China is considered to be one of the most drought prone countries. This study is dedicated to analyzing the regionalization and spatiotemporal variations of drought based on the Standardized Precipitation Evapotranspiration Index, which covers the period 1961–2013 across 810 stations in China. Using Spatial “K”luster Analysis by Tree Edge Removal method, China was divided into eight regions: southwest (SW), northeast (NE), north (N), southeast (SE), Yangtze River (YR), northwest (NW), central China (C), and Tibet Plateau (TP). The spatiotemporal variations of drought characteristics indicated that the drought count in NE and C was generally high. Southern China and NW had suffered long drought duration and extreme severity. The MK test results show that stations with significant drying trends mainly locate in SW, N, NW, and C. The severe drought frequency was very high in 1990s and 2000s. Furthermore, more attention should be paid to abnormal less precipitation in summer and abnormal high temperature in spring in SW, NE, N, and C. Besides, abnormal less precipitation is the main factor of drought in SE and YR in whole year. This study is anticipated to support the water resources management, and to promote the realization of environmental protection and agricultural production.

On 16 March 2014, the State Council of China launched its first urbanization planning initiative dubbed “National New Urbanization Planning (2014–2020)” (NNUP). NNUP put forward 20 urban agglomerations and a sustainable development approach aiming to transform traditional Chinese urbanization to sustainable new urbanization. This study quantitatively evaluates the level of sustainability of the present new urbanization process in 20 Chinese urban agglomerations and provides some positive suggestions for the achievement of sustainable new urbanization. A three-level index system which is based on six fundamental elements in a city and a Full Permutation Polygon Synthetic Indicator evaluation method are adopted. The results show that China is undergoing a new urbanization process with a low level of sustainability and there are many problems remaining from traditional urbanization processes. There exists a polarized phenomenon in the urbanization of 20 urban agglomerations. Based on their own development patterns, the 20 urban agglomerations can be divided into seven categories. Every category has its own development characteristics. The analyses also show that waste of water resources, abuse of land resources, and air pollution are three big problems that are closely linked to traditional Chinese urbanization processes. To achieve sustainable new urbanization in China, four relevant suggestions and comments have been provided.

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.

The rising machine learning (ML) models have become the preferred way for landslide detection based on remote sensing images, but the performance of these models in a sample-free area are rarely concerned in many studies. In this study, we used a cross-validation method (training model in one area and validation in another) to compare the model portability of trained ML models applied in an “off-site” area, as a consideration of the landslide detection ability of these models in sample-free areas. We integrate nighttime light imagery, multi-seasonal optical Landsat time-series and digital elevation data, and we employed support vector machines (SVM), artificial neural networks (ANN) and random forest (RF) models to classify the satellite imagery and identify landslides. Samples of two scenarios generated from two subareas of the Jiuzhaigou disaster-stricken region are used for the cross-application and accuracy evaluation of three ML models. The results revealed that when the trained models are applied in areas outside those in which they were developed, the landslide identification accuracy of these three models has declined. Especially for the SVM and ANN models, the accuracy is greatly reduced and there appears a seriously imbalanced user’s and producer’s accuracy. However, although the performance of the RF model is lower than that of SVM and ANN models in their local area, the RF model exhibits stable portability, and retains the original performance and achieves a satisfactory balance between overestimation and underestimation in “off-site” areas. An additional validation from a new area proved that the landslide detection performance of the RF model with stable portability is higher than that of the SVM and ANN models in “off-site” areas. The results suggest that evaluating the model portability through cross-application can be a useful way to determine the most suitable model for landslide detection in “off-site” areas with a similar geographic environment to model development areas, so as to maximize the accuracy of landslide detection based on limited samples.