Hyperspectral imagery has been widely used in precision agriculture due to its rich spectral characteristics. With the rapid development of remote sensing technology, the airborne hyperspectral imagery shows detailed spatial information and temporal flexibility, which open a new way to accurate agricultural monitoring. To extract crop types from the airborne hyperspectral images, we propose a fine classification method based on multi-feature fusion and deep learning. In this research, the morphological profiles, GLCM texture and endmember abundance features are leveraged to exploit the spatial information of the hyperspectral imagery. Then, the multiple spatial information is fused with the original spectral information to generate classification result by using the deep neural network with conditional random field (DNN+CRF) model. Specifically, the deep neural network (DNN) is a deep recognition model which can extract depth features and mine the potential information of data. As a discriminant model, conditional random field (CRF) considers both spatial and contextual information to reduce the misclassification noises while keeping the object boundaries. Moreover, three multiple feature fusion approaches, namely feature stacking, decision fusion and probability fusion, are taken into account. In the experiments, two airborne hyperspectral remote sensing datasets (Honghu dataset and Xiong’an dataset) are used. The experimental results show that the classification performance of the proposed method is satisfactory, where the salt and pepper noise is decreased, and the boundary of the ground object is preserved.

Meteorological drought, one of the most frequent climate-related disasters, causes great danger for human health and socioeconomic development. With an aim to improve the accuracy of meteorological drought monitoring, this study collected multi-source remotely-sensed precipitation products, i.e., the Tropical Rainfall Measuring Mission (TRMM), the Global Precipitation Measurement Mission (GPM), and Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), and compared their performance over Hubei Province, China. The geographic difference analysis was used to blend the best-fitted product with gauged precipitation data. Based on the fused dataset with verification, the spatio-temporal characteristics of drought were investigated. Results showed that GPM performed the best in precipitation numerical evaluation and event detection with a 5 mm/d threshold. The fused data accurately captured 80% of historical drought events and indicated that extreme annual droughts mainly occurred in the northern and northwestern regions, while slight, moderate, and severe droughts mainly occurred in the central and eastern parts. The short-term drought exhibited the highest frequency of 33% in summer and the lowest frequency of 27% in spring, while the medium-term drought showed a higher frequency in autumn and winter. This could be a preliminary assessment of drought based on multi-source fused precipitation data for precise drought outlook and risk management.