Remote Sens., Volume 14, Issue 14 (July-2 2022) – 269 articles

This paper focuses on sea surface wind speed estimation using L1B level v3.1 data of reflected GNSS signals from the Cyclone GNSS (CYGNSS) mission and European Centre for Medium-range Weather Forecast Reanalysis (ECMWF) wind speed data. Seven machine learning methods are applied for wind speed retrieval, i.e., Regression trees (Binary Tree (BT), Ensembles of Trees (ET), XGBoost (XGB), LightGBM (LGBM)), ANN (Artificial neural network), Stepwise Linear Regression (SLR), and Gaussian Support Vector Machine (GSVM), and a comparison of their performance is made. The wind speed is divided into two different ranges to study the suitability of the different algorithms. A total of 10 observation variables are considered as input parameters to study the importance of individual variables or combinations thereof. The results show that the LGBM model performs the best with an RMSE of 1.419 and a correlation coefficient of 0.849 in the low wind speed interval (0–15 m/s), while the ET model performs the best with an RMSE of 1.100 and a correlation coefficient of 0.767 in the high wind speed interval (15–30 m/s). The effects of the variables used in wind speed retrieval models are investigated using the XGBoost importance metric, showing that a number of variables play a very significant role in wind speed retrieval. It is expected that these results will provide a useful reference for the development of advanced wind speed retrieval algorithms in the future. Full article

The rapid and nondestructive determination of wheat aboveground biomass (AGB) is important for accurate and efficient agricultural management. In this study, we established a novel hybrid model, known as extreme gradient boosting (XGBoost) optimization using the grasshopper optimization algorithm (GOA-XGB), which could accurately determine an ideal combination of vegetation indices (VIs) for simulating wheat AGB. Five multispectral bands of the unmanned aerial vehicle platform and 56 types of VIs obtained based on the five bands were used to drive the new model. The GOA-XGB model was compared with many state-of-the-art models, for example, multiple linear regression (MLR), multilayer perceptron (MLP), gradient boosting decision tree (GBDT), Gaussian process regression (GPR), random forest (RF), support vector machine (SVM), XGBoost, SVM optimization by particle swarm optimization (PSO), SVM optimization by the whale optimization algorithm (WOA), SVM optimization by the GOA (GOA-SVM), XGBoost optimization by PSO, XGBoost optimization by the WOA. The results demonstrated that MLR and GOA-MLR models had poor prediction accuracy for AGB, and the accuracy did not significantly improve when input factors were more than three. Among single-factor-driven machine learning (ML) models, the GPR model had the highest accuracy, followed by the XGBoost model. When the input combinations of multispectral bands and VIs were used, the GOA-XGB model (having 37 input factors) had the highest accuracy, with RMSE = 0.232 kg m⁻², R² = 0.847, MAE = 0.178 kg m⁻², and NRMSE = 0.127. When the XGBoost feature selection was used to reduce the input factors to 16, the model accuracy improved further to RMSE = 0.226 kg m⁻², R² = 0.855, MAE = 0.172 kg m⁻², and NRMSE = 0.123. Based on the developed model, the average AGB of the plot was 1.49 ± 0.34 kg. Full article

Surface urban heat islands are widely focused on due to their close relationship with a series of environmental issues. Obtaining a precise footprint is an important prerequisite for heat island research. However, the land surface temperature curves used for calculating footprint are affected by factors such as the complexity of land-use types, thereby affecting the accuracy of footprint. Therefore, the rotational-scan exponential decay model is developed in this paper, which first takes the gravity center of an urban area as the origin of polar coordinates, specifies due north as the starting direction, and rotationally scans the suburbs that are within 20 km outside urban areas in a clockwise direction at an angle of 1°. The eligible suburbs are screened out according to the built-up area rate, water body rate, and merge tolerance. Then, exponential decay fitting of the temperature curve is performed to obtain the extension distance of the heat island and the background temperature, which are used to determine the final footprint. Based on the method, the footprints of 15 cities were calculated and compared with those of the traditional method. The results show that: (1) this method could effectively eliminate the influence of a large number of contiguous built-up areas and water bodies in the suburbs on the footprint calculation, thus greatly improving the accuracy of the temperature curve and footprint. (2) Three of four cities had the largest footprint boundary in spring. All four cities had the strongest heat island intensity in summer and the smallest footprint boundary and intensity in winter. (3) Coupling effect would aggravate the negative impact of heat islands in the suburbs and threaten the suburban environment. As a state-of-the-art method, it can enhance the calculation accuracy and precisely reflect the spatial pattern of footprint, which is of great significance for the sustainable development of cities. Full article

Nitrogen balance index (NBI) is an important indicator for scientific diagnostic and quantitative research on crop growth status. The quick and accurate assessment of NBI is necessary for farmers to make timely N management decisions. The objective of the study was to estimate winter wheat NBI based on canopy hyperspectral features between 400–1350 nm combined with machine learning (ML) methods in the individual and whole growth stages. In this study, 3 years of winter wheat plot experiments were conducted. Ground-level canopy hyperspectral reflectance and corresponding plant NBI values were measured during the jointing, booting, flowering and filling stages. Continuous removal spectra (CRS) and logarithmic transformation spectra (LOGS) were derived from the original canopy spectra. Sensitive bands and vegetation indices (VIs) highly correlated with NBI under different spectral transformations were selected as hyperspectral features to construct the NBI estimation models combined with ML algorithms. The study indicated that the spectral transformation significantly improved the correlation between the sensitive bands, VIs and the NBI. The correlation coefficient of the sensitive band in CRS in the booting stage increased by 27.87%, reaching −0.78. The leaf chlorophyll index (LCI) in LOGS had the highest correlation with NBI in the filling stage, reaching a correlation coefficient of −0.96. The NBI prediction accuracies based on the sensitive band combined with VIs were generally better than those based on the univariate hyperspectral feature, and the prediction accuracy of each growth stage was better than that of the whole growth stage. The random forest regression (RFR) method performed better than the support vector regression (SVR) and partial least squares regression (PLS) methods. The NBI estimation model based on the LOGS-RFR method in the filling stage could explain 95% of the NBI variability with relative prediction deviation (RPD) being 3.69. These results will provide a scientific basis for better nitrogen nutrition monitoring, diagnosis, and later for field management of winter wheat. Full article

Remote sensing of ocean colour has been fundamental to the synoptic-scale monitoring of marine water quality in the Great Barrier Reef (GBR). However, ocean colour sensors onboard low orbit satellites, such as the Sentinel-3 constellation, have insufficient revisit capability to fully resolve diurnal variability in highly dynamic coastal environments. To overcome this limitation, this work presents a physics-based coastal ocean colour algorithm for the Advanced Himawari Imager onboard the Himawari-8 geostationary satellite. Despite being designed for meteorological applications, Himawari-8 offers the opportunity to estimate ocean colour features every 10 min, in four broad visible and near-infrared spectral bands, and at 1 km² spatial resolution. Coupled ocean–atmosphere radiative transfer simulations of the Himawari-8 bands were carried out for a realistic range of in-water and atmospheric optical properties of the GBR and for a wide range of solar and observation geometries. The simulated data were used to develop an inverse model based on artificial neural network techniques to estimate total suspended solids (TSS) concentrations directly from the Himawari-8 top-of-atmosphere spectral reflectance observations. The algorithm was validated with concurrent in situ data across the coastal GBR and its detection limits were assessed. TSS retrievals presented relative errors up to 75% and absolute errors of 2 mg L⁻¹ within the validation range of 0.14 to 24 mg L⁻¹, with a detection limit of 0.25 mg L⁻¹. We discuss potential applications of Himawari-8 diurnal TSS products for improved monitoring and management of water quality in the GBR. Full article

Passive multi-frequency microwave sensors are indispensable instruments for worldwide environmental monitoring. However, they often suffer from the issues of poor spatial resolution and the original land–sea transition zone data are contaminated severely. Conventional analytical deconvolution methods enhance the spatial resolution at the expense of noise amplification and Gibbs fluctuations in the land–sea transition zone. In order to enhance the spatial resolution as well as simultaneously enhance the integrity of the Microwave Radiometer data, a method based on Total Variation deconvolution, Bilateral Filter, and data fusion (TVBF+) is proposed. Our method substantially improves data integrity and obtains similar enhanced resolution compared to existing methods. Experiments performed using both simulated and actual microwave radiation Imager (MWRI) data demonstrate the method’s robustness and effectiveness. Full article

Typical features of lightning distribution in the mountain area of Mt. Cimone (2165 m a.s.l., Northern-Central Italy) have been studied through detections provided by the ground-based LIghtning NETwork data (LINET) and the Lightning Imaging Sensor (LIS) onboard the International Space Station (ISS-LIS). This study was performed within the context of the Gamma-Flash program, which includes the in situ observation of high-energy radiation (e.g., Terrestrial Gamma-ray Flashes (TGFs), gamma-ray glows) and neutron emissions from thunderstorms at the mountain-top “O. Vittori” climate observatory. LINET VLF/LF radio measurements allowed the characterization of both cloud-to-ground (CG) and intra-cloud (IC) strokes’ geographical distribution and an altitude of occurrence from 2012 through 2020. The lightning distribution showed a remarkable clustering of CGs at the mountain top in contrast to a homogeneous distribution of ICs, highlighting the likely impact of orography. IC strokes peaked around 4 to 6 km altitude, in agreement with the observed typical cloud range. The joint exploitation of ISS-LIS optical observations of LINET detections extended the study to further features of flashes not seen in radio wavelengths and stands as the cross-validation of the two detection methods over such a complex orography. These results gave the quantitative indication of the expected occurrence of lightning and ionizing radiation emissions in the Mt. Cimone area and an example of mountain-driven changes in lightning occurrence. Full article

Maintaining the ecological security of arid Central Asia (CA) is essential for the sustainable development of arid CA. Based on the moderate-resolution imaging spectroradiometer (MODIS) data stored on the Google Earth Engine (GEE), this paper investigated the spatiotemporal changes and factors related to ecological environment quality (EEQ) in CA from 2000 to 2020 using the remote sensing ecological index (RSEI). The RSEI values in CA during 2000, 2005, 2010, 2015, and 2020 were 0.379, 0.376, 0.349, 0.360, and 0.327, respectively; the unchanged/improved/deteriorated areas during 2000–2005, 2005–2010, 2010–2015, and 2015–2020 were about 83.21/7.66%/9.13%, 77.28/6.68%/16.04%, 79.03/11.99%/8.98%, and 81.29/2.16%/16.55%, respectively, which indicated that the EEQ of CA was poor and presented a trend of gradual deterioration. Consistent with the RSEI trend, Moran’s I index values in 2000, 2005, 2010, 2015, and 2020 were 0.905, 0.893, 0.901, 0.898, and 0.884, respectively, revealing that the spatial distribution of the EEQ was clustered rather than random. The high–high (H-H) areas were mainly located in mountainous areas, and the low–low (L-L) areas were mainly distributed in deserts. Significant regions were mainly located in H-H and L-L, and most reached the significance level of 0.01, indicating that EEQ exhibited strong correlation. The EEQ in CA is affected by both natural and human factors. Among the natural factors, greenness and wetness promoted the EEQ, while heat and dryness reduced the EEQ, and heat had greater effects than the other three indexes. Human factors such as population growth, overgrazing, and hydropower development are important factors affecting the EEQ. This study provides important data for environmental protection and regional planning in arid and semi-arid regions. Full article

Brightness temperature (TB) observations at an infrared channel (10.3 $\mathsf{\mu }\mathrm{m}$) of the Advanced Baseline Imager (ABI) on board the U. S. 16th Geostationary Operational Environmental Satellite (GOES-16) are used for determining tropical cyclone (TC) center positions and rainband sizes. Firstly, an azimuthal spectral analysis method is employed to obtain an azimuthally symmetric center of a TC. Then, inner and outer rainbands radii, denoted as R_IR and R_OR, respectively, are estimated based on radial gradients of TB observations at different azimuthal angles. The radius R_IR describes the size of the TC inner-core region, and the radius R_OR reflects the maximum radial extent of TC rainbands. Compared with the best track centers, the root mean square differences of ABI-determined centers for tropical storms and hurricanes, which totals 108 samples, are 45.35 and 29.06 km, respectively. The larger the average wavenumber-0 amplitude, the smaller the difference between the ABI-determined center and the best track center. The TB-determined R_IR is close but not identical to the radius of the outermost closed isobar and usually coincides with the radius where the strongest wavenumber 1 asymmetry is located. The annulus defined by the two circles with radii of R_OR and R_IR is the asymmetric area of rainbands described by azimuthal wavenumbers 1–3. In general, amplitudes of wavenumber 0 component centered on the ABI-determined center are greater than or equal to those from the best track. For a case of a 60 km distance between the ABI-determined and the best track TC center, the innermost azimuthal waves of wavenumbers 1–3 are nicely distributed along or within the radial distance R_IR that is determined based on the ABI-determined TC center. If R_IR is determined based on the best track, the azimuthal waves of wavenumbers 1–3 are found at several radial distances that are smaller than R_IR. The TC center positions, and rainband size radii are important for many applications, including specification of a bogus vortex for hurricane initialization and verification of propagation mechanism of vortex Rossby waves. Full article

Road traffic elements are important components of roads and the main elements of structuring basic traffic geographic information databases. However, the following problems still exist in the detection and recognition of road traffic elements: dense elements, poor detection effect of multi-scale objects, and small objects being easily affected by occlusion factors. Therefore, an adaptive spatial feature fusion (ASFF) YOLOv5 network (ASFF-YOLOv5) was proposed for the automatic recognition and detection of multiple multiscale road traffic elements. First, the K-means++ algorithm was used to make clustering statistics on the range of multiscale road traffic elements, and the size of the candidate box suitable for the dataset was obtained. Then, a spatial pyramid pooling fast (SPPF) structure was used to improve the classification accuracy and speed while achieving richer feature information extraction. An ASFF strategy based on a receptive field block (RFB) was proposed to improve the feature scale invariance and enhance the detection effect of small objects. Finally, the experimental effect was evaluated by calculating the mean average precision (mAP). Experimental results showed that the mAP value of the proposed method was 93.1%, which is 19.2% higher than that of the original YOLOv5 model. Full article

The impact of climate change on glaciers and the hydrological processes in the easternmost end of the eastern Tianshan Mountains has yet to be understood. This study investigated the glacier change (area, surface elevation and volume change) and analyzed the variation of the observed runoff series over the past four decades in the Yushugou Basin, Eastern Tianshan Mountains. The hydrological processes were also simulated through the HBV-light model to quantify the impact of climate change on the glacier and runoff. The results showed that the glacier area has decreased by 13% and the total volume has decreased by 0.018 km³ over the past four decades. A significant increasing trend (p < 0.01) was detected for the annual runoff and monthly runoff (May to September; p < 0.01). The simulation results revealed that the Yushugou River was highly recharged by glacial runoff and a negative tendency was found for the glacier mass balance on the basin scale over the past 38 years. As a region with an extremely dry climate and the lowest precipitation in the Tianshan Mountains, the observation and simulation of glaciers is critical to the security assessment of local water resources. Full article

Forest fires have frequently occurred and caused great harm to people’s lives. Many researchers use machine learning techniques to predict forest fires by considering spatio-temporal data features. However, it is difficult to efficiently obtain the features from large-scale, multi-source, heterogeneous data. There is a lack of a method that can effectively extract features required by machine learning-based forest fire predictions from multi-source spatio-temporal data. This paper proposes a forest fire prediction method that integrates spatio-temporal knowledge graphs and machine learning models. This method can fuse multi-source heterogeneous spatio-temporal forest fire data by constructing a forest fire semantic ontology and a knowledge graph-based spatio-temporal framework. This paper defines the domain expertise of forest fire analysis as the semantic rules of the knowledge graph. This paper proposes a rule-based reasoning method to obtain the corresponding data for the specific machine learning-based forest fire prediction methods, which are dedicated to tackling the problem with real-time prediction scenarios. This paper performs experiments regarding forest fire predictions based on real-world data in the experimental areas Xichang and Yanyuan in Sichuan province. The results show that the proposed method is beneficial for the fusion of multi-source spatio-temporal data and highly improves the prediction performance in real forest fire prediction scenarios. Full article

Natural hazards generate disasters and huge losses in several aspects, with landslides being one of the natural risks that have caused great impacts worldwide. The aim of this research was to explore a method based on machine learning to evaluate susceptibility to rotational landslides in an area near Cuenca city, Ecuador, which has a high incidence of these phenomena, mainly due to its environmental conditions, and in which, however, such studies are scarce. The implemented method consisted of an artificial neural network multilayer perceptron (ANN MLP), generated with the neuralnet R package, with which, by means of different backpropagation algorithms (RPROP+, RPROP−, SLR, SAG, and Backprop), five landslide susceptibility maps (LSMs) were generated for the study area. A landslide inventory updated to 2019 and 10 conditioning factors, mainly topographical, geological, land cover, and hydrological, were considered. The results obtained, which were validated through the AUC-ROC value and statistical parameters of precision, recall, accuracy, and F-Score, showed a good degree of adjustment and an acceptable predictive capacity. The resulting maps showed that the area has mostly sectors of moderate, high, and very high susceptibility, whose landslide occurrence percentages vary between approximately 63% and 80%. In this research, different variants of the backpropagation algorithm were implemented to verify which one gave the best results. With the implementation of additional methodologies and correct zoning, future analyses could be developed, contributing to adequate territorial planning and better disaster risk management in the area. Full article

Accurately estimating the ocean’s interior structures using sea surface data is of vital importance for understanding the complexities of dynamic ocean processes. In this study, we proposed an advanced machine-learning method, the Light Gradient Boosting Machine (LightGBM)-based Deep Forest (LGB-DF) method, to estimate the ocean subsurface salinity structure (OSSS) in the South China Sea (SCS) by using sea surface data from multiple satellite observations. We selected sea surface salinity (SSS), sea surface temperature (SST), sea surface height (SSH), sea surface wind (SSW, decomposed into eastward wind speed (USSW) and northward wind speed (VSSW) components), and the geographical information (including longitude and latitude) as input data to estimate OSSS in the SCS. Argo data were used to train and validate the LGB-DF model. The model performance was evaluated using root mean square error (RMSE), normalized root mean square error (NRMSE), and determination coefficient (R²). The results showed that the LGB-DF model had a good performance and outperformed the traditional LightGBM model in the estimation of OSSS. The proposed LGB-DF model using sea surface data by SSS/SST/SSH and SSS/SST/SSH/SSW performed less satisfactorily than when considering the contribution of the wind speed and geographical information, indicating that these are important parameters for accurately estimating OSSS. The performance of the LGB-DF model was found to vary with season and water depth. Better estimation accuracy was obtained in winter and autumn, which was due to weaker stratification. This method provided important technical support for estimating the OSSS from satellite-derived sea surface data, which offers a novel insight into oceanic observations. Full article

Precipitable water vapor (PWV) is an important component in the climate system and plays a pivotal role in the global water and energy cycles. Over the years, many approaches have been devised to accurately estimate the PWV. Among them, global navigation satellite systems (GNSS) have become one of the most promising and fastest-growing PWV acquisition methods because of its high accuracy, high temporal and spatial resolution, and ability to acquire PWV in all weather and in near real time. We compared GNSS-derived PWV with a 5 min resolution globally distributed over 14,000 stations from the Nevada Geodetic Laboratory (NGL) from 1994 to 2020 with global radiosonde (RS) data, temperature anomalies, and sea height variations. Then, we examined the temporal and spatial variability of the global PWV and analyzed its climate implications. On a global scale, the average bias and root mean square error (RMSE) between GNSS PWV and RS PWV were ~0.72 ± 1.29 mm and ~2.56 ± 1.13 mm, respectively. PWV decreased with increasing latitude, and the rate of this decrease slowed down at latitudes greater than 35°, with standard deviation (STD) values reaching a maximum at latitudes less than 35°. The global average linear trend was ~0.64 ± 0.81 mm/decade and strongly correlated with temperature and sea height variations. For each 1 °C and 1 mm change, PWV increased by ~2.075 ± 0.765 mm and ~0.015 ± 0.005 mm, respectively. For the time scale, the PWV content peaked ~40 days after the maximum solar radiation of the year (the summer solstice), and the delay was ~40 days relative to the summer solstice. Full article

The hyperspectral, multispectral, and synthetic aperture radar (SAR) remote sensing images provide complementary advantages in high spectral resolution, high spatial resolution, and geometric and polarimetric properties, generally. How to effectively integrate cross-modal information to obtain a high spatial resolution hyperspectral image with the characteristics of the SAR is promising. However, due to divergent imaging mechanisms of modalities, existing SAR and optical image fusion techniques generally remain limited due to the spectral or spatial distortions, especially for complex surface features such as coastal wetlands. This paper provides, for the first time, an efficient multi-resolution collaborative fusion method for multispectral, hyperspectral, and SAR images. We improve generic multi-resolution analysis with spectral-spatial weighted modulation and spectral compensation to achieve minimal spectral loss. The backscattering gradients of SAR are guided to fuse, which is calculated from saliency gradients with edge preserving. The experiments were performed on ZiYuan-1 02D (ZY-1 02D) and GaoFen-5B (AHSI) hyperspectral, Sentinel-2 and GaoFen-5B (VIMI) multispectral, and Sentinel-1 SAR images in the challenging coastal wetlands. Specifically, the fusion results were comprehensively tested and verified on the qualitative, quantitative, and classification metrics. The experimental results show the competitive performance of the proposed method. Full article

Climate variability has profound effects on vegetation. Spatial distributions of vegetation vulnerability that comprehensively consider vegetation sensitivity and resilience are not well understood in China. Furthermore, the combination of cumulative climate effects and a one-month-lagged autoregressive model represents an advance in the technical approach for calculating vegetation sensitivity. In this study, the spatiotemporal characteristics of vegetation sensitivity to climate variability and vegetation resilience were investigated at seasonal scales. Further analysis explored the spatial distributions of vegetation vulnerability for different regions. The results showed that the spatial distribution pattern of vegetation vulnerability exhibited spatial heterogeneity in China. In spring, vegetation vulnerability values of approximately 0.9 were mainly distributed in northern Xinjiang and northern Inner Mongolia, while low values were scattered in Yunnan Province and the central region of East China. The highest proportion of severe vegetation vulnerability to climate variability was observed in the subhumid zone (28.94%), followed by the arid zone (26.27%). In summer and autumn, the proportions of severe vegetation vulnerability in the arid and humid zones were higher than those in the other climate zones. Regarding different vegetation types, the highest proportions of severe vegetation vulnerability were found in sparse vegetation in different seasons, while the highest proportions of slight vegetation vulnerability were found in croplands in different seasons. In addition, vegetation with high vulnerability is prone to change in Northeast and Southwest China. Although ecological restoration projects have been implemented to increase vegetation cover in northern China, low vegetation resilience and high vulnerability were observed in this region. Most grasslands, which were mainly concentrated on the Qinghai–Tibet Plateau, had high vulnerability. Vegetation areas with low resilience were likely to be degraded in this region. The areas with highly vulnerable vegetation on the Qinghai–Tibet Plateau could function as warning signals of vegetation degradation. Knowledge of spatial patterns of vegetation resilience and vegetation vulnerability will help provide scientific guidance for regional environmental protection. Full article

This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. To reduce information redundancy and ensure noise immunity and image detail preservation, we first use a superpixel segmentation to obtain the local spatial information of the HSRRS image. Secondly, based on the bias-corrected fuzzy C-means (BCFCM) clustering algorithm, the superpixel spatial intuitionistic fuzzy membership matrix is constructed by counting an intuitionistic fuzzy set and spatial function. Finally, to minimize the classification uncertainty, the local relation between adjacent superpixels is used to obtain the classification results according to the spectral features of superpixels. Four HSRRS images of different scenes in the aerial image dataset (AID) are selected to analyze the classification performance, and fifteen main existing unsupervised classification algorithms are used to make inter-comparisons with the proposed SSIFCM algorithm. The results show that the overall accuracy and Kappa coefficients obtained by the proposed SSIFCM algorithm are the best within the inter-comparison of fifteen algorithms, which indicates that the SSIFCM algorithm can effectively improve the classification accuracy of HSRRS image. Full article

In the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-based target detection algorithms to obtain effective feature information, resulting in missed and false detection. The effective expression of the feature information of the target to be detected is the key to the target detection algorithm. How to improve the clear expression of image feature information in the network has always been a difficult point. Aiming at the above problems, this paper proposes a new target detection algorithm, the feature information efficient representation network (FIERNet). The algorithm can extract better feature details, enhance network feature fusion and information expression, and improve model detection capabilities. First, the convolution transformer feature extraction (CTFE) module is proposed, and a convolution transformer feature extraction network (CTFENet) is built with this module as a feature extraction block. The network enables the model to obtain more accurate and comprehensive feature information, weakens the interference of invalid information, and improves the overall performance of the network. Second, a new effective feature information fusion (EFIF) module is proposed to enhance the transfer and fusion of the main information of feature maps. Finally, a new frame-decoding formula is proposed to further improve the coincidence between the predicted frame and the target frame and obtain more accurate picture information. Experiments show that the method achieves 94.14% and 92.01% mean precision (mAP) on SSDD and SAR-ship datasets, and it works well on large-scale SAR ship images. In addition, FIERNet greatly reduces the occurrence of missed detection and false detection in SAR ship detection. Compared to other state-of-the-art object detection algorithms, FIERNet outperforms them on various performance metrics on SAR images. Full article

Urban expansion and ecological restoration policies can simultaneously affect land-cover changes and further affect ecosystem services (ES). However, it is unclear whether and to what extent the distribution and equity of urban ES are influenced by the stage of urban development and government policies. This study aims to assess the quantity and equity of ES under different scenarios in cites of China and Europe. Firstly, we used the Conversion of Land Use and its Effects at Small regional extent (CLUE-S) model to simulate future land cover under three scenarios: business-as-usual (BAU), a market-liberal scenario (MLS), and an ecological protection scenario (EPS). Then using ecosystem service model approaches and the landscape analysis, the dynamics of green infrastructure (GI) fraction and connectivity, carbon sequestration, and PM_2.5 removal were further evaluated. The results show that: (1) over the past 20 years, Chinese cities have experienced dramatic changes in land cover and ES relative to European cities. (2) Two metropolises in China, Shanghai and Beijing have experienced an increase in the fraction and connectivity of GI and ES in the long-term built-up areas between 2010 and 2020. (3) EPS scenarios are not only effective in increasing the quantity of ES but also in improving the equity of ES distribution. The proposed framework as well as the results may provide important guidance for future urban planning and sustainable city development. Full article

Rapid urbanization in China has led to an increasing problem of atmospheric nitrogen dioxide (NO₂) pollution, which negatively impacts urban ecology and public health. Nitrogen dioxide is an important atmospheric pollutant, and quantitative spatio-temporal analysis and influencing factor analysis of Chinese cities can help improve urban air pollution. In this study, the spatio-temporal analysis methods were used to explore the variations of NO₂ pollution in Chinese cities from 2005 to 2020. The findings are as follows. In more than half of Chinese cities, NO₂ levels remarkably decreased between 2005 and 2020. The effective NO₂ reduction strategies contributed to the significant NO₂ reduction during the 13th Five-Year Plan (2016–2020). Moreover, we found that the pandemic of COVID-19 alleviated NO₂ pollution in China since it reduced the traffic, industrial, and living activities. The NO₂ pollution in Chinese cities was found highly spatially clustered. The geographically and temporally weighted regression model was used to analyze the spatio-temporal heterogeneity of NO₂ pollution influencing factors in Chinese cities, including natural meteorological and socio-economic factors. The results showed that the GDPPC, population densities, and ambient air pressure were positively correlated with NO₂ pollution. In contrast, the ratio of the tertiary to the secondary industry, temperature, wind speed, and relative humidity negatively impacted the NO₂ pollution level. The findings of this research contribute to the improvement of urban air quality, stimulating the achievements of the sustainable development goals of Chinese cities. Full article

Land desertification is a major challenge to global sustainable development. Therefore, the timely and accurate monitoring of the land desertification status can provide scientific decision support for desertification control. The existing automatic interpretation methods are affected by factors such as “same spectrum different matter”, “different spectrum same object”, staggered distribution of desertification areas, and wide ranges of ground objects. We propose an automatic interpretation method for the remote sensing of land desertification that incorporates multi-scale local binary pattern (MSLBP) and spectral features based on the above issues. First, a multi-scale convolutional LBP feature extraction network is designed to obtain the spatial texture features of remote sensing images and fuse them with spectral features to enhance the feature representation capability of the model. Then, considering the continuity of the distribution of the same kind of ground objects in local space, we designed an adaptive median filtering method to process the probability map of the extreme learning machine (ELM) classifier output to improve the classification accuracy. Four typical datasets were developed using GF-1 multispectral imagery with the Horqin Left Wing Rear Banner as the study area. Experimental results on four datasets show that the proposed method solves the problem of ill classification and omission in classifying the remote sensing images of desertification, effectively suppresses the effects of “homospectrum” and “heterospectrum”, and significantly improves the accuracy of the remote sensing interpretation of land desertification. Full article

Vertical green living walls (VGWs)—growing plants on vertical walls inside or outside buildings—have been suggested as a nature-based solution to improve air quality and comfort in modern cities. However, as with other greenery systems (e.g., agriculture), managing VGW systems requires adequate temporal and spatial monitoring of the plants as well as the surrounding environment. Remote sensing cameras and small, low-cost sensors have become increasingly valuable for conventional vegetation monitoring; nevertheless, they have rarely been used in VGWs. In this descriptive paper, we present a first-of-its-kind remote sensing high-throughput monitoring system in a VGW workplace. The system includes low- and high-cost sensors, thermal and hyperspectral remote sensing cameras, and in situ gas-exchange measurements. In addition, air temperature, relative humidity, and carbon dioxide concentrations are constantly monitored in the operating workplace room (scientific computer lab) where the VGW is established, while data are continuously streamed online to an analytical and visualization web application. Artificial Intelligence is used to automatically monitor changes across the living wall. Preliminary results of our unique monitoring system are presented under actual working room conditions while discussing future directions and potential applications of such a high-throughput remote sensing VGW system. Full article

In this study, the regional Weather Research and Forecasting model (WRF)-based quantitative precipitation forecasts (QPFs) are conducted for an extreme Meiyu rainfall event over East Asia in 2020. The data of water vapor channels 9 and 10 from the Advanced Geosynchronous Radiation Imager (AGRI) onboard the Fengyun-4A (FY-4A) satellite are assimilated through the Gridpoint Statistical Interpolation (GSI) system. It shows that a reasonable amount of assimilated AGRI data can produce reasonable water vapor increments, compared to the too sparse or dense assimilated AGRI observations. In addition, the critical success indexes (CSIs) of the precipitation forecasts within 72 h are obviously improved. The enhanced variational bias correction (VarBC) scheme is applied to remove the air-mass and scan-angle biases, and the mean observation-minus-background (O − B) values before and after the VarBC of channel 9 are −1.185 and 0.02 K, respectively, and those of channel 10 are −0.559 and −0.01 K, respectively. Assimilating the upper-level channel 9 data of AGRI (EXP_WV9) lead to a neutral-to-positive effect on QPFs, compared to the control run (CTL), which is based on the assimilation of Advanced Microwave Sounding Unit-A (AMSU-A) data. In particular, the CSIs from 42 to 72 h are significantly improved. However, the assimilation of the AGRI channel 10 (EXP_WV10) shows a neutral-to-negative effect on QPFs in this study, probably due to the complicated surface situations. This study confirms the feasibility of assimilating the water vapor channel data of FY4A AGRI in the GSI system and highlights the importance of assimilating AGRI channel 9 data to improve the QPFs of the Meiyu rainfall event. Full article

Monitoring the evolution of lava flows is a challenging task for volcano observatories, especially in remote volcanic areas. Here we present a near real-time (every 12 h) and free tool for producing interactive thermal maps of the advance of lava flows over time by taking advantage of the free thermal data provided by FIRMS and the open-source R software. To achieve this, we applied two filters on the FIRMS datasets, one on the satellite layout (track) and another on the fire radiative power (FRP). To determine the latter, we carried out a detailed statistical analysis of the FRP values of nine hotspot subaerial eruptions that included Cumbre Vieja-2021 (Spain), Fagradalsfjall-2021 (Iceland), LERZ Kilauea-2018 (USA), and six eruptions on the Galápagos Archipelago (Ecuador). We found that an FRP filter of 35 ± 17 MW/pixel worked well at the onset and during the first weeks of an eruption. Afterward, once the cumulative statistical parameters had stabilized, a filter that better fit the investigated case could be obtained by running our statistical code. Using the suggested filters, the thermal maps resulting from our mapping code have an accuracy higher than 75% on average when compared with the official lava flow maps of each eruption and an offset of only 3% regarding the maximum lava flow extension. Therefore, our easy-to-use codes constitute an additional, novel, and simple tool for rapid preliminary mapping of lava fields during crises, especially when regular overflights and/or unoccupied aerial vehicle campaigns are out of budget. Full article

Aerosol direct radiative forcing is strongly dependent on aerosol distributions and aerosol types. A detailed understanding of such information is still missing at the Alpine region, which currently undergoes amplified climate warming. Our goal was to study the vertical variability of aerosol types within and above the Vipava valley (45.87$°$N, 13.90$°$E, 125 m a.s.l.) to reveal the vertical impact of each particular aerosol type on this region, a representative complex terrain in the Alpine region which often suffers from air pollution in the wintertime. This investigation was performed using the entire dataset of a dual-wavelength polarization Raman lidar system, which covers 33 nights from September to December 2017. The lidar provides measurements from midnight to early morning (typically from 00:00 to 06:00 CET) to provide aerosol-type dependent properties, which include particle linear depolarization ratio, lidar ratio at 355 nm and the aerosol backscatter Ångström exponent between 355 nm and 1064 nm. These aerosol properties were compared with similar studies, and the aerosol types were identified by the measured aerosol optical properties. Primary anthropogenic aerosols within the valley are mainly emitted from two sources: individual domestic heating systems, which mostly use biomass fuel, and traffic emissions. Natural aerosols, such as mineral dust and sea salt, are mostly transported over large distances. A mixture of two or more aerosol types was generally found. The aerosol characterization and statistical properties of vertical aerosol distributions were performed up to 3 km. Full article

Detection of the Fusarium head blight (FHB) is crucial for wheat yield protection, with precise and rapid FHB detection increasing wheat yield and protecting the agricultural ecological environment. FHB detection tasks in agricultural production are currently handled by cloud servers and utilize unmanned aerial vehicles (UAVs). Hence, this paper proposed a lightweight model for wheat ear FHB detection based on UAV-enabled edge computing, aiming to achieve the purpose of intelligent prevention and control of agricultural disease. Our model utilized the You Only Look Once version 4 (YOLOv4) and MobileNet deep learning architectures and was applicable in edge devices, balancing accuracy, and FHB detection in real-time. Specifically, the backbone network Cross Stage Partial Darknet53 (CSPDarknet53) of YOLOv4 was replaced by a lightweight network, significantly decreasing the network parameters and the computing complexity. Additionally, we employed the Complete Intersection over Union (CIoU) and Non-Maximum Suppression (NMS) to regress the loss function to guarantee the detection accuracy of FHB. Furthermore, the loss function incorporated the focal loss to reduce the error caused by the unbalanced positive and negative sample distribution. Finally, mixed-up and transfer learning schemes enhanced the model’s generalization ability. The experimental results demonstrated that the proposed model performed admirably well in detecting FHB of the wheat ear, with an accuracy of 93.69%, and it was somewhat better than the MobileNetv2-YOLOv4 model (F1 by 4%, AP by 3.5%, Recall by 4.1%, and Precision by 1.6%). Meanwhile, the suggested model was scaled down to a fifth of the size of the state-of-the-art object detection models. Overall, the proposed model could be deployed on UAVs so that wheat ear FHB detection results could be sent back to the end-users to intelligently decide in time, promoting the intelligent control of agricultural disease. Full article

Numerous individual tree detection (ITD) methods have been developed for use with airborne laser scanning (ALS) data to provide tree-scale forest inventories across large spatial extents. Despite the growing number of methods, relatively few have been comparatively assessed using a single benchmark forest inventory validation dataset, limiting their operational application. In this study, we assessed seven ITD methods, representing three common approaches (point-cloud-based, raster-based, hybrid), across coniferous forest stands with diverse structure and composition to understand how ITD and height measurement accuracy vary with method, input parameters and data, and stand density. There was little variability in accuracy between the ITD methods where the average F-score and standard deviation (±SD) were 0.47 ± 0.03 using a lower pulse density ALS dataset with an average of 8 pulses per square meter (ppm²) and 0.50 ± 0.02 using a higher pulse density ALS dataset with an average of 22 ppm². Using higher ALS pulse density data produced higher ITD accuracies (F-score increase of 10–13%) in some of the methods versus more modest gains in other methods (F-score increase of 1–3%). Omission errors were strongly related with stand density and largely consisted of suppressed trees underneath the dominant canopy. Simple canopy height model (CHM)-based methods that utilized fixed-size local maximum filters had the lowest omission errors for trees across all canopy positions. ITD accuracy had large intra-method variation depending on input parameters; however, the highest accuracies were obtained when parameters such as search window size and spacing thresholds were equal to or less than the average crown diameter of trees in the study area. All ITD methods produced height measurements for the detected trees that had low RMSE (<1.1 m) and bias (<0.5 m). Overall, the results from this study may help guide end-users with ITD method application and highlight future ITD method improvements. Full article

The North American Derecho of 29–30 June 2012 exhibits many classic progressive and serial derecho features. It remains one of the highest-impact derecho-producing convective systems (DCS) over CONUS since 2000. This research effort enhances the understanding of the science of operational forecasting of severe windstorms through examples of employing new satellite and ground-based microwave and vertical wind profile data. During the track of the derecho from the upper Midwestern U.S. through the Mid-Atlantic region on 29 June 2012, clear signatures associated with a severe MCS were apparent in polar-orbiting satellite imagery, especially from the EPS METOP-A Microwave Humidity Sounder (MHS), Defense Meteorological Satellite Program (DMSP) Special Sensor Microwave Imager Sounder (SSMIS), and NASA TERRA Moderate Resolution Imaging Spectroradiometer (MODIS). In addition, morning (descending node) and the evening (ascending node) METOP-A Infrared Atmospheric Sounding Interferometer (IASI) soundings are compared to soundings from surface-based Radiometrics Corporation MP-3000 series microwave radiometer profilers (MWRPs) along the track of the derecho system. The co-located IASI and MWRP soundings revealed a pre-convective environment that indicated a favorable volatile tropospheric profile for severe downburst wind generation. An important outcome of this study will be to formulate a functional relationship between satellite-derived parameters and signatures, and severe convective wind occurrence. Furthermore, a comprehensive approach to observational data analysis involves both surface- and satellite-based instrumentation. Because this approach utilizes operational products available to weather service forecasters, it can feasibly be used for monitoring and forecasting local-scale downburst occurrence within derecho systems, as well as larger-scale convective wind intensity associated with the entire DCS. Full article

This study quantitatively examines the contribution of assimilating observations in the regions with different dynamic instabilities to the analysis and prediction of an extreme rainstorm event in Fujian Province of China. The wind profiling radar (WPR) observations are classified into two groups, i.e., strong and weak instability areas (SIA and WIA), according to their local dynamic instability identified by the ensemble spread. Their performance of assimilation and prediction in terms of the wind and precipitation are evaluated and compared in detail. The results show that the wind analysis error by assimilating all of the WPR observations can be reduced by about 30%. In particular, the wind analysis errors by only assimilating the observations in the SIA are about 12% lower than those in the WIA. They are related to the existence of the low-level horizontal wind shear with strong instability in the SIA. The case study shows that the assimilation of observations in the SIA can effectively correct the wind fields on the two sides of the wind shear line, producing an improved precipitation forecast compared to observation assimilation in the WIA. Full article