ISSN / EISSN : 2072-4292 / 2072-4292
Current Publisher: MDPI AG (10.3390)
Total articles ≅ 15,395
Latest articles in this journal
Remote Sensing, Volume 13; doi:10.3390/rs13081503
Climate change influences the vulnerability of urban populations worldwide. To improve their adaptive capacity, the implementation of nature-based solutions (NBS) in urban areas has been identified as an appropriate action, giving urban planning and development an important role towards climate change adaptation/mitigation and risk management and resilience. However, the importance of extensively applying NBS is still underestimated, especially regarding its potential to induce significantly positive environmental and socioeconomic impacts across cities. Concerning environmental impacts, monitoring and evaluation is an important step of NBS management, where earth observation (EO) can contribute. EO is known for providing valuable disaggregated data to assess the modifications caused by NBS implementation in terms of land cover, whereas the potential of EO to uncover the role of NBS in urban metabolism modifications (e.g., energy, water, and carbon fluxes and balances) still remains underexplored. This study reviews the EO potential in the monitoring and evaluation of NBS implementation in cities, indicating that satellite observations combined with data from complementary sources may provide an evidence-based approach in terms of NBS adaptive management. EO-based tools can be applied to assess NBS’ impacts on urban energy, water, and carbon balances, further improving our understanding of urban systems dynamics and supporting sustainable urbanization.
Remote Sensing, Volume 13; doi:10.3390/rs13081506
Nowadays, as the number of remote sensing satellites launched and applied in China has been mounting, relevant institutions’ workload of processing raw satellite images to be distributed to users is also growing. However, due to factors such as extreme atmospheric conditions, diversification of on-board device status, data loss during transmission and algorithm issues of ground systems, defect of image quality is inevitable, including abnormal color, color cast, data missing, obvious stitching line between Charge-Coupled Devices (CCDs), and inconstant radiation values between CCDs. Product application has also been impeded. This study presents a unified framework based on well-designed features an Artificial Neural Network (ANN) to automatically identify defective images. Samples were collected to form the dataset for training and validation, systematic experiments designed to verify the effectiveness of the features, and the optimal network architecture of ANN determined. Moreover, an effective method was proposed to explain the inference of ANN based on local gradient approximation. The recall of our final model reached 81.18% and F1 score 80.13%, verifying the effectiveness of our method.
Remote Sensing, Volume 13; doi:10.3390/rs13081508
Unmanned aerial vehicle-based multispectral imagery including five spectral bands (blue, green, red, red-edge, and near-infrared) for a rice field in the ripening stage was used to develop regression models for predicting the rice yield and protein content and to select the most suitable regression analysis method for the year-invariant model: partial least squares regression, ridge regression, and artificial neural network (ANN). The regression models developed with six vegetation indices (green normalization difference vegetation index (GNDVI), normalization difference red-edge index (NDRE), chlorophyll index red edge (CIrededge), difference NIR/Green green difference vegetation index (GDVI), green-red NDVI (GRNDVI), and medium resolution imaging spectrometer terrestrial chlorophyll index (MTCI)), calculated from the spectral bands, were applied to single years (2018, 2019, and 2020) and multiple years (2018 + 2019, 2018 + 2020, 2019 + 2020, and all years). The regression models were cross-validated through mutual prediction against the vegetation indices in nonoverlapping years, and the prediction errors were evaluated via root mean squared error of prediction (RMSEP). The ANN model was reproducible, with low and sustained prediction errors of 24.2 kg/1000 m2 ≤ RMSEP ≤ 59.1 kg/1000 m2 in rice yield and 0.14% ≤ RMSEP ≤ 0.28% in rice-protein content in all single-year and multiple-year analyses. When the importance of each vegetation index of the regression models was evaluated, only the ANN model showed the same ranking in the vegetation index of the first (MTCI in both rice yield and protein content) and second importance (CIrededge in rice yield and GRNDVI in rice-protein content). Overall, this means that the ANN model has the highest potential for developing a year-invariant model with stable RMSEP and consistent variable ranking.
Remote Sensing, Volume 13; doi:10.3390/rs13081509
Accurate burned area information is needed to assess the impacts of wildfires on people, communities, and natural ecosystems. Various burned area detection methods have been developed using satellite remote sensing measurements with wide coverage and frequent revisits. Our study aims to expound on the capability of deep learning (DL) models for automatically mapping burned areas from uni-temporal multispectral imagery. Specifically, several semantic segmentation network architectures, i.e., U-Net, HRNet, Fast-SCNN, and DeepLabv3+, and machine learning (ML) algorithms were applied to Sentinel-2 imagery and Landsat-8 imagery in three wildfire sites in two different local climate zones. The validation results show that the DL algorithms outperform the ML methods in two of the three cases with the compact burned scars, while ML methods seem to be more suitable for mapping dispersed burn in boreal forests. Using Sentinel-2 images, U-Net and HRNet exhibit comparatively identical performance with higher kappa (around 0.9) in one heterogeneous Mediterranean fire site in Greece; Fast-SCNN performs better than others with kappa over 0.79 in one compact boreal forest fire with various burn severity in Sweden. Furthermore, directly transferring the trained models to corresponding Landsat-8 data, HRNet dominates in the three test sites among DL models and can preserve the high accuracy. The results demonstrated that DL models can make full use of contextual information and capture spatial details in multiple scales from fire-sensitive spectral bands to map burned areas. Using only a post-fire image, the DL methods not only provide automatic, accurate, and bias-free large-scale mapping option with cross-sensor applicability, but also have potential to be used for onboard processing in the next Earth observation satellites.
Remote Sensing, Volume 13; doi:10.3390/rs13081505
The lower Vistula River was regulated in the years 1856–1878, at a distance of 718–939 km. The regulation plan did not take into consideration the large transport of the bed load. The channel was shaped using simplified geometry—too wide for the low flow and overly straight for the stabilization of the sandbar movement. The hydraulic parameters of the lower Vistula River show high velocities of flow and high shear stress. The movement of the alternate sandbars can be traced on the optical satellite images of Sentinel-2. In this study, a method of sandbar detection through the remote sensing indices, Sentinel Water Mask (SWM) and Automated Water Extraction Index no shadow (AWEInsh), and the manual delineation with visual interpretation (MD) was used on satellite images of the lower Vistula River, recorded at the time of low flows (20 August 2015, 4 September 2016, 30 July 2017, 20 September 2018, and 29 August 2019). The comparison of 32 alternate sandbar areas obtained by SWM, AWEInsh, and MD manual delineation methods on the Sentinel-2 images, recorded on 20 August 2015, was performed by the statistical analysis of the interclass correlation coefficient (ICC). The distance of the shift in the analyzed time intervals between the image registration dates depends on the value of the mean discharge (MQ). The period from 30 July 2017 to 20 September 2018 was wet (MQ = 1140 m3 × s−1) and created conditions for the largest average distance of the alternate sandbar shift, from 509 to 548 m. The velocity of movement, calculated as an average shift for one day, was between 1.2 and 1.3 m × day−1. The smallest shift of alternate sandbars was characteristic of the low flow period from 20 August 2015 to 4 September 2016 (MQ = 306 m3 × s−1), from 279 to 310 m, with an average velocity from 0.7 to 0.8 m × day−1.
Remote Sensing, Volume 13; doi:10.3390/rs13081507
Automatic detection of newly constructed building areas (NCBAs) plays an important role in addressing issues of ecological environment monitoring, urban management, and urban planning. Compared with low-and-middle resolution remote sensing images, high-resolution remote sensing images are superior in spatial resolution and display of refined spatial details. Yet its problems of spectral heterogeneity and complexity have impeded research of change detection for high-resolution remote sensing images. As generalized machine learning (including deep learning) technologies proceed, the efficiency and accuracy of recognition for ground-object in remote sensing have been substantially improved, providing a new solution for change detection of high-resolution remote sensing images. To this end, this study proposes a refined NCBAs detection method consisting of four parts based on generalized machine learning: (1) pre-processing; (2) candidate NCBAs are obtained by means of bi-temporal building masks acquired by deep learning semantic segmentation, and then registered one by one; (3) rules and support vector machine (SVM) are jointly adopted for classification of NCBAs with high, medium and low confidence; and (4) the final vectors of NCBAs are obtained by post-processing. In addition, area-based and pixel-based methods are adopted for accuracy assessment. Firstly, the proposed method is applied to three groups of GF1 images covering the urban fringe areas of Jinan, whose experimental results are divided into three categories: high, high-medium, and high-medium-low confidence. The results show that NCBAs of high confidence share the highest F1 score and the best overall effect. Therefore, only NCBAs of high confidence are considered to be the final detection result by this method. Specifically, in NCBAs detection for three groups GF1 images in Jinan, the mean Recall of area-based and pixel-based assessment methods reach around 77% and 91%, respectively, the mean Pixel Accuracy (PA) 88% and 92%, and the mean F1 82% and 91%, confirming the effectiveness of this method on GF1. Similarly, the proposed method is applied to two groups of ZY302 images in Xi’an and Kunming. The scores of F1 for two groups of ZY302 images are also above 90% respectively, confirming the effectiveness of this method on ZY302. It can be concluded that adoption of area registration improves registration efficiency, and the joint use of prior rules and SVM classifier with probability features could avoid over and missing detection for NCBAs. In practical applications, this method is contributive to automatic NCBAs detection from high-resolution remote sensing images.
Remote Sensing, Volume 13; doi:10.3390/rs13081504
The aim of this study is to evaluate the effectiveness of the identification of Natura 2000 wetland habitats (Alkaline fens—code 7230, and Transition mires and quaking bogs—code 7140) depending on various remotely sensed (RS) data acquired from an airborne platform. Both remote sensing data and botanical reference data were gathered for mentioned habitats in the Lower (LB) and Upper Biebrza (UB) River Valley and the Janowskie Forest (JF) in different seasonal stages. Several different classification scenarios were tested, and the ones that gave the best results for analyzed habitats were indicated in each campaign. In the final stage, a recommended term of data acquisition, as well as a list of remote sensing products, which allowed us to achieve the highest accuracy mapping for these two types of wetland habitats, were presented. Designed classification scenarios integrated different hyperspectral products such as Minimum Noise Fraction (MNF) bands, spectral indices and products derived from Airborne Laser Scanning (ALS) data representing topography (developed in SAGA), or statistical products (developed in OPALS—Orientation and Processing of Airborne Laser Scanning). The image classifications were performed using a Random Forest (RF) algorithm and a multi-classification approach. As part of the research, the correlation analysis of the developed remote sensing products was carried out, and the Recursive Feature Elimination with Cross-Validation (RFE-CV) analysis was performed to select the most important RS sub-products and thus increase the efficiency and accuracy of developing the final habitat distribution maps. The classification results showed that alkaline fens are better identified in summer (mean F1-SCORE equals 0.950 in the UB area, and 0.935 in the LB area), transition mires and quaking bogs that evolved on/or in the vicinity of alkaline fens in summer and autumn (mean F1-SCORE equals 0.931 in summer, and 0.923 in autumn in the UB area), and transition mires and quaking bogs that evolved on dystrophic lakes in spring and summer (mean F1-SCORE equals 0.953 in spring, and 0.948 in summer in the JF area). The study also points out that the classification accuracy of both wetland habitats is highly improved when combining selected hyperspectral products (MNF bands, spectral indices) with ALS topographical and statistical products. This article demonstrates that information provided by the synergetic use of data from different sensors can be used in mapping and monitoring both Natura 2000 wetland habitats for its future functional assessment and/or protection activities planning with high accuracy.
Remote Sensing, Volume 13; doi:10.3390/rs13081494
Globally, grassland biomes form one of the largest terrestrial covers and present critical social–ecological benefits. In Kenya, Arid and Semi-arid Lands (ASAL) occupy 80% of the landscape and are critical for the livelihoods of millions of pastoralists. However, they have been invaded by Invasive Plant Species (IPS) thereby compromising their ecosystem functionality. Opuntia stricta, a well-known IPS, has invaded the ASAL in Kenya and poses a threat to pastoralism, leading to livestock mortality and land degradation. Thus, identification and detailed estimation of its cover is essential for drawing an effective management strategy. The study aimed at utilizing the Sentinel-2 multispectral sensor to detect Opuntia stricta in a heterogeneous ASAL in Laikipia County, using ensemble machine learning classifiers. To illustrate the potential of Sentinel-2, the detection of Opuntia stricta was based on only the spectral bands as well as in combination with vegetation and topographic indices using Extreme Gradient Boost (XGBoost) and Random Forest (RF) classifiers to detect the abundance. Study results showed that the overall accuracies of Sentinel 2 spectral bands were 80% and 84.4%, while that of combined spectral bands, vegetation, and topographic indices was 89.2% and 92.4% for XGBoost and RF classifiers, respectively. The inclusion of topographic indices that enhance characterization of biological processes, and vegetation indices that minimize the influence of soil and the effects of atmosphere, contributed by improving the accuracy of the classification. Qualitatively, Opuntia stricta spatially was found along river banks, flood plains, and near settlements but limited in forested areas. Our results demonstrated the potential of Sentinel-2 multispectral sensors to effectively detect and map Opuntia stricta in a complex heterogeneous ASAL, which can support conservation and rangeland management policies that aim to map and list threatened areas, and conserve the biodiversity and productivity of rangeland ecosystems.
Remote Sensing, Volume 13; doi:10.3390/rs13081491
In the context of the problem of image blur and nonlinear reflectance difference between bands in the registration of hyperspectral images, the conventional method has a large registration error and is even unable to complete the registration. This paper proposes a robust and efficient registration algorithm based on iterative clustering for interband registration of hyperspectral images. The algorithm starts by extracting feature points using the scale-invariant feature transform (SIFT) to achieve initial putative matching. Subsequently, feature matching is performed using four-dimensional descriptors based on the geometric, radiometric, and feature properties of the data. An efficient iterative clustering method is proposed to perform cluster analysis on the proposed descriptors and extract the correct matching points. In addition, we use an adaptive strategy to analyze the key parameters and extract values automatically during the iterative process. We designed four experiments to prove that our method solves the problem of blurred image registration and multi-modal registration of hyperspectral images. It has high robustness to multiple scenes, multiple satellites, and multiple transformations, and it is better than other similar feature matching algorithms.
Remote Sensing, Volume 13; doi:10.3390/rs13081499
Rapid urban expansion has seriously threatened ecological security and the natural environment on a global scale, thus, the simulation of dynamic urban expansion is a hot topic in current research. Existing urban expansion simulation models focus on the mining of spatial neighborhood features among driving factors, however, they ignore the over-fitting, gradient explosion, and vanishing problems caused by the long-term dependence of time series data, which results in limited model accuracy. In this study, we proposed a new dynamic urban expansion simulation model. Considering the long-time dependence issue, long short term memory (LSTM) was employed to automatically extract the transformation rules through memory units and provide the optimal attribute features for cellular automata (CA). This study selected Lanzhou, which is a semi-arid region in Northwest China, as an example to confirm the validity of the model performance using data from 2000 to 2020. The results revealed that the overall accuracy of the model was 91.01%, which was higher than that of the traditional artificial neural network (ANN)-CA and recurrent neural network (RNN)-CA models. The LSTM-CA framework resolved existing problems with the traditional algorithm, while it significantly reduced complexity and improved simulation accuracy. In addition, we predicted urban expansion to 2030 based on natural expansion (NE) and ecological constraint (EC) scenarios, and found that EC was an effective control strategy. This study provides a certain theoretical basis and reference value toward the realization of new urbanization and ecologically sound civil construction, in the context of territorial spatial planning and healthy/sustainable urban development.