A deep inverse convolutional neural network-based semantic classification method for land cover remote sensing images.

The imbalance of land cover categories is a common problem. Some categories appear less frequently in the image, while others may occupy the vast majority of the proportion. This imbalance can lead the classifier to tend to predict categories with higher frequency of occurrence, while the recognition effect on minority categories is poor.

Atomistic liquid crystalline structures of discotic bent-core-like mesogens formed by hydrogen bonding and interchain interactions.

Integrated atomistic and molecular dynamic simulations are used to characterize the role hydrogen bonding and interchain interactions on structures and phase transitions of novel bent-core-like mesogenic materials that exhibit new self-assembly features, attractive to the development of functional materials. Multi-step simulations were carried out to model phase transitions and various spectra of two complex mesogenic materials formed from acid functionalized azo compounds, 4-[2,3,4-tri(octyloxy)phenylazo] benzoic acid and 4-[2,3,4- tri(heptyloxy)phenylazo] benzoic acid. The simulations contain three consecutive steps, involving molecular quantum chemistry, molecular crystal packing, and super cell molecular dynamics calculations.

Temperature influence on the structure and interfacial properties of surfactin micelle: a molecular dynamics simulation study.

Surfactin is an efficient biosurfactant excreted by different strains of Bacillus subtilis. Our study provides a molecular view of the temperature dependence of the structure and the interfacial properties of un-ionized surfactin micelles. The overall size and shape, the surface area, the radial density distribution of the micelles, the conformation of the hydrocarbon chain, and the intramolecular/intermolecular hydrogen bonds formed in surfactin molecules were investigated.