Prediction of Potential Sorghum Suitability Distribution in China Based on Maxent Model

It is increasingly relevant to study the effects of climate change on species habitats. Using a maximum entropy model, 22 environmental factors with significant effects on sorghum habitat distribution in China were selected to predict the potential habitat distribution of sorghum in China. The potential distribution of sorghum under baseline climate conditions and future climate conditions (2050s and 2070s) under two climate change scenarios, RCP4.5 and RCP8.5, were simulated, and the receiver operating curve under the accuracy of the model was evaluated using the area under the receiver operating curve (AUC). The results showed that the maximum entropy model predicted the potential sorghum habitat distribution with high accuracy, with Bio2 (monthly mean diurnal temperature difference), Bio6 (minimum temperature in the coldest month), and Bio13 (rainfall in the wettest month) as the main climatic factors affecting sorghum distribution among the 22 environmental factors. Under the baseline climate conditions, potential sorghum habitats are mainly distributed in the southwest, central, and east China. Over time, the potential sorghum habitat expanded into northern and southern China, with significant additions and negligible decreases in potential sorghum habitat in the study area, and a significant increase in total area, with the RCP8.5 scenario adding much more area than the RCP4.5 scenario.

Graph attention network for global search of atomic clusters:A case study of Ag_(n)(n=14-26)clusters

Due to coexistence of huge number of structural isomers,global search for the ground-state structures of atomic clusters is a challenging issue.The difficulty also originates from the computational cost of ab initio methods for describing the potential energy surface.Recently,machine learning techniques have been widely utilized to accelerate materials discovery and molecular simulation.Compared to the commonly used artificial neural network,graph network is naturally suitable for clusters with flexible geometric environment of each atom.Herein we develop a cluster graph attention network(CGANet)by aggregating information of neighboring vertices and edges using attention mechanism,which can precisely predict the binding energy and force of silver clusters with root mean square error of 5.4 meV/atom and mean absolute error of 42.3 meV/Å,respectively.As a proof-of-concept,we have performed global optimization of mediumsized Agn clusters(n=14–26)by combining CGANet and genetic algorithm.The reported ground-state structures for n=14–21,have been successfully reproduced,while entirely new lowest-energy structures are obtained for n=22–26.In addition to the description of potential energy surface,the CGANet is also applied to predict the electronic properties of clusters,such as HOMO energy and HOMO-LUMO gap.With accuracy comparable to ab initio methods and acceleration by at least two orders of magnitude,CGANet holds great promise in global search of lowest-energy structures of large clusters and inverse design of functional clusters.