Based on the assumption of a linear relationship between near-surface temperature difference and radiometric surface temperature such as the surface energy balance algorithm for land (SEBAL), a satellite-based energy balance algorithm with reference dry and wet limits (REDRAW) is proposed to estimate evapo-transpiration (ET) for the regional scale. REDRAW supposes that extreme hydrological conditions can be represented by the reference dry and wet limits, which consist of four reference limits: reference bare soil dry limit (RBD), reference vegetated soil dry limit (RVD), reference bare soil wet limit (RBW), and reference vegetated soil wet limit (RVW). These reference limits should be derived geographically and used to estimate actual ET under common hydrological conditions. A comparison is made between REDRAW and a commonly used model, SEBAL, at two sites: the Tongyu in China and the Cabauw in The Netherlands. The performances in both cases show that REDRAW can provide more reliable ET estimation in relatively arid and humid areas. Meanwhile, error analysis shows that estimation of sensible heat flux is sensitive to meteorological data, and further study is needed to make REDRAW more robust to environmental conditions.

The fast and accurate identification of apple leaf diseases is beneficial for disease control and management of apple orchards. An improved network for apple leaf disease classification and a lightweight model for mobile terminal usage was designed in this paper. First, we proposed SE-DEEP block to fuse the Squeeze-and-Excitation (SE) module with the Xception network to get the SE_Xception network, where the SE module is inserted between the depth-wise convolution and point-wise convolution of the depth-wise separable convolution layer. Therefore, the feature channels from the lower layers could be directly weighted, which made the model more sensitive to the principal features of the classification task. Second, we designed a lightweight network, named SE_miniXception, by reducing the depth and width of SE_Xception. Experimental results show that the average classification accuracy of SE_Xception is 99.40%, which is 1.99% higher than Xception. The average classification accuracy of SE_miniXception is 97.01%, which is 1.60% and 1.22% higher than MobileNetV1 and ShuffleNet, respectively, while its number of parameters is less than those of MobileNet and ShuffleNet. The minimized network decreases the memory usage and FLOPs, and accelerates the recognition speed from 15 to 7 milliseconds per image. Our proposed SE-DEEP block provides a choice for improving network accuracy and our network compression scheme provides ideas to lightweight existing networks.

No abstract