Flash floods are considered to be one of the most destructive natural hazards, and they are difficult to accurately model and predict. In this study, three hybrid models were proposed, evaluated, and used for flood susceptibility prediction in the Dadu River Basin. These three hybrid models integrate a bivariate statistical method of the fuzzy membership value (FMV) and three machine learning methods of support vector machine (SVM), classification and regression trees (CART), and convolutional neural network (CNN). Firstly, a geospatial database was prepared comprising nine flood conditioning factors, 485 flood locations, and 485 non-flood locations. Then, the database was used to train and test the three hybrid models. Subsequently, the receiver operating characteristic (ROC) curve, seed cell area index (SCAI), and classification accuracy were used to evaluate the performances of the models. The results reveal the following: (1) The ROC curve highlights the fact that the CNN-FMV hybrid model had the best fitting and prediction performance, and the area under the curve (AUC) values of the success rate and the prediction rate were 0.935 and 0.912, respectively. (2) Based on the results of the three model performance evaluation methods, all three hybrid models had better prediction capabilities than their respective single machine learning models. Compared with their single machine learning models, the AUC values of the SVM-FMV, CART-FMV, and CNN-FMV were 0.032, 0.005, and 0.055 higher; their SCAI values were 0.05, 0.03, and 0.02 lower; and their classification accuracies were 4.48%, 1.38%, and 5.86% higher, respectively. (3) Based on the results of the flood susceptibility indices, between 13.21% and 22.03% of the study area was characterized by high and very high flood susceptibilities. The three hybrid models proposed in this study, especially CNN-FMV, have a high potential for application in flood susceptibility assessment in specific areas in future studies.

The Tibetan Plateau is one of the most vulnerable areas to extreme precipitation. In recent decades, water cycles have accelerated, and the temporal and spatial characteristics of extreme precipitation have undergone dramatic changes across the Tibetan Plateau, especially in its various ecosystems. However, there are few studies that considered the variation of extreme precipitation in various ecosystems, and the impact of El Niño-Southern Oscillation (ENSO), and few researchers have made a quantitative analysis between them. In this study, we analyzed the spatial and temporal pattern of 10 extreme precipitation indices across the Tibetan Plateau (including its four main ecosystems: Forest, alpine meadow, alpine steppe, and desert steppe) based on daily precipitation from 76 meteorological stations over the past 30 years. We used the linear least squares method and Pearson correlation coefficient to examine variation magnitudes of 10 extreme precipitation indices and correlation. Temporal pattern indicated that consecutive wet days (CWD) had a slightly decreasing trend (slope = −0.006), consecutive dry days (CDD), simple daily intensity (SDII), and extreme wet day precipitation (R99) displayed significant increasing trends, while the trends of other indices were not significant. For spatial patterns, the increasing trends of nine extreme precipitation indices (excluding CDD) occurred in the southwestern, middle and northern regions of the Tibetan Plateau; decreasing trends were distributed in the southeastern region, while the spatial pattern of CDD showed the opposite distribution. As to the four different ecosystems, the number of moderate precipitation days (R10mm), number of heavy precipitation days (R20mm), wet day precipitation (PRCPTOT), and very wet day precipitation (R95) in forest ecosystems showed decreasing trends, but CDD exhibited a significant increasing trend (slope = 0.625, P < 0.05). In the other three ecosystems, all extreme precipitation indices generally exhibited increasing trends, except for CWD in alpine meadow (slope = −0.001) and desert steppe (slope = −0.005). Furthermore, the crossover wavelet transform indicated that the ENSO had a 4-year resonance cycle with R95, SDII, R20mm, and CWD. These results provided additional evidence that ENSO play an important remote driver for extreme precipitation variation in the Tibetan Plateau.

Poverty alleviation is one of the most important tasks facing human social development. It is necessary to make accurate monitoring and evaluations for areas with poverty to improve capability of implementing poverty alleviation policies. Here, this study introduced nighttime light (NTL) data to estimate county-level poverty in southwest China. First, this study used particle swarm optimization-back propagation hybrid algorithm to explore the potential relationship between two NTL data (the Defense Meteorological Satellite Program’s Operational Line Scan System data and the Suomi National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite data). Then, we integrated two NTL data at the pixel level to establish a consistent time-series of NTL dataset from 2000 to 2019. Next, an actual comprehensive poverty index (ACPI) was employed as an indicator of multidimensional poverty at county level based on 11 socioeconomic and natural variables, and which could be the reference to explore the poverty evaluation using NTL data. Based on the correlation between the ACPI and NTL characteristic variables, a poverty evaluation model was developed to evaluate the poverty situation. The result showed the great matching relationship between DMSP-OLS and NPP-VIIRS data (R² = 0.84). After calibration, the continuity and comparability of DMSP-OLS data were significantly improved. The integrated NTL data also reflected great consistency with socioeconomic development (r = 0.99). The RMSE between ACPI and the estimated comprehensive poverty index (ECPI) based on the integrated NTL data is approximately 0.19 (R² = 0.96), which revealed the poverty evaluation model was feasible and reliable. According to the ECPI, we found that the magnitude of poverty eradication increased in southwest China until 2011, but slowed down from 2011 to 2019. Regarding the spatial scale, geographic barriers are a key factor for poverty, with high altitude and mountainous areas typically having a high incidence of poverty. Our approach offers an effective model for evaluation poverty based on the NTL data, which can contribute a more reliable and efficient monitoring of poverty dynamic and a better understanding of socioeconomic development.

High-quality and equitable primary education services promote the building of a harmonious socialist society and are an important basis for improving people’s quality of life and promoting high-quality and sustainable regional development. Here, we take Chengdu City as a test area, integrate data from multiple sources, use the random forest model to simulate the distribution data of primary school-age children in Chengdu City in 2020, and use the kernel density estimation method and the multi-traffic mode two-stage floating catchment area method to measure the spatial distribution characteristics and accessibility of primary school educational facilities in Chengdu City and combine the imbalance index and spatial autocorrelation analysis, examination of the equalization of the distribution of primary school educational facilities, and the correlation between school-age population and accessibility. The results show that in the past decade, the population of Chengdu has grown rapidly, and the number of primary school-age children has also been increasing. The overall distribution of primary school-age children in Chengdu presents a decentralized pattern of “one point with multiple cores”, with the population decreasing from the center to the periphery, and the population distribution dominates the spatial distribution of primary school facilities, which also highlights the imbalance in the construction of primary school facilities to some extent (S = 0.257), which was mainly manifested by the fact that the central-eastern part of the city has more primary school facilities, while the western part has fewer. In addition, the results of both accessibility and autocorrelation analyses show that the overall accessibility of the central circle of Chengdu was high, while the accessibility of the second and third circles was at a lower level and below, with very obvious cross-regional and cross-circle differences. This study can not only provide more accurate recommendations for the allocation of educational facilities but also serve as a reference for evaluating the spatial equity of other public services in the city.

Flash flood can cause dramatic damages to the infrastructure of transportation networks. Because of the uncertainty of flash floods and the access function of roads, assessing the impact of flash floods on transportation systems has been a great challenge. In this study, we proposed a framework for evaluating the risk posed by flash floods to transportation network, which considers the interruption probability of road links and the expected impact on the access function of transportation. To assess the probability of interruption, we used the random forest model to output the flash floods susceptibility. Then, a multiple centrality model was used to evaluate the expected impact when a link was interrupted. The risk takes into account the flash floods susceptibility and road multiple centrality, and it identify critical links. Using the natural break points method, the result of flash floods susceptibility, road multiple centrality and risk were divided into five levels: extremely low, low, moderate, high and extremely high. Approximately 30.8% of the roads were found to be at high and extremely high risk, and most of these roads were located in Sichuan and Yunnan provinces. The flash floods susceptibility contributes more to the risk than the road multiple centrality, thus, further study should be focused on the areas with high flash floods susceptibility. We discussed different disaster prevention and mitigation measures for the different types of high risk links. The results can improve our understanding of the risks posed by flash floods to road networks. The proposed generalized network risk analysis method provides a new perspective and tool for analyzing the impact of flash floods on road network.