Search

The point cloud segmentation method plays an important role in practical applications, such as remote sensing, mobile robots, and 3D modeling. However, there are still some limitations to the current point cloud data segmentation method when applied to large-scale scenes. Therefore, this paper proposes an adaptive clustering segmentation method. In this method, the threshold for clustering points within the point cloud is calculated using the characteristic parameters of adjacent points. After completing the preliminary segmentation of the point cloud, the segmentation results are further refined according to the standard deviation of the cluster points. Then, the cluster points whose number does not meet the conditions are further segmented, and, finally, scene point cloud data segmentation is realized. To test the superiority of this method, this study was based on point cloud data from a park in Guilin, Guangxi, China. The experimental results showed that this method is more practical and efficient than other methods, and it can effectively segment all ground objects and ground point cloud data in a scene. Compared with other segmentation methods that are easily affected by parameters, this method has strong robustness. In order to verify the universality of the method proposed in this paper, we test a public data set provided by ISPRS. The method achieves good segmentation results for multiple sample data, and it can distinguish noise points in a scene. [ABSTRACT FROM AUTHOR]

This study investigates the application of hyperspectral image space–spectral fusion technology in lithologic classification, using data from China's GF-5 and Europe's Sentinel-2A. The research focuses on the southern region of Tuanjie Peak in the Western Kunlun Range, comparing five space–spectral fusion methods: GSA, SFIM, CNMF, HySure, and NonRegSRNet. To comprehensively evaluate the effectiveness and applicability of these fusion methods, the study conducts a comprehensive assessment from three aspects: evaluation of fusion effects, lithologic classification experiments, and field validation. In the evaluation of fusion effects, the study uses an index analysis and comparison of spectral curves before and after fusion, concluding that the GSA fusion method performs the best. For lithologic classification, the Random Forest (RF) classification method is used, training with both area and point samples. The classification results from area sample training show significantly higher overall accuracy compared to point samples, aligning well with 1:50,000 scale geological maps. In field validation, the study employs on-site verification combined with microscopic identification and comparison of images with actual spectral fusion, finding that the classification results for the five lithologies are essentially consistent with field validation results. The "GSA+RF" method combination established in this paper, based on data from GF-5 and Sentinel-2A satellites, can provide technical support for lithological classification in similar high-altitude regions. [ABSTRACT FROM AUTHOR]

Land desertification is one of the serious ecological and environmental problems facing mankind today, which threatens the survival and development of human society. China is one of the countries with the most serious land desertification problems in the world. Therefore, it is of great theoretical value and practical significance to carry out accurate identification and monitoring of land desertification and its influencing factors in ecologically fragile areas of China. This is conducive to curbing land desertification and ensuring regional ecological security. Minqin County, Gansu Province, located in northwestern China, is one of the most serious areas of land desertification, which is also one of the four sandstorm sources in China. Based on ENVINet5, this paper constructs a high-precision land desertification identification method with an accuracy of 93.71%, which analyzes the trend and reasons of land desertification in this area, provides suggestions for disaster prevention in Minqin County. and provides a reference for other similar areas to make corresponding desertification control policies. [ABSTRACT FROM AUTHOR]

The Three Gorges is a region with a very high landslide distribution density and a concentrated population. In Three Gorges there are often landslide disasters, and the potential risk of landslides is tremendous. In this paper, focusing on Three Gorges, which has a complicated landform, spatial forecasting of landslides is studied by establishing 20 forecast factors (spectra, texture, vegetation coverage, water level of reservoir, slope structure, engineering rock group, elevation, slope, aspect, etc). China-Brazil Earth Resources Satellite (Cbers) images were adopted based on C4.5 decision tree to mine spatial forecast landslide criteria in Guojiaba Town (Zhigui County) in Three Gorges and based on this knowledge, perform intelligent spatial landslide forecasts for Guojiaba Town. All landslides lie in the dangerous and unstable regions, so the forecast result is good. The method proposed in the paper is compared with seven other methods: IsoData, K-Means, Mahalanobis Distance, Maximum Likelihood, Minimum Distance, Parallelepiped and Information Content Model. The experimental results show that the method proposed in this paper has a high forecast precision, noticeably higher than that of the other seven methods. [ABSTRACT FROM AUTHOR]

Seagrass distribution is a very important index for costal management and protection. Seagrass distribution changes can be used as indexes to analyze the reasons for the changes. In this paper, in situ hyperspectral observation and satellite images of QuickBird, CBERS (China Brazil Earth Resources Satellite data) and Landsat data were used to retrieve bio-optical models and seagrass (Enhalus acoroides, Thalassia hemperichii) distribution in Xincun Bay, Hainan province, and seagrass distribution changes from 1991 to 2006 were analyzed. Hyperspectral results showed that the spectral bands at 555, 635, 650 and 675 nm are sensitive to leaf area index (LAI). Seagrass detection with QuickBird was more accurate than that with Landsat TM and CBERS; five classes could be classified clearly and used as correction for seagrass remote sensing data from Landsat TM and CBERS. In order to better describe seagrass distribution changes, the seagrass distribution area was divided as three regions: region A connected with region B in 1991, however it separated in 1999 and was wholly separated in 2001; seagrass in region C shrank gradually and could not be detected in 2006. Analysis of the reasons for seagrass reduction indicated it was mainly affected by aquaculture and typhoons and in recent years, by land use changes. [ABSTRACT FROM AUTHOR]

In the field of water depth inversion using imagery, the commonly used methods are based on water reflectance and wave extraction. Among these methods, the Optical Bathymetry Method (OBM) is significantly influenced by bottom sediment and climate, while the wave method requires a specific study area. This study introduces a method combining the FFT and spatial profile measurement to invert the wavelength of the wave bathymetry method (WBM), which enhances accuracy and reduces workload. The method was applied to remote sensing images of Sanya Bay in China, obtained from the Worldview satellite. The average error of the inverted depth results after applying the wavelength inversion technique was 15.9%, demonstrating consistency with the depth measurements obtained through the OBM in clear water of the bay. The WBM has notable advantages over the OBM, as it is unaffected by water quality. In addition, the influence of wave period on the accuracy of water depth retrieval was theoretically evaluated, revealing that a larger wave period leads to a better depth measurement. The depth measurement from two images with different wave periods aligned with the theoretical analysis. These results showcase the applicability and potential of the WBM for accurately estimating water depth in various coastal environments. [ABSTRACT FROM AUTHOR]

A new Field Imaging Spectrometer System (FISS) based on a cooling area CCD was developed. This paper describes the imaging principle, structural design, and main parameters of the FISS sensor. The FISS was spectrally calibrated with a double grating monochromator to determine the center wavelength and FWHM of each band. Calibration results showed that the spectral range of the FISS system is 437-902 nm, the number of channels is 344 and the spectral resolution of each channel is better than 5 nm. An integrating sphere was used to achieve absolute radiometric calibration of the FISS with less than 5% calibration error for each band. There are 215 channels with signal to noise ratios (SNRs) greater than 500 (62.5% of the bands). The results demonstrated that the FISS has achieved high performance that assures the feasibility of its practical use in various fields. [ABSTRACT FROM AUTHOR]

Data on the urban environment such as climate or air quality is usually collected at a few point monitoring stations distributed over a city. However, the synoptic viewpoint of satellites where a whole city is visible on a single image permits the collection of spatially comprehensive data at city-wide scale. In spite of rapid developments in remote sensing systems, deficiencies in image resolution and algorithm development still exist for applications such as air quality monitoring and urban heat island analysis. This paper describes state-of-the-art techniques for enhancing and maximising the spatial detail available from satellite images, and demonstrates their applications to the densely urbanised environment of Hong Kong. An Emissivity Modulation technique for spatial enhancement of thermal satellite images permits modelling of urban microclimate in combination with other urban structural parameters at local scale. For air quality monitoring, a Minimum Reflectance Technique (MRT) has been developed for MODIS 500 m images. The techniques described can promote the routine utilization of remotely sensed images for environmental monitoring in cities of the 21st century. [ABSTRACT FROM AUTHOR]

Soil salinization is a major obstacle to land productivity, crop yield and crop quality in arid areas and directly affects food security. Soil profile salt data are key for accurately determining irrigation volumes. To explore the potential for using Landsat 8 time-series data to monitor soil salinization, 172 Landsat 8 images from 2013 to 2019 were obtained from the Alar Reclamation Area of Xinjiang, northwest China. The multiyear extreme dataset was synthesized from the annual maximum or minimum values of 16 vegetation indices, which were combined with the soil conductivity of 540 samples from soil profiles at 0~0.375 m, 0~0.75 m and 0~1.00 m depths in 30 cotton fields with varying degrees of salinization as investigated by EM38-MK2. Three remote sensing monitoring models for soil conductivity at different depths were constructed using the Cubist method, and digital mapping was carried out. The results showed that the Cubist model of soil profile electrical conductivity from 0 to 0.375 m, 0 to 0.75 m and 0 to 1.00 m showed high prediction accuracy, and the determination coefficients of the prediction set were 0.80, 0.74 and 0.72, respectively. Therefore, it is feasible to use a multiyear extreme value for the vegetation index combined with a Cubist modeling method to monitor soil profile salinization at a regional scale. [ABSTRACT FROM AUTHOR]

Considering the complexity of the physical model of wildfire occurrence, this paper develops a method to evaluate the wildfire risk of transmission-line corridors based on Naïve Bayes Network (NBN). First, the data of 14 wildfire-related factors including anthropogenic, physiographic, and meteorologic factors, were collected and analyzed. Then, the relief algorithm is used to rank the importance of factors according to their impacts on wildfire occurrence. After eliminating the least important factors in turn, an optimal wildfire risk assessment model for transmission-line corridors was constructed based on the NBN. Finally, this model was carried out and visualized in Guangxi province in southern China. Then a cost function was proposed to further verify the applicability of the wildfire risk distribution map. The fire events monitored by satellites during the first season in 2020 shows that 81.8% of fires fall in high- and very-high-risk regions. [ABSTRACT FROM AUTHOR]

Image classification is a fundamental task in remote sensing image processing. In recent years, deep convolutional neural networks (DCNNs) have experienced significant breakthroughs in natural image recognition. The remote sensing field, however, is still lacking a large-scale benchmark similar to ImageNet. In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsourced data. Using crowdsourced data, such as Open Street Map (OSM) data, ground objects in remote sensing images can be annotated effectively using points of interest, vector data from OSM, or other crowdsourced data. These annotated images can, then, be used in remote sensing image classification tasks. Based on this method, we construct a worldwide large-scale benchmark for remote sensing image classification. This benchmark has large-scale geographical distribution and large total image number. It contains six categories with 35 sub-classes of more than 24,000 images of size 256 × 256 pixels. This classification system of ground objects is defined according to the national standard of land-use classification in China and is inspired by the hierarchy mechanism of ImageNet. Finally, we conduct numerous experiments to compare RSI-CB with the SAT-4, SAT-6, and UC-Merced data sets. The experiments show that RSI-CB is more suitable as a benchmark for remote sensing image classification tasks than other benchmarks in the big data era and has many potential applications. [ABSTRACT FROM AUTHOR]

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation. [ABSTRACT FROM AUTHOR]

Mapping the distribution of bamboo species is vital for the sustainable management of bamboo and for assessing its ecological and socioeconomic value. However, the spectral similarity between bamboo species makes this work extremely challenging through remote sensing technology. Existing related studies rarely integrate multiple feature variables and consider how to quantify the main factors affecting classification. Therefore, feature variables, such as spectra, topography, texture, and vegetation indices, were used to construct the XGBoost model to identify bamboo species using the Zhuhai-1 Orbita hyperspectral (OHS) imagery in the Southern Sichuan Bamboo Sea and its surrounding areas in Sichuan Province, China. The random forest and Spearman's rank correlation analysis were used to sort the main variables that affect classification accuracy and minimize the effects of multicollinearity among variables. The main findings were: (1) The XGBoost model achieved accurate and reliable classification results. The XGBoost model had a higher overall accuracy (80.6%), kappa coefficient (0.708), and mean F1-score (0.805) than the spectral angle mapper (SAM) method; (2) The optimal feature variables that were important and uncorrelated for classification accuracy included the blue band (B1, 464–468 nm), near-infrared band (B27, 861–871 nm), green band (B5, 534–539 nm), elevation, texture feature mean, green band (B4, 517–523 nm), and red edge band (B17, 711–720 nm); and (3) the XGBoost model based on the optimal feature variable selection showed good adaptability to land classification and had better classification performance. Moreover, the mean F1-score indicated that the model could well balance the user's and producer's accuracy. Additionally, our study demonstrated that OHS imagery has great potential for land cover classification and that combining multiple features to enhance classification is an approach worth exploring. Our study provides a methodological reference for the application of OHS images for plant species identification. [ABSTRACT FROM AUTHOR]

Observation schedules depend upon the accurate understanding of a single sensor’s observation capability and the interrelated observation capability information on multiple sensors. The general ontologies for sensors and observations are abundant. However, few observation capability ontologies for satellite sensors are available, and no study has described the dynamic associations among the observation capabilities of multiple sensors used for integrated observational planning. This limitation results in a failure to realize effective sensor selection. This paper develops a sensor observation capability association (SOCA) ontology model that is resolved around the task-sensor-observation capability (TSOC) ontology pattern. The pattern is developed considering the stimulus-sensor-observation (SSO) ontology design pattern, which focuses on facilitating sensor selection for one observation task. The core aim of the SOCA ontology model is to achieve an observation capability semantic association. A prototype system called SemOCAssociation was developed, and an experiment was conducted for flood observations in the Jinsha River basin in China. The results of this experiment verified that the SOCA ontology based association method can help sensor planners intuitively and accurately make evidence-based sensor selection decisions for a given flood observation task, which facilitates efficient and effective observational planning for flood satellite sensors. [ABSTRACT FROM AUTHOR]

The MODerate resolution Imaging Spectroradiometer (MODIS) and the Advanced Spaceborne Thermal Emission Reflection Radiometer (ASTER) are onboard the same satellite platform NASA TERRA. Both MODIS and ASTER offer routine retrieval of land surface temperatures (LSTs), and the ASTER- and MODIS-retrieved LST products have been used worldwide. Because a large fraction of the earth surface consists of mountainous areas, variations in elevation, terrain slope and aspect angles can cause biases in the retrieved LSTs. However, terrain-induced effects are generally neglected in most satellite retrievals, which may generate discrepancy between ASTER and MODIS LSTs. In this paper, we reported the terrain effects on the LST discrepancy with a case examination over a relief area at the Loess Plateau of China. Results showed that the terrain-induced effects were not major, but nevertheless important for the total LST discrepancy. A large local slope did not necessarily lead to a large LST discrepancy. The angle of emitted radiance was more important than the angle of local slope in generating the LST discrepancy. Specifically, the conventional terrain correction may be unsuitable for densely vegetated areas. The distribution of ASTER-to-MODIS emissivity suggested that the terrain correction was included in the generalized split window (GSW) based approach used to rectify MODIS LSTs. Further study should include the classification-induced uncertainty in emissivity for reliable use of satellite-retrieved LSTs over relief areas. [ABSTRACT FROM AUTHOR]

Areas and spatial distribution information of paddy rice are important for managing food security, water use, and climate change. However, there are many difficulties in mapping paddy rice, especially mapping multi-season paddy rice in rainy regions, including differences in phenology, the influence of weather, and farmland fragmentation. To resolve these problems, a novel multi-season paddy rice mapping approach based on Sentinel-1A and Landsat-8 data is proposed. First, Sentinel-1A data were enhanced based on the fact that the backscattering coefficient of paddy rice varies according to its growth stage. Second, cropland information was enhanced based on the fact that the NDVI of cropland in winter is lower than that in the growing season. Then, paddy rice and cropland areas were extracted using a K-Means unsupervised classifier with enhanced images. Third, to further improve the paddy rice classification accuracy, cropland information was utilized to optimize distribution of paddy rice by the fact that paddy rice must be planted in cropland. Classification accuracy was validated based on ground-data from 25 field survey quadrats measuring 600 m × 600 m. The results show that: multi-season paddy rice planting areas effectively was extracted by the method and adjusted early rice area of 1630.84 km2, adjusted middle rice area of 556.21 km2, and adjusted late rice area of 3138.37 km2. The overall accuracy was 98.10%, with a kappa coefficient of 0.94. [ABSTRACT FROM AUTHOR]

In the arid grasslands of northern China, unreasonable grazing methods can reduce the water content and species numbers of grassland vegetation. This project uses solar-powered GPS collars to obtain track data for sheep grazing. In order to eliminate the trajectory data of the rest area and the drinking area, the kernel density analysis method was used to cluster the trajectory point data. At the same time, the vegetation index of the experimental area, including elevation, slope and aspect data, was obtained through satellite remote sensing images. Therefore, using trajectory data and remote sensing image data to establish a neural network model of grazing intensity of sheep, the accuracy of the model could be high. The results showed that the best input parameters of the model were the combination of vegetation index, sheep weight, duration, moving distance and ambient temperature, where the coefficient of determination R 2 = 0.97 , and the mean square error MSE = 0.73. The error of grazing intensity obtained by the model is the smallest, and the spatial-temporal distribution of grazing intensity can reflect the actual situation of grazing intensity in different locations. Monitoring the grazing behavior of sheep in real time and obtaining the spatial-temporal distribution of their grazing intensity can provide a basis for scientific grazing. [ABSTRACT FROM AUTHOR]

Through the integrated approach of remote sensing and geographic information system (GIS) techniques, four Landsat TM/ETM+ imagery acquired during 1979 and 2008 were used to quantitatively characterize the patterns of land use and land cover change (LULC) and urban sprawl in the fast-growing Shanghai Metropolis, China. Results showed that, the urban/built-up area grew on average by 4,242.06 ha yr-1. Bare land grew by 1,594.66 ha yr-1 on average. In contrast, cropland decreased by 3,286.26 ha yr-1 on average, followed by forest and shrub, water, and tidal land, which decreased by 1,331.33 ha yr-1, 903.43 ha yr-1, and 315.72 ha yr-1 on average, respectively. As a result, during 1979 and 2008 approximately 83.83% of the newly urban/built-up land was converted from cropland (67.35%), forest and shrub (9.12%), water (4.80%), and tidal land (2.19%). Another significant change was the continuous increase in regular residents, which played a very important role in contributing to local population growth and increase in urban/builtup land. This can be explained with this city's huge demand for investment and qualified labor since the latest industrial transformation. Moreover, with a decrease in cropland, the proportion of population engaged in farming decreased 13.84%. Therefore, significant socio-economic transformation occurred, and this would lead to new demand for land resources. However, due to very scarce land resources and overload of population in Shanghai, the drive to achieve economic goals at the loss of cropland, water, and the other lands is not sustainable. Future urban planning policy aiming at ensuring a win-win balance between sustainable land use and economic growth is urgently needed. [ABSTRACT FROM AUTHOR]

The use of Geographic Information Systems (GIS) and Remote Sensing (RS) by climatologists, environmentalists and urban planners for three dimensional modeling and visualization of the landscape is well established. However no previous study has implemented these techniques for 3D modeling of atmospheric aerosols because air quality data is traditionally measured at ground points, or from satellite images, with no vertical dimension. This study presents a prototype for modeling and visualizing aerosol vertical profiles over a 3D urban landscape in Hong Kong. The method uses a newly developed technique for the derivation of aerosol vertical profiles from AERONET sunphotometer measurements and surface visibility data, and links these to a 3D urban model. This permits automated modeling and visualization of aerosol concentrations at different atmospheric levels over the urban landscape in near-real time. Since the GIS platform permits presentation of the aerosol vertical distribution in 3D, it can be related to the built environment of the city. Examples are given of the applications of the model, including diagnosis of the relative contribution of vehicle emissions to pollution levels in the city, based on increased near-surface concentrations around weekday rush-hour times. The ability to model changes in air quality and visibility from ground level to the top of tall buildings is also demonstrated, and this has implications for energy use and environmental policies for the tall mega-cities of the future. [ABSTRACT FROM AUTHOR]

The spatial distribution of population is closely related to land use and land cover (LULC) patterns on both regional and global scales. Population can be redistributed onto geo-referenced square grids according to this relation. In the past decades, various approaches to monitoring LULC using remote sensing and Geographic Information Systems (GIS) have been developed, which makes it possible for efficient updating of georeferenced population data. A Spatial Population Updating System (SPUS) is developed for updating the gridded population database of China based on remote sensing, GIS and spatial database technologies, with a spatial resolution of 1 km by 1 km. The SPUS can process standard Moderate Resolution Imaging Spectroradiometer (MODIS L1B) data integrated with a Pattern Decomposition Method (PDM) and an LULC-Conversion Model to obtain patterns of land use and land cover, and provide input parameters for a Population Spatialization Model (PSM). The PSM embedded in SPUS is used for generating 1 km by 1 km gridded population data in each population distribution region based on natural and socio-economic variables. Validation results from finer township-level census data of Yishui County suggest that the gridded population database produced by the SPUS is reliable. [ABSTRACT FROM AUTHOR]

As a local environmental issue with global importance, land use/land cover change (LUCC) has always been one of the key issues in geography and environmental studies with the expansion of regional case studies. While most of LUCC studies in China have focused on urban land use change, meanwhile, compared with the rapid change of urban land use in the coastal areas of eastern China, slow but distinct rural land use changes have also occurred in the mountainous areas of western China since the late 1980s. In this case through a study in Lijiang County of Yunnan Province, with the application of remote sensing data and geographic information system techniques, the process of rural land use change in mountain areas of western China was monitored through extensive statistical analysis of detailed regional data. The results showed significant increases in construction land, paddy field and dry land, and a decrease in dense forest land and waste grassland between 1986 and 2002. The conversions between dense forest land and sparse forest land, grassland, waste grassland and dry land were the primary processes of rural land use change. Sparse forest land had the highest rate of land use change, with glacier or snow-capped land the lowest; while human settlement and rural economic development were found to be the main driving forces of regional difference in the integrated land use change rate among the 24 towns of Lijiang County. Quantified through landscape metrics, spatial patterns of rural land use change were represented as an increase in landscape diversity and landscape fragmentation, and the regularization of patch shapes, suggesting the intensification of human disturbances and degradation of ecological quality in the rural landscape. [ABSTRACT FROM AUTHOR]

Land use/cover change (LUCC), which results from the complex interaction of social, ecological and geophysical processes, is a major issue and the main cause of global environmental change. This study analyzed the land use/cover dynamics and their environmental and socio-political forces in the upper reaches of the Yangtze River from 1980 to 2000 by using remote sensing, climatic and socio-economic data from both research institutes and government departments. The results indicated that there had been significant land use/cover changes between 1980 and 2000 in the study area, which were characterized by a severe replacement of cropland and woodland with grassland and builtup land. The transition matrices highlight the dominant dynamic events and the internal conversions between land use/cover types during the study period and reveal two distinct transition phases. Land use/cover changes in the upper reaches of the Yangtze River during 1980 to 2000, while restricted by environmental attributes, were strongly driven by socio-political factors. However, excessively pursuing higher land use benefits likely results in serious environmental degradation. This study suggests that the restructuring of land use should be based on land suitability and sustainable protection of fragile environment in the upper reaches of the Yangtze River. A thorough comprehension of historical changes will enhance our capability to predict future land use change and contribute to effective management strategies and policies for the rational land use. [ABSTRACT FROM AUTHOR]

Accurate and quantitative assessment of the impact of natural environmental changes and human activities on total suspended solids (TSS) concentration is one of the important components of water environment protection. Due to the limits of traditional cross-sectional point monitoring, a novel water quality evaluation method based on the Markov model and remote sensing retrieval is proposed to realize the innovation of large-scale spatial monitoring across administrative boundaries. Additionally, to explore the spatiotemporal characteristics and driving factors of TSS, a new three-band remote sensing model of TSS was built by regression analysis for the inland reservoir using the synchronous field spectral data, water quality samples and remote sensing data in the trans-provincial Hedi Reservoir in the Guangdong and Guangxi Provinces of South China. The results show that: (1) The three-band model based on the OLI sensor explained about 82% of the TSS concentration variation ( R 2 = 0.81 ,   N = 34 ,     p   value < 0.01 ) with an acceptable validation accuracy ( R M S E = 6.24   mg / L , M R E = 18.02 % ,   N = 15 ), which is basically the first model of its kind available in South China. (2) The TSS concentration has spatial distribution characteristics of high upstream and low downstream, where the average TSS at 31.54 mg/L in the upstream are 2.5 times those of the downstream (12.55 mg/L). (3) Different seasons and rainfall are important factors affecting the TSS in the upstream cross-border area, the TSS in the dry season are higher with average TSS of 33.66 mg/L and TSS are negatively correlated with rainfall from upstream mankind activity. Generally, TSS are higher in rainy seasons than those in dry seasons. However, the result shows that TSS are negatively correlated with rainfall, which means human activities have higher impacts on water quality than climate change. (4) The Markov dynamic evaluation results show that the water quality improvement in the upstream Shijiao Town is the most obvious, especially in 2018, the improvement in the water quality level crossed three levels and the TSS were the lowest. This study provided a technical method for remote sensing dynamic monitoring of water quality in a large reservoir, which is of great significance for remediation of the water environment and the effective evaluation of the river and lake chief system in China. [ABSTRACT FROM AUTHOR]

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the "pooling" process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction. [ABSTRACT FROM AUTHOR]

Integrated and intelligent in situ observations are important for the remote sensing monitoring of dynamic water environments. To meet the field investigation requirements of ocean color remote sensing, we developed a water color remote sensing-oriented unmanned surface vehicle (WC-USV), which consisted of an unmanned surface vehicle platform with ground control station, data acquisition, and transmission modules. The WC-USV was designed with functions, such as remote controlling, status monitoring, automatic obstacle avoidance, and water and meteorological parameter measurement acquisition, transmission, and processing. The key data acquisition module consisted of four parts: A floating optical buoy (FOBY) for collecting remote sensing reflectance ( R r s ) via the skylight-blocked approach; a water sample autocollection system that can collect 12 1-L bottles for analysis in the laboratory; a water quality measurement system for obtaining water parameters, including Chlorophyll-a (Chl-a), turbidity, and water temperature, among others; and meteorological sensors for measuring wind speed and direction, air pressure, temperature, and humidity. Field experiments were conducted to validate the performance of the WC-USV on 23–28 March 2018 in the Honghu Lake, which is the seventh largest freshwater lake in China. The tests proved the following: (1) The WC-USV performed well in terms of autonomous navigation and obstacle avoidance; (2) the mounted FOBY-derived R r s showed good precision in terms of the quality assurance score (QAS), which was higher than 0.98; (3) the Chl-a and suspended matters (SPM) as ocean color parameters measured by the WC-USV were highly consistent with laboratory analysis results, with determination coefficients (R2) of 0.71 and 0.77, respectively; and (4) meteorological parameters could be continuously and stably measured by WC-USV. Results demonstrated the feasibility and practicability of the WC-USV for automatic in situ observations. The USV provided a new way of thinking for the future development of intelligent automation of the aquatic remote sensing ground verification system. It could be a good option to conduct field investigations for ocean color remote sensing and provide an alternative for highly polluted and/or shallow high-risk waters which large vessels have difficulty reaching. [ABSTRACT FROM AUTHOR]

Landslide susceptibility prediction (LSP) modeling is an important and challenging problem. Landslide features are generally uncorrelated or nonlinearly correlated, resulting in limited LSP performance when leveraging conventional machine learning models. In this study, a deep-learning-based model using the long short-term memory (LSTM) recurrent neural network and conditional random field (CRF) in cascade-parallel form was proposed for making LSPs based on remote sensing (RS) images and a geographic information system (GIS). The RS images are the main data sources of landslide-related environmental factors, and a GIS is used to analyze, store, and display spatial big data. The cascade-parallel LSTM-CRF consists of frequency ratio values of environmental factors in the input layers, cascade-parallel LSTM for feature extraction in the hidden layers, and cascade-parallel full connection for classification and CRF for landslide/non-landslide state modeling in the output layers. The cascade-parallel form of LSTM can extract features from different layers and merge them into concrete features. The CRF is used to calculate the energy relationship between two grid points, and the extracted features are further smoothed and optimized. As a case study, the cascade-parallel LSTM-CRF was applied to Shicheng County of Jiangxi Province in China. A total of 2709 landslide grid cells were recorded and 2709 non-landslide grid cells were randomly selected from the study area. The results show that, compared with existing main traditional machine learning algorithms, such as multilayer perception, logistic regression, and decision tree, the proposed cascade-parallel LSTM-CRF had a higher landslide prediction rate (positive predictive rate: 72.44%, negative predictive rate: 80%, total predictive rate: 75.67%). In conclusion, the proposed cascade-parallel LSTM-CRF is a novel data-driven deep learning model that overcomes the limitations of traditional machine learning algorithms and achieves promising results for making LSPs. [ABSTRACT FROM AUTHOR]

Solar-induced chlorophyll fluorescence (SIF) is regarded as a proxy for photosynthesis in terrestrial vegetation. Tower-based long-term observations of SIF are very important for gaining further insight into the ecosystem-specific seasonal dynamics of photosynthetic activity, including gross primary production (GPP). Here, we present the design and operation of the tower-based automated SIF measurement (SIFSpec) system. This system was developed with the aim of obtaining synchronous SIF observations and flux measurements across different terrestrial ecosystems, as well as to validate the increasing number of satellite SIF products using in situ measurements. Details of the system components, instrument installation, calibration, data collection, and processing are introduced. Atmospheric correction is also included in the data processing chain, which is important, but usually ignored for tower-based SIF measurements. Continuous measurements made across two growing cycles over maize at a Daman (DM) flux site (in Gansu province, China) demonstrate the reliable performance of SIF as an indicator for tracking the diurnal variations in photosynthetically active radiation (PAR) and seasonal variations in GPP. For the O2–A band in particular, a high correlation coefficient value of 0.81 is found between the SIF and seasonal variations of GPP. It is thus concluded that, in coordination with continuous eddy covariance (EC) flux measurements, automated and continuous SIF observations can provide a reliable approach for understanding the photosynthetic activity of the terrestrial ecosystem, and are also able to bridge the link between ground-based optical measurements and airborne or satellite remote sensing data. [ABSTRACT FROM AUTHOR]

The Chengdu–Chongqing Economic Zone (CCEZ), which is located in southwestern China, is the fourth largest economic zone in China. The rapid economic development of this area has resulted in many environmental problems, including extremely high concentrations of nitrogen dioxide (NO2) and fine particulate matter (PM2.5). However, current ground observations lack spatial and temporal coverage. In this study, satellite remote sensing techniques were used to analyze the variation in NO2 and PM2.5 from 2005 to 2015 in the CCEZ. The Ozone Monitoring Instrument (OMI) and the Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol optical depth (AOD) product were used to retrieve tropospheric NO2 vertical columns and estimate ground-level PM2.5 concentrations, respectively. Geographically, high NO2 concentrations were mainly located in the northwest of Chengdu and southeast of Chongqing. However, high PM2.5 concentrations were mainly located in the center areas of the basin. The seasonal average NO2 and PM2.5 concentrations were both highest in winter and lowest in summer. The seasonal average NO2 and PM2.5 were as high as 749.33 × 1013 molecules·cm−2 and 132.39 µg·m−3 in winter 2010, respectively. Over 11 years, the annual average NO2 and PM2.5 values in the CCEZ increased initially and then decreased, with 2011 as the inflection point. In 2007, the concentration of NO2 reached its lowest value since 2005, which was 230.15 × 1013 molecules·cm−2, and in 2015, the concentration of PM2.5 reached its lowest value since 2005, which was 26.43 µg·m−3. Our study demonstrates the potential use of satellite remote sensing to compensate for the lack of ground-observed data when quantitatively analyzing the spatial–temporal variations in regional air quality. [ABSTRACT FROM AUTHOR]