Explore the vast range of titles available.

In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.

Asia dominates the world’s aquaculture sector, generating almost 90 percent of its total annual global production. Fish, shrimp, and mollusks are mainly farmed in land-based pond aquaculture systems and serve as a primary protein source for millions of people. The total production and area occupied for pond aquaculture has expanded rapidly in coastal regions in Asia since the early 1990s. The growth of aquaculture was mainly boosted by an increasing demand for fish and seafood from a growing world population. The aquaculture sector generates income and employment, contributes to food security, and has become a billion-dollar industry with high socio-economic value, but has also led to severe environmental degradation. In this regard, geospatial information on aquaculture can support the management of this growing food sector for the sustainable development of coastal ecosystems, resources, and human health. With free and open access to the rapidly growing volume of data from the Copernicus Sentinel missions as well as machine learning algorithms and cloud computing services, we extracted coastal aquaculture at a continental scale. We present a multi-sensor approach that utilizes Earth observation time series data for the mapping of pond aquaculture within the entire Asian coastal zone, defined as the onshore area up to 200 km from the coastline. In this research, we developed an object-based framework to detect and extract aquaculture at a single-pond level based on temporal features derived from high-spatial-resolution SAR and optical satellite data acquired from the Sentinel-1 and Sentinel-2 satellites. In a second step, we performed spatial and statistical data analyses of the Earth-observation-derived aquaculture dataset to investigate spatial distribution and identify production hotspots at various administrative units at regional, national, and sub-national scale.

Drought is a recurring natural climatic hazard event over terrestrial land; it poses devastating threats to human health, the economy, and the environment. Given the increasing climate crisis, it is likely that extreme drought phenomena will become more frequent, and their impacts will probably be more devastating. Drought observations from space, therefore, play a key role in dissimilating timely and accurate information to support early warning drought management and mitigation planning, particularly in sparse in-situ data regions. In this paper, we reviewed drought-related studies based on Earth observation (EO) products in Southeast Asia between 2000 and 2021. The results of this review indicated that drought publications in the region are on the increase, with a majority (70%) of the studies being undertaken in Vietnam, Thailand, Malaysia and Indonesia. These countries also accounted for nearly 97% of the economic losses due to drought extremes. Vegetation indices from multispectral optical remote sensing sensors remained a primary source of data for drought monitoring in the region. Many studies (~21%) did not provide accuracy assessment on drought mapping products, while precipitation was the main data source for validation. We observed a positive association between spatial extent and spatial resolution, suggesting that nearly 81% of the articles focused on the local and national scales. Although there was an increase in drought research interest in the region, challenges remain regarding large-area and long time-series drought measurements, the combined drought approach, machine learning-based drought prediction, and the integration of multi-sensor remote sensing products (e.g., Landsat and Sentinel-2). Satellite EO data could be a substantial part of the future efforts that are necessary for mitigating drought-related challenges, ensuring food security, establishing a more sustainable economy, and the preservation of the natural environment in the region.

Human settlements are the cause and consequence of most environmental and societal changes on Earth; however, their location and extent is still under debate. We provide here a new 10 m resolution (0.32 arc sec) global map of human settlements on Earth for the year 2015, namely the World Settlement Footprint 2015 (WSF2015). The raster dataset has been generated by means of an advanced classification system which, for the first time, jointly exploits open-and-free optical and radar satellite imagery. The WSF2015 has been validated against 900,000 samples labelled by crowdsourcing photointerpretation of very high resolution Google Earth imagery and outperforms all other similar existing layers; in particular, it considerably improves the detection of very small settlements in rural regions and better outlines scattered suburban areas. The dataset can be used at any scale of observation in support to all applications requiring detailed and accurate information on human presence (e.g., socioeconomic development, population distribution, risks assessment, etc.). Measurement(s) global settlement extent Technology Type(s) satellite imaging • machine learning Factor Type(s) geographic location Sample Characteristic - Environment anthropogenic environment • populated place Sample Characteristic - Location Earth (planet) Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.12424970

Vietnam’s 3260 km coastline is densely populated, experiences rapid urban and economic growth, and faces at the same time a high risk of coastal hazards. Satellite archives provide a free and powerful opportunity for long-term area-wide monitoring of the coastal zone. This paper presents an automated analysis of coastline dynamics from 1986 to 2021 for Vietnam’s entire coastal zone using the Landsat archive. The proposed method is implemented within the cloud-computing platform Google Earth Engine to only involve publicly and globally available datasets and tools. We generated annual coastline composites representing the mean-high water level and extracted sub-pixel coastlines. We further quantified coastline change rates along shore-perpendicular transects, revealing that half of Vietnam’s coast did not experience significant change, while the remaining half is classified as erosional (27.7%) and accretional (27.1%). A hotspot analysis shows that coastal segments with the highest change rates are concentrated in the low-lying deltas of the Mekong River in the south and the Red River in the north. Hotspots with the highest accretion rates of up to +47 m/year are mainly associated with the construction of artificial coastlines, while hotspots with the highest erosion rates of −28 m/year may be related to natural sediment redistribution and human activity.

Rising sea levels, warming ocean temperatures, and other climate change impacts threaten the German North Sea coast, making monitoring of this system even more critical. This study reviews the potential of remote sensing for the German North Sea coast, analyzing 97 publications from 2000 to 2024. Publications fell into four main research topics: coastal morphology (33), water quality (34), ecology (22), and sediment (8). More than two-thirds of these papers (69%) used satellite platforms, whereas about one third (29%) used aircrafts and very few (4%) used uncrewed aerial vehicles (UAVs). Multispectral data were the most used data type in these studies (59%), followed by synthetic aperture radar data (SAR) (23%). Studies on intertidal topography were the most numerous overall, making up one-fifth (21%) of articles. Research gaps identified in this review include coastal morphology and ecology studies over large areas, especially at scales that align with administrative or management areas such as the German Wadden Sea National Parks. Additionally, few studies utilized free, publicly available high spatial resolution imagery, such as that from Sentinel-2 or newly available very high spatial resolution satellite imagery. This review finds that remote sensing plays a notable role in monitoring the German North Sea coast at local scales, but fewer studies investigated large areas at sub-annual temporal resolution, especially for coastal morphology and ecology topics. Earth Observation, however, has the potential to fill this gap and provide critical information about impacts of coastal hazards on this region.

Remote sensing multi-decadal time-series provide important information for analysing long-term environmental change. The Advanced Very High Resolution Radiometer (AVHRR) has been providing data since the early 1980s. Normalised Difference Vegetation Index (NDVI) time-series derived thereof can be used for monitoring vegetation conditions. This study presents the novel TIMELINE NDVI product, which provides a consistent set of daily, 10-day, and monthly NDVI composites at a 1 km spatial resolution based on AVHRR data for Europe and North Africa, currently spanning the period from 1981 to 2018. After investigating temporal and spatial data availability within the TIMELINE monthly NDVI composite product, seasonal NDVI trends have been derived thereof for the period 1989–2018 to assess long-term vegetation change in Europe and northern Africa. The trend analysis reveals distinct patterns with varying NDVI trends for spring, summer and autumn for different regions in Europe. Integrating the entire growing season, the result shows positive NDVI trends for large areas within Europe that confirm and reinforce previous research. The analyses show that the TIMELINE NDVI product allows long-term vegetation dynamics to be monitored at 1 km resolution on a pan-European scale and the detection of specific regional and seasonal patterns.

Global warming-induced climate change evolved to be one of the most important research topics in Earth System Sciences, where remote sensing-based methods have shown great potential for detecting spatial temperature changes. This study utilized a time series of Landsat images to investigate the Land Surface Temperature (LST) of dry seasons between 1989 and 2019 in the Bac Binh district, Binh Thuan province, Vietnam. Our study aims to monitor LST change, and its relationship to land-cover change during the last 30 years. The results for the study area show that the share of Green Vegetation coverage has decreased rapidly for the dry season in recent years. The area covered by vegetation shrank between 1989 and 2019 by 29.44%. Our findings show that the LST increase and decrease trend is clearly related to the change of the main land-cover classes, namely Bare Land and Green Vegetation. For the same period, we find an average increase of absolute mean LST of 0.03 °C per year for over thirty years across all land-cover classes. For the dry season in 2005, the LST was extraordinarily high and the area with a LST exceeding 40 °C covered 64.10% of the total area. We expect that methodological approach and the findings can be applied to study change in LST, land-cover, and can contribute to climate change monitoring and forecasting of impacts in comparable regions.

The analysis of the Earth system and interactions among its spheres is increasingly important to improve the understanding of global environmental change. In this regard, Earth observation (EO) is a valuable tool for monitoring of long term changes over the land surface and its features. Although investigations commonly study environmental change by means of a single EO-based land surface variable, a joint exploitation of multivariate land surface variables covering several spheres is still rarely performed. In this regard, we present a novel methodological framework for both, the automated processing of multisource time series to generate a unified multivariate feature space, as well as the application of statistical time series analysis techniques to quantify land surface change and driving variables. In particular, we unify multivariate time series over the last two decades including vegetation greenness, surface water area, snow cover area, and climatic, as well as hydrological variables. Furthermore, the statistical time series analyses include quantification of trends, changes in seasonality, and evaluation of drivers using the recently proposed causal discovery algorithm Peter and Clark Momentary Conditional Independence (PCMCI). We demonstrate the functionality of our methodological framework using Indo-Gangetic river basins in South Asia as a case study. The time series analyses reveal increasing trends in vegetation greenness being largely dependent on water availability, decreasing trends in snow cover area being mostly negatively coupled to temperature, and trends of surface water area to be spatially heterogeneous and linked to various driving variables. Overall, the obtained results highlight the value and suitability of this methodological framework with respect to global climate change research, enabling multivariate time series preparation, derivation of detailed information on significant trends and seasonality, as well as detection of causal links with minimal user intervention. This study is the first to use multivariate time series including several EO-based variables to analyze land surface dynamics over the last two decades using the causal discovery algorithm PCMCI.

Forests provide essential ecosystem services, including biodiversity conservation, climate regulation, and livelihoods for millions of people worldwide. This study provides a comprehensive analysis of land-use and land-cover (LULC) changes with a focus on forest cover changes in Huế, central Vietnam, over the period from 1988 to 2022. Huế is a region of ecological and cultural significance, home to diverse forest ecosystems that play a critical role in water regulation, flood mitigation, and soil stabilization. The province’s forests also support rich biodiversity and provide vital resources for local livelihoods. By leveraging time-series Landsat observations and employing the continuous change detection and classification—spectral mixture analysis method, we synthesized multi-decadal geospatial data to track and categorize forest dynamics. The results indicate substantial LULC changes, highlighted by a significant reduction in stable forest cover from 58.3% in 1993 to 48.9% in 2022, accompanied by an increase in degraded forests from 11.7% to 18.0%. Peak forest loss was recorded at 1.5% by the end of 2013. The study discusses economic expansion, infrastructure development, climate variability, and agricultural intensification as key drivers of forest cover change. The findings underscore the importance of sustainable land management practices and provide actionable insights to inform policy development, particularly in regions with complex socio-economic and ecological interactions.