As a variant of Convolutional Neural Networks (CNNs) in Deep Learning, the Fully Convolutional Network (FCN) model achieved state-of-the-art performance for natural image semantic segmentation. In this paper, an accurate classification approach for high resolution remote sensing imagery based on the improved FCN model is proposed. Firstly, we improve the density of output class maps by introducing Atrous convolution, and secondly, we design a multi-scale network architecture by adding a skip-layer structure to make it capable for multi-resolution image classification. Finally, we further refine the output class map using Conditional Random Fields (CRFs) post-processing. Our classification model is trained on 70 GF-2 true color images, and tested on the other 4 GF-2 images and 3 IKONOS true color images. We also employ object-oriented classification, patch-based CNN classification, and the FCN-8s approach on the same images for comparison. The experiments show that compared with the existing approaches, our approach has an obvious improvement in accuracy. The average precision, recall, and Kappa coefficient of our approach are 0.81, 0.78, and 0.83, respectively. The experiments also prove that our approach has strong applicability for multi-resolution image classification.

This paper summarizes the main flash flood early-warning systems of America, Europe, Japan, and Taiwan China and discusses their advantages and disadvantages. The latest development in flash flood prevention is also presented. China’s flash flood prevention system involves three stages. Herein, the warning methods and achievements in the first two stages are introduced in detail. Based on the worldwide experience of flash flood early-warning systems, the general research idea of the third stage is proposed from the viewpoint of requirements for flash flood prevention and construction progress of the next stage in China. Real-time dynamic warning systems can be applied to the early-warning platform at four levels (central level, provincial level, municipal level, and county level) . Through this, soil moisture, peak flow, and water level can be calculated in real-time using distributed hydrological models, and then flash flood warning indexes can be computed based on defined thresholds of runoff and water level. A compound warning index (CWI) can be applied to regions where rainfall and water level are measured by simple equipment. In this manner, flash-flood-related factors such as rainfall intensity and antecedent and cumulative rainfall depths can be determined using the CWI method. The proposed methodology for the third stage could support flash flood prevention measures in the 13th 5-Year Plan for Economic and Social Development of the People’s Republic of China (2016–2020). The research achievements will serve as a guidance for flash flood monitoring and warning as well as flood warning in medium and small rivers.

Flash flood, one of the most devastating weather-related hazards in the world, has become more and more frequent in past decades. For the purpose of flood mitigation, it is necessary to understand the distribution of flash flood risk. In this study, artificial intelligence (Least squares support vector machine: LSSVM) and classical canonical method (Logistic regression: LR) are used to assess the flash flood risk in the Yunnan Province based on historical flash flood records and 13 meteorological, topographical, hydrological and anthropological factors. Results indicate that: (1) the LSSVM with Radial basis function (RBF) Kernel works the best (Accuracy = 0.79) and the LR is the worst (Accuracy = 0.75) in testing; (2) flash flood risk distribution identified by the LSSVM in Yunnan province is near normal distribution; (3) the high-risk areas are mainly concentrated in the central and southeastern regions, where with a large curve number; and (4) the impact factors contributing the flash flood risk map from higher to low are: Curve number > Digital elevation > Slope > River density > Flash Flood preventions > Topographic Wetness Index > annual maximum 24 h precipitation > annual maximum 3 h precipitation.

Accurate rainfall forecasting in watersheds is of indispensable importance for predicting streamflow and flash floods. This paper investigates the accuracy of several forecasting technologies based on Wavelet Packet Decomposition (WPD) in monthly rainfall forecasting. First, WPD decomposes the observed monthly rainfall data into several subcomponents. Then, three data-based models, namely Back-propagation Neural Network (BPNN) model, group method of data handing (GMDH) model, and autoregressive integrated moving average (ARIMA) model, are utilized to complete the prediction of the decomposed monthly rainfall series, respectively. Finally, the ensemble prediction result of the model is formulated by summing the outputs of all submodules. Meanwhile, these six models are employed for benchmark comparison to study the prediction performance of these conjunction methods, which are BPNN, WPD-BPNN, GMDH, WPD-GMDH, ARIMA, and WPD-ARIMA models. The paper takes monthly data from Luoning and Zuoyu stations in Luoyang city of China as the case study. The performance of these conjunction methods is tested by four quantitative indexes. Results show that WPD can efficiently improve the forecasting accuracy and the proposed WPD-BPNN model can achieve better prediction results. It is concluded that the hybrid forecast model is a very efficient tool to improve the accuracy of mid- and long-term rainfall forecasting.