Zhanya Xu

China University of Geosciences · School of Geography and Information Engineering

Since the beginning of the twenty-first century, urban heat island (UHI) has become a problem of the urban ecological environment. Land Surface Temperature (LST) is one of the most effective methods to study UHI. Taking Nanjing, Jiangsu province, China, as an example, we identified and discussed the changes of urban heat island associated with the...

Rainfall-induced landslides are currently one of the most frequent disasters in China. Compared with rainfall, the increase of soil moisture and its continuous infiltration of soil are the direct factors leading to landslides. However, few researches have studied landslide forecasting taking the soil moisture into consideration. In addition, soil m...

Landslides are a serious natural hazard in the world. A map of landslide susceptibility can help to effectively reduce losses. In this paper, a hybrid ensemble technique based on random subspace (RS) and a J48 decision tree named RS–J48T was proposed for landslide susceptibility mapping. This model could enhance the effect of a single classifier si...

Landslide susceptibility assessment is usually considered as an essential part of landslide hazard risk reduction, and the key steps of it are to choose landslide causal factors and construct landslide susceptibility assessment models. The main purpose of the study is to develop an advanced model framework to assess landslide susceptibility and use...

Deep convolutional networks have obtained remarkable achievements on various visual tasks due to their strong ability to learn a variety of features. A well-trained deep convolutional network can be compressed to 20%–40% of its original size by removing filters that make little contribution, as many overlapping features are generated by redundant f...

Characterized by essential complexity, dynamism, and dynamics, streamflow forecasting presents a great challenge to hydrologists. Long short-term memory (LSTM) streamflow forecast model has received a lot of attention in recent years due to its powerful non-linear modeling ability. But probabilistic streamflow forecasting has rarely been addressed...

In recent decades, to provide accurate and reliable warning of impending flash flood disasters, wireless sensor networks consisting of numerous hydrological and meteorological physical sensors have been widely used. However, due to the harsh natural environment and hazardous aftermath of flooding disasters, the equipment damage and data anomalies c...

Drought is a natural hazard driven by extreme macroclimatic variability, and generally resulting in serious damage to the environment over a sizable area. Accurate, reliable, and timely forecasting of drought behavior plays a key role in early warning of drought management. In this study, a hybrid hidden Markov model coupled with multivariate copul...

Figuring out the impacts of future urbanization on hydrological response is significant in a rapidly changing environment. As an important urbanization element, the various impacts of land use/land cover change have been studied a lot with the methods of combining different land use scenarios and hydrological models. However, it needs to be improve...

in this article, the trends in global vegetative drought were investigated using MODIS- and AVHRR-based NDVI products. A set of selected methods were employed to perform trend analysis including trend test, trend location detection, and trend estimates. Accounting for the effect of the global geographical heterogeneity on trend analysis, the NDVI d...

Global analyses show that climate change has already increased the frequency and strength of extreme weather events. The observed and remote-sensed precipitation productions have been deeply studied considering the stationary and non-stationary characteristics of extreme series. However, as these studies largely addressed the evolution of precipita...

An increasing amount of studies have emphasized that more frequent and extensive extreme events have occurred around the world. The effects of climate change and anthropogenic activities on the variation in runoff have been studied extensively. However, the effects of variation in hydrological extremes have rarely been studied. In this study, a mod...

Frequent geological disasters based on a range of precipitating factors occur in areas with fragile geological environments, and the traditional artificial geological disaster survey method is often too dangerous to be carried out effectively. In order to achieve more efficient influence factors and refine the evaluation of micro-scale geological d...

Landslide disasters cause huge casualties and economic losses every year, how to accurately forecast the landslides has always been an important issue in geo-environment research. In this paper, a hybrid machine learning approach RSLMT is firstly proposed by coupling Random Subspace (RS) and Logistic Model Tree (LMT) for producing a landslide susce...

The potential of long short-term memory network on ultra-short term wind speed forecast attracted attentions of researchers in recent years. Extending a probabilistic long short-term memory network model to provide an uncertainty estimation than to make a point forecast is more valuable in practice. However, due to complex recurrent structure and f...

A preliminary study on the application of LSTM in prediction of vegetative drought

Multipronged statistical approaches were applied to give spatiotemporal insight into the long-term patterns of vegetative drought over the contiguous United States (CONUS) from a weekly NOAA/AVHRR VHI product of 1981–2017. Based on the analysis results, the following characteristics have been found: First, the category of the most frequently occurr...

Monthly streamflow time series are highly non-linear. How to improve forecast accuracy is a great challenge in hydrological studies. A lot of research has been conducted to address the streamflow forecasting problem, however, few methods are developed to make a systematic research. The objective of this study is to understand the underlying trend o...

Gaussian Process Regression (GPR) is a new machine-learning method based on Bayesian theory and statistical learning theory. It provides a flexible framework for probabilistic regression and uncertainty estimation. The main effort in GPR modelling is determining the structure of the kernel function. As streamflow is composed of trend, period and ra...

In China, Weibo, a prevailing social media service attracts billions of users who use smart phones to send twits with text, image, and video to record and monitor the event. The social media information could be a certain earth observation data when the information relates to a certain earth observation event. While the method of extracting useful...

The integration of Sensor Web Enablement services with other Open Geospatial Consortium (OGC) Web Services as Geospatial Processing Workflows (GPW) is essential for future Sensor Web application scenarios. With the help of GPW technology, distributed and heterogeneous OGC Web Services can be organized and integrated as compound Web Service applicat...

Location-aware applications based on local wireless networks ,like Wi-Fi, RFID, are becoming more realistic and attractive for many research and commercial organizations in recent years. In this paper, we provide comprehensive analysis on key characteristics of museum mobile guide system with location-aware features, including related location tech...

With the development of mobile devices and digitalization of information, the GIS system will be more popular than before. For the variable of mobile devices and different system structure, the design of universal embedded GIS system will be more difficult. In this paper, we talked the features of embedded GIS and the key techniques, design a highl...

This paper analyzes the existing spatial structure of mobile information services and the current new characteristics of the service, proposes a new service model. The model adopts a unified deployment solution of spatial data. It extends the spatial data management and lightweight computing to the embedded computing devices, and enhanced the servi...