Jiangxia Han^1,2, Liang Xue^1,2,*, Ying Jia³, Mpoki Sam Mwasamwasa^1,2, Felix Nanguka⁴, Charles Sangweni⁵, Hailong Liu³, Qian Li³

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.2, pp. 1323-1340, 2024, DOI:10.32604/cmes.2023.031093

Abstract Recent advances in deep neural networks have shed new light on physics, engineering, and scientific computing. Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots. The physics-informed neural network (PINN) is currently the most general framework, which is more popular due to the convenience of constructing NNs and excellent generalization ability. The automatic differentiation (AD)-based PINN model is suitable for the homogeneous scientific problem; however, it is unclear how AD can enforce flux continuity across boundaries between cells of different properties where spatial heterogeneity is represented by grid cells with different physical properties. In this work,… More >

Longlong Bai^1,#, Yong Zhang^2,#, Min Wang¹, Ying He¹, Tao Ye¹, Keli Zhao^1,*

Phyton-International Journal of Experimental Botany, Vol.91, No.10, pp. 2221-2233, 2022, DOI:10.32604/phyton.2022.021422

Abstract Chinese Torreya grandis (Torreya grandis cv. Merrillii) is a unique economic tree species in China. Intensive management related to application of chemical fertilizer and herbicides caused serious soil quality degradation of Chinese Torreya grandis plantations. Totally, 120 soil samples were collected from the main disbtributed areas of Chinese Torreya grandis in Southeastern China. In this area, soil pH values varied from 3.68 to 6.78, with a median value of 4.91, implying a trend of acidification. The average concentrations of organic matter, available nitrogen, available phosphorus and available potassium were 27.52 g kg⁻¹, 135.77 mg kg⁻¹, 15.12 mg kg⁻¹, and 153.43… More >