Robust imputation method with context-aware voting ensemble model for management of water-quality data.

Water-quality monitoring and management are crucial for ensuring the safety and sustainability of water resources. However, missing data is a frequent problem in water-quality datasets, which can result in biased results in hydrological modeling and data analysis. While classic statistical methods and emerging machine/deep learning methods have been applied for imputing missing values, most existing studies perform well in specific missing scenarios, but not in universal scenarios. Therefore, existing imputation methods often fail to robustly impute missing values across various scenarios. To address the problem, we propose an imputation method that uses a context-aware voting-ensemble model to dynamically select optimal weights to integrate various imputation models across different missingness scenarios. For first identify the attributes of missingness scenarios that influence imputation accuracy. Then after introducing missing values in collected data according to the missingness scenarios, we measure the accuracy of various imputation models across the missingness scenarios. Weights of imputation models are optimized by estimating non-linear functions with regression model that can capture relationships between missingness scenarios and imputation accuracies of models. The final imputed value of the ensemble model for a missing scenario can be determined by multiplying each imputation model's weight by its imputed value, then summing the products. The method inherits the advantages of state-of-art imputation models, including the ability to learn long-term dependencies in time series, as well as the flexibility of using a dynamic weighting strategy to process various missingness scenarios. To validate the superiority of our method, we evaluate on real-world water-quality data from a river in South Korea. The proposed method achieves higher accuracy and lower variation of imputed values than baseline models across various missingness scenarios. Furthermore, we showed the applicability of our method to various hydrological environment by validating our method on industrial water quality dataset. This study highlights the potential value of the ensemble model with dynamic weighting in robust imputation of water-quality data.

Deep Regression Prediction of Rheological Properties of SIS-Modified Asphalt Binders.

The engineering properties of asphalt binders depend on the types and amounts of additives. However, measuring engineering properties is time-consuming, requires technical expertise, specialized equipment, and effort. This study develops a deep regression model for predicting the engineering property of asphalt binders based on analysis of atomic force microscopy (AFM) image analysis to test the feasibility of replacing traditional measuring estimate techniques. The base asphalt binder PG 64-22 and styrene-isoprene-styrene (SIS) modifier were blended with four different polymer additive contents (0%, 5%, 10%, and 15%) and then tested with a dynamic shear rheometer (DSR) to evaluate the rheological data, which indicate the rutting properties of the asphalt binders. Different deep regression models are trained for predicting engineering property using AFM images of SIS binders. The mean absolute percentage error is decisive for the selection of the best deep regression architecture. This study's results indicate the deep regression architecture is found to be effective in predicting the G*/sin δ value after the training and validation process. The deep regression model can be an alternative way to measure the asphalt binder's engineering property quickly. This study would encourage applying a deep regression model for predicting the engineering properties of the asphalt binder.