel-2, as well as from the U.S. Landsat Analysis Ready Data surface reflectance products. Then, at each pixel, EVI2 time series were fitted using two different land surface phenology models: The Convex Quadratic model (CxQ), in which EVI2 = f(AGDD) and the Hybrid Piecewise Logistic Model (HPLM), in which EVI2 = f(day of year). Phenometrics and spectral variables were submitted separately and together to Random Forest Classifiers (RFC) to depict land use/land cover in Roberts County, South Dakota. HPLM RFC models showed slightly better accuracy than CxQ RFC models (about 1% relative higher in overall accuracy). Compared to phenometrically-based RFC models, spectrally-based RFC models yielded more accurate land cover maps, especially for non-crop cover types. However, the RFC models built from spectral variables could not accurately classify the wheat class, which contained mostly spring wheat with some fields in durum or winter varieties. The most accurate RFC models were obtained when using both phenometrics and spectral variables as inputs. The combined-variable RFC models overcame weaknesses of both phenometrically-based classification (low accuracy for non-vegetated covers) and spectrally-based classification (low accuracy for wheat). The analysis of important variables indicated that land cover classification for this study area was strongly driven by variables related to the initial green-up phase of seasonal growth and maximum fitted EVI2. For a deeper evaluation of RFC performance, RFC classifications were also executed with several alternative sampling scenarios, including different spatiotemporal filters to improve accuracy of sample pools and different sample sizes. Results indicated that a sample pool with less filtering yielded the most accurate predicted land cover map and a stratified random sample dataset covering approximately 0.25% or more of the study area were required to achieve an accurate land cover map. In case of data scarcity, a smaller dataset might be acceptable, but should not smaller than 0.05% of the study area.

scholarly journals Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series

2017 ◽  
Vol 9 (1) ◽  
pp. 95 ◽  
Author(s):  
Jordi Inglada ◽  
Arthur Vincent ◽  
Marcela Arias ◽  
Benjamin Tardy ◽  
David Morin ◽  
...  
Keyword(s):  
Time Series ◽  
High Resolution ◽  
Land Cover ◽  
Satellite Image ◽  
Land Cover Map

scholarly journals Long Time Series High-Quality and High-Consistency Land Cover Mapping Based on Machine Learning Method at Heihe River Basin

2021 ◽  
Vol 13 (8) ◽  
pp. 1596
Author(s):  
Bo Zhong ◽  
Aixia Yang ◽  
Kunsheng Jue ◽  
Junjun Wu
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Regional Scale ◽  
Heihe River ◽  
Land Cover Mapping ◽  
High Quality ◽  
Long Time Series ◽  
Training Samples ◽  
Long Time ◽  
Land Cover Map

Long time series of land cover changes (LCCs) are critical in the analysis of long-term climate, environmental, and ecological changes. Although several moderate to fine resolution global land cover datasets have been publicly released and they show strong consistency at the global scale, they have large deviations at the regional scale; furthermore, high-quality land cover datasets from before 2000 are not available and the classification consistency among different datasets is not very good. Thus, long time series of land cover datasets with high quality and consistency are in great demand but they are still unavailable, even at the regional scale. The Landsat series of satellite imagery composed of eight successive satellites can be traced back to 1972 and it is, therefore, possible to produce a long time series land cover dataset. In addition, the newly available satellite data have the capability to construct time series satellite images and a time series analysis method such as LCMM can be employed for making high-quality land cover datasets. Therefore, by taking the advantages of the two categories of satellite data, we proposed a new time series land cover mapping method based on machine learning and it, thereafter, is applied to Heihe River Basin (HRB) for verification purposes. Firstly, the high-quality land cover datasets at HRB from 2011–2015, which were retrieved using the LCMM method, are used for quickly and accurately making training samples. Secondly, a strategy for transferring the training samples after 2011 to earlier years is established. Thirdly, the random forest model is employed to train the selected yearly samples and a land cover map for every year is subsequently made. Finally, comprehensive analysis and validation are carried out for evaluation. In this study, a long time series land cover dataset including 1986, 1990, 1995, 2000, 2005, 2010, 2011, 2012, 2013, 2014, and 2015 is finally made and an average precision of about 90% is achieved. It is the longest time series land cover map with 30 m resolution at HRB and the dataset has good time continuity and stability.

scholarly journals ASSESSING THE ACCURACY OF LAND USE LAND COVER (LULC) MAPS USING CLASS PROPORTIONS IN THE REFERENCE DATA

2020 ◽  
Vol V-3-2020 ◽  
pp. 669-674 ◽  
Author(s):  
C. C. Fonte ◽  
L. See ◽  
J. C. Laso-Bayas ◽  
M. Lesiv ◽  
S. Fritz
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Reference Data ◽  
Accuracy Assessment ◽  
Reference Database ◽  
Data Sets ◽  
Land Use Land Cover ◽  
Data Set ◽  
Mixed Pixels ◽  
Land Cover Map

Abstract. Traditionally the accuracy assessment of a hard raster-based land use land cover (LULC) map uses a reference data set that contains one LULC class per pixel, which is the class that has the largest area in each pixel. However, when mixed pixels exist in the reference data, this is a simplification of reality that has implications for both the accuracy assessment and subsequent applications of LULC maps, such as area estimation. This paper demonstrates how the use of class proportions in the reference data set can be used easily within regular accuracy assessment procedures and how the use of class proportions can affect the final accuracy assessment. Using the CORINE land cover map (CLC) and the more detailed Urban Atlas (UA), two accuracy assessments of the raster version of CLC were undertaken using UA as the reference and considering for each pixel: (i) the class proportions retained from the UA; and (ii) the class with the majority area. The results show that for the study area and the classes considered here, all accuracy indices decrease when the class proportions are considered in the reference database, achieving a maximum difference of 16% between the two approaches. This demonstrates that if the UA is considered as representing reality, then the true accuracy of CLC is lower than the value obtained when using the reference data set that assigns only one class to each pixel. Arguments for and against using class proportions in reference data sets are then provided and discussed.

Studying of Land Cover And Use Maps of South Asia Regions From 2001 To 2015 With AVHRR And MODIS Data

2021 ◽  
Author(s):  
Shahzad Ali ◽  
Huang An Qi ◽  
Malak Henchiri ◽  
Zhang Sha ◽  
Fahim Ullah Khan ◽  
...  
Keyword(s):  
Time Series ◽  
Land Cover ◽  
South Asia ◽  
Earth Science ◽  
Regional Climate ◽  
The South ◽  
Time Dynamics ◽  
Modis Data ◽  
Land Cover Map ◽  
Gimms Ndvi3g

Abstract In South Asia, annual land cover and land use (LCLU) is a severe issue in the field of earth science because it affects regional climate, global warming, and human activities. Therefore, it is vital essential to obtain correct information on the LCLU in the South Asia regions. LULC annual map covering the entire period is the primary dataset for climatological research. Although the LULC annual global map was produced from the MODIS dataset in 2001, this limited the perspective of the climatological analysis. This study used AVHRR GIMMS NDVI3g data from 2001 to 2015 to randomly forests classify and produced a time series of the annual LCLU map of the South Asia. The MODIS land cover products (MCD12Q1) are used as data from reference for trained classifiers. The results were verified using of the annual map of LCLU time series, and the space-time dynamics of the LCLU map were shown in the last 15 years, from 2001 to 2015. The overall precision of our 15-year land cover map simplifies 16 classes, which is 1.23% and 86.70% significantly maximum as compared to the precision of the MODIS data map. Findings of the past 15 years shows the changing detection that forest land, savanna, farmland, urban and established land, arid land, and cultivated land have increased; by contrast, woody prairie, open shrub-lands, permanent ice and snow, mixed forests, grasslands, evergreen broadleaf forests, permanent wetlands, and water bodies have been significantly reduced over South Asia regions.

scholarly journals Multi-Type Forest Change Detection Using BFAST and Monthly Landsat Time Series for Monitoring Spatiotemporal Dynamics of Forests in Subtropical Wetland

2020 ◽  
Vol 12 (2) ◽  
pp. 341 ◽  
Author(s):  
Ling Wu ◽  
Zhaoliang Li ◽  
Xiangnan Liu ◽  
Lihong Zhu ◽  
Yibo Tang ◽  
...  
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Dongting Lake ◽  
Spatiotemporal Dynamics ◽  
Data Availability ◽  
Rapid Expansion ◽  
Core Zone ◽  
The Core ◽  
Subtropical Wetland ◽  
Ndvi Time Series

Land cover changes, especially excessive economic forest plantations, have significantly threatened the ecological security of West Dongting Lake wetland in China. This work aimed to investigate the spatiotemporal dynamics of forests in the West Dongting Lake region from 2000 to 2018 using a reconstructed monthly Landsat NDVI time series. The multi-type forest changes, including conversion from forest to another land cover category, conversion from another land cover category to forest, and conversion from forest to forest (such as flooding and replantation post-deforestation), and land cover categories before and after change were effectively detected by integrating Breaks For Additive Seasonal and Trend (BFAST) and random forest algorithms with the monthly NDVI time series, with an overall accuracy of 87.8%. On the basis of focusing on all the forest regions extracted through creating a forest mask for each image in time series and merging these to produce an ‘anytime’ forest mask, the spatiotemporal dynamics of forest were analyzed on the basis of the acquired information of multi-type forest changes and classification. The forests are principally distributed in the core zone of West Donting Lake surrounding the water body and the southwestern mountains. The forest changes in the core zone and low elevation region are prevalent and frequent. The variation of forest areas in West Dongting Lake experienced three steps: rapid expansion of forest plantation from 2000 to 2005, relatively steady from 2006 to 2011, and continuous decline since 2011, mainly caused by anthropogenic factors, such as government policies and economic profits. This study demonstrated the applicability of the integrated BFAST method to detect multi-type forest changes by using dense Landsat time series in the subtropical wetland ecosystem with low data availability.

scholarly journals A Suite of Tools for Continuous Land Change Monitoring in Google Earth Engine

2020 ◽  
Vol 2 ◽  
Author(s):  
Paulo Arévalo ◽  
Eric L. Bullock ◽  
Curtis E. Woodcock ◽  
Pontus Olofsson
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Land Cover Change ◽  
Google Earth ◽  
Data Availability ◽  
Ecosystem Change ◽  
Series Data ◽  
Land Change ◽  
Continuous Change ◽  
Google Earth Engine

Land cover has been designated by the Global Climate Observing System (GCOS) as an Essential Climate Variable due to its integral role in many climate and environmental processes. Land cover and change affect regional precipitation patterns, surface energy balance, the carbon cycle and biodiversity. Accurate information on land cover and change is essential for climate change mitigation programs such as UN-REDD+. Still, uncertainties related to land change are large, in part due to the use of traditional land cover and change mapping techniques that use one or a few remotely sensed images, preventing a comprehensive analysis of ecosystem change processes. The opening of the Landsat archive and the initiation of the Copernicus Program have enabled analyses based on time series data, allowing the scientific community to explore global land cover dynamics in ways that were previously limited by data availability. One such method is the Continuous Change Detection and Classification algorithm (CCDC), which uses all available Landsat data to model temporal-spectral features that include seasonality, trends, and spectral variability. Until recently, the CCDC algorithm was restricted to academic environments due to computational requirements and complexity, preventing its use by local practitioners. The situation has changed with the recent implementation of CCDC in the Google Earth Engine, which enables analyses at global scales. What is still missing are tools that allow users to explore, analyze and process CCDC outputs in a simplified way. In this paper, we present a suite of free tools that facilitate interaction with CCDC outputs, including: (1) time series viewers of CCDC-generated time segments; (2) a spatial data viewer to explore CCDC model coefficients and derivatives, and visualize change information; (3) tools to create land cover and land cover change maps from CCDC outputs; (4) a tool for unbiased area estimation of key climate-related variables like deforestation extent; and (5) an API for accessing the functionality underlying these tools. We illustrate the usage of these tools at different locations with examples that explore Landsat time series and CCDC coefficients, and a land cover change mapping example in the Southeastern USA that includes area and accuracy estimates.

Sign in / Sign up

Export Citation Format

Share Document