Showing papers in "International Journal of Applied Earth Observation and Geoinformation in 2020"

TL;DR: Evidence collectively indicate that the seepage erosion (piping) is the primary cause for the chronic weakening of the structure and, hence, the internal “liquefaction” condition.

TL;DR: The present study showed the first attempt to develop a machine-learning workflow to map the spatial pattern of the forest canopy height in a mountainous region in the northeast China by coupling the recently available canopy height (Hcanopy) footprint product from ICESat-2 with the Sentinel-1 and Sentinel-2 satellite data.

TL;DR: The results for the St. Lucia wetlands in South Africa showed that combining Sentinel-1 and -2 led to significantly higher classification accuracies than for using the systems separately, and Sentinel-2 was particularly of value for general wetland delineation, while Sentinel- 1 showed more value for mapping wetland vegetation types.

TL;DR: It is concluded that GP algorithms, and in particular the heteroscedastic GP, should be implemented for global agricultural monitoring of aboveground N from future imaging spectroscopy data.

TL;DR: Modification of tree and building cover may have the potential to regulate urban LST, and spectral indices using different combinations of the infrared bands have stronger correlations with LST than the more widely used vegetation indices such as NDVI.

TL;DR: This study provides a highly robust and accurate method for predicting and mapping regional SOC contents and indicates that at a low decomposition scale, DWT can effectively eliminate the noise in satellite hyperspectral data, and the FDR combined withDWT can improve the SOC prediction accuracy significantly.

TL;DR: This study proposed a novel upscaling method for mangrove AGB estimation using field plots, UAV-LiDAR strip data and Sentinel-2 imagery based on a point-line-polygon framework and showed that northeast Hainan Island has a total mangroves AGB of 312,806.

TL;DR: The significant time-lag and -accumulation effects of climatic factors on global vegetation growth need to be incorporated into dynamic vegetation models to better understand vegetation growth under accelerating climate change.

TL;DR: It is found that high-resolution SIF products from OCO-2 and TROPOMI outperformed coarse-resolution GOME-2 SIF product in crop yield prediction, and using NIRv could achieve similar or even better yield prediction performance than using Oco-2 or TROPOspheric Monitoring Instrument Sif products.

TL;DR: An innovative, scalable and flexible approach to monitor land degradation at various scales using various components of the Global Earth Observation System of Systems (GEOSS) platform to leverage EO resources for informing SDG 15.3.1.

TL;DR: LUCAS in-situ data is a suitable source for reference information for large scale high resolution LC mapping using Sentinel-2 imagery, and existing sample selection approaches developed for Landsat imagery can be transferred to Sentinel- 2 imagery, achieving comparable semantic accuracies while increasing the spatial resolution.

TL;DR: Predictive performance peaked early in the season, at 100–142 days after the previous harvest (DAH), and declined closer to the harvest date, which is of particular interest to nutrient management programs aiming to deliver N fertilizer guidelines for sustainable sugarcane production.

TL;DR: The sensitivity analysis performed in this study illustrates that the Support Vector Machine (SVM) is less sensitive to the number of samples and mislabeling in the model training than other MLAs.

TL;DR: An exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest, demonstrates the potential of GRRF for remote sensing image classification and regression, especially in the context of increasingly large geodatabases that challenge the application of traditional methods.

TL;DR: A feature-fusing OCNN, including the object contour-preserving mask strategy with the supplement of object deformation coefficient, is developed for accurate object discrimination by learning simultaneously high-level features from independent spectral patterns, geometric characteristics, and object-level contextual information.

TL;DR: A new algorithm for quickly mapping SDDs in Chinese lakes was developed based on the time-saving and low-cost Google Earth Engine cloud platform and demonstrated that lake water depth spatially differentiated transparency.

TL;DR: An approach for mapping flooded areas from Sentinel-2 MSI (Multispectral Instrument) data based on soft fuzzy integration of evidence scores derived from both band combinations and components of the Hue, Saturation and Value (HSV) colour transformation is proposed.

TL;DR: The stacked generalization algorithm is superior to single classifiers in classifying vegetation of high heterogeneity areas and extract the wetland information based on the optimal feature combination in the Dongting Lake wetland.

TL;DR: A test regarding wall-to-wall, spatially explicit estimation of forest growing stock volume (GSV) based on field measurement of 1350 plots during the last Italian NFI found model-assisted estimates were more precise than the original design-based estimates provided by the NFI.

TL;DR: The results emphasize the spatial variation of the relationships between SUHII and relevant driving factors across global major cities, further indicating that the spatially non-stationary effect of driving factors onSUHII need to be considered in the future.

TL;DR: A deep extraction of localized spectral features and multi-scale spatial features convolution (LSMSC) framework for spectral-spatial fusion based classification of hyperspectral images (HSIs) outperforms several state-of-the-art approaches.

TL;DR: A modular Regional Land Cover Monitoring System (RLCMS) architecture that is easily customized to create land cover products using primitive map layers is presented and best practices to create and assemble primitives from optical satellite are presented.

TL;DR: It is revealed that, though LST depends on LSE, other parameters should also be taken into account when predicting LST, as more accurate LSE results did not increase the prediction accuracy of LST.

TL;DR: The CNN approach emerged as a promising technique as it leveraged spatial information from the UAV images within the architecture of the learning framework by enforcing a local connectivity pattern between neurons of adjacent layers to incorporate the spatial relationships between features that comprised the shape of the Lomandra tussocks detected.

TL;DR: The seed points extracted from Backpack-LiDAR could significantly improve the overall accuracy of individual tree detection and increase the forest AGB estimation accuracy, and compared with MLR model, the RF model led to a higher estimation accuracy.

TL;DR: It is indicated that mapping dominant tree species with airborne hyperspectral data can be accomplished also over large areas and that forest management and its effects on forest structure has an influence on classification accuracies and should be actively considered when progressing towards operational mapping of tree species composition.

TL;DR: Estimating SOS of temperate broadleaf forests at medium spatial resolution has become feasible with combined Landsat and Sentinel-2 time series and EVI-based SOS showed higher correlation with ground observations compared to NDVI, and data density played an important role in estimating land surface phenology.

TL;DR: Landscape metrics, LISA indices are applied to analyse the temporal variability in clustering and fragmentation patterns of vegetation patches in Harare metropolitan city, Zimbabwe using Landsat series data for 1994, 2001 and 2017 to demonstrate the utility of LISA indexes in identifying key hot spot and cold spots.

TL;DR: The threshold-based method applied to the smoothed and gap-filled LAI V2 time series agreed best with the ground phenology, with root mean square errors of ˜10 d and ˜25 d for the timing of SoS and EoS respectively.

TL;DR: Over and underestimation of low and high CCC values were observed mainly in the statistical approaches, and further validation using in situ data from different terrestrial ecosystems is imperative for both the statistical and physical-based approaches' effectiveness to quantify CCC.