Long-term water demand forecasting using artificial intelligence models in the Tuojiang River basin, China.

Accurate forecasts of water demand are a crucial factor in the strategic planning and judicious use of finite water resources within a region, underpinning sustainable socio-economic development. This study aims to compare the applicability of various artificial intelligence models for long-term water demand forecasting across different water use sectors. We utilized the Tuojiang River basin in Sichuan Province as our case study, comparing the performance of five artificial intelligence models: Genetic Algorithm optimized Back Propagation Neural Network (GA-BP), Extreme Learning Machine (ELM), Gaussian Process Regression (GPR), Support Vector Regression (SVR), and Random Forest (RF). These models were employed to predict water demand in the agricultural, industrial, domestic, and ecological sectors using actual water demand data and relevant influential factors from 2005 to 2020. Model performance was evaluated based on the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with the most effective model used for 2025 water demand projections for each sector within the study area. Our findings reveal that the GPR model demonstrated superior results in predicting water demand for the agricultural, domestic, and ecological sectors, attaining R2 values of 0.9811, 0.9338, and 0.9142 for the respective test sets. Also, the GA-BP model performed optimally in predicting industrial water demand, with an R2 of 0.8580. The identified optimal prediction model provides a useful tool for future long-term water demand forecasting, promoting sustainable water resource management.

An interval water demand prediction method to reduce uncertainty: A case study of Sichuan Province, China.

Effective prediction of water demand is a prerequisite for decision makers to achieve reliable management of water supply. Currently, the research on water demand prediction focuses on point prediction method. In this study, we constructed a GA-BP-KDE hybrid interval water demand prediction model by combining non-parametric estimation and point prediction. Multiple metaheuristic algorithms were used to optimize the Back-Propagation Neural Network (BP) and Kernel Extreme Learning Machine (KELM) network structures. The performance of the water demand point prediction models was compared by the Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Kling-Gupta Efficiency (KGE), computation time, and fitness convergence curves. The kernel density estimation method (KDE) and the normal distribution method were used to fit the distribution of errors. The probability density function with the best fitting degree was selected based on the index G. The shortest confidence interval under 95% confidence was calculated according to the asymmetry of the error distribution. We predicted the impact indicator values for 2025 using the exponential smoothing method, and obtained water demand prediction intervals for various water use sectors. The results showed that the GA-BP model was the optimal model as it exhibited the highest computational efficiency, algorithmic stability, and prediction accuracy. The three prediction intervals estimated after adjusting the KDE bandwidth parameter covered most of the sample points in the test set. The prediction intervals of the four water use sectors were evaluated as F values of 1.6845, 1.3294, 1.6237, and 1.3600, which indicates high accuracy and quality of the prediction intervals. The mixed water demand interval prediction based on GA-BP-KDE reduces the uncertainty of the point prediction results and can provide a basis for water resource management by decision makers.

The Effect of Activity Participation in Middle-Aged and Older People on the Trajectory of Depression in Later Life: National Cohort Study.

BACKGROUND: More activity participation is an important means of handling depression and promoting positive aging, but the impact of changes in activity participation on the developmental trajectory of depression has not been fully studied. OBJECTIVE: The purpose of this study is to study the relationship between current activity participation and depression in middle-aged and older people (≥45 years old) and the relationship between activity participation and the developmental trajectory of depression in later life in China. METHODS: This study used data from the China Health and Retirement Longitudinal Study (CHARLS) across 7 years and included a total of 4818 middle-aged and older people (≥45 years old). Controlling for relevant control variables, the latent growth curve model and the cross-lag model were used to assess the effect of changes in activity participation on the depression trajectory in later life and the main lag relationship between activity participation and depression. Activity participation as well as depression were measured using the self-reported activity and health status based on the CHARLS questionnaire. RESULTS: Among the 4818 respondents, the mean values of physical activity participation, social leisure activity participation, and depression ranged from 76.98 (SD 15.16) to 83.95 (SD 5.72), from 7.43 (SD 8.67) to 9.25 (SD 10.16), and from 7.61 (SD 5.72) to 8.82 (SD 6.51), respectively. Our findings revealed that activity participation could be related to depression. Physical activity participation predicted initial depression (ß=-0.631, P<.001) and its trajectory (ß=0.461, P<.001). However, social leisure activity participation predicted initial depression (ß=-0.223, P<.001) but did not predict its trajectory (ß=0.067, P=.159). Finally, cross-lag regression analysis further demonstrated the predictive effect of activity participation on depression. CONCLUSIONS: This study demonstrates the prediction of activity participation for future depression in the Chinese middle-aged and older populations. The data showed that activity participation is significantly associated with changes in depression and future depression among middle-aged and older people in China. The Chinese government should encourage middle-aged and older people to participate in various activities, which can effectively prevent the aggravation of depression and also have a positive significance for positive aging.

Comparison of earthquake-induced shallow landslide susceptibility assessment based on two-category LR and KDE-MLR.

Geological hazards caused by strong earthquakes have caused continuous social and economic losses and destruction of the ecological environment in the hazard area, and are mostly manifested in the areas with frequent occurrence of geological hazards or the clustering of geological hazards. Considering the long-term nature of earthquakes and geological disasters in this region, this paper takes ten earthquake-stricken areas in Wenchuan earthquake zone as examples to collect shallow landslide data in 2010, combined with the spatial location of landslides and other factors. Kernel density estimation (KDE) method is used to analyze the spatial characteristics of shallow landslide. Taking the space of shallow landslide as the characteristic variable and fully considering the regulating factors of earthquake-induced landslide: terrain complexity, distance to river, distance to fault, distance to road, lithology, normalized vegetation difference index (NDVI) and ground peak acceleration (PGA) as independent variables, based on KDE and polynomial logistic regression (MLR), A quantitative model of shallow landslide in the earthquake area is constructed. The results show that: (1) PGA has the greatest impact on landslide in the study area. (2) Compared with the two-category logistic regression (two-category LR) model, the susceptibility map of landslide prediction results based on the KDE-MLR landslide susceptibility prediction model is more consistent with the actual situation. (3) The prediction accuracy of the model validation set is 70.7%, indicating that the landslide susceptibility prediction model based on KDE-MLR can effectively highlight the spatial characteristics of shallow landslides in 10 extreme disaster areas. The research results can provide decision-making basis for shallow landslide warning and post-disaster reconstruction in earthquake-stricken areas.

Effects of pain and depression on the relationship between household solid fuel use and disability among middle-aged and older adults.

Household air pollution (HAP) is suggested to increases people's risk of disability, but mediating mechanisms between HAP and disability remains under-investigated. The aim of this study was to investigate the underlying mechanisms between household air pollution and disability in middle-aged and older adults (i.e., older than 45 years) using a nationally representative prospective cohort. In total, 3754 middle-aged and older adults were selected from the China Health and Retirement Longitudinal Study. Correlation analysis and logistic regression analysis were employed to estimate the association between HAP, pain, depression and disability. Finally, three significant mediation pathways through which HAP directly impacts disability were found: (1) pain (B = 0.09, 95% CI 0.01, 0.02), accounting for 15.25% of the total effect; (2) depression (B = 0.07, 95% CI 0.004, 0.02), accounting for 11.86% of the total effect; (3) pain and depression (B = 0.04, 95% CI 0.003, 0.01), accounting for 6.78% of the total effect. The total mediating effect was 33.89%. This study clarified that HAP can indirectly affect disability through the respective and serial mediating roles of pain and depression. These findings potentially have important implications for national strategies concerning the widespread use of clean fuels by citizens.

The relationship between gender, marital status and depression among Chinese middle-aged and older people: Mediation by subjective well-being and moderation by degree of digitization.

The purposes of this study were to investigate the effects of gender and marital status on depression among middle-aged and older people in China, and to explore the mediating effect of subjective well-being and the moderating effect of degree of digitization in the relationship between subjective well-being and depression. A total of 15,586 Chinese middle-aged and older people (≥ 45 years old) were included in the study using data from the 2018 China Health and Retirement Longitudinal Survey (CHARLS). T-test, ANOVA, hierarchical regression and Bootstrap methods were adopted to test the mediating role of subjective well-being and the moderating role of degree of digitization. The results showed that middle-aged and older women were more likely to suffer from depression than men, and married middle-aged and older people were less likely to be depressed than those who were separated or divorced, widowed and never married. Subjective well-being partially mediated the relationship between gender and depression, and masked the relationship between marital status and depression, and all five dimensions it contains also played a mediating role. Degree of digitization moderated the effect of subjective well-being on depression. Simple slope tests indicated that the effect of subjective well-being on depression increased as degree of digitization increased. In conclusion, to address the mental health problems of middle-aged and older people brought about by the ageing and digital society, we should start by improving their subjective well-being and promoting their integration into the digital society.

Longitudinal Relationship between Cognitive Function and Health-Related Quality of Life among Middle-Aged and Older Patients with Diabetes in China: Digital Usage Behavior Differences.

BACKGROUND: Cognitive function and health-related quality of life (HRQoL) are important issues in diabetes care. According to the China Association for Aging, it is estimated that by 2030, the number of elderly people with dementia in China will reach 22 million. The World Health Organization reports that by 2044, the number of people with diabetes in China is expected to reach 175 million. METHODS: Cohort analyses were conducted based on 854 diabetic patients aged ≥45 years from the third (2015) and fourth (2018) survey of the China Health and Retirement Longitudinal Study (CHARLS). Correlation analysis, repeated-measures variance analysis, and cross-lagged panel models were used to measure the difference in digital usage behavior in the established relationship. RESULTS: The results show that the cognitive function of middle-aged and older diabetic patients is positively correlated with HRQoL. HRQoL at T1 could significantly predict cognitive function at T2 (PCS: B = 0.12, p < 0.01; MCS: B = 0.14, p < 0.01). This relationship is more associated with individual performance than digital usage behavior. CONCLUSIONS: Unidirectional associations may exist between cognitive function and HRQoL among middle-aged and older Chinese diabetes patients. In the future, doctors and nurses can recognize the lowering of self-perceived HRQoL of middle-aged and older diabetic patients, and thus draw more attention to their cognitive function, in turn strengthening the evaluation, detection, and intervention of their cognitive function.

Effects of exercise combined with diet intervention on body composition and serum biochemical markers in adolescents with obesity: a systematic review and meta-analysis.

BACKGROUND: This systematic review aims to evaluate the effects of exercise combined with diet (ECWD), exercise alone, diet alone, and no intervention on body composition and serum biochemical markers in adolescents with obesity to provide reference for solving the metabolic disorders of adolescents caused by obesity. CONTENTS: Studies published before January 5, 2021 were retrieved from PubMed, Web of Science, Ovid, Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang data, VIP database, and SinoMed. Randomized controlled trials with an age between 10 and 20 years, body mass index (BMI) ≥28 kg/m2 or ≥95th percentiles, no history of endocrine and metabolic diseases, heart disease, hematologic disease, and so on before the trial were included. SUMMARY: Fifteen of the 50,155 studies met the criteria. Meta-analysis showed that ECWD was more effective in reducing BMI (kg/m2) (-2.45 kg/m2, 95% CI: -3.06; -1.85) and fat thickness of back (-13.77 mm, 95% CI: -15.92; -11.62), abdomen (-11.56 mm, 95% CI: -14.04; -9.09), and upper arm (-14.81 mm, 95% CI: -16.74; -12.89) than other interventions; in reducing body fat (-7.03 kg, 95% CI: -9.77; -4.29) and thigh circumference (-4.05 cm, 95% CI: -5.58; -2.52), ECWD and diet alone were more effective than exercise alone; ECWD and exercise alone were more effective in reducing waist circumference (-6.05 cm, 95% CI: -8.37; -3.72), waist-to-hip ratio (WHR; -0.06, 95% CI: -0.11; -0.01), upper arm circumference (-2.57 cm, 95% CI: -3.70; -1.45), triglycerides (TG; -0.30 mmol/L, 95% CI: -0.45; -0.14), total cholesterol (TC; -0.30 mmol/L, 95% CI: -0.59; -0.01), and low density lipoprotein (LDL; -0.22 mmol/L, 95% CI: -0.40; -0.04) than diet alone. ECWD also had effects on tumor necrosis factor-α (TNF-α), interleukin-6, leptin, and so on. OUTLOOK: ECWD is more effective than exercise alone, diet alone, or no intervention in solving the problems of body shape and metabolic disorder of adolescents with obesity.

Proper Orthogonal Decomposition Analysis Reveals Cell Migration Directionality During Wound Healing.

A proper orthogonal decomposition (POD) order reduction method was implemented to reduce the full high dimensional dynamical system associated with a wound healing cell migration assay to a low-dimensional approximation that identified the prevailing cell trajectories. The POD analysis generated POD modes that were representative of the prevalent cell trajectories. The shapes of the POD modes depended on the location of the cells with respect to the wound and exposure to disturbed (DF) or undisturbed (UF) fluid flow where the net flow was in the antegrade direction with a retrograde component or fully antegrade, respectively. For DF and UF, the POD modes of the downstream cells identified trajectories that moved upstream against the flow, while upstream POD modes exhibited sideways cell migrations. In the absence of flow, no major shape differences were observed in the POD modes on either side of the wound. The POD modes also served to reconstruct the cell migration of individual cells. With as few as three modes, the predominant cell migration trajectories were reconstructed, while the level of accuracy increased with the inclusion of more POD modes. The POD order reduction method successfully identified the predominant cell migratory trajectories under static and varying pulsatile fluid flow conditions serving as a first step in the development of artificial intelligence models of cell migration in disease and development.

Flow inside a bone scaffold: Visualization using 3D phase contrast MRI and comparison with numerical simulations.

We report on results of experimental flow measurements inside a bone scaffold model, subjected to a uniform incoming flow (applied perfusion). Understanding the flow behavior inside a tissue engineered scaffold is essential for mechanistic studies of mechanobiology, particularly flow-sensitive bone cells. Nearly all existing studies that quantify interstitial flow inside engineered bone scaffolds have been based on numerical results, in part due to the difficulties associated with quantitative measurements and visualization of flow inside large, opaque bone or bone mimics. Thus, an experimental platform to complement and validate in silico studies is needed. Therefore, we developed a flow visualization method using Phase-Contrast Magnetic Resonance Imaging (PC-MRI) to measure flow velocities within a 3D-printed microCT-based rendering of a bone scaffold. We designed and built a non-magnetic recirculating water tunnel to apply uniform perfusion to the 3D-printed model and we measured flow distribution within the scaffold and compared these experimental results with CFD results. Both magnitude and distribution of flow velocities observed at different slices of the scaffold were in quantitative agreement numerically and experimentally. This experimental approach can be used to both validate numerical studies and provide insight into the flow behavior inside tissue-engineered scaffolds for a range of applications, including fundamental mechanobiology of healthy cells, and in the context of diseases, such as cancer.

Multiphysics simulation of a compression-perfusion combined bioreactor to predict the mechanical microenvironment during bone metastatic breast cancer loading experiments.

Incurable breast cancer bone metastasis causes widespread bone loss, resulting in fragility, pain, increased fracture risk, and ultimately increased patient mortality. Increased mechanical signals in the skeleton are anabolic and protect against bone loss, and they may also do so during osteolytic bone metastasis. Skeletal mechanical signals include interdependent tissue deformations and interstitial fluid flow, but how metastatic tumor cells respond to each of these individual signals remains underinvestigated, a barrier to translation to the clinic. To delineate their respective roles, we report computed estimates of the internal mechanical field of a bone mimetic scaffold undergoing combinations of high and low compression and perfusion using multiphysics simulations. Simulations were conducted in advance of multimodal loading bioreactor experiments with bone metastatic breast cancer cells to ensure that mechanical stimuli occurring internally were physiological and anabolic. Our results show that mechanical stimuli throughout the scaffold were within the anabolic range of bone cells in all loading configurations, were homogenously distributed throughout, and that combined high magnitude compression and perfusion synergized to produce the largest wall shear stresses within the scaffold. These simulations, when combined with experiments, will shed light on how increased mechanical loading in the skeleton may confer anti-tumorigenic effects during metastasis.

Disaster resilience assessment based on the spatial and temporal aggregation effects of earthquake-induced hazards.

Since the "5.12" Wenchuan earthquake in 2008, frequent geologic hazards along the Longmenshan fault zone have had significant impacts on the socioeconomic conditions in the earthquake-stricken areas. Therefore, from the perspective of earthquake-induced hazards, this paper focuses on analyzing the change rules of disaster resilience under the spatial and temporal aggregation effects of earthquake-induced hazards, and this analysis provides an important basis for understanding the developmental characteristics of earthquake-induced hazards and disaster prevention, and mitigation after earthquakes. This paper takes Wenchuan County as an example. By collecting the 2008-2018 landslide geological hazards data, the global autocorrelation coefficient and local autocorrelation coefficient are adopted to analyze the temporal trends and spatial patterns of earthquake-induced hazards. At the same time, from the socioeconomic perspective, two disaster resilience indexes, the compatibility coefficient of industrial and employment structure and per capita GDP growth rate, were constructed to analyze the disaster resilience under the spatial and temporal aggregation effect of landslide geological hazards. The results show that, on the temporal trend, the temporal aggregation effect of earthquake-induced hazards has periodically decayed with time; in the spatial distribution, the spatial clustering effect as a whole increases first and then decreases, and the scope of the aggregation effect tends to narrow spatially. Disaster resilience (Hxy and RGDP) showed a trend of increasing first and then decreasing, and could not recover to the level before the earthquake in 2017, indicating that Wenchuan County was greatly affected by earthquake-induced hazards in the post-earthquake reconstruction process.

A reduced-order model of a patient-specific cerebral aneurysm for rapid evaluation and treatment planning.

We discuss a computationally-efficient numerical Reduced Order Model (ROM) for patient-specific cerebral aneurysms, which can be used to examine the rupture-related hemodynamic parameters over a range of relevant physiological flow parameters, rapidly. The ROMs were derived using a Proper Orthogonal Decomposition (POD) technique, which also took advantage of the method of Snapshot POD. Initially a series of Computational Fluid Dynamics(CFD) training runs were performed, which were subsequently improved using a QR-decomposition technique to satisfy the various boundary conditions in physiological flow problems. We used the obtained ROMs to study the influence of Pulsatility Index (PI) on a patient-specific aneurysm's Wall Shear Stress (WSS) and Oscillatory Shear Index (OSI). In addition, we discuss how each of the obtained high-energy POD modes represents a separate significant flow pattern that is believed to influence the aneurysm's WSS and OSI.

Perfusion applied to a 3D model of bone metastasis results in uniformly dispersed mechanical stimuli.

Breast cancer most frequently metastasizes to the skeleton. Bone metastatic cancer is incurable and induces wide-spread bone osteolysis, resulting in significant patient morbidity and mortality. Mechanical cues in the skeleton are an important microenvironmental parameter that modulate tumor formation, osteolysis, and tumor cell-bone cell signaling, but which mechanical signals are the most beneficial and the corresponding molecular mechanisms are unknown. We focused on interstitial fluid flow based on its well-known role in bone remodeling and in primary breast cancer. We created a full-scale, microCT-based computational model of a 3D model of bone metastasis undergoing applied perfusion to predict the internal mechanical environment during in vitro experimentation. Applied perfusion resulted in uniformly dispersed, heterogeneous fluid velocities, and wall shear stresses throughout the scaffold's interior. The distributions of fluid velocity and wall shear stress did not change within model sub-domains of varying diameter and location. Additionally, the magnitude of these stimuli is within the range of anabolic mechanical signals in the skeleton, verifying that our 3D model reflects previous in vivo studies using anabolic mechanical loading in the context of bone metastasis. Our results indicate that local populations of cells throughout the scaffold would experience similar mechanical microenvironments.