No abstract

Hyperspectral remote sensing images (HSIs) are 1 rich in spectral-spatial information. The deep learning models 2 can help to automatically extract and discover these rich3 information from HSIs for classifying HSIs. However, the 4 sampling of the models and the design of the hyperparameters 5 depend on the number of samples and the size of each 6 sample's input space. In the case of limited samples, the 7 description dimension of features is also limited and 8 overfitting to other remote sensing image datasets is evident.9 This study proposes a novel deep feature aggregation network 10 (DFAN) for HSI classification based on a 3D-convolutional 11 neural network (3D-CNN) from the perspective of feature 12 aggregation patterns. By introducing the residual learning 13 and dense connectivity strategies, we established a deep 14 feature residual network (DFRN) and a deep feature dense 15 1 network (DFDN) to exploit the low-, middle-and high-level

Dust emission is an important corollary of the soil degradation process in arid and semi-arid areas worldwide. Soil organic carbon (SOC) is the main terrestrial pool in the carbon cycle, and dust emission redistributes SOC within terrestrial ecosystems and to the atmosphere and oceans. This redistribution plays an important role in the global carbon cycle. Herein, we present a systematic review of dust modelling, global dust budgets, and the effects of dust emission on SOC dynamics. Focusing on selected dust models developed in the past five decades at different spatio-temporal scales, we discuss the global dust sources, sinks, and budgets identified by these models and the effect of dust emissions on SOC dynamics. We obtain the following conclusions: (1) dust models have made considerable progress, but there are still some uncertainties; (2) a set of parameters should be developed for the use of dust models in different regions, and direct anthropogenic dust should be considered in dust emission estimations; and (3) the involvement of dust emission in the carbon cycle models is crucial for improving the accuracy of carbon assessment.

No abstract

No abstract