The real-time, accurate, and refined monitoring of urban green space status information is of great significance in the construction of urban ecological environment and the improvement of urban ecological benefits. The high-resolution technology can provide abundant information of ground objects, which makes the information of urban green surface more complicated. The existing classification methods are challenging to meet the classification accuracy and automation requirements of high-resolution images. This paper proposed a deep learning classification method for urban green space based on phenological features constraints in order to make full use of the spectral and spatial information of green space provided by high-resolution remote sensing images (GaoFen-2) in different periods. The vegetation phenological features were added as auxiliary bands to the deep learning network for training and classification. We used the HRNet (High-Resolution Network) as our model and introduced the Focal Tversky Loss function to solve the sample imbalance problem. The experimental results show that the introduction of phenological features into HRNet model training can effectively improve urban green space classification accuracy by solving the problem of misclassification of evergreen and deciduous trees. The improvement rate of F1-Score of deciduous trees, evergreen trees, and grassland were 0.48%, 4.77%, and 3.93%, respectively, which proved that the combination of vegetation phenology and high-resolution remote sensing image can improve the results of deep learning urban green space classification.

Quantitative evaluation of the coupling coordination degree (CCD) between regional haze the disaster risk index (HRI) and urbanization development index level (UDI) is of great significance for the realization of regional sustainable development goals. Given the lack of the combination of remote sensing and statistical data to evaluate the CCD between two systems, the Chinese mainland’s 31 provinces and autonomous regions were taken to evaluate their HRI and UDI by building index systems. Then, an entropy method and one improved coupling coordination model were used to calculate and analyze the spatiotemporal characteristics of CCD between HRI and UDI during 2000–2020. The results showed that: (1) From 2000 to 2020, the value of HRI in China showed a “W” type change trend with its value increased from 0.7041 in 2000 to 0.8859 in 2020, indicating that haze pollution level showed a fluctuating downward trend; (2) From 2000 to 2020, China’s UDI values showed a gradual upward trend with its value increased from 0.1647 in 2000 to 0.4640 in 2020, with an average annual growth rate of 8.63%; (3) From 2000 to 2020, CCD values between HRI and UDI showed a fluctuating upward trend with its value increased from 0.5374 in 2000 to 0.7781 in 2020, with an average annual growth rate of 2.13%; the overall level of China’s CCD had raised from low coordination to moderate coordination, and eastern coastal provinces had higher CCD values, while those of central and western provinces had lower CCD values; (4) HRI, UDI and CCD could be well fitted with the R² of 0.9869. Specifically, UDI had a higher contribution to improving the CCD than the HRI.

Earthquake disasters are marked by their unpredictability and potential for extreme destructiveness. Accurate information on building damage, captured in post-earthquake remote sensing images, is critical for an effective post-disaster emergency response. The foundational features within these images are essential for the accurate extraction of building damage data following seismic events. Presently, the availability of publicly accessible datasets tailored specifically to earthquake-damaged buildings is limited, and existing collections of post-earthquake building damage characteristics are insufficient. To address this gap and foster research advancement in this domain, this paper introduces a new, large-scale, publicly available dataset named the Major Earthquake Damage Building Feature Set (MEDBFS). This dataset comprises image data sourced from five significant global earthquakes and captured by various optical remote sensing satellites, featuring diverse scale characteristics and multiple spatial resolutions. It includes over 7000 images of buildings pre- and post-disaster, each subjected to stringent quality control and expert validation. The images are categorized into three primary groups: intact/slightly damaged, severely damaged, and completely collapsed. This paper develops a comprehensive feature set encompassing five dimensions: spectral, texture, edge detection, building index, and temporal sequencing, resulting in 16 distinct classes of feature images. This dataset is poised to significantly enhance the capabilities for data-driven identification and analysis of earthquake-induced building damage, thereby supporting the advancement of scientific and technological efforts for emergency earthquake response.

The quantitative evaluation of the coupling coordination degree (CCD) between the regional economy and eco-environment systems is of great importance for the realization of sustainable development goals, which could identify economic or eco-environmental cold areas. To date, traditional evaluation frameworks mainly include the indicator system construction based on statistical data, which seldom utilize the geo-spatiotemporal datasets. Hence, this study aimed to evaluate the CCD change trend of the Yangtze River Delta (YRD) and explore the relationship between the CCD, economy, and eco-environment on the county scale. In this study, YRD was selected as the study area to evaluate its level of CCD at different periods, and then the nighttime difference index (NTDI) and eco-environmental comprehensive evaluation index (ECEI) were calculated to represent the difference in the development of the regional economy and the eco-environmental quality (EEQ). The CCD between the two systems was then calculated and analyzed using global, local, and Geary’s C spatial autocorrelation indicators, in addition to change trend methods. The main findings showed that: (1) During the period 2000–2020, the economic system in YRD showed a continuously upward trend (0.0487 a⁻¹), with average NTDI values of 0.2308, 0.2964, 0.3223, 0.3971, and 0.4239, respectively. In spatial terms, the economy system showed a distribution of “high in the east and low in the west”. (2) YRD’s EEQ indicated a gradual upward trend (from 0.3590 in 2000 to 0.3970 in 2020), with a change trend value of 0.0020 a⁻¹. Spatially, the regions with high ECEI were mainly located in southwestern counties. (3) In the past 20 years, the CCD between economic and eco-environment systems showed an increased change trend, with a change trend value of 0.0302 a⁻¹. The average CCD values for the five periods were 0.3992, 0.4745, 0.4633, 0.5012, and 0.5369. The overall level of CCD improved from “moderate incoordination” to “low coordination”. (4) Both NTDI and ECEI indexes have a positive effect on the improvement of regional CCD. However, the contribution of NTDI is a little higher than that of ECEI.

The regional differences in carbon dioxide (CO₂) variations from the Orbiting Carbon Observatory-2 (OCO-2) over the Beijing-Tianjin-Hebei (Jing-Jin-Ji) region from 2015 to 2021 are analyzed in this study. This study shows an annual increase and a seasonal cycle; the CO₂ annual growth rate was about 2.63 ppm year⁻¹, with the highest value being in spring and the lowest in summer. The spatial distribution is unbalanced, regional differences are prominent, and the CO₂ concentration is lower in the north of the Jing-Jin-Ji region (like Zhangjiakou, Chengde, and Qinhuangdao). Land-type structures and population economy distributions are the key factors affecting CO₂ concentration. By analyzing the land-type structures over Jing-Jin-Ji in 2020, we find that cropland, woodland, and grassland (CWG) are the main land cover types in Jing-Jin-Ji; the proportion of these three types is about 83.3%. The woodland areas in Zhangjiakou, Chengde, and Qinhuangdao account for about 65% of the total woodland areas in Jing-Jin-Ji; meanwhile, the grassland areas in these three regions account for 62% of the total grassland areas in Jing-Jin-Ji. CO₂ concentration variation shows a high negative correlation with CWG land areas (coefficient of determination (R²) > 0.76). The regions with lower population and GDP secondary industry (SI) density also have lower CO₂ concentration (like Zhangjiakou, Chengde, and Qinhuangdao), and the regions with higher population and GDP SI density also have higher CO₂ concentration (like the southeast of Jing-Jin-Jin).