A comprehensive evaluation of influencing factors of neonicotinoid insecticides (NEOs) in farmland soils across China: First focus on film mulching

Neonicotinoid insecticide (NEO) residues in agricultural soils have concerning and adverse effects on agroecosystems. Previous studies on the effects of farmland type on NEOs are limited to comparing greenhouses with open fields. On the other hand, both NEOs and microplastics (MPs) are commonly found in agricultural fields, but their co-occurrence characteristics under realistic fields have not been reported. This study grouped farmlands into three types according to the covering degree of the film, collected 391 soil samples in mainland China, and found significant differences in NEO residues in the soils of the three different farmlands, with greenhouse having the highest NEO residue, followed by farmland with film mulching and farmland without film mulching (both open fields). Furthermore, this study found that MPs were significantly and positively correlated with NEOs. As far as we know this is the first report to disclose the association of film mulching and MPs with NEOs under realistic fields. Moreover, multiple linear regression and random forest models were used to comprehensively evaluate the factors influencing NEOs (including climatic, soil, and agricultural indicators). The results indicated that the random forest model was more reliable, with MPs, farmland type, and total nitrogen having higher relative contributions.

Cooling Effect of Green Spaces on Urban Heat Island in a Chinese Megacity: Increasing Coverage versus Optimizing Spatial Distribution

Enhancing the cooling effectiveness of green spaces (GSs) is crucial for improving urban thermal environments in the context of global warming. Increasing GS coverage and optimizing its spatial distribution individually proved to be effective urban cooling measures. However, their comparative cooling effectiveness and potential interaction remain unclear. Here, using the moving window approach and random forest algorithm, we established a robust model (R2 = 0.89 ± 0.01) to explore the relationship between GS and land surface temperature (LST) in the Chinese megacity of Guangzhou. Subsequently, the response of LST to varying GS coverage and its spatial distribution was simulated, both individually and in combination. The results indicate that GS with higher coverage and more equitable spatial distribution is conducive to urban heat mitigation. Increasing GS coverage was found to lower the city's average LST by up to 4.73 °C, while optimizing GS spatial distribution led to a decrease of 1.06 °C. Meanwhile, a synergistic cooling effect was observed when combining both measures, resulting in additional cooling benefits (0.034-0.341 °C). These findings provide valuable insights into the cooling potential of GS and crucial guidance for urban green planning aimed at heat mitigation in cities.

Quantification of Central and Eastern China's atmospheric CH4 enhancement changes and its contributions based on machine learning approach

Methane is the second largest anthropogenic greenhouse gas, and changes in atmospheric methane concentrations can reflect the dynamic balance between its emissions and sinks. Therefore, the monitoring of CH4 concentration changes and the assessment of underlying driving factors can provide scientific basis for the government's policy making and evaluation. China is the world's largest emitter of anthropogenic methane. However, due to the lack of ground-based observation sites, little work has been done on the spatial-temporal variations for the past decades and influencing factors in China, especially for areas with high anthropogenic emissions as Central and Eastern China. Here to quantify atmospheric CH4 enhancements trends and its driving factors in Central and Eastern China, we combined the most up-to-date TROPOMI satellite-based column CH4 (xCH4) concentration from 2018 to 2022, anthropogenic and natural emissions, and a random forest-based machine learning approach, to simulate atmospheric xCH4 enhancements from 2001 to 2018. The results showed that (1) the random forest model was able to accurately establish the relationship between emission sources and xCH4 enhancement with a correlation coefficient (R²) of 0.89 and a root mean-square error (RMSE) of 11.98 ppb; (2)The xCH4 enhancement only increased from 48.21±2.02 ppb to 49.79±1.87 ppb from the year of 2001 to 2018, with a relative change of 3.27%±0.13%; (3) The simulation results showed that the energy activities and waste treatment were the main contributors to the increase in xCH4 enhancement, contributing 68.00% and 31.21%, respectively, and the decrease of animal ruminants contributed -6.70% of its enhancement trend.

Predictions of heavy metal concentrations by physiochemical water quality parameters in coastal areas of Yangtze river estuary

Due to the degradation-resistant and strong toxicity, heavy metals pose a serious threat to the safety of water environment and aquatic ecology. Rapid acquisition and prediction of heavy metal concentrations are of paramount importance for water resource management and environmental preservation. In this study, heavy metal concentrations (Cr, Ni, Cu, Pb, Zn, Cd) and physicochemical parameters of water quality including Temperature (Temp), pH, Oxygen redox potential (ORP), Dissolved oxygen (DO), Electrical conductivity (EC), Electrical resistivity (RES), Total dissolved solids (TDS), Salinity (SAL), Cyanobacteria (BGA-PE), and turbidity (NTU) were measured at seven stations in the Yangtze river estuary. Principal Component Analysis (PCA) and Spearman correlation analysis were employed to analyze the main factors and sources of heavy metals. Results of PCA revealed that the main sources of Cr, Ni, Zn, and Cd were steel industry wastewater, domestic and industrial sewage, whereas shipping and vessel emissions were typically considered sources of Pb and Cu. Spearman correlation analysis identified Temp, pH, ORP, EC, RES, TDS, and SAL as the key physicochemical parameters of water quality, exhibiting the strongest correlation with heavy metal concentrations in sediment and water samples. Based on these results, multiple linear regression as well as non-linear models (SVM and RF) were constructed for predicting heavy metal concentrations. The results showed that the results of the nonlinear model were more suitable for predicting the concentrations of most heavy metals than the linear model, with average R values of the SVM test set and RF test set being 0.83 and 0.90. The RF model showed better applicability for simulating the concentration of heavy metals along the Yangtze river estuary. It was demonstrated that non-linear research methods provided efficient and accurate predictions of heavy metal concentrations in a simple and rapid manner, thereby offering decision-making support for watershed managers.

Evaluation of physical education teaching effect using Random Forest model under artificial intelligence

This work aims to optimize the physical education (PE) teaching effect based on deep learning (DL) to cultivate high-level college students better. Firstly, the present situation of college teachers' teaching ability is surveyed to realize the deficiencies in teaching. Secondly, an optimization algorithm is proposed to improve the node splitting mode. This algorithm can solve the problem of single and similar node splitting modes in the Random Forest (RF) algorithm. The independent node splitting method Iterative Dichotomiser 3 and Classification and Regression Tree in the algorithm are recombined, and new splitting rules are obtained through adaptive parameter selection. Finally, the scheme designed is tested. The results suggest: The results suggest: (1) During the training of the proposed algorithm, although the loss curve at 4550 and 6800 points has a small crest, the error of the network loss function shows a downward trend and tends to be flat; (2) Compared with unoptimized Genetic Algorithm (GA) and Genetic Algorithm-Back Propagation (GA-BP), the proposed algorithm shows better performance both in terms of time consumption and accuracy (time consumption is less than 5.4 ms, and accuracy is more than 95 %). In a word, using the GA-BP-RF algorithm proposed to improve the PE teaching effect is feasible. The proposed model provides ideas for applying DL technology to improve teachers' teaching abilities.

Primary sources of HONO vary during the daytime: Insights based on a field campaign

Nitrous acid (HONO) is an established precursor of hydroxyl (OH) radical and has significant impacts on the formation of PM2.5 and O3. Despite extensive research on HONO observation in recent years, knowledge regarding its sources and sinks in urban areas remains inadequate. In this study, we monitored the atmospheric concentrations of HONO and related pollutants, including gaseous nitric acid and particulate nitrate, simultaneously at a supersite in downtown Chengdu, a megacity in southwestern China during spring, when was chosen due to its tolerance for both PM2.5 and O3 pollution. Furthermore, we employed the random forest model to fill the missing data of HONO, which exhibited good predictive performance (R2 = 0.96, RMSE = 0.36 ppbv). During this campaign, the average mixing ratio of HONO was measured to be 1.0 ± 0.7 ppbv. Notably, during periods of high O3 and PM2.5 concentrations, the mixing ratio of HONO was >50 % higher compared to the clean period. We developed a comprehensive parameterization scheme for the HONO budget, and it performed well in simulating diurnal variations of HONO. Based on the HONO budget analysis, we identified different mechanisms that dominate HONO formation at different times of the day. Vehicle emissions and NO2 heterogeneous conversions were found to be the primary sources of HONO during nighttime (21.0 %, 30.2 %, respectively, from 18:00 to 7:00 the next day). In the morning (7:00-12:00), NO2 heterogeneous conversions and the reaction of NO with OH became the main sources (35.0 %, 32.2 %, respectively). However, in the afternoon (12:00-18:00), the heterogeneous photolysis of HNO3 on PM2.5 was identified as the most substantial source of HONO (contributing 52.5 %). This study highlights the significant variations in primary HONO sources throughout the day.

Deriving a high-quality daily dataset of large-pan evaporation over China using a hybrid model

Global warming is expected to increase the atmospheric evaporative demand and make more surface water for evapotranspiration, aggerating water sources' social and ecological shortage. Pan evaporation, as a routine observation worldwide, is an excellent metric to indicate the response of terrestrial evaporation to global warming. However, several non-climatic effects, such as instrument upgrades, have destroyed the homogenization of pan evaporation and limited its applications. In China, 2400s meteorological stations have observed daily pan evaporation since 1951. The observed records became discontinuous and inconsistent due to the instrument upgrade from micro-pan D20 to large-pan E601. Here, combining the Penpan model (PM) and random forest model (RFM), we developed a hybrid model to assimilate different types of pan evaporation into a consistent dataset. Based on the cross-validation test, on a daily scale, the hybrid model has a lower bias (RMSE=0.41 mm day^-1) and better stability (NSE=0.94) than the two sub-models and the conversion coefficient method. Finally, we produced a homogenized daily dataset of E601 across China from 1961 to 2018. Based on this dataset, we analyzed the long-term trend of pan evaporation. Pan evaporation showed a -1.23±0.57 mm a^-2 downward trend from 1961-1993, primarily caused by decreased pan evaporation in warm seasons over North China. After 1993, the pan evaporation in South China increased significantly, resulting in a 1.83±0.87 mm a^-2 upward trend across China. With better homogeneity and higher temporal resolution, the new dataset is expected to promote drought monitoring, hydrological modeling, and water resources management. Free access to the dataset can be found at https://figshare.com/s/0cdbd6b1dbf1e22d757e.

Accuracy assessment of inverse distance weighting interpolation of groundwater nitrate concentrations in Bavaria (Germany)

For the designation of nitrate vulnerable zones under the EU Nitrate Directive, some German federal states use inverse distance weighting (IDW) as interpolation method. Our study quantifies the accuracy of IDW with respect to the designation of areas with a groundwater nitrate concentration above the threshold of 50 mg NO₃/l using a dataset of 5790 groundwater monitoring sites in Bavaria. The results show that the absolute differences of nitrate concentrations between the monitoring sites are only weakly correlated within a range of no more than 0.4 km. The IDW cross-validated nitrate concentration of measurement sites shows a mean absolute error of 7.0 mg NO₃/l and the number of measurement sites above 50 mg NO₃/l is 44% too low by interpolation for all sites as a whole. The corresponding values for interpolation separately for the 18 hydrogeological regions in Bavaria are 7.1 mg NO₃/l and 38%. The sensitivity and the accuracy of nitrate concentration maps due to the variation of IDW parameters and the position of sampling points are analysed by Monte Carlo IDW interpolations using a Random Forest modelled map as reference spatial distribution. Compared to this reference map, the area with a concentration above 50 mg NO₃/l in groundwater is estimated by IDW to be 46% too low for the best IDW parametrization. Overall, IDW interpolation systematically underrates the occurrence of higher range nitrate concentrations. In view of these underestimations, IDW does not appear to be a suitable regionalization method for the designation of nitrate vulnerable zones, neither when applied for a federal state as a whole nor when interpolated separately for hydrogeological regions.

Predicting spatial variability of species diversity with the minimum data set of soil properties in an arid desert riparian forest

Species diversity has spatial heterogeneity in ecological systems. Although a large number of studies have demonstrated the influence of soil properties on species diversity, most of them have not considered their spatial variabilities. To remedy the knowledge gap, a 1 ha (100 m × 100 m) plots of arid desert riparian forest was set up in the Ebinur Wetland Nature Reserve (ELWNR) in the NW China. Then, the minimum data set of soil properties (soil MDS) was established using the Principal Component Analysis (PCA) and the Norm Value Determination to represent the total soil property data set (soil TDS). The Geo-statistics and two models (i.e., Random Forest/RF and Multiple Linear Regression/MLR) were used to measure the spatial variability of species diversity, and predict its spatial distribution by the soil MDS, respectively. The results showed that the soil MDS was composed of soil salt content (SSC), soil total phosphorus (STP), soil available phosphorus (SAP), soil organic carbon (SOC) and soil nitrate nitrogen (SNN); which represented the soil TDS perfectly (R^{2 =} 0.62). Three species diversity indices (i.e., Shannon-Wiener, Simpson and Pielou indices) had a high spatial dependence (C₀/(C₀+C)< 25%; 0.72 m ≤ range≤ 0.77 m). Ordinary kriging distribution maps showed that the spatial distribution pattern of species diversity predicted by RF model was closer to its actual distribution compared with MLR model. RF model results suggested that the soil MDS had significant effect on spatial distribution of Shannon-Wiener, Simpson and Pielou indices (Var_ex = 56%, 49% and 36%, respectively). Among all constituents, SSC had the largest contribution on the spatial variability of species diversity (nearly 10%), while STP had least effect (< 5.3%). We concluded that the soil MDS affected spatial variability of species diversity in arid desert riparian forests. Using RF model can predict spatial variability of species diversity through soil properties. Our work provided a new case and insight for studying the spatial relationship between soil properties and plant species diversity.

Machine learning for distinguishing right from left premature ventricular contraction origin using surface electrocardiogram features

BACKGROUND

Precise localization of the site of origin of premature ventricular contractions (PVCs) before ablation can facilitate the planning and execution of the electrophysiological procedure.

OBJECTIVE

The purpose of this study was to develop a predictive model that can be used to differentiate PVCs between the left ventricular outflow tract and right ventricular outflow tract (RVOT) using surface electrocardiogram characteristics.

METHODS

A total of 851 patients undergoing radiofrequency ablation of premature ventricular beats from January 2015 to March 2022 were enrolled. Ninety-two patients were excluded. The other 759 patients were enrolled into the development (n = 605), external validation (n = 104), or prospective cohort (n = 50). The development cohort consisted of the training group (n = 423) and the internal validation group (n = 182). Machine learning algorithms were used to construct predictive models for the origin of PVCs using body surface electrocardiogram features.

RESULTS

In the development cohort, the Random Forest model showed a maximum receiver operating characteristic curve area of 0.96. In the external validation cohort, the Random Forest model surpasses 4 reported algorithms in predicting performance (accuracy 94.23%; sensitivity 97.10%; specificity 88.57%). In the prospective cohort, the Random Forest model showed good performance (accuracy 94.00%; sensitivity 85.71%; specificity 97.22%).

CONCLUSION

Random Forest algorithm has improved the accuracy of distinguishing the origin of PVCs, which surpasses 4 previous standards, and would be used to identify the origin of PVCs before the interventional procedure.

The remarkable role of shikimic acid pathway in humic acid formation during biochar and montmorillonite addition composting

The final products of shikimic acid pathway, aromatic amino acids (AAA), can be used as humic acid (HA) precursors. Therefore, the aim of this study was to explore the contribution of shikimic acid pathway on the formation of HA during composting. Four composting treatments were carried out in this study, including the control, biochar addition, montmorillonite addition, biochar and montmorillonite combined addition. The results showed that the correlations between AAA and HA were enhanced during combined addition composting, and functional microorganisms involved in the shikimic acid pathway increased. In addition, random forest model suggested that 63.3% of the top 30 genera contributing to the HA formation were functional microorganisms involved in the shikimic acid pathway, which fully proved the critical role of shikimic acid pathway. Therefore, this study provided a new perspective for revealing the crucial factors that promoted the formation of HA during composting.

Analysis on impacts of hydro-climatic changes and human activities on available water changes in Central Asia

Water resources in Central Asia are very scarce due to natural and anthropogenic impacts. Water shortages have been a major factor hampering the socio-economic development of Central Asia. Exploring internal interactions among climate change, human activities and terrestrial hydrological cycles will help to improve the management of water resources in Central Asia. In this paper, hydro-climatic and anthropogenic data for the period 2003-2016 from the Gravity Recovery and Climate Experiment (GRACE), the Global Land Data Assimilation System (GLDAS), the Climatic Research Unit (CRU) and the Moderate Resolution Imaging Spectroradiometer (MODIS) were used to analyze the influence of natural factors and human activities on changes of available water (AWC). The terrestrial water storage derived from GRACE and GLDAS remarkably declined in 2008, due to a serious drought, but increased thereafter. The AWC positively responded to the vegetation index, evapotranspiration, potential evapotranspiration and air temperature at a lag of 0-1 month, but to precipitation at a lag of 2-3 months. Results of correlation analysis with a spatial square moving window indicated that forests, grasses, croplands and water areas presented significantly positive correlations with AWC, while barren areas and urban areas were negatively correlated with AWC. According to the Boruta algorithm and the Random Forest model, natural factors, namely precipitation, evapotranspiration and potential evapotranspiration, were major factors for AWC in the whole Central Asia. Human activities had direct and indirect impacts on AWC. With the development of society and economy, croplands and urban areas gradually increased, resulting in a rising demand for water withdrawals for agriculture irrigation and industry. The unreasonable utilization and exploitation of water resources led to vegetation degradation and ecosystem deterioration, which would worsen the shortage of water resources in arid regions of Central Asia.

Effects of natural and socioeconomic factors on dengue transmission in two cities of China from 2006 to 2017

Dengue fever (DF) is a common and rapidly spreading vector-borne viral disease in tropical and subtropical regions. In recent years, in China, DF still poses an increasing threat to public health in many cities; but the incidence shows significant spatiotemporal differences. The purpose of this study was to identify the key factors affecting the spatial and temporal distribution of DF. We collected natural environmental and socio-economic data for two adjacent cities, Guangzhou (73 variables) and Foshan (71 variables), with the most DF cases in China. We performed random forest modelling to rank the factors according to their level of importance, and used negative binomial regression analysis to compare the risk factors between outbreak years and non-outbreak years. The natural environmental factors contributing to DF incidence for Guangzhou were temperature (relative risk (RR) = 18.80, 95% confidence interval (CI) = 3.11-113.67), humidity (RR = 1.85, 95% CI = 1.17-2.90) and green area (RR = 12.11, 95% CI = 6.14-55.50), and for Foshan was forest coverage (RR = 5.83, 95% CI = 2.72-12.45). Socio-economic impact were shown in Guangzhou with foreign visitor (RR = 1.18, 95% CI = 1.05-1.34) and oversea air passenger transport (RR = 7.34, 95% CI = 2.26-23.86); in Foshan, with oversea tourism (RR = 1.65, 95% CI = 1.34-2.04); and in Guangzhou-Foshan, with the development of intercity metro (RR = 1.26, 95% CI = 1.10-1.44). The difference between the two cities was the greater impact of the foreign visitor, green spaces and climate factor on DF in Guangzhou; the impact of the construction of intercity metro; and the more significant impact of oversea tourism on DF in Foshan. Our results suggest meaningful clues to public health authorities implementing joint interventions on DF prevention and early warning, to increase health education on DF prevention for international visitors and oversea travelers, and cross-city metro passengers; using rapid body temperature detection in public places such as airports, metros and parks can help detect cases early.

Integrating molecular and ecological approaches to identify potential polymicrobial pathogens over a shrimp disease progression

It is now recognized that some gut diseases attribute to polymicrobial pathogens infections. Thus, traditional isolation of single pathogen from disease subjects could bias the identification of causal agents. To fill this gap, using Illumina sequencing of the bacterial 16S rRNA gene, we explored the dynamics of gut bacterial communities over a shrimp disease progression. The results showed significant differences in the gut bacterial communities between healthy and diseased shrimp. Potential pathogens were inferred by a local pathogens database, of which two OTUs (affiliated with Vibrio tubiashii and Vibrio harveyi) exhibited significantly higher abundances in diseased shrimp as compared to healthy subjects. The two OTUs cumulatively contributed 64.5% dissimilarity in the gut microbiotas between shrimp health status. Notably, the random Forest model depicted that profiles of the two OTUs contributed 78.5% predicted accuracy of shrimp health status. Removal of the two OTUs from co-occurrence networks led to network fragmentation, suggesting their gatekeeper features. For these evidences, the two OTUs were inferred as candidate pathogens. Three virulence genes (bca, tlpA, and fdeC) that were coded by the two candidate pathogens were inferred by a virulence factor database, which were enriched significantly (P < 0.05 in the three cases, as validated by qPCR) in diseased shrimp as compared to healthy ones. The two candidate pathogens were repressed by Flavobacteriaceae, Garvieae, and Photobacrerium species in healthy shrimp, while these interactions shifted into synergy in disease cohorts. Collectively, our findings offer a frame to identify potential polymicrobial pathogen infections from an ecological perspective.

Importance of Non-invasive Right and Left Ventricular Variables on Exercise Capacity in Patients with Tetralogy of Fallot Hemodynamics

Good quality of life correlates with a good exercise capacity in daily life in patients with tetralogy of Fallot (ToF). Patients after correction of ToF usually develop residual defects such as pulmonary regurgitation or stenosis of variable severity. However, the importance of different hemodynamic parameters and their impact on exercise capacity is unclear. We investigated several hemodynamic parameters measured by cardiovascular magnetic resonance (CMR) and echocardiography and evaluated which parameter has the most pronounced effect on maximal exercise capacity determined by cardiopulmonary exercise testing (CPET). 132 patients with ToF-like hemodynamics were tested during routine follow-up with CMR, echocardiography and CPET. Right and left ventricular volume data, ventricular ejection fraction and pulmonary regurgitation were evaluated by CMR. Echocardiographic pressure gradients in the right ventricular outflow tract and through the tricuspid valve were measured. All data were classified and correlated with the results of CPET evaluations of these patients. The analysis was performed using the Random Forest model. In this way, we calculated the importance of the different hemodynamic variables related to the maximal oxygen uptake in CPET (VO₂%predicted). Right ventricular pressure showed the most important influence on maximal oxygen uptake, whereas pulmonary regurgitation and right ventricular enddiastolic volume were not important hemodynamic variables to predict maximal oxygen uptake in CPET. Maximal exercise capacity was only very weakly influenced by right ventricular enddiastolic volume and not at all by pulmonary regurgitation in patients with ToF. The variable with the most pronounced influence was the right ventricular pressure.

Prehospital triage of trauma patients using the Random Forest computer algorithm

BACKGROUND

Overtriage not only wastes resources but also displaces the patient from their community and causes delay of treatment for the more seriously injured. This study aimed to validate the Random Forest computer model (RFM) as means of better triaging trauma patients to level 1 trauma centers.

METHODS

Adult trauma patients with "medium activation" presenting via helicopter to a level 1 trauma center from May 2007 to May 2009 were included. The "medium activation" trauma patient is alert and hemodynamically stable on scene but has either subnormal vital signs or accumulation of risk factors that may indicate a potentially serious injury. Variables included in the RFM analysis were demographics, mechanism of injury, prehospital fluid, medications, vitals, and disposition. Statistical analysis was performed via the Random Forest algorithm to compare our institutional triage rate to rates determined by the RFM.

RESULTS

A total of 1653 patients were included in this study, of which 496 were used in the testing set of the RFM. In our testing set, 33.8% of patients brought to our level 1 trauma center could have been managed at a level 3 trauma center, and 88% of patients who required a level 1 trauma center were identified correctly. In the testing set, there was an overtriage rate of 66%, whereas using the RFM, we decreased the overtriage rate to 42% (P < 0.001). There was an undertriage rate of 8.3%. The RFM predicted patient disposition with a sensitivity of 89%, specificity of 42%, negative predictive value of 92%, and positive predictive value of 34%.

CONCLUSIONS

Although prospective validation is required, it appears that computer modeling potentially could be used to guide triage decisions, allowing both more accurate triage and more efficient use of the trauma system.