Air quality modeling in the metropolitan area of São Paulo, Brazil: A review.

Numerous studies have used air quality models to estimate pollutant concentrations in the Metropolitan Area of São Paulo (MASP) by using different inputs and assumptions. Our objectives are to summarize these studies, compare their performance, configurations, and inputs, and recommend areas of further research. We examined 29 air quality modeling studies that focused on ozone (O3) and fine particulate matter (PM2.5) performed over the MASP, published from 2001 to 2023. The California Institute of Technology airshed model (CIT) was the most used offline model, while the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) was the most used online model. Because the main source of air pollution in the MASP is the vehicular fleet, it is commonly used as the only anthropogenic input emissions. Simulation periods were typically the end of winter and during spring, seasons with higher O3 and PM2.5 concentrations. Model performance for hourly ozone is good with half of the studies with Pearson correlation above 0.6 and root mean square error (RMSE) ranging from 7.7 to 27.1 ppb. Fewer studies modeled PM2.5 and their performance is not as good as ozone estimates. Lack of information on emission sources, pollutant measurements, and urban meteorology parameters is the main limitation to perform air quality modeling. Nevertheless, researchers have used measurement campaign data to update emission factors, estimate temporal emission profiles, and estimate volatile organic compounds (VOCs) and aerosol speciation. They also tested different emission spatial disaggregation approaches and transitioned to global meteorological reanalysis with a higher spatial resolution. Areas of research to explore are further evaluation of models' physics and chemical configurations, the impact of climate change on air quality, the use of satellite data, data assimilation techniques, and using model results in health impact studies. This work provides an overview of advancements in air quality modeling within the MASP and offers practical approaches for modeling air quality in other South American cities with limited data, particularly those heavily impacted by vehicle emissions.

Research on Coal and Gangue Recognition Based on the Improved YOLOv7-Tiny Target Detection Algorithm.

The recognition technology of coal and gangue is one of the key technologies of intelligent mine construction. Aiming at the problems of the low accuracy of coal and gangue recognition models and the difficult recognition of small-target coal and gangue caused by low-illumination and high-dust environments in the coal mine working face, a coal and gangue recognition model based on the improved YOLOv7-tiny target detection algorithm is proposed. This paper proposes three model improvement methods. The coordinate attention mechanism is introduced to improve the feature expression ability of the model. The contextual transformer module is added after the spatial pyramid pooling structure to improve the feature extraction ability of the model. Based on the idea of the weighted bidirectional feature pyramid, the four branch modules in the high-efficiency layer aggregation network are weighted and cascaded to improve the recognition ability of the model for useful features. The experimental results show that the average precision mean of the improved YOLOv7-tiny model is 97.54%, and the FPS is 24.73 f·s-1. Compared with the Faster-RCNN, YOLOv3, YOLOv4, YOLOv4-VGG, YOLOv5s, YOLOv7, and YOLOv7-tiny models, the improved YOLOv7-tiny model has the highest recognition rate and the fastest recognition speed. Finally, the improved YOLOv7-tiny model is verified by field tests in coal mines, which provides an effective technical means for the accurate identification of coal and gangue.

Application of machine learning approaches in predicting clinical outcomes in older adults - a systematic review and meta-analysis.

BACKGROUND: Machine learning-based prediction models have the potential to have a considerable positive impact on geriatric care. DESIGN: Systematic review and meta-analyses. PARTICIPANTS: Older adults (≥ 65 years) in any setting. INTERVENTION: Machine learning models for predicting clinical outcomes in older adults were evaluated. A random-effects meta-analysis was conducted in two grouped cohorts, where the predictive models were compared based on their performance in predicting mortality i) under and including 6 months ii) over 6 months. OUTCOME MEASURES: Studies were grouped into two groups by the clinical outcome, and the models were compared based on the area under the receiver operating characteristic curve metric. RESULTS: Thirty-seven studies that satisfied the systematic review criteria were appraised, and eight studies predicting a mortality outcome were included in the meta-analyses. We could only pool studies by mortality as there were inconsistent definitions and sparse data to pool studies for other clinical outcomes. The area under the receiver operating characteristic curve from the meta-analysis yielded a summary estimate of 0.80 (95% CI: 0.76 - 0.84) for mortality within 6 months and 0.81 (95% CI: 0.76 - 0.86) for mortality over 6 months, signifying good discriminatory power. CONCLUSION: The meta-analysis indicates that machine learning models display good discriminatory power in predicting mortality. However, more large-scale validation studies are necessary. As electronic healthcare databases grow larger and more comprehensive, the available computational power increases and machine learning models become more sophisticated; there should be an effort to integrate these models into a larger research setting to predict various clinical outcomes.

Modelling the reference crop evapotranspiration in the Beas-Sutlej basin (India): an artificial neural network approach based on different combinations of meteorological data.

Accurate prediction of the reference evapotranspiration (ET0) is vital for estimating the crop water requirements precisely. In this study, we developed multi-layer perceptron artificial neural network (MLP-ANN) models considering different combinations of the meteorological data for predicting the ET0 in the Beas-Sutlej basin of Himachal Pradesh (India). Four climatic locations in the basin namely, Kullu, Mandi, Bilaspur, and Chaba were selected. The meteorological dataset comprised air temperature (maximum, minimum and mean), relative humidity, solar radiation, and wind speed, recorded daily for a period of 35 years (1984-2019). The datasets from 1984 to 2012 and 2013 to 2019 were utilized for training and testing the models, respectively. The performance of the developed models was evaluated using several statistical indices. For each location, the best performed MLP-ANN model was the one with the complete combination of the meteorological data. The architecture of the best performing model for Kullu, Mandi, Bilaspur, and Chaba was (6-2-4-1), (6-5-4-1), (6-5-4-1), and (6-4-6-1), respectively. It was observed, however, that the performance of other models was also relatively good, given the limited meteorological data utilized in those models. Further, to appreciate the relative predictive ability of the developed models, a comparison was performed with four existing established empirical models. The approach adopted in this study can be effectively utilized by water users and field researchers for modelling and predicting ET0 in data-scarce locations.

Hydrological model using ground- and satellite-based data for river flow simulation towards supporting water resource management in the Red River Basin, Vietnam.

The Red River basin (RRB) exhibits substantial variation of water resource seasonally and annually. Sustainable water resource management in the RRB has been challenging due to the lack of in situ hydrological measurement data over the basin-wide scale. To address this issue, this study aimed to perform the setting up, calibration, and validation of the variable infiltration capacity (VIC) hydrological model forced with ground- and satellite-based datasets at a high spatial resolution of 0.1° for simulating the daily river flow of the Red River system in the RRB during the period of 2005-2014. By using the finely resolved land cover characterization with 15 types of land cover and leaf area index - the most important feature of vegetation that significantly influences the simulation of hydrological variables provided by the spatially distributed satellite remote sensing data, this study would not only address the poor data availability over the RRB but also enhance the accuracy of model simulation. The simulation results generally indicated that the calibrated VIC model could satisfactorily capture the river flow dynamics of the Red River system in the RRB. The VIC model's underestimated river flow compared to the observed data during the dry season for the downstream stations was likely due to the operation of the large man-made reservoirs and dams in the upstream catchments of the RRB that not represented by the VIC model. The findings also suggested that for further improving the VIC model performance, the use of more spatially representative meteorological data provided by satellite remote sensing should be considered in future studies.

Regionalized PM2.5 Community Multiscale Air Quality model performance evaluation across a continuous spatiotemporal domain.

The regulatory Community Multiscale Air Quality (CMAQ) model is a means to understanding the sources, concentrations and regulatory attainment of air pollutants within a model's domain. Substantial resources are allocated to the evaluation of model performance. The Regionalized Air quality Model Performance (RAMP) method introduced here explores novel ways of visualizing and evaluating CMAQ model performance and errors for daily Particulate Matter ≤ 2.5 micrometers (PM2.5) concentrations across the continental United States. The RAMP method performs a non-homogenous, non-linear, non-homoscedastic model performance evaluation at each CMAQ grid. This work demonstrates that CMAQ model performance, for a well-documented 2001 regulatory episode, is non-homogeneous across space/time. The RAMP correction of systematic errors outperforms other model evaluation methods as demonstrated by a 22.1% reduction in Mean Square Error compared to a constant domain wide correction. The RAMP method is able to accurately reproduce simulated performance with a correlation of r = 76.1%. Most of the error coming from CMAQ is random error with only a minority of error being systematic. Areas of high systematic error are collocated with areas of high random error, implying both error types originate from similar sources. Therefore, addressing underlying causes of systematic error will have the added benefit of also addressing underlying causes of random error.

Rules versus layers: which side wins the battle of model calibration?

Continuous surface of urbanization suitability, as an input to many urban growth models (UGM), has a significant role on a proper calibration process. The present study evaluates and compares the simulation success of the Cellular Automata-Markov Chain (CA-MC) model through multiple methods. For this, a series of mapping algorithms are applied ranging from empirical methods such as multi-criteria evaluation (MCE) to statistical algorithms without spatially explicit suitability mapping rules such as logistic regression (LR) and multi-layer perceptron (MLP) neural network and finally statistical and spatially explicit rule-based methods such as SLEUTH-Genetic Algorithm (SLEUTH-GA) model. The CA-MC model was calibrated in three study locations including Azadshahr, Gonbad, and Gorgan cities in northeastern Iran. Applying Kappa-based indices (Kappa, K location, K Simulation, and K Transloc) and computing relative error (RE) values of landscape metrics, performance of the model was quantified and compared across the three study sites. The MCE and SLEUTH-GA methods, as the most data-demanding and the most computationally complex methods, respectively, yielded approximately similar results (especially in case of Kappa-based indices) and these methods were less successful compared to LR and MLP models. LR and MLP models were less data-demanding, while they produced approximately equal results. This study concludes that, when historical growth patterns feed an urbanization suitability mapping process, neither rules (SLEUTH-GA) nor layers (MCE) are effectively efficient when applied in a separated manner. Instead, methods with statistical rules and least-correlated input layers (LR and MLP) provide better simulation outputs. In contrast, methods such as MCE are more applicable when a non-path-dependent mapping procedure is desired since this method does not require training data (dependent variable) and the provided flexibilities in urbanization suitability mapping under various scenarios can improve the functionality of land-use change prediction algorithms into innovative land allocation tools.

Predictive Modeling Using Artificial Intelligence and Machine Learning Algorithms on Electronic Health Record Data: Advantages and Challenges.

The rapid adoption of electronic health record (EHR) systems in US hospitals from 2008 to 2014 produced novel data elements for analysis. Concurrent innovations in computing architecture and machine learning (ML) algorithms have made rapid consumption of health data feasible and a powerful engine for clinical innovation. In critical care research, the net convergence of these trends has resulted in an exponential increase in outcome prediction research. In the following article, we explore the history of outcome prediction in the intensive care unit (ICU), the growing use of EHR data, and the rise of artificial intelligence and ML (AI) in critical care.

Identification of factors influencing hydrologic model performance using a top-down approach in a large number of U.S. catchments.

Investigating the performance that can be achieved with different hydrological models across catchments with varying characteristics is a requirement for identifying an adequate model for any catchment, gauged or ungauged, just based on information about its climate and catchment properties. As parameter uncertainty increases with the number of model parameters, it is important not only to identify a model achieving good results but also to aim at the simplest model still able to provide acceptable results. The main objective of this study is to identify the climate and catchment properties determining the minimal required complexity of a hydrological model. As previous studies indicate that the required model complexity varies with the temporal scale, the study considers the performance at the daily, monthly, and annual timescales. In agreement with previous studies, the results show that catchments located in arid areas tend to be more difficult to model. They therefore require more complex models for achieving an acceptable performance. For determining which other factors influence model performance, an analysis was carried out for four catchment groups (snowy, arid, and eastern and western catchments). The results show that the baseflow and aridity indices are the most consistent predictors of model performance across catchment groups and timescales. Both properties are negatively correlated with model performance. Other relevant predictors are the fraction of snow in the annual precipitation (negative correlation with model performance), soil depth (negative correlation with model performance), and some other soil properties. It was observed that the sign of the correlation between the catchment characteristics and model performance varies between clusters in some cases, stressing the difficulties encountered in large sample analyses. Regarding the impact of the timescale, the study confirmed previous results indicating that more complex models are needed for shorter timescales.