Time Series Of Imagery Research Articles

Comparison of Physical-Based Models to Measure Forest Resilience to Fire as a Function of Burn Severity

We aimed to compare the potential of physical-based models (radiative transfer and pixel unmixing models) for evaluating the short-term resilience to fire of several shrubland communities as a function of their regenerative strategy and burn severity. The study site was located within the perimeter of a wildfire that occurred in summer 2017 in the northwestern Iberian Peninsula. A pre- and post-fire time series of Sentinel-2 satellite imagery was acquired to estimate fractional vegetation cover (FVC) from the (i) PROSAIL-D radiative transfer model inversion using the random forest algorithm, and (ii) multiple endmember spectral mixture analysis (MESMA). The FVC retrieval was validated throughout the time series by means of field data stratified by plant community type (i.e., regenerative strategy). The inversion of PROSAIL-D featured the highest overall fit for the entire time series (R2 > 0.75), followed by MESMA (R2 > 0.64). We estimated the resilience of shrubland communities in terms of FVC recovery using an impact-normalized resilience index and a linear model. High burn severity negatively influenced the short-term resilience of shrublands dominated by facultative seeder species. In contrast, shrublands dominated by resprouters reached pre-fire FVC values regardless of burn severity.

Towards an Automated Approach for Monitoring Tree Phenology Using Vehicle Dashcams in Urban Environments.

Trees in urban environments hold significant value in providing ecosystem services, which will become increasingly important as urban populations grow. Tree phenology is highly sensitive to climatic variation, and resultant phenological shifts have significant impact on ecosystem function. Data on urban tree phenology is important to collect. Typical remote methods to monitor tree phenological transitions, such as satellite remote sensing and fixed digital camera networks, are limited by financial costs and coarse resolutions, both spatially and temporally and thus there exists a data gap in urban settings. Here, we report on a pilot study to evaluate the potential to estimate phenological metrics from imagery acquired with a conventional dashcam fitted to a car. Dashcam images were acquired daily in spring 2020, March to May, for a 2000 m stretch of road in Melksham, UK. This pilot study indicates that time series imagery of urban trees, from which meaningful phenological data can be extracted, is obtainable from a car-mounted dashcam. The method based on the YOLOv3 deep learning algorithm demonstrated suitability for automating stages of processing towards deriving a greenness metric from which the date of tree green-up was calculated. These dates of green-up are similar to those obtained by visual analyses, with a maximum of a 4-day difference; and differences in green-up between trees (species-dependent) were evident. Further work is required to fully automate such an approach for other remote sensing capture methods, and to scale-up through authoritative and citizen science agencies.

A Review of Spectral Indices for Mangrove Remote Sensing

Mangrove ecosystems provide critical goods and ecosystem services to coastal communities and contribute to climate change mitigation. Over four decades, remote sensing has proved its usefulness in monitoring mangrove ecosystems on a broad scale, over time, and at a lower cost than field observation. The increasing use of spectral indices has led to an expansion of the geographical context of mangrove studies from local-scale studies to intercontinental and global analyses over the past 20 years. In remote sensing, numerous spectral indices derived from multiple spectral bands of remotely sensed data have been developed and used for multiple studies on mangroves. In this paper, we review the range of spectral indices produced and utilised in mangrove remote sensing between 1996 and 2021. Our findings reveal that spectral indices have been used for a variety of mangrove aspects but excluded identification of mangrove species. The included aspects are mangrove extent, distribution, mangrove above ground parameters (e.g., carbon density, biomass, canopy height, and estimations of LAI), and changes to the aforementioned aspects over time. Normalised Difference Vegetation Index (NDVI) was found to be the most widely applied index in mangroves, used in 82% of the studies reviewed, followed by the Enhanced Vegetation Index (EVI) used in 28% of the studies. Development and application of potential indices for mangrove cover characterisation has increased (currently 6 indices are published), but NDVI remains the most popular index for mangrove remote sensing. Ultimately, we identify the limitations and gaps of current studies and suggest some future directions under the topic of spectral index application in connection to time series imagery and the fusion of optical sensors for mangrove studies in the digital era.

Cross-phenological-region crop mapping framework using Sentinel-2 time series Imagery: A new perspective for winter crops in China

Precise large-area crop mapping products are the foundation for cropland monitoring, market policy decision-making, and subsequent agricultural applications. However, owing to sharp discrepancies among the temporal-spectral attributes of crops from different areas, crop mapping across phenological regions faces significant challenges. Given the inadequacy of generalizing mapping frameworks from the source to target regions, research areas are often limited, and trained models cannot be reused beyond a particular study area. In this paper, we propose a novel framework called the Phenology Alignment Network (PAN) to address the cross-phenological-region (CPR) crop-mapping problem using deep recurrent networks and unsupervised domain adaptation. Our PAN adopts a Siamese structure consisting of two identical deep models called the Temporal Spectral Network (TSNet), which serves as an adaptive multilevel phenological feature extractor for crops under various planting conditions. Specifically, the two branches of PAN accept crop samples from the source and target regions, and aim to encode them into similar deep phenological features. By constraining the distribution of hidden states from the two branches, the deep temporal-spectral features are aligned, and regional discrepancies between the source and target regions are alleviated. Consequently, the PAN adapts the deep model pretrained on the source region to the target area, improving the mapping accuracy without using additional target label information. To verify the effectiveness of our model, crop samples were collected from three plains of China, and a winter crop dataset based on Sentinel-2 time-series imagery containing over two million pixels was annotated. Experiments conducted on this dataset indicate that PAN serves as a practical CPR crop mapping framework and achieves significant improvement in the overall accuracy as well as the macro-average F1 score compared to other state-of-the-art methods. Further visual interpretation illustrates the capability of PAN to correct inaccurate predictions ascribed to phenological diversity and suggests the potential of PAN for large-area crop mapping applications.

Characterizing ecosystem change in wetlands using dense earth observation time series

Wetlands in drylands are vulnerable to degradation and disappearance due to the combined effects of increasing anthropogenic disturbances and climatic extremes. Such influences may drive non-linear shifts in surface responses that require long-term monitoring approaches for their study. Here, we used a piece-wise regression model to characterize long-term Ecosystem Change Types (ECT) in the surface water and vegetation dynamics of the Inner Niger Delta wetlands in Mali between 2000 and 2019. We also examined the added benefits of using a dense Landsat time series for such segmented trend analysis in comparison with MODIS products that are regularly used for ecosystem trends assessment. Our approach has found statistically significant (p < 0.05) long-term changes in wetland ecosystems, as calculated from Modified Normalized Difference Water Index (MNDWI) and Normalized Difference Vegetation Index (NDVI) image series on both the MODIS and the Landsat scales. The class-specific accuracies of the detected ECTs were evaluated through the validation of temporal trajectories based on the TimeSync logic at selected probability sample locations. Results showed higher user's, producer's, and overall accuracies (OA) when using a dense Landsat time series (OA = 0.89 ± 0.01), outperforming the MOD09A1 time series (OA = 0.37 ± 0.03). Our study provides a robust framework for long-term wetland monitoring that demonstrates the benefits of applying dense Landsat time-series imagery for accurate quantifications of linear and non-linear ecosystem responses in vast highly dynamic floodplain systems. Delivering such an improved assessment, in a spatial resolution that better resolves the characteristics of wetlands ecosystems, has the potential to support the information needs of global conservation and restoration efforts.

Time series analysis of the Caspian Sea shoreline in response to sea level fluctuation using remotely sensed data

The Caspian Sea (CS), biggest inland water worldwide has experienced around 3 m oscillation in sea level during the 20th century. These rapid sea level fluctuations have had a great impact on the coastal habitat around this sea. Therefore, this study is aimed to investigate the long-term changes of the western part of the Caspian Sea shoreline and Anzali lagoon and their dynamic responses to the sea level fluctuation using time series analysis of remotely sensed data over the 40-years. To this end, the long-term Caspian Sea shoreline and the area and perimeter of the Anzali Lagoon were extracted from the time series of Landsat satellite imagery (1975 till 2016) by using an automatic procedure including the combination of the Tasseled-Cap and texture filter methods. Afterwards, shoreline erosion/accretion rates were evaluated by using the Net Shoreline Movement (NSM) and End Point Rate (EPR) techniques. Finally, the sea level changes of the CS, were extracted through the multiple altimetry satellite data and the relationship between the relative sea level fluctuation and CS shoreline and Anzali lagoon area were studied. Results of the changes of shoreline positions over the study period (1975–2016) indicate that the whole coastal study area is subjected to accretion and erosion of 20.37 and -19.22 (m/year) respectively. There is balance between the whole EPR in all transects and periods between 1975 and 2016. This shows that when erosion happens in a region, accretion will be happened in another region, and this behavior is symmetrical. When the sea level decreased, the EPR values showed the accretion/seaward and vice versa. So, the shoreline movement has a strong nonlinear response to the sea level fluctuation with a coefficient of determination of −0.66. Also results show the strong response of the Anzali lagoon to the sea level fluctuation with a coefficient of determination of 0.78 for a nonlinear relationship between the changes of area of Anzali Lagoon and the CS fluctuation. This lagoon experienced the greatest and lowest values of its area on 2003 and 1985, respectively, which are matched with the high and low stands of the Caspian Sea Level.

Diachronic analysis to Detect and Monitor Barchan Dune Migration in Ain Salah (Algeria)

The aim of this work is to analyse barchan dunes migration patterns and their effect on urban and agricultural areas in Ain Salah region in southern Algeria. A supervised classification of Landsat images over a 13 years period (2005, 2009, 2013 and 2017) was applied to create land cover maps which were used for a spatiotemporal monitoring of barchan migration by dune feature changes. The results show that sand dunes covered area has increased between 2005 and 2017 with direction movements from northeast to southwest and represents the potential of using time series imagery for a better understanding of dune migration and sand encroachment.

Estimate the Earliest Phenophase for Garlic Mapping Using Time Series Landsat 8/9 Images

Garlic is the major economic crop in China. Timely and accurate identification and mapping of garlic are significant for garlic yield prediction and garlic market management. Previous studies on garlic mapping were mainly based on all observations of the entire growing season, so the resulting maps have a hysteresis. Here, we determined the optimal identification strategy and the earliest identifiable phenophase for garlic based on all available Landsat 8/9 time series imagery in Google Earth Engine. Specifically, we evaluated the performance of different vegetation indices for each phenophase to determine the optimal classification metrics for garlic. Secondly, we identified garlic using random forest algorithm and classification metrics of different time series lengths. Finally, we determined the earliest identifiable phenophase of garlic and generated an early-season garlic distribution map. Garlic could be identified as early as March (bud differentiation period) with an F1 of 0.91. Our study demonstrates the differences in the performance of vegetation indices at different phenophases, and these differences provide a new idea for mapping crops. The generated early-season garlic distribution map provides timely data support for various stakeholders.

Small dams: determining the minimum waterbody surface area that can be successfully detected using Sentinel-1 SAR imagery

Water is a scarce resource in South Africa, and approximately 62% of the water used in South Africa is for irrigation. This water is stored in many small dams scattered across the country. If not managed correctly, they could have a negative effect on catchment areas and on the availability of water. As such, there is a need for a new monitoring and management system to be developed. This study determined the minimum surface area that would be required for a waterbody to be detected on Sentinel-1 Synthetic Aperture Radar imagery. A Random Forest classifier was used to detect waterbodies on a Sentinel-1 image calculated from a time series of imagery taken over a period of three months. Steep incidence angles outperformed shallow incidence angles, with the classification having an overall accuracy of 80%. Detection rates were almost 90% for waterbodies of one hectare and greater, with no false positives, and a 10% false negative rate. These findings provide the foundation for developing a detection and monitoring system, which would allow for the better management of water resources in South Africa.

Deforestation, plantation-related land cover dynamics and oil palm age-structure change during 1990–2020 in Riau Province, Indonesia

The expansion of plantations, such as oil palm, in Indonesia has caused large-scale deforestation. Loss of tropical forest, in particular peatland forest, is a major ecological and environmental threat as well as a source of atmospheric carbon emissions. Understanding the spatio-temporal dynamics of plantation expansion may illuminate pathways to reduce deforestation while maintaining high yields in existing plantations. Beyond mapping forest conversion to plantations, it is also important to understand post-conversion plantation success and crop age. In the case of oil palm, the typical productive lifespan is 25–30 years before replanting or conversion to other land use becomes necessary. Knowledge about the extent of oil palm in different productive growth stages is important for yield estimation and improving management strategies. This study characterizes the land-cover and land-use changes inherent to oil palm plantation expansion and age-structured oil palm dynamics across Riau, the province with the greatest production of oil palm in Indonesia, using a 30 year time-series of Landsat satellite imagery. From 1990 to 2020, Riau lost 4.63 M ha of forest, while oil palm extent grew six-fold, reaching an estimated 3.52 M ha in 2020. Rapid expansion of oil palm plantations in Riau resulted in the predominance of younger age classes (<10 yr-old) and rapidly increasing yields during 2010–2020. Conversion dynamics changed over time such that, after 2014, the <10 yr age class declined by 14%, whereas the 10–20 yr-old (peak yield stage) and ⩾20 yr-old (decline stage) age classes increased by 11% and 3%, respectively. In 28 years of observation (1992–2020), 41% of oil palm planted between 1990 and 1992 underwent at least one cycle of replanting in Riau.

Satellite based lake bed elevation model of Lake Urmia using time series of Landsat imagery

This study presents a lake bed elevation model of Lake Urmia. In the course of model generation, a time series of the extent of the lake surface was derived from 129 satellite images with different acquisition dates based on the Landsat sensors Thematic Mapper (TM), Enhanced Thematic Mapper Plus (ETM+), and Operational Land Imager (OLI). Due to the rapid shrinking of the lake during the last two decades, lake surface areas ranging from 890 km2 to 6125 km2 could be covered. The water edge of the various lake extents was then linked to the observed water level on the day of the satellite image acquisition. The resulting contour lines, covering water levels between 1270.04 m and 1278.42 m a.s.l. and thus representing the lakebed morphology in its shallow parts, were merged with existing data (deeper parts) and interpolated to generate a lake bed elevation model. Finally, Lake Urmia’s Level-Area-Volume relationships were derived from the lake bed elevation model and compared to bathymetric data previously published.

Time-series metrics applied to land use and land cover mapping with focus on landslide detection

Landslides are a recurring phenomenon in Brazil and have caused many socioeconomic losses and casualties. To monitor them, land use and land cover (LULC) and landslide inventory maps are essential to identifying high susceptibility areas. In this sense, the main aim of this study is to produce LULC classification focused on landslide detection via semi-automatic methods, using data mining techniques with remote sensing time-series imagery. For that, different indices, such as the normalized difference vegetation index, the normalized difference built-up index (NDBI), and the soil adjusted vegetation index were extracted from Sentinel-2 imagery. Basic, polar, and fractal metrics were extracted from the time series. From the Shuttle Radar Topography Mission digital elevation model, six geomorphometric features were extracted. Then, classification was performed with random forest with four different approaches: mono-temporal, bi-temporal, metrical, and all. In every approach, the NDBI index or metric derived from it presented the highest importance, and the slope was ranked among the six first predictors. The all approach showed the highest overall accuracy (OA) (88.96%), followed by metrical (87.90%), bi-temporal (82.59%), and mono-temporal (74.95%). Briefly, the metrical approach presented the most beneficial result, presenting high OA and low levels of commission and omission errors.

Nightlight Intensity Change Surrounding Nature Reserves: A Case Study in Orbroicher Bruch Nature Reserve, Germany

Persistent global urbanization has a direct relationship to measurable artificial light at night (ALAN), and the Defense Meteorological Satellite Program has served an important role in monitoring this relationship over time. Recent studies have observed significant declines in insect abundance and populations, and ALAN has been recognized as a contributing factor. We investigated changes in nightlight intensity at various spatial scales surrounding insect traps located in Orbroicher Bruch Nature Reserve, Germany. Using a time series of global nighttime light imagery (1992–2010), we evaluated pixel-level trends through linear regressions and the Mann–Kendall test. Paired with urban land cover delineation, we compared nightlight trends across rural and urban areas. We utilized high-resolution satellite imagery to identify landscape features potentially related to pixel-level trends within areas containing notable change. Approximately 96% of the pixel-level trends had a positive slope, and 22% of pixels experienced statistically significant increases in nightlight intensity. We observed that 80% of the region experienced nightlight intensity increases &gt;1%, concurrent with the observed decline in insect biomass. While it is unclear if these trends extend to other geographic regions, our results highlight the need for future studies to concurrently investigate long-term trends in ALAN and insect population decline across multiple scales, and consider the spatial and temporal overlaps between these patterns.

Surface-area development of foredune trough blowouts and associated parabolic dunes quantified from time series of satellite imagery

• Blowout surface area quantified from medium-scale satellite imagery. • Blowouts grow, stabilize and decay with a life time exceeding multiple decades. • Seasonal variation in blowout area increases with latitude. • Foredune erosion results in episodic, yet temporary increase in blowout surface area. Foredune trough blowouts are elongated wind-eroded depressions in the most seaward dune and their adjoining depositional lobes. Despite their importance to the sand budget and floral diversity of coastal dunes, the spatiotemporal evolution of trough blowouts is not well understood. We designed an automated workflow in the Google Earth Engine platform to produce time series of blowout surface area from medium-resolution satellite imagery available since the mid-1980s and applied it to a blowout system in the Netherlands, Denmark and the USA. Blowout surface areas were found to vary on multi-annual, seasonal and episodic time scales. Multi-annual change reflects successive development through stages of growth, stabilization and decay. The transition from growth to stabilization appears to be related to a change in blowout shape (width-to-length ratio). The decay phase starts with vegetation obstructing the blowout connection to the beach; the lobe can still migrate inland and develop into a parabolic dune before also becoming fully vegetated. The seasonal variations in blowout area increase with latitude; the observed larger areas in winter at the Dutch and Danish site presumably reflect seasonal plant development and the effect of stronger winds in winter. Episodic increases in blowout area, observed during winter at the Danish site only, are associated with pronounced foredune erosion. None of the episodic events changed blowouts into a different stage or persistently affected seasonal dynamics. Future work should focus on the combined analysis of changes in blowout area and sand volume to improve our understanding of sand-vegetation interactions driving blowout dynamics.

Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery

AbstractDepleting lake ice is a climate change indicator, just like sea-level rise or glacial retreat. Monitoring Lake Ice Phenology (LIP) is useful because long-term freezing and thawing patterns serve as sentinels to understand regional and global climate change. We report a study for the Oberengadin region of Switzerland, where several small- and medium-sized mountain lakes are located. We observe the LIP events, such as freeze-up, break-up and ice cover duration, across two decades (2000–2020) from optical satellite images. We analyse the time series of MODIS imagery by estimating spatially resolved maps of lake ice for these Alpine lakes with supervised machine learning. To train the classifier we rely on reference data annotated manually based on webcam images. From the ice maps, we derive long-term LIP trends. Since the webcam data are only available for two winters, we cross-check our results against the operational MODIS and VIIRS snow products. We find a change in complete freeze duration of $$-\,0.76$$ - 0.76 and $$-\,0.89$$ - 0.89 days per annum for lakes Sils and Silvaplana, respectively. Furthermore, we observe plausible correlations of the LIP trends with climate data measured at nearby meteorological stations. We notice that mean winter air temperature has a negative correlation with the freeze duration and break-up events and a positive correlation with the freeze-up events. Additionally, we observe a strong negative correlation of sunshine during the winter months with the freeze duration and break-up events.

Evaluating Effects of Post-Fire Climate and Burn Severity on the Early-Term Regeneration of Forest and Shrub Communities in the San Gabriel Mountains of California from Sentinel-2(MSI) Images

Studying the early changes in post-fire vegetation communities may improve the overall resilience of forests. The necessity for doing so was demonstrated by the Bobcat Fire, which seriously threatened the central San Gabriel Mountains and the Angeles National Forest in California. This study aimed to monitor and quantify the effects of climatological and topographic conditions along with burn severity on early (within 1 year) post-fire forests and shrubs community regeneration. In this study, we used Sentinel-2(MSI) intensive time-series imagery (July 2020–October 2021) to make a confusion matrix combined with 389 vegetation sample points on Google Earth Pro. The overall accuracy (OA) and the Kappa coefficient, calculated from the confusion matrix, were used as evaluation parameters to validate the classification results. With multiple linear regression models and Environmental Systems Research Institute (ESRI) historical images, we analyzed the effects of climate and slope aspects on the regeneration of post-fire forest and shrub communities. We also quantitatively analyzed the regeneration rates based on five burn severity types. The results show that the normalized burning rate (NBR) was the most accurate vegetation classification indicator in this study (OA: 92.3–99.5%, Kappa: 0.88–0.98). The vegetation classification accuracy based on SVM is about 6.6% higher than K-Means. The overall accuracy of the burn area is 94.87%. Post-fire climate factors had a significant impact on the regeneration of the two vegetation communities (R2: 0.42–0.88); the optimal regeneration slope was 15–35°; and the fire severity changed the original competition relationship and regeneration rate. The results provide four main insights into the regeneration of post-fire vegetation communities: (1) climate factors in the first regenerating season have important impacts on the regeneration of forest and shrub communities; (2) daytime duration and rainfall are the most significant factors for forests and shrubs regeneration; (3) tolerable low burn severity promotes forests regeneration; and (4) forests have a certain ability to resist fires, while shrubs can better tolerate high-intensity fire ecology. This study could support the implementation of strategies for regionalized forest management and the targeted enhancement of post-fire vegetation community resilience.

Medium Spatial Resolution Mapping of Global Land Cover and Land Cover Change Across Multiple Decades From Landsat

Land cover maps are essential for characterizing the biophysical properties of the Earth’s land areas. Because land cover information synthesizes a rich array of information related to both the ecological condition of land areas and their exploitation by humans, they are widely used for basic and applied research that requires information related to land surface properties (e.g., terrestrial carbon models, water balance models, weather, and climate models) and are core inputs to models and analyses used by natural resource scientists and land managers. As the Earth’s global population has grown over the last several decades rates of land cover change have increased dramatically, with enormous impacts on ecosystem services (e.g., biodiversity, water supply, carbon sequestration, etc.). Hence, accurate information related to land cover is essential for both managing natural resources and for understanding society’s ecological, biophysical, and resource management footprint. To address the need for high-quality land cover information we are using the global record of Landsat observations to compile annual maps of global land cover from 2001 to 2020 at 30 m spatial resolution. To create these maps we use features derived from time series of Landsat imagery in combination with ancillary geospatial data and a large database of training sites to classify land cover at annual time step. The algorithm that we apply uses temporal segmentation to identify periods with stable land cover that are separated by breakpoints in the time series. Here we provide an overview of the methods and data sets we are using to create global maps of land cover. We describe the algorithms used to create these maps and the core land cover data sets that we are creating through this effort, and we summarize our approach to accuracy assessment. We also present a synthesis of early results and discuss the strengths and weaknesses of our early map products and the challenges that we have encountered in creating global land cover data sets from Landsat. Initial accuracy assessment for North America shows good overall accuracy (77.0 ± 2.0% correctly classified) and 79.8% agreement with the European Space Agency (ESA) WorldCover product. The land cover mapping results we report provide the foundation for robust, repeatable, and accurate mapping of global land cover and land cover change across multiple decades at 30 m spatial resolution from Landsat.

A high-accuracy genotype classification approach using time series imagery

Genotype classification plays a vital role in cultivar evaluation, selection, and production. However, classifying plant genotypes by phenotypes remains an unresolved issue. In this paper, a high-accuracy approach is proposed for plant genotype classification. Based on the Densenet201 and bi-directional Long Short-Term Memory model (bi-directional LSTM), a Densenet201-BLSTM model is given in the approach for classifying various genotypes based on time series of plant images. The growth and development dynamic behaviours and important phenotypes of plants are bi-directionally encoded by the proposed Densenet201-BLSTM to model the complex relationship between phenotypes and genotypes. The accuracy of genotype classification obtained by the proposed DenseNet201-BLSTM model on the test dataset reaches 98.31%. The first attempt is made to classify genotypes of panicoid grain crops . What's more, the proposed genotype classification approach will be useful for the classification of progeny accessions based on their similarity to reference accessions. • A high-accuracy approach of plant genotype classification is proposed. • Genotypes were classified by simultaneously considering spatiotemporal features. • The first attempt is made to classify genotypes of panicoid grain crops. • This study provides the foundation for genotype–phenotype correlation research.

Sub-pixel building area mapping based on synthetic training data and regression-based unmixing using Sentinel-1 and -2 data

ABSTRACT The identification of buildings has become a major research focus of settlement mapping with Earth Observation data. Building area or building footprint data is particularly required in research related to population, such as disaster risk management or urban health. This study examined the suitability of machine learning regression-based unmixing for quantifying the pixel-wise share of building area with decametre resolution Copernicus Sentinel-1 and Sentinel-2 imagery. Compared to using a single-step approach directly estimating building area, leading to an over-estimation of building area compared to non-building impervious surface area due to feature similarity, the introduction of a hierarchical approach considerably improved mapping results. While the original mapping resolution was 10 m, we found that building area was most accurately mapped starting at a spatial resolution of 100 m – a resolution well suitable for many urban applications. The proposed approach is widely transferable in space as it used spatially robust spectral-temporal metrics from time series imagery and as its requirements for training data are very limited.

THE EUROSDR TIME BENCHMARK FOR HISTORICAL AERIAL IMAGES

Abstract. Automatic photogrammetric processing of historical (or archival) aerial photos is still a challenging task, particularly in cases of missing ancillary information, low radiometric and image quality, limited stereo coverage or large temporal span. However, with recent advances in photogrammetry and Artificial Intelligence (AI) algorithms for image processing and interpretation, an increasing number of applications are now feasible. The article presents the TIME (hisTorical aerIal iMagEs) benchmark (https://time.fbk.eu/), promoted by EuroSDR to explore the potential of historical aerial images. Realized in collaboration with various European NMCAs, the benchmark has garnered aerial image blocks and time series imagery captured since the 1950s. To support the photogrammetric processing of the digitized photos, ancillary data are supplied with available information about flight missions, taking cameras, and ground control points (GCPs). Several diverse investigations have been undertaken with the benchmark datasets, all captured over historical urban areas or landscapes. The paper describes the benchmark datasets and some potential research topics, presenting several tests and analyses realized with the collated and shared data.