Explore the vast range of titles available.

Sea ice in the Southern Ocean has expanded over most of the past 20 y, but the decline in sea ice since 2016 has taken experts by surprise. This recent evolution highlights the poor performance of numerical models for predicting extent and thickness, which is due to our poor understanding of ice dynamics. Ocean waves are known to play an important role in ice break-up and formation. In addition, as ocean waves decay, they cause a stress that pushes the ice in the direction of wave propagation. This wave stress could not previously be quantified due to insufficient observations at large scales. Sentinel-1 synthetic aperture radars (SARs) provide high-resolution imagery from which wave height is measured year round encompassing Antarctica since 2014. Our estimates give an average wave stress that is comparable to the average wind stress acting over 50 km of sea ice. We further reveal highly variable half-decay distances ranging from 400 m to 700 km, and wave stresses from 0.01 to 1 Pa. We expect that this variability is related to ice properties and possibly different floe sizes and ice thicknesses. A strong feedback of waves on sea ice, via break-up and rafting, may be the cause of highly variable sea-ice properties.

Accurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables from Sentinel-1 synthetic aperture radar (SAR), Sentinal-2 multispectral instrument (MSI) and SRTM digital elevation model (DEM) data were composed into four groups and evaluated for their effectiveness in prediction of AGB. Five evaluated algorithms include linear regression such as stepwise regression (SWR) and geographically weighted regression (GWR); machine learning (ML) such as artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that the RF model used predictors from both the Sentinel series and SRTM DEM performed the best, based on the independent validation set. The RF model achieved accuracy with the mean error, mean absolute error, root mean square error, and correlation coefficient in 1.39, 25.48, 61.11 Mg·ha−1 and 0.9769, respectively. Texture characteristics, reflectance, vegetation indices, elevation, stream power index, topographic wetness index and surface roughness were recommended predictors for AGB prediction. Predictor variables were more important than algorithms for improving the accuracy of AGB estimates. The study demonstrated encouraging results in the optimal combination of predictors and algorithms for forest AGB mapping, using openly accessible and fine-resolution data based on RF algorithms.

Due to its relation to the Earth’s climate and weather and phenomena like drought, flooding, or landslides, knowledge of the soil moisture content is valuable to many scientific and professional users. Remote-sensing offers the unique possibility for continuous measurements of this variable. Especially for agriculture, there is a strong demand for high spatial resolution mapping. However, operationally available soil moisture products exist with medium to coarse spatial resolution only (≥1 km). This study introduces a machine learning (ML)—based approach for the high spatial resolution (50 m) mapping of soil moisture based on the integration of Landsat-8 optical and thermal images, Copernicus Sentinel-1 C-Band SAR images, and modelled data, executable in the Google Earth Engine. The novelty of this approach lies in applying an entirely data-driven ML concept for global estimation of the surface soil moisture content. Globally distributed in situ data from the International Soil Moisture Network acted as an input for model training. Based on the independent validation dataset, the resulting overall estimation accuracy, in terms of Root-Mean-Squared-Error and R², was 0.04 m3·m−3 and 0.81, respectively. Beyond the retrieval model itself, this article introduces a framework for collecting training data and a stand-alone Python package for soil moisture mapping. The Google Earth Engine Python API facilitates the execution of data collection and retrieval which is entirely cloud-based. For soil moisture retrieval, it eliminates the requirement to download or preprocess any input datasets.

Aquaculture has enormous potential for ensuring global food security and has experienced rapid growth globally. Thus, the accurate monitoring and mapping of coastal aquaculture ponds is necessary for the sustainable development and efficient management of the aquaculture industry. Here, we developed a map of coastal aquaculture ponds in China using Google Earth Engine (GEE) and the ArcGIS platform, Sentinel-1 SAR image data for 2020, the Sentinel-1 Dual-Polarized Water Index (SDWI), and water frequency obtained by identifying the special object features of aquaculture ponds and postprocessing interpretation. Our map had an overall accuracy of 93%, and we found that the coastal aquaculture pond area in China reached 6937 km2 in 2020. The aquaculture pond area was highest in Shandong, Guangdong, and Jiangsu Provinces, and at the city level, Dongying, Binzhou, Tangshan, and Dalian had the most aquaculture pond area. Aquaculture ponds had spatial heterogeneity; the aquaculture pond area in north China was larger than in south China and seaside areas had more pond area than inland regions. In addition, aquaculture ponds were concentrated near river estuaries, coastal plains, and gulfs, and were most dense in the Huang-Huai-Hai Plain and Pearl River Delta. We showed that GEE cloud processing and ArcGIS local processing could facilitate the classification of coastal aquaculture ponds, which can be used to inform and improve decision-making for the spatial optimization and intelligent monitoring of coastal aquaculture, with certain potential for spatial migration.

The Lower Kosi Basin (LKB) in North Bihar is highly prone to floods and is influenced by upstream hydrology. A flood susceptibility index has been modelled by integrating eleven flood conditioning parameters (precipitation, elevation, slope, drainage density, distance from the river, ruggedness index, topographic wetness index, stream power index, curvature, normalized difference vegetation index, land use and land cover) derived from the satellite data, using a weighted linear summation model. The study uses Sentinel-1 synthetic aperture radar data to estimate flood frequency over a temporal scale of 2016–2020. The flood frequency was used to validate the flood susceptibility derived using multi-criteria decision making methods combined with geographical information system (MCDM-GIS). The study shows that ~ 66% of the area in LKB is susceptible to high to moderate flooding while the remaining ~ 34% is falls in the low flooding category. 15.24% of the area has high frequency (> 3 flood occurrences) of the flood, 9.66% has moderate (2 flood occurrences) and 9.72% of the area faced one-time flood during five years of period (2016–2020). The accuracy of MCDM-GIS derived flood susceptibility map was assessed using area under curve, confusion matrix, precision, recall, F1 score, weighted F1 score and overall accuracy.

Land cover (LC) maps are crucial to environmental modeling and define sustainable management and planning policies. The development of a land cover mapping continuous service according to the new EAGLE legend criteria has become of great interest to the public sector. In this work, a tentative approach to map land cover overcoming remote sensing (RS) limitations in the mountains according to the newest EAGLE guidelines was proposed. In order to reach this goal, the methodology has been developed in Aosta Valley, NW of Italy, due to its higher degree of geomorphological complexity. Copernicus Sentinel-1 and 2 data were adopted, exploiting the maximum potentialities and limits of both, and processed in Google Earth Engine and SNAP. Due to SAR geometrical distortions, these data were used only to refine the mapping of urban and water surfaces, while for other classes, composite and timeseries filtered and regularized stack from Sentinel-2 were used. GNSS ground truth data were adopted, with training and validation sets. Results showed that K-Nearest-Neighbor and Minimum Distance classification permit maximizing the accuracy and reducing errors. Therefore, a mixed hierarchical approach seems to be the best solution to create LC in mountain areas and strengthen local environmental modeling concerning land cover mapping.

Earth Observation services guarantee continuous land cover mapping and are becoming of great interest worldwide. The Google Earth Engine Dynamic World represents a planetary example. This work aims to develop a land cover mapping service in geomorphological complex areas in the Aosta Valley in NW Italy, according to the newest European EAGLE legend starting in the year 2020. Sentinel-2 data were processed in the Google Earth Engine, particularly the summer yearly median composite for each band and their standard deviation with multispectral indexes, which were used to perform a k-nearest neighbor classification. To better map some classes, a minimum distance classification involving NDVI and NDRE yearly filtered and regularized stacks were computed to map the agronomical classes. Furthermore, SAR Sentinel-1 SLC data were processed in the SNAP to map urban and water surfaces to improve optical classification. Additionally, deep learning and GIS updated datasets involving urban components were adopted beginning with an aerial orthophoto. GNSS ground truth data were used to define the training and the validation sets. In order to test the effectiveness of the implemented service and its methodology, the overall accuracy was compared to other approaches. A mixed hierarchical approach represented the best solution to effectively map geomorphological complex areas to overcome the remote sensing limitations. In conclusion, this service may help in the implementation of European and local policies concerning land cover surveys both at high spatial and temporal resolutions, empowering the technological transfer in alpine realities.

Flood susceptibility maps are vital tools for implementing prevention and mitigation strategies. This study describes the potential application of convolutional neural networks (CNN) from two standpoints, single-input and multi-input CNN, to improve flood susceptibility modeling. Firstly, optical (Sentinel-2 and Landsat-8) and radar (Sentinel-1) satellite images were integrated to identify flooded and non-flooded areas. Moreover, a geospatial database with thirteen geo-environmental features including altitude, slope, rainfall, land use and land cover (LULC), normalized difference vegetation index (NDVI), normalized difference moisture index (NDMI), aspect, curvature, drainage density, topographic wetness index (TWI), stream power index (SPI), soil texture, and distance from the river, was created in Aqqala County, Golestan Province, Iran. This study concentrates on improving the prediction performance by enhancing the feature extraction capabilities of the CNN model. To achieve this, a multi-input CNN model is developed and compared with the single-input CNN model. The validation results in terms of the area under the receiver operating characteristic (ROC) curve (AUC) showed that the multi-input CNN model in training (AUC = 0.998) and testing (AUC = 0.946) performed better than the single-input CNN model in training (AUC = 0.987) and testing (AUC = 0.896). The results also demonstrated the potential of the multi-input CNN model as a promising flood susceptibility prediction model.

In recent times, the development of algorithms to delineate water surface maps has significantly boosted flood monitoring and mitigation efforts by utilizing dual polarization, multi‐temporal Sentinel‐1 synthetic aperture radar (SAR) data. The Sentinel‐1 mission, with its global land monitoring capability, has been widely employed for SAR‐based flood mapping. Compared to single‐image flood algorithms, change‐detection methods offer superior results by deriving flood extent from classified changes, requiring data‐based parameterization. This study critically evaluates the effectiveness of three cutting‐edge thresholding algorithms—Edge Otsu, Bmax Otsu, and Kittler–Illingworth (KI)—for automated flood water detection using dual polarization, multi‐temporal Sentinel‐1 SAR data, focusing on the September 2019 flood event in North‐eastern Thailand. Utilizing Google Earth Engine for preprocessing and image correction, the study examines three Sentinel‐1 change detection models—Difference Image, Normalized Difference Flood Index (NDFI), and Normalized Difference Sigma‐naught Index (NDSI). Among 27 combinations of inputs, change detection methods, and thresholding algorithms, the “Harmonic data‐S1GBM (2016–2017)” input paired with the KI thresholding algorithm and the NDSI change detection method achieved the highest overall accuracy of 86.29% (calculated using user accuracy, producer accuracy, and overall accuracy metrics against 2000 validation samples from GISTDA flood maps and Sentinel‐2 NDWI data). This combination proved most effective in distinguishing flooded from non‐flooded areas, underscoring the importance of selecting optimal data inputs and algorithms for accurate flood inundation mapping. The results highlight the superiority of the KI thresholding algorithm, particularly when used with harmonic data inputs, and establish a robust framework for future flood monitoring applications using Sentinel‐1 SAR data. Furthermore, the study emphasizes that for global and automatic flood services, algorithms should not depend on locally optimized parameters, as these cannot be automatically estimated and vary spatially, significantly affecting mapping accuracy.

Applications of machine learning on remote sensing data appear to be endless. Its use in damage identification for early response in the aftermath of a large-scale disaster has a specific issue. The collection of training data right after a disaster is costly, time-consuming, and many times impossible. This study analyzes a possible solution to the referred issue: the collection of training data from past disaster events to calibrate a discriminant function. Then the identification of affected areas in a current disaster can be performed in near real-time. The performance of a supervised machine learning classifier to learn from training data collected from the 2018 heavy rainfall at Okayama Prefecture, Japan, and to identify floods due to the typhoon Hagibis on 12 October 2019 at eastern Japan is reported in this paper. The results show a moderate agreement with flood maps provided by local governments and public institutions, and support the assumption that previous disaster information can be used to identify a current disaster in near-real time.