Estimation of Precipitation Area Using S-Band Dual-Polarization Radar Measurements

Estimating precipitation area is important for weather forecasting as well as real-time application. This paper aims to develop an analytical framework for efficient precipitation area estimation using S-band dual-polarization radar measurements. Several types of factors, such as types of sensors, thresholds, and models, are considered and compared to form a data set. After building the appropriate data set, this paper yields a rigorous comparison of classification methods in statistical (logistic regression and linear discriminant analysis) and machine learning (decision tree, support vector machine, and random forest). To achieve better performance, spatial classification is considered by incorporating latitude and longitude of observation location into classification, compared with non-spatial classification. The data used in this study were collected by rain detector and present weather sensor in a network of automated weather systems (AWS), and an S-band dual-polarimetric weather radar during ten different rainfall events of varying lengths. The mean squared prediction error (MSPE) from leave-one-out cross validation (LOOCV) is computed to assess the performance of the methods. Of the methods, the decision tree and random forest methods result in the lowest MSPE, and spatial classification outperforms non-spatial classification. Particularly, machine-learning-based spatial classification methods accurately estimate the precipitation area in the northern areas of the study region.

Study on the Spatial Classification of Construction Land Types in Chinese Cities: A Case Study in Zhejiang Province

Identifying the land-use type and spatial distribution of urban construction land is the basis of studying the degree of exposure and the economic value of disaster-affected bodies, which are of great significance for disaster risk predictions, emergency disaster reductions, and asset allocations. Based on point of interest (POI) data, this study adopts POI spatialization and the density-based spatial clustering of applications with noise (DBSCAN) algorithm to accomplish the spatial classification of construction land. Zhejiang province is selected as a study area, and its construction land is divided into 11 land types using an accurate spatial classification method based on measuring the area of ground items. In the research, the POI dataset, which includes information, such as spatial locations and usage types, was constructed by big data cleaning and visual interpretation and approximately 620,000 pieces in total. The overall accuracy of the confusion matrix is 76.86%, which is greatly improved compared with that constructed with EULUC data (61.2%). In addition, compared with the official statistical data of 11 cities in Zhejiang Province, the differences between the calculated spatial proportions and statistics are not substantial. Meanwhile, the spatial characteristics of the studied land-use types are consistent with the urban planning data but with higher accuracy. The research shows that the construction land in Zhejiang Province has a high degree of land intensity, concentrated assets, and high economic exposure. The approach proposed in this study can provide a reference for city management including urbanization process, risk assessment, emergency management and asset allocation.

Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion

Convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds of fusion features and the combination of spatial and spectral features for classification. The authors of this paper propose an HSI spectral–spatial classification method based on deep adaptive feature fusion (SSDF). This method first implements the deep adaptive fusion of two hyperspectral features, and then it performs spectral–spatial classification on the fused features. In SSDF, a U-shaped deep network model with the principal component features as the model input and the edge features as the model label is designed to adaptively fuse two kinds of different features. One comprises the edge features of the HSIs extracted by the guided filter, and the other comprises the principal component features obtained by dimensionality reduction of HSIs using principal component analysis. The fused new features are input into a multi-scale and multi-level feature extraction model for further extraction of deep features, which are then combined with the spectral features extracted by the long short-term memory (LSTM) model for classification. The experimental results on three datasets demonstrated that the performance of the proposed SSDF was superior to several state-of-the-art methods. Additionally, SSDF was found to be able to perform best as the number of training samples decreased sharply, and it could also obtain a high classification accuracy for categories with few samples.