Search

In order to promote the economic development of China's provinces and provide references for the provinces to make effective economic decisions, it is urgent to investigate the trend of province-level economic development. In this study, DMSP/OLS data and NPP/VIIRS data were used to predict economic development. Based on the GDP data of China's provinces from 1992 to 2016 and the nighttime light remote sensing (NTL) data of corresponding years, we forecast GDP via the linear model (LR model), ARIMA model, ARIMAX model, and SARIMA model. Models were verified against the GDP records from 2017 to 2019. The experimental results showed that the involvement of NTL as exogenous variables led to improved GDP prediction. [ABSTRACT FROM AUTHOR]

• Developed a volume-driven framework to estimate material stocks using multi-source geographical data. • Generated spatially explicit material stocks maps of buildings and infrastructures at a 10 m resolution. • Estimated total material stocks within BTH-UA at 195,000 Mt in 2020, amounting to 182 t/capita and 2.43 Mt/km². • Identified significant correlations between material stocks, population size, and economic activity at the administrative level. Spatial patterns of material stocks in buildings and infrastructures are crucial for understanding resource use, spatial planning and environmental management. So far, spatially explicit stock-driven approaches face substantial data limitations, requiring costly and time-intensive efforts to map stocks at urban micro-scales. Herein, we developed a volume-based framework for material stocks mapping in buildings and infrastructures at a 10 m resolution, applied across the entire Beijing–Tianjin–Hebei urban agglomeration (BTH-UA) in China, a key growth pole for regional economic development. We integrated multi-source remote sensing data, GIS products, crowdsourced data, and material intensity databases, covering ten bulk materials. The findings reveal that the total mass of buildings and infrastructures in BTH-UA amounts to 195,000 Mt, equivalent to 182 t/cap, 2.43 Mt/km2. Material stocks are spatially clustered and correlate with the population size and economic activity of the secondary industry. This research contributes to the quantitative description and detailed mapping of material stocks in built environment. [ABSTRACT FROM AUTHOR]

Urban–rural land transition and the coordination of coupled human–environmental systems are two important issues in the process of global urban–rural development. Although existing studies have explored the coupling coordination degree (CCD) of human–environmental interactions under the context of urbanization, few studies have taken land transitions into consideration. In this study, we investigated the dynamics of CCD in China from 2001 to 2018 using multisource remote sensing data and quantified the CCD changes in land transitions among urban construction land (UCL), rural residential land (RRL), and non-construction land (NCL). The CCD alterations mainly occurred in the decline in NCL stock, the increase in UCL stock, and especially the losses during RRL to NCL transfers. We urge academics and government decision-makers to pay more attention to the CCD transfers and losses during urban–rural transitions. This study provides scientific guidance for the development of urban–rural integration and is expected to assist the coordinated evaluation of human–environmental interactions in the process of sustainable development. [ABSTRACT FROM AUTHOR]

The performance of deep learning is heavily influenced by the size of the learning samples, whose labeling process is time consuming and laborious. Deep learning algorithms typically assume that the training and prediction data are independent and uniformly distributed, which is rarely the case given the attributes and properties of different data sources. In remote sensing images, representations of urban land surfaces can vary across regions and by season, demanding rapid generalization of these surfaces in remote sensing data. In this study, we propose Meta-FSEO, a novel model for improving the performance of few-shot remote sensing scene classification in varying urban scenes. The proposed Meta-FSEO model deploys self-supervised embedding optimization for adaptive generalization in new tasks such as classifying features in new urban regions that have never been encountered during the training phase, thus balancing the requirements for feature classification tasks between multiple images collected at different times and places. We also created a loss function by weighting the contrast losses and cross-entropy losses. The proposed Meta-FSEO demonstrates a great generalization capability in remote sensing scene classification among different cities. In a five-way one-shot classification experiment with the Sentinel-1/2 Multi-Spectral (SEN12MS) dataset, the accuracy reached 63.08%. In a five-way five-shot experiment on the same dataset, the accuracy reached 74.29%. These results indicated that the proposed Meta-FSEO model outperformed both the transfer learning-based algorithm and two popular meta-learning-based methods, i.e., MAML and Meta-SGD. [ABSTRACT FROM AUTHOR]

In Shanxi Province, China, groundwater is a major problem and exploration of groundwater potential zones (GWPZs) is a great necessity. This paper contributed to integrate RS-GIS to delineate GWPZ and applied Fuzzy-AHP method in a single platform. The main objective includes delineation GWPZs with RS and geo-environmental factors using Fuzzy-AHP method. Fuzzy-AHP method was employed to calculate weight of factors. RS-GIS was used to create maps and discover groundwater availability. GWPZs were classified in five separate classes. Results indicated that 13.26%, 27.02%, 26.35%, 23.64%, and 9.71% area classified as very good, good, moderate, poor, and very poor GWPZs. The validated analytical results revealed 82.5%, 12.3%, 3.5%, and 1.7% existing water wells exhibited in very good, good, moderate, and poor/very poor GWPZs. This indicates Fuzzy-AHP model generated findings were in very good agreement with ground-truth data. This RS-GIS based Fuzzy-AHP method is proficient and efficient in identification and delineation of GWPZs. Image 1 • Groundwater potential zones (GWPZs) in semi-arid area delineated with RS-GIS. • Seven geo-environmental factors are used for GWPZ. • RS-GIS for GWPZ and Fuzzy-AHP model are used in a single platform. • Fuzzy-AHP method was employed to calculate the weight of the factors. • GWPZs are classified as very good, good, moderate, poor, and very poor GWPZ. [ABSTRACT FROM AUTHOR]

• Assess the exacerbated severity and magnitude of flood occurrences. • Reflect long-term trends in areas impacted by floods. • Revealed the extent of spatial clustering of flood events. • Explored the magnitude, range, and progression impact of floods on vegetation. The impact of flooding on vegetation ecosystems worldwide has resulted in severe and widespread threats. Despite this, there is a significant knowledge gap in understanding the impact of floods on vegetation. To gain a comprehensive understanding of the response mechanism of the global vegetation ecosystem to flood disasters, it is crucial to assess the loss of vegetation caused by flood events. In this study, we analyzed 3325 flood events around the world from 2001 to 2020, including the geographic distribution, start and end dates, duration, severity and affected areas. Using kernel density estimation, we assessed the exacerbated severity and magnitude of flood occurrences, identifying spatial clustering of events. Through moving average was utilized to reveal the prolonged trends in areas impacted by floods. Additionally, by spatially matching with global land cover products, we comprehensively explored the magnitude, range, and progression of the impact of floods on vegetation. The findings indicate that (1) Extreme flood events have been increasing in number, affected area, severity, and magnitude since the 21st century, with the majority of events occurring between 10°S-50°N. (2) Strong spatial clustering of flood events was identified in the southeast of North America, the southeast of South America, the east of Africa, the south of Europe, and the south of Asia. (3) Flood hazards in frequent flood-affected areas pose severe threats to the terrestrial vegetation ecosystem, highlighting the necessity of further detailed estimation of flood damages to vegetation at a global scale. This research provides an extensive evaluation of the impact of floods on vegetation at the global-national-regional scale, with a focus on understanding the temporal trends and spatial distribution characteristics over the past 20 years (2001–2020). [ABSTRACT FROM AUTHOR]