The accurate mapping of urban housing prices at a fine scale is essential to policymaking and urban studies, such as adjusting economic factors and determining reasonable levels of residential subsidies. Previous studies focus mainly on housing price analysis at a macro scale, without fine‐scale study due to a lack of available data and effective models. By integrating a convolutional neural network for united mining (UMCNN) and random forest (RF), this study proposes an effective deep‐learning‐based framework for fusing multi‐source geospatial data, including high spatial resolution (HSR) remotely sensed imagery and several types of social media data, and maps urban housing prices at a very fine scale. With the collected housing price data from China's biggest online real estate market, we produced the spatial distribution of housing prices at a spatial resolution of 5 m in Shenzhen, China. By comparing with eight other multi‐source data mining techniques, the UMCNN obtained the highest housing price simulation accuracy (Pearson R = 0.922, OA = 85.82%). The results also demonstrated a complex spatial heterogeneity inside Shenzhen's housing price distribution. In future studies, we will work continuously on housing price policymaking and residential issues by including additional sources of spatial data. 相似文献
The runoff and sediment load of the Loess Plateau have changed significantly due to the implementation of soil and water conservation measures since the 1970s. However, the effects of soil and water conservation measures on hydrological extremes have rarely been considered. In this study, we investigated the variations in hydrological extremes and flood processes during different periods in the Yanhe River Basin (a tributary of the Loess Plateau) based on the daily mean runoff and 117 flood event data from 1956 to 2013. The study periods were divided into reference period (1956–1969), engineering measures period (1970–1995), and biological control measures period (1996–2013) according to the change points of the annual streamflow and the actual human activity in the basin. The results of the hydrological high extremes (HF1max, HF3max, HF7max) exhibit a decreasing trend (P?<?0.01), whereas the hydrological low extremes (HBF1min, HBF3min, HBF7min) show an increasing trend during 1956–2013. Compared with the hydrological extremes during the reference period, the hydrological high extremes increased during the engineering measures period at low (<?15%) and high frequency (>?80%), whereas decreased during the biological control measures period at almost all frequencies. The hydrological low extremes generally increased during both the engineering measures and biological control measures periods, particularly during the latter period. At the flood event scale, most flood event indices in connection with the runoff and sediment during the engineering measures period were significantly higher than those during the biological control measures period. The above results indicate that the ability to withstand hydrological extremes for the biological control measures was greater than that for the engineering measures in the studied basin. This work reveals the effects of different soil and water conservation measures on hydrological extremes in a typical basin of the Loess Plateau and hence can provide a useful reference for regional soil erosion control and disaster prevention policy-making.
Acta Geochimica - Isotopic signature is a powerful tool to discriminate methane (CH4) source types and constrain regional and global scale CH4 budgets. Peatlands on the Qinghai-Tibetan Plateau are... 相似文献
Acta Geotechnica - Animal fibers with α-keratin had obvious advantages of mechanical strength and durability on reinforced microbially induced carbonate precipitation (MICP)-cemented loose... 相似文献