Search

In intelligent traffic control systems, the features extracted by loop detectors are insufficient to accurately impute missing data. Most of the existing imputation methods use only these extracted features, which leads to the construction of data models that cannot fulfill the required accuracy. This deficiency is the main motivation to propose an enrichment imputation method for loop detectors namely EIM-LD, in which the imputation accuracy is increased for different missing patterns and ratios by introducing a data enrichment technique using statistical multi-class labeling. It first enriches the clean data by adding a statistical multi-class label, including C1...Cn classes. Then, the class of samples in the missed-volume data is labeled using the best data model constructed from the labeled clean data by five different classifiers. Experts of the traffic control department in Isfahan city determined classes of the statistical multi-class label for n = 5 (class labels), and we also developed subclass labels (n = 20) since the number of samples in the subclass labels was sufficient. Next, the enriched data are divided into n datasets, each of them is imputed independently using various imputation methods, and their results are finally merged. To evaluate the impact of using the proposed method, the original data, including missing volumes, are first imputed without our enrichment method. Then, the proposed method's accuracy is evaluated by considering two class labels and subclass labels. The experimental and statistical results prove that the proposed EIM-LD method can enrich the real data collected by loop detectors, by which the comparative imputation methods construct a more accurate data model. In addition, using subclass labels further enhances the imputation method's accuracy. [ABSTRACT FROM AUTHOR]

Satellite data is of high importance for ocean environment monitoring and protection. However, due to the missing values in satellite data, caused by various force majeure factors such as cloud cover, bad weather and sensor failure, the quality of satellite data is reduced greatly, which hinders the applications of satellite data in practice. Therefore, a variety of methods have been proposed to conduct missing data imputation for satellite data to improve its quality. However, these methods cannot well learn the short-term temporal dependence and dynamic spatial dependence in satellite data, resulting in bad imputation performance when the data missing rate is large. To address this issue, we propose the Spatio-Temporal Attention Generative Adversarial Network (STA-GAN) for missing value imputation in satellite data. First, we develop the Spatio-Temporal Attention (STA) mechanism based on Graph Attention Network (GAT) to learn features for capturing both short-term temporal dependence and dynamic spatial dependence in satellite data. Then, the learned features from STA are fused to enrich the spatio-temporal information for training the generator and discriminator of STA-GAN. Finally, we use the generated imputation data by the trained generator of STA-GAN to fill the missing values in satellite data. Experimental results on real datasets show that STA-GAN largely outperforms the baseline data imputation methods, especially for filling satellite data with large missing rates. [ABSTRACT FROM AUTHOR]

Sustainable groundwater management requires an accurate characterization of aquifer-storage change over time. This process begins with an analysis of historical water levels at observation wells. However, water-level records can be sparse, particularly in developing areas. To address this problem, we developed an imputation method to approximate missing monthly averaged groundwater-level observations at individual wells since 1948. To impute missing groundwater levels at individual wells, we used two global data sources: Palmer Drought Severity Index (PDSI), and the Global Land Data Assimilation System (GLDAS) for regression. In addition to the meteorological datasets, we engineered four additional features and encoded the temporal data as 13 parameters that represent the month and year of an observation. This extends previous similar work by using inductive bias to inform our models on groundwater trends and structure from existing groundwater observations, using prior estimates of groundwater behavior. We formed an initial prior by estimating the long-term ground trends and developed four additional priors by using smoothing. These prior features represent the expected behavior over the long term of the missing data and allow the regression approach to perform well, even over large gaps of up to 50 years. We demonstrated our method on the Beryl-Enterprise aquifer in Utah and found the imputed results follow trends in the observed data and hydrogeological principles, even over long periods with no observed data. [ABSTRACT FROM AUTHOR]

The immense problem of missing satellite aerosol retrievals (Aerosol Optical Depth, (AOD)) detrimentally affects the prediction ability of ground-level PM2.5 concentrations and may lead to unavoidable biases. An appropriate missing-imputation method has not been well developed to date. This study developed a two-stage approach (AOD-imputation stage and PM2.5-prediction stage) to predict short-term PM2.5 exposure in mainland China from 2013–2018. At the AOD-imputation stage, geostatistical methods and machine learning (ML) algorithms were examined to interpolate 1 km satellite aerosol retrievals. At the PM2.5-prediction stage, the daily levels of PM2.5 were predicted at a resolution of 1 km, based on interpolated AOD and meteorological data. The statistical performances of the different interpolation methods were comprehensively compared at each stage. The original coverage of retrieved AOD was 15.46% on average. For the AOD-imputation stage, ML methods produced a higher coverage (98.64%) of AOD than geostatistical methods (21.43–87.31%). Among ML algorithms, random forest (RF) or extreme gradient boosted (XG-interpolated) AOD produced better interpolated quality (CV R2 = 0.89 and 0.85) than other algorithms (0.49–0.78), but XGBoost required only 15% of the computing time of RF. For the PM2.5 predicted stage, neither RF-AOD nor XG-AOD could guarantee higher accuracy in PM2.5 estimations (CV R2 = 0.88 (RF or XG-AOD) compared to 0.85 (original)), or more stable spatial and temporal extrapolation (spatial, (temporal) CV R2 = 0.83 (0.83), 0.82 (0.82), and 0.65 (0.61) for RF, XG, and original). For the AOD-imputation stage, the missing-filled efficiency depended more on external information, while the missing-filled accuracy relied more on model structure. For the PM2.5 predicted stage, efficient AOD interpolation (or the ability to eliminate the missing data) was a precondition for the stable spatial and temporal extrapolation, while the quality of interpolated AOD showed less significant improvements. It was found that XG-AOD is a better choice to estimate daily PM2.5 exposure in health assessments. [ABSTRACT FROM AUTHOR]