Using machine learning approach to reproduce the measured feature and understand the model-to-measurement discrepancy of atmospheric formaldehyde

Research on nondestructive detection of sweet-waxy corn seed varieties and mildew based on stacked ensemble learning and hyperspectral feature fusion technology

The variety and quality of corn seeds are crucial factors affecting crop yield and farmers' economic benefits. This study adopts an innovative method based on a hyperspectral imaging system combined with stacked ensemble learning, aiming to achieve varieties classification and mildew detection of sweet-waxy corn seeds. First, data interference is eliminated by extracting the spectral and texture information of each corn sample and preprocessing the data. Secondly, a stacked ensemble learning model (Stack) was constructed by stacking base models and meta-models. Its results were compared with those of the base models, including Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF).Finally, the overall performance of the model is improved through the information fusion strategy of hyperspectral data and texture information. The research results indicate that the GBDT-Stack model, which integrates spectral and texture data, demonstrated optimal performance in the comprehensive classification of both corn seed varieties and mold detection. On the test set, the model achieved an average prediction accuracy of 97.01%. Specifically, the model achieved a test set accuracy ranging from 94.49% to 97.58% for different corn seed varieties and a test set accuracy of 98.89% for mildew detection. This model not only classifies corn seed varieties but also accurately detects mildew, demonstrating its wide applicability. The method has huge potential and is of great significance for improving crop yield and quality.

Spatial distribution prediction of soil heavy metals based on sparse sampling and multi-source environmental data

Predicting the precise spatial distribution of heavy metals in soil is crucial, especially in the fields of environmental management and remediation. However, achieving accurate spatial predictions of soil heavy metals becomes quite challenging when the number of soil sampling points is relatively limited. To address this challenge, this study proposes a hybrid approach, namely, Light Gradient Boosting Machine plus Ordinary Kriging (LGBK), for predicting the spatial distribution of soil heavy metals. A total of 137 soil samples were collected from the Shengli Coal-mine Base in Inner Mongolia, China, and their heavy metal concentrations were measured. Leveraging environmental covariates and soil heavy metal data, we constructed the predictive model. Experimental results demonstrate that, in comparison to traditional models, LGBK exhibits superior predictive performance. For copper (Cu), zinc (Zn), chromium (Cr), and arsenic (As), the coefficients of determination (R²) from the cross-validation results are 0.65, 0.52, 0.57, and 0.63, respectively. Moreover, the LGBK model excels in capturing intricate spatial features in heavy metal distribution. It accurately forecasts trends in heavy metal distribution that closely align with actual measurements. ENVIRONMENTAL IMPLICATION: This study introduces a novel method, LGBK, for predicting the spatial distribution of soil heavy metals. This method yields higher-precision predictions even with a limited number of sampling points. Furthermore, the study analyzes the spatial distribution characteristics of Cu, Zn, Cr, and As in the grassland coal-mine base, along with the key environmental factors influencing their spatial distribution. This research holds significant importance for the environmental regulation and remediation of heavy metal pollution.

Use of feature importance statistics to accurately predict asthma attacks using machine learning: A cross-sectional cohort study of the US population

BACKGROUND

Asthma attacks are a major cause of morbidity and mortality in vulnerable populations, and identification of associations with asthma attacks is necessary to improve public awareness and the timely delivery of medical interventions.

OBJECTIVE

The study aimed to identify feature importance of factors associated with asthma in a representative population of US adults.

METHODS

A cross-sectional analysis was conducted using a modern, nationally representative cohort, the National Health and Nutrition Examination Surveys (NHANES 2017-2020). All adult patients greater than 18 years of age (total of 7,922 individuals) with information on asthma attacks were included in the study. Univariable regression was used to identify significant nutritional covariates to be included in a machine learning model and feature importance was reported. The acquisition and analysis of the data were authorized by the National Center for Health Statistics Ethics Review Board.

RESULTS

7,922 patients met the inclusion criteria in this study. The machine learning model had 55 out of a total of 680 features that were found to be significant on univariate analysis (P<0.0001 used). In the XGBoost model the model had an Area Under the Receiver Operator Characteristic Curve (AUROC) = 0.737, Sensitivity = 0.960, NPV = 0.967. The top five highest ranked features by gain, a measure of the percentage contribution of the covariate to the overall model prediction, were Octanoic Acid intake as a Saturated Fatty Acid (SFA) (gm) (Gain = 8.8%), Eosinophil percent (Gain = 7.9%), BMXHIP-Hip Circumference (cm) (Gain = 7.2%), BMXHT-standing height (cm) (Gain = 6.2%) and HS C-Reactive Protein (mg/L) (Gain 6.1%).

CONCLUSION

Machine Learning models can additionally offer feature importance and additional statistics to help identify associations with asthma attacks.

River ecological flow early warning forecasting using baseflow separation and machine learning in the Jiaojiang River Basin, Southeast China

Ecological flow early warning is crucial for the rational management of watershed water resources. However, determining of accurate ecological flow threshold and choosing the appropriate forecasting model are challenging tasks. In this study, we initially developed a baseflow separation and Tennant method-based technique for calculating ecological river flow. Then an ecological flow early warning model was created using the machine learning technique based on distributed gradient enhancement framework (LightGBM). Finally, we utilized the framework of Shapley Additive Planning (SHAP) to explain how various hydrometeorological factors affect the variations in ecological flow conditions. The Jiaojiang River basin in southeast China is selected as the study area, and the hydrological stations in upstream of Baizhiao (BZA) and Shaduan (SD) are chosen for key analysis. The results of these applications show that the monthly baseflow frequency of the river ecological flow conditions of the two stations in the dry season is 20 % (7.49 m³/s) and 30 % (4.79 m³/s), respectively. The ecological flow level early warning forecasting accuracy is close to 90 % in the BZA and SD stations during dry and wet seasons. The variations of ecological flow are most affected by evaporation and base flow index. The results of this study can serve as a strong basis for the effective allocation and utilization of locally available water resources.