Machine learning applied to lentic habitat use by spawning walleye demonstrates the benefits of considering multiple spatial scales in aquatic research

Scale and hierarchy have received less attention in aquatic systems compared to terrestrial. Walleye Sander vitreus spawning habitat offers an opportunity to investigate scale’s importance. We estimated lake-, transect-, and quadrat-scale influences on nearshore walleye egg deposition in 28 Minnesota lakes from 2016-2018. Random forest models (RFM) estimated importance of predictive variables to walleye egg deposition. Predictive accuracies of a multi-scale classification tree (CT) and a quadrat-scale CT were compared. RFM results suggested that five of our variables were unimportant when predicting egg deposition. The multi-scale CT was more accurate than the quadrat-scale CT when predicting egg deposition. Both model results suggest that in-lake egg deposition by walleye is regulated by hierarchical abiotic processes and that silt/clay abundance at the transect-scale (reef-scale) is more important than abundance at the quadrat-scale (within-reef). Our results show machine learning can be used for scale-optimization and potentially to determine cross-scale interactions. Further incorporation of scale and hierarchy into studies of aquatic systems will increase our understanding of species-habitat relationships, especially in lentic systems where multi-scale approaches are rarely used.

Geochemistry of Sub-Depositional Environments in Estuarine Sediments: Development of an Approach to Predict Palaeo-Environments from Holocene Cores

In the quest to use modern analogues to understand clay mineral distribution patterns to better predict clay mineral occurrence in ancient and deeply buried sandstones, it has been necessary to define palaeo sub-environments from cores through modern sediment successions. Holocene cores from Ravenglass in the NW of England, United Kingdom, contained metre-thick successions of massive sand that could not be unequivocally interpreted in terms of palaeo sub-environments using conventional descriptive logging facies analysis. We have therefore explored the use of geochemical data from portable X-ray fluorescence analyses, from whole-sediment samples, to develop a tool to uniquely define the palaeo sub-environment based on geochemical data. This work was carried out through mapping and defining sub-depositional environments in the Ravenglass Estuary and collecting 497 surface samples for analysis. Using R statistical software, we produced a classification tree based on surface geochemical data from Ravenglass that can take compositional data for any sediment sample from the core or the surface and define the sub-depositional environment. The classification tree allowed us to geochemically define ten out of eleven of the sub-depositional environments from the Ravenglass Estuary surface sediments. We applied the classification tree to a core drilled through the Holocene succession at Ravenglass, which allowed us to identify the dominant paleo sub-depositional environments. A texturally featureless (massive) metre-thick succession, that had defied interpretation based on core description, was successfully related to a palaeo sub-depositional environment using the geochemical classification approach. Calibrated geochemical classification models may prove to be widely applicable to the interpretation of sub-depositional environments from other marginal marine environments and even from ancient and deeply buried estuarine sandstones.

Environmentally-friendly electric vehicles: a silent menace to vulnerable road users?

Prediction models have been extensively used in the field of road safety, however, none of these models have been particularly applied to zero-emission electric vehicle (EV) related injuries so far; which may lead to different outcomes due to their inaudible engines. Using an optimizable classification tree, this first-ever study aims to predict the likelihood of personal injury severities stemming from EV-related crashes on Britain's roads. The prediction model was found to be capable of detecting significant and insignificant factors. The factors provide important insights into how the severity of injuries can be reduced in the future deployment of EVs. Although there was an increased risk for injuries classified as ‘slight severity’, particularly at lower urban speed limits, several predictors are suggesting that EVs do not pose more of a risk to a certain group. Contrary to popular belief, no convincing evidence has been found to suggest that eco-friendly EVs are ‘silent killers’ for vulnerable road users.

Ten years of NIHR research training: who got an award? A retrospective cohort study

ObjectiveIn 2017, the National Institute for Health Research (NIHR) academy produced a strategic review of training, which reported the variation in application characteristics associated with success rates. It was noted that variation in applicant characteristic was not independent of one another. Therefore, the aim of this secondary analysis was to investigate the inter-relationships in order to identify factors (or groups of factors) most associated with application numbers and success rates.DesignRetrospective data were gathered from 4388 applications to NIHR Academy between 2007 and 2016. Multinominal logistic regression models quantified the likelihood of success depending on changes in the explanatory factors; relative risk ratios with 95% CIs. A classification tree analysis was built using exhaustive χ2 automatic interaction detection to better understand the effect of interactions between explanatory variables on application success rates.Results936 (21.3%) applications were awarded. Applications from males and females were equally likely to be successful (p=0.71). There was an overall reduction in numbers of applications from females as award seniority increased from predoctoral to professorship. Applications from institutions with a medical school had a 2.6-fold increase in likelihood of success (p<0.001). Classification tree analysis revealed key predictors of application success: award level, type of programme, previous NIHR award experience and applying form a medical school.ConclusionSuccess rates did not differ according to gender, and doctors were not more likely to be successful than applications from other professions. Taken together, these findings suggest an essential fairness in how the quality of a submitted application is assessed, but they also raise questions about variation in the opportunity to submit a high-quality application. The companion qualitative study (Burkshaw et al. (2021) BMJ Open) provides valuable insight into potential candidate mechanisms and discusses how research capacity development initiatives might be targeted in the future.

Klasifikasi Resiko Kehamilan Menggunakan Ensemble Learning berbasis Classification Tree

In health science there is a technique to determine the level of risk of pregnancy, namely the Poedji Rochyati score technique. In this evaluation technique, the level of pregnancy risk is calculated from the values ​​of 22 parameters obtained from pregnant women. Under certain conditions, some parameter values ​​are unknown. This causes the level of risk of pregnancy can not be calculated. For that we need a way to predict pregnancy risk status in cases of incomplete attribute values. There are several studies that try to overcome this problem. The research "classification of pregnancy risk using cost sensitive learning" [3] applies cost sensitive learning to the process of classifying the level of pregnancy risk. In this study, the best classification accuracy achieved was 73% and the best value was 77.9%. To increase the accuracy and recall of predicting pregnancy risk status, in this study several improvements were proposed. 1) Using ensemble learning based on classification tree 2) using the SVMattributeEvaluator evaluator to optimize the feature subset selection stage. In the trials conducted using the classification tree-based ensemble learning method and the SVMattributeEvaluator at the feature subset selection stage, the best value for accuracy was up to 76% and the best value for recall was up to 89.5%

A Novel Hybrid Feature Selection Method for Day-Ahead Electricity Price Forecasting

The paper proposes a novel hybrid feature selection (FS) method for day-ahead electricity price forecasting. The work presents a novel hybrid FS algorithm for obtaining optimal feature set to gain optimal forecast accuracy. The performance of the proposed forecaster is compared with forecasters based on classification tree and regression tree. A hybrid FS method based on the elitist genetic algorithm (GA) and a tree-based method is applied for FS. Making use of selected features, aperformance test of the forecaster was carried out to establish the usefulness of the proposed approach. By way of analyzing and forecasts for day-ahead electricity prices in the Australian electricity markets, the proposed approach is evaluated and it has been established that, with the selected feature, the proposed forecaster consistently outperforms the forecaster with a larger feature set. The proposed method is simulated in MATLAB and WEKA software.

Role of Storm Erosion Potential and Beach Morphology in Controlling Dune Erosion

Coastal erosion is controlled by two sets of factors, one related to storm intensity and the other related to a location’s vulnerability. This study investigated the role of each set in controlling dune erosion based on data compiled for eighteen historical events in New Jersey. Here, storm intensity was characterized by the Storm Erosion Index (SEI) and Peak Erosion Intensity (PEI), factors used to describe a storm’s cumulative erosion potential and maximum erosive power, respectively. In this study, a direct relationship between these parameters, beach morphology characteristics, and expected dune response was established through a classification tree ensemble. Of the seven input parameters, PEI was the most important, indicating that peak storm conditions with time scales on the order of hours were the most critical in predicting dune impacts. Results suggested that PEI, alone, was successful in distinguishing between storms most likely to result in no impacts (PEI < 69) and those likely to result in some (PEI > 102), regardless of beach condition. For intensities in between, where no consistent behavior was observed, beach conditions must be considered. Because of the propensity for beach conditions to change over short spatial scales, it is important to predict impacts on a local scale. This study established a model with the computational effectiveness to provide such predictions.

The Relative Contribution of Medical Comorbidities in the OARA Score: A Machine Learning Analysis

Background/Objective: The Outpatient Arthroplasty Risk Assessment (OARA) score has been used successfully to identify patients who can safely undergo outpatient primary total joint arthroplasty (TJA) based on medical risk stratification. The targeted score (0 to 79) was conservatively established to ensure patient safety. However, the number of points associated with each of the 52 comorbidities in the OARA score were assigned based on physician experience with early discharge. This study applied machine learning (ML) to empirically identify the relative contribution/importance of each medical comorbidity to safe same-day discharge (SDD). Methods: 3,047 patients who underwent primary unilateral TJA by a single surgeon at a single institution were included in the analysis; 573 were SDDs. Before ML analysis, associations among binary (yes/no) comorbidities were examined using Cramér's V. A CART decision tree model using Gini method was used to develop a model for SDD (yes/no) based on the presence or absence of the comorbidities. Results: To produce interpretable results with acceptable face validity the 52 comorbidities were grouped in 19 common medical categories (heart disease, liver disease, etc.). Although the resulting model was less than perfectly predictive (AROC = 0.652, 95% CI 0.629–0.675), it resulted in an interpretable classification tree identifying heart disease, kidney disease, immunosuppression, chronic sedative use, pulmonary disease, thrombophilia, anemia, and history of stroke, in order, as the most important predictors of SDD. Conclusion: Model limitations expressed as AROC were not unexpected because the relative contribution (expressed as points) of comorbidities to the OARA score are based on physician decision-making, not empirical identification of the importance of each medical condition to safe SDD. Study results moved the goal of empirical classification forward but the low prevalence of many of the comorbidities limited variability and hence model performance and accuracy. Future work with a larger sample is being planned.