Self-supervised probabilistic models for exploring shape memory alloys

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

The ongoing Russia–Ukraine conflict has exacerbated the global crisis of natural gas supply, particularly in Europe. During the winter season, major importers of liquefied natural gas (LNG), such as South Korea and Japan, were directly affected by fluctuating spot LNG prices. This study aimed to use machine learning (ML) to predict the Japan Korea Marker (JKM), a spot LNG price index, to reduce price fluctuation risks for LNG importers such as the Korean Gas Corporation (KOGAS). Hence, price prediction models were developed based on long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM) algorithms, which were used for time series data prediction. Eighty-seven variables were collected for JKM prediction, of which eight were selected for modeling. Four scenarios (scenarios A, B, C, and D) were devised and tested to analyze the effect of each variable on the performance of the models. Among the eight variables, JKM, national balancing point (NBP), and Brent price indexes demonstrated the largest effects on the performance of the ML models. In contrast, the variable of LNG import volume in China had the least effect. The LSTM model showed a mean absolute error (MAE) of 0.195, making it the best-performing algorithm. However, the LSTM model demonstrated a decreased in performance of at least 57% during the COVID-19 period, which raises concerns regarding the reliability of the test results obtained during that time. The study compared the ML models’ prediction performances with those of the traditional statistical model, autoregressive integrated moving averages (ARIMA), to verify their effectiveness. The comparison results showed that the LSTM model’s performance deviated by an MAE of 15–22%, which can be attributed to the constraints of the small dataset size and conceptual structural differences between the ML and ARIMA models. However, if a sufficiently large dataset can be secured for training, the ML model is expected to perform better than the ARIMA. Additionally, separate tests were conducted to predict the trends of JKM fluctuations and comprehensively validate the practicality of the ML models. Based on the test results, LSTM model, identified as the optimal ML algorithm, achieved a performance of 53% during the regular period and 57% d during the abnormal period (i.e., COVID-19). Subject matter experts agreed that the performance of the ML models could be improved through additional studies, ultimately reducing the risk of price fluctuations when purchasing spot LNG.

Shear viscosity, though being a fundamental property of all fluids, is computationally expensive to calculate from equilibrium molecular dynamics simulations. Recently, machine learning (ML) methods have been used to augment molecular simulations in many contexts, thus showing promise to estimate viscosity too in a relatively inexpensive manner. However, ML methods face significant challenges—such as overfitting, when the size of the data set is small, as is the case with viscosity. In this work, we train seven ML models to predict the shear viscosity of a Lennard–Jones fluid, with particular emphasis on addressing issues arising from a small data set. Specifically, the issues related to model selection, performance estimation and uncertainty quantification were investigated. First, we show that the widely used performance estimation procedure of using a single unseen data set shows a wide variability—in estimating the errors on—small data sets. In this context, the common practice of using cross validation (CV) to select the hyperparameters (model selection) can be adapted to estimate the generalization error (performance estimation) as well. We compare two simple CV procedures for their ability to do both model selection and performance estimation, and find that k-fold CV based procedure shows a lower variance of error estimates. Also, these CV procedures naturally lead to an ensemble of trained ML models. We discuss the role of performance metrics in training and evaluation and propose a method to rank the ML models based on multiple metrics. Finally, two methods for uncertainty quantification—Gaussian process regression (GPR) and ensemble method—were used to estimate the uncertainty on individual predictions. The uncertainty estimates from GPR were also used to construct an applicability domain using which the ML models provided even more reliable predictions on an independent viscosity data set generated in this work. Overall, the procedures prescribed in this work, together, lead to robust ML models for small data sets.

Discovering novel, multicomponent crystalline materials is a complex task owing to the large space of feasible structures. Here we demonstrate a method to significantly accelerate materials discovery by using a machine learning (ML) model trained on density functional theory (DFT) data from the Open Quantum Materials Database (OQMD). Our ML model predicts the stability of a material based on its crystal structure and chemical composition, and we illustrate the effectiveness of the method by application to finding new quaternary Heusler (QH) compounds. Our ML-based approach can find new stable materials at a rate 30 times faster than undirected searches and we use it to predict 55 previously unknown, stable QH compounds. We find the accuracy of our ML model is higher when trained using the diversity of crystal structures available in the OQMD than when training on well-curated datasets which contain only a single family of crystal structures (i.e., QHs). The advantage of using diverse training data shows how large datasets, such as OQMD, are particularly valuable for materials discovery and that we need not train separate ML models to predict each different family of crystal structures. Compared to other proposed ML approaches, we find that our method performs best for small $(l{10}^{3})$ and large $(g{10}^{5})$ training set sizes. The excellent flexibility and accuracy of the approach presented here can be easily generalized to other types of crystals.

Accurate estimation of reference evapotranspiration (ETo) plays a vital role in irrigation and water resource planning. The Penman–Monteith method recommended by the Food and Agriculture Organization (FAO PM56) is widely used and considered a standard to calculate ETo. However, FAO PM56 cannot be used with limited meteorological variables, so it is compulsory to choose an alternative model for ETo estimation, which requires fewer variables. This study built ten machine learning (ML) models based on multi-function, neural network, and tree-based structure against the FAO PM56 method. For this purpose, time series temperature data on a monthly scale are only used to train ML models. The developed ML models were applied to estimate ETo at different test stations and the obtained results were compared with the FAO PM56 method to verify and validate their performance in ETo estimation for the selected stations. In addition, multiple statistical indicators, including root-mean-square error (RMSE), coefficient of determination (R2), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and correlation coefficient (r) were calculated to compare the performance of each ML model on ETo estimation. Among the applied ML models, the ETo tree boost (TB) ML model outperformed the other ML models in estimating ETo in diverse climatic conditions based on statistical indicators (R2, NSE, r, RMSE, and MAE). Moreover, the observed R2, NSE, and r were the highest for the TB ML model, while RMSE and MAE were found to be the lowest at the study sites compared to other applied ML models. Lastly, ETo point data yielded from the TB ML model was used in an interpolation process to create monthly and annual ETo maps. Based on the ETo maps, this study suggests mainly a focus on areas with high ETo values and proper irrigation scheduling of crops to ensure water sustainability.

Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

PD27-01 DEVELOPMENT OF A MACHINE LEARNING (ML) MODEL TO AUTOMATICALLY AND PRECISELY IDENTIFY KIDNEY STONES FROM URETEROSCOPY VIDEO RECORDINGS

Annual burned areas in the United States have increased twofold during the past decades. With more large fires resulting in more emissions of fine particulate matter, an accurate prediction of fire emissions is critical for quantifying the impacts of fires on air quality, human health, and climate. This study aims to construct a machine learning (ML) model with game-theory interpretation to predict monthly fire emissions over the contiguous US and to understand the controlling factors of fire emissions. By comparing the predicted fire PM2.5 emissions from the interpretable ML model with the Global Fire Emissions Database (GFED) observations and predictions from process-based models in the Fire Modeling Intercomparison Project (FireMIP), the ML model is also used to diagnose the process-based models to inform future development. Results show promising performance for the ML model, Community Land Model (CLM), and Joint UK Land Environment Simulator-Interactive Fire And Emission Algorithm For Natural Environments (JULES-INFERNO) in reproducing the spatial distributions, seasonality, and interannual variability of fire emissions over CONUS. Regional analysis shows that only the ML model and CLM simulate the realistic interannual variability of fire emissions for most of the subregions (r > 0.95 for ML and r = 0.14 ~ 0.70 for CLM), except for Mediterranean California, where all the models perform poorly (r = 0.74 for ML and r < 0.30 for the FireMIP models). Regarding seasonality, most models capture the peak emission in July over western US. However, all models except for the ML model fail to reproduce the bimodal peaks in July and October over Mediterranean California, which may be explained by the coarse spatial resolutions of the processed-based models or atmospheric forcing data or limitations in model parameterizations for capturing the effects of Santa Ana winds on fire activity. Furthermore, most models struggle to capture the spring peak in emissions in southeastern US, probably due to underrepresentation of human effects and the influences of winter dryness on fires in the models. As for extreme events, both the ML model and CLM successfully reproduce the frequency map of extreme emission occurrence but overestimate the number of months with extremely large fire emissions. Comparing the fire PM2.5 emissions from the interpretable ML model with process-based fire models highlights their strengths and uncertainties for regional analysis and prediction and provides useful insights on future directions for model improvements.

Perinatal depression (PND) is one of the most common medical complications during pregnancy and postpartum period, affecting 10–20% of pregnant individuals. Black and Latina women have higher rates of PND, yet they are less likely to be diagnosed and receive treatment. Machine learning (ML) models based on Electronic Medical Records (EMRs) have been effective in predicting postpartum depression in middle-class White women but have rarely included sufficient proportions of racial and ethnic minorities, which contributed to biases in ML models for minority women. Our goal is to determine whether ML models could serve to predict depression in early pregnancy in racial/ethnic minority women by leveraging EMR data. We extracted EMRs from a hospital in a large urban city that mostly served low-income Black and Hispanic women (N=5,875) in the U.S. Depressive symptom severity was assessed from a self-reported questionnaire, PHQ-9. We investigated multiple ML classifiers, used Shapley Additive Explanations (SHAP) for model interpretation, and determined model prediction bias with two metrics, Disparate Impact, and Equal Opportunity Difference. While ML model (Elastic Net) performance was low (ROCAUC=0.67), we identified well-known factors associated with PND, such as unplanned pregnancy and being single, as well as underexplored factors, such as self-report pain levels, lower levels of prenatal vitamin supplement intake, asthma, carrying a male fetus, and lower platelet levels blood. Our findings showed that despite being based on a sample mostly composed of 75% low-income minority women (54% Black and 27% Latina), the model performance was lower for these communities. In conclusion, ML models based on EMRs could moderately predict depression in early pregnancy, but their performance is biased against low-income minority women.

BACKGROUND Atrial fibrillation (AF) is a progressive disease, and its clinical type is classified according to the AF duration: paroxysmal AF, persistent AF (PeAF; AF duration of less than 1 year), and long-standing persistent AF (AF duration of more than 1 year). When considering the indication for catheter ablation, having a long AF duration is considered a risk factor for recurrence, and therefore, the duration of AF is an important factor in determining the treatment strategy for PeAF. OBJECTIVE This study aims to improve the accuracy of the cardiologists’ diagnosis of the AF duration, and the steps to achieve this goal are to develop a predictive model of the AF duration and validate the support performance of the prediction model. METHODS The study included 272 patients with PeAF (aged 20-90 years), with data obtained between January 1, 2015, and December 31, 2023. Of those, 189 (69.5%) were included in the study, excluding 83 (30.5%) who met the exclusion criteria. Of the 189 patients included, 145 (76.7%) were used as training data to build the machine learning (ML) model and 44 (23.3%) were used as test data for predictive ability of the ML model. Using a questionnaire, 10 cardiologists (group A) evaluated whether the test data (44 patients) included AF of more than a 1-year duration (phase 1). Next, the same questionnaire was performed again after providing the ML model’s answer (phase 2). Subsequently, another 10 cardiologists (group B) were shown the test results of group A, were made aware of the limitations of their own diagnostic abilities, and were then administered the same 2-stage test as group A. RESULTS The prediction results with the ML model using the test data provided 81.8% accuracy (72% sensitivity and 89% specificity). The mean percentage of correct answers in group A was 63.9% (SD 9.6%) for phase 1 and improved to 71.6% (SD 9.3%) for phase 2 (&lt;i&gt;P&lt;/i&gt;=.01). The mean percentage of correct answers in group B was 59.8% (SD 5.3%) for phase 1 and improved to 68.2% (SD 5.9%) for phase 2 (&lt;i&gt;P&lt;/i&gt;=.007). The mean percentage of answers that differed from the ML model’s prediction for phase 2 (percentage of answers where cardiologists did not trust the ML model and believed their own determination) was 17.3% (SD 10.3%) in group A and 20.9% (SD 5%) in group B and was not significantly different (&lt;i&gt;P&lt;/i&gt;=.85). CONCLUSIONS ML models predicting AF duration improved the diagnostic ability of cardiologists. However, cardiologists did not entirely rely on the ML model’s prediction, even if they were aware of their diagnostic capability limitations.

BackgroundThe large amount of heterogeneous data collected in surgical/endoscopic practice calls for data-driven approaches as machine learning (ML) models. The aim of this study was to develop ML models to predict endoscopic sleeve gastroplasty (ESG) efficacy at 12 months defined by total weight loss (TWL) % and excess weight loss (EWL) % achievement. Multicentre data were used to enhance generalizability: evaluate consistency among different center of ESG practice and assess reproducibility of the models and possible clinical application. Models were designed to be dynamic and integrate follow-up clinical data into more accurate predictions, possibly assisting management and decision-making.MethodsML models were developed using data of 404 ESG procedures performed at 12 centers across Europe. Collected data included clinical and demographic variables at the time of ESG and at follow-up. Multicentre/external and single center/internal and temporal validation were performed. Training and evaluation of the models were performed on Python’s scikit-learn library. Performance of models was quantified as receiver operator curve (ROC-AUC), sensitivity, specificity, and calibration plots.ResultsMulticenter external validation: ML models using preoperative data show poor performance. Best performances were reached by linear regression (LR) and support vector machine models for TWL% and EWL%, respectively, (ROC-AUC: TWL% 0.87, EWL% 0.86) with the addition of 6-month follow-up data.Single-center internal validation: Preoperative data only ML models show suboptimal performance. Early, i.e., 3-month follow-up data addition lead to ROC-AUC of 0.79 (random forest classifiers model) and 0.81 (LR models) for TWL% and EWL% achievement prediction, respectively. Single-center temporal validation shows similar results.ConclusionsAlthough preoperative data only may not be sufficient for accurate postoperative predictions, the ability of ML models to adapt and evolve with the patients changes could assist in providing an effective and personalized postoperative care. ML models predictive capacity improvement with follow-up data is encouraging and may become a valuable support in patient management and decision-making.

Learning What Makes Catalysts Good

Abstract. Annual burned areas in the United States have increased 2-fold during the past decades. With more large fires resulting in more emissions of fine particulate matter, an accurate prediction of fire emissions is critical for quantifying the impacts of fires on air quality, human health, and climate. This study aims to construct a machine learning (ML) model with game-theory interpretation to predict monthly fire emissions over the contiguous US (CONUS) and to understand the controlling factors of fire emissions. The optimized ML model is used to diagnose the process-based models in the Fire Modeling Intercomparison Project (FireMIP) to inform future development. Results show promising performance for the ML model, Community Land Model (CLM), and Joint UK Land Environment Simulator-Interactive Fire And Emission Algorithm For Natural Environments (JULES-INFERNO) in reproducing the spatial distributions, seasonality, and interannual variability of fire emissions over the CONUS. Regional analysis shows that only the ML model and CLM simulate the realistic interannual variability of fire emissions for most of the subregions (r&gt;0.95 for ML and r=0.14∼0.70 for CLM), except for Mediterranean California, where all the models perform poorly (r=0.74 for ML and r&lt;0.30 for the FireMIP models). Regarding seasonality, most models capture the peak emission in July over the western US. However, all models except for the ML model fail to reproduce the bimodal peaks in July and October over Mediterranean California, which may be explained by the smaller wind speeds of the atmospheric forcing data during Santa Ana wind events and limitations in model parameterizations for capturing the effects of Santa Ana winds on fire activity. Furthermore, most models struggle to capture the spring peak in emissions in the southeastern US, probably due to underrepresentation of human effects and the influences of winter dryness on fires in the models. As for extreme events, both the ML model and CLM successfully reproduce the frequency map of extreme emission occurrence but overestimate the number of months with extremely large fire emissions. Comparing the fire PM2.5 emissions from the ML model with process-based fire models highlights their strengths and uncertainties for regional analysis and prediction and provides useful insights into future directions for model improvements.