As one of the most severe natural disasters in the world, floods caused substantial economic losses and casualties every year. Timely and accurate acquisition of flood inundation extent could provide technical support for relevant departments in the field of flood emergency response and disaster relief. Given the accuracy of existing research works extracting flood inundation extent based on Synthetic Aperture Radar (SAR) images and deep learning methods is relatively low, this study utilized Sentinel-1 SAR images as the data source and proposed a novel model named flood water body extraction convolutional neural network (FWENet) for flood information extraction. Then three classical semantic segmentation models (UNet, Deeplab v3 and UNet++) and two traditional water body extraction methods (Otsu global thresholding method and Object-Oriented method) were compared with the FWENet model. Furthermore, this paper analyzed the water body area change situations of Poyang Lake. The main results of this paper were as follows: Compared with other five water body extraction methods, the FWENet model achieved the highest water body extraction accuracy, its F1 score and mean intersection over union (mIoU) were 0.9871 and 0.9808, respectively. This study could guarantee the subsequent research on flood extraction based on SAR images.

Identifying the changes and relationships between regional eco-environment quality and landscape pattern in an urban agglomeration have a great significance in realizing sustainable development goal. However, limited research has been performed to understand the spatiotemporal change of eco-environment quality, the variation of landscape pattern, and their relationship in an urban agglomeration. This study selected the Jing-Jin-Ji (JJJ) urban agglomeration as the study area. A comprehensive index, the remote sensing ecological index (RSEI), was utilized to understand the eco-environment spatiotemporal change and landscape pattern variation at class-level and landscape-level of JJJ during 2001~2015, then, their relationship was explored. The major conclusions were as follows: (1) The average RSEI value of JJJ increased from 0.43 to 0.46, which represented that the eco-environment of JJJ had improved in the fourteen years. Among it, the improved region was mainly located in Zhangjiakou city, while the degraded region was mainly distributed in the eastern Hebei plain. (2) The landscape characteristics of entire JJJ eco-environment were becoming more aggregated, connected, diverse, and regular. However, fair, moderate, and good grades were getting more concentrated and continuous; poor grade indicated a more fragmented and disconnected trend; excellent grade displayed an expanded and concentrated situation. (3) Human factors have an increasing influence on regional eco-environment changes. (4) Fair, moderate, and good grades showed a more dominant and stronger influence on the variation of landscape pattern in JJJ. Specifically, the fair grade had a positive correlation with the variation of landscape pattern, while moderate and good grades had a negative one. All of these conclusions could be valuable information for relevant decision-makers in managing or achieving the optimal eco-environment landscape pattern.

With the advent of high spatial resolution remote sensing imagery, numerous image features can be utilized. Applying a reasonable feature selection approach is critical to effectively reduce feature redundancy and improve the efficiency and accuracy of classification. This paper proposes a novel feature selection approach, in which ReliefF, genetic algorithm, and support vector machine (RFGASVM) are integrated to extract buildings. We adopt the ReliefF algorithm to preliminary filter high-dimensional features in the feature database. After eliminating the sorted features, the feature subset and the C and γ parameters of support vector machine (SVM) are encoded into the chromosome of the genetic algorithm. A fitness function is constructed considering the sample identification accuracy, the number of selected features, and the feature cost. The proposed method was applied to high-resolution images obtained from different sensors, GF-2, BJ-2, and unmanned aerial vehicles (UAV). The confusion matrix, precision, recall and F1-score were applied to assess the accuracy. The results showed that the proposed method achieved feature reduction, and the overall accuracy (OA) was more than 85%, with Kappa coefficient values of 0.80, 0.83 and 0.85, respectively. The precision of each image was more than 85%. The time efficiency of the proposed method was two-fold greater than SVM with all the features. The RFGASVM method has the advantages of large feature reduction and high extraction performance and can be applied in feature selection.

Exploring the regional eco-environmental quality (EEQ) and its driving factors is of great significance for regional management. Although existing studies have paid much attention to evaluate EEQ, few studies have been performed to investigate the spatiotemporal variations of EEQ and its driving factors in different ecosystem service regions (ESR) at an urban agglomeration scale. In this study, we selected Jing-Jin-Ji urban agglomeration (JJJ) as the study area to evaluate its EEQ, analyze its spatiotemporal variations, and investigate potential driving factors explanatory power based on the geographical detector methods in different ESR during 2001∼2015. The main conclusions were as follows: (1) The EEQ of JJJ had improved from 2001 to 2015, with the average RSEI increased from 0.43 to 0.46; among them, Bashang Plateau and Western Hebei Ecosystem Service Region (BWHE) had the highest RSEI change rate (±26.19%) and the highest NTEDI value (0.13), while Central Hebei Plain Ecosystem Service Region (CHPE) had the lowest RSEI change rate (-5.41%) and the lowest NTEDI value (-0.02). (2) The EEQ of JJJ had strong spatial agglomeration effects, with the global Moran’s I increased from 0.82 to 0.88. Spatially, the LL regions mainly changed into the HH regions in the northwestern part, while in the central and eastern areas, some isolated LL regions displayed an aggregated trend. (3) In terms of the driving factors, soil type and elevation were primary factors in explaining the variations of EEQ. Specifically, natural factors explained the highest variations in BWHE. The interaction of topographical and socio-economic factors had high explanatory power in Yanshan and Taihang Mountain Ecosystem Service Region (YTME) and CHPE; To Bohai and Coastal Ring Ecosystem Service Region (BCRE), the interaction of meteorological and socio-economic factors accounted for the high variations of EEQ. All these findings could provide more valuable advice for relevant policy-makers.

As the backbone and arteries of a comprehensive transportation network, highways play an important role in improving people’s living standards and promoting economic growth. However, globally, there is limited quantifiable data evaluating the highway traffic state, characteristics, and performance. From the 1960s to the present, remote sensing has been regarded as the most effective technology for long-term and large-scale monitoring of surface information. However, how to reflect the dynamic “flow” information of traffic with a static remote sensing image has always been a difficult problem that is hard to solve in the field. This study aims to construct a method of evaluating highway traffic prosperity using nighttime remote sensing. First, based on nighttime light data that indicate social and economic activities, a highway-oriented method was proposed to extract highway nighttime light data from 2015 annual nighttime light data of the Suomi National Polar-Orbiting Partnership Visible Infrared Imaging Radiometer Suite sensor (SNPP-VIIRS). Subsequently, Pearson correlation analysis was used to fit the relationship between freeway traffic flow volume and freeway nighttime light at the provincial level. The results showed that Pearson Correlation Coefficient of freeway nighttime light and freeway traffic flow volume for coach and truck are 0.905 and 0.731, respectively, which are higher than between freeway traffic flow volume for coach and truck and total nighttime light (0.593 and 0.516, respectively). A new index—Highway Nighttime Traffic Prosperity Index (HNTPI)—was proposed to evaluate highway traffic across China. The results showed that HNTPI has a strong correspondence with socio-economic parameters. The Pearson Correlation Coefficient of HNTPI and gross domestic product (GDP) per capita, consumption per capita, and population are 0.772, 0.895, and 0.968, respectively. There is a huge spatial heterogeneity in China nighttime traffic, the prosperity degree of highway traffic in developed coastal areas is obviously higher than that inland. The national general highway is the most prosperous highway at night and the national general highway nighttime prosperity of Shanghai reached 22.34%. This research provides basic data for the long-term monitoring and evaluation of regional traffic operation at night and research on the correlation between regional highway construction and the economy.

Estimates of regional net primary productivity (NPP) are useful in modeling regional and global carbon cycles, especially in karst areas. This work developed a new method to study NPP characteristics and changes in Chongqing, a typical karst area. To estimate NPP accurately, the model which integrated an ecosystem process model (CEVSA) with a light use efficiency model (GLOPEM) called GLOPEM-CEVSA was applied. The fraction of photosynthetically active radiation (fPAR) was derived from remote sensing data inversion based on moderate resolution imaging spectroradiometer atmospheric and land products. Validation analyses showed that the PAR and NPP values, which were simulated by the model, matched the observed data well. The values of other relevant NPP models, as well as the MOD17A3 NPP products (NPP MOD17), were compared. In terms of spatial distribution, NPP decreased from northeast to southwest in the Chongqing region. The annual average NPP in the study area was approximately 534 gC/m²a (Std. = 175.53) from 2001 to 2011, with obvious seasonal variation characteristics. The NPP from April to October accounted for 80.1% of the annual NPP, while that from June to August accounted for 43.2%. NPP changed with the fraction of absorbed PAR, and NPP was also significantly correlated to precipitation and temperature at monthly temporal scales, and showed stronger sensitivity to interannual variation in temperature.