Search

Accurate moisture prediction aids in taking early preventive measures to minimize damage caused by severe storms, droughts, and floods. The study collected 24 types of statistical data from the Xilingol Grassland, Inner Mongolia, spanning from 2011 to 2021. By integrating Elman, backpropagation (BP), and soil moisture prediction model (Elman‐BP) neural networks, soil moisture to 2 m was predicted. The soil moisture mechanism model analysis revealed that soil moisture is related to water supply rather than directly correlated with time. Based on these findings, a two‐stage soil moisture prediction model was established. In the first stage, the Elman neural network model predicted future precipitation data based on observed values. In the second stage, soil moisture was predicted using a BP neural network model based on predicted precipitation data. Comparing the mean squared errors of training and prediction data across the three models revealed that the Elman‐BP neural network had superior predictive accuracy. The maximum relative errors for the trained Elman neural network, BP neural network, and Elman‐BP model were 31.35%, 20.98%, and 3.94%. Overall, results showed a link between soil moisture and water supply and that soil moisture decreased with increasing temperatures. Soil moisture at 10‐ and 40‐cm depths was increased with increasing rainfall. Furthermore, a delay exists between the 40‐ and 100‐cm soil depths. Moreover, soil moisture stability increased with depth. Core Ideas: Accurate soil moisture prediction aids disaster preparedness, reducing damage from severe weather.By comparing three models and making optimal model selection, the maximum error decreased from 31.15% to 94%.Enhance data presentation through vivid visualization to effectively display soil moisture prediction outcomes.The BP‐Elman neural network integrates soil moisture–rainfall–surface evaporation, boosting prediction accuracy.Long‐term data: 11‐year Xilingol Grassland data evaluates models. [ABSTRACT FROM AUTHOR]

Objective To understand the prevalence and annual change trend of Internet addiction among students aged 11 and 22 in Inner Mongolia in 2019 and 2021, and to explore the influencing factors of Internet addiction behavior, so as to provide reference basis for the prevention of Internet addiction among students. Methods Students were selected from 12 cities of Inner Mongolia Autonomous Region by stratified cluster random sampling. Internet addiction disorder was determined according to the items of "surveillance and intervention of common diseases and health influencing factors of students in China". Logistic regression method was used to analyze the relationship between Internet addiction and behavioral factors. Results The prevalence of Internet addiction among students aged 11 to 22 years in Inner Mongolia in 2019 was 1.92%, 2.50%, and 2.21%, respectively. Logistic regression analysis showed that vocational high school (OR=1.347, 95%CI: 1.083-1.675), single parent family (OR=1.279, 95% CI: 1.090-1.500), reconstituted family (OR=1326, 95% CI: 1.041-1.690), bullying (OR=1.755, 95% CI: 1.443-2.135), depression (OR=3.557, 95% CI: 3.146-4.021), fighting (OR=3.374, 95% CI: 2.512-4.531), sugary drinks (OR=2.182. 95% CI:1.753-2.716), and eating fried food (OR=2.398, 95% CI: 1.908-3.014) were the risk factor of Internet addiction. Outdoor activities for 2 hours (OR= 0.620, 95% CI: 0.530-0.726), non-smoking (OR=0.553, 95% CI: 0.476-0.643), and non-drinking (OR=0.581, 95% CI: 0.507-0.666) were the protective factors of Internet addiction. Conclusion The current situation of Internet addiction among students in Inner Mongolia is not optimistic. Attention should be paid to bullying, depression, reconstituted families, fighting students, and vocational high school students. Outdoor activities for 1 to 2 hours a day, reducing the intake of sugary drinks and fried foods, and no smoking and drinking can effectively reduce the incidence of Internet addiction. [ABSTRACT FROM AUTHOR]