ALBERT

Description: Air quality monitoring is vital because air pollution caused by particulate matter invokes social problems and adversely affects human health. The atmospheric boundary-layer and its sub-layers strongly influence the spatiotemporal distributions of air pollutants and hence modulating air quality. Thus, continuous measurements of the atmospheric boundary-layer are needed to assess air quality and air pollution. A ceilometer vertically emits a laser pulse of a single wavelength into the atmosphere and measures the returned intensity of backscattered laser by atmospheric hydrometeors (e.g., aerosols and cloud particles), which allows determining the atmospheric boundary-layer height (ABLH) based on the ceilometer measurements. Thus, dense ceilometer measurement networks have emerged across the world for sampling the ABLH vertical profile. In this study, two different ceilometer measurement networks (i.e., the National Institute of Environmental Research (NIER) and the Korea Meteorological Administration (KMA)) in the Republic of Korea were introduced. The models and specifications of the installed ceilometers in these networks were explained. A new generalized algorithm calculating ABLH based on a gradient method, applicable to all installed ceilometers of the NIER and KMA networks, was developed. The impacts of the selection of spatial (i.e., vertical) and temporal resolutions of vertical profiling on the calculations of ABLH were quantified for different ceilometers. The optimal spatial and temporal resolutions for determining ABLH based on ceilometer measurements were also determined.

Description: Due to the difficulties in estimating groundwater recharge and cross-boundary nature of many aquifers, estimating groundwater recharge at large scale has been called upon. Process-based models as well as data-driven models have been established to meet this need. Meanwhile, with the advent of explainable artificial intelligence (XAI) methods, data-driven machine learning models can take advantage of enhanced explainability while keeping the strength of high flexibility. In this study, an ensemble neural network model was built to check the suitability of the model to predict groundwater recharge and the possibility to gain new insights from large data set. Recent large inputs of groundwater recharge data and additional input for the Arabian Peninsula collated in this study were fed to the model with multiple predictors related to climatology considering seasonality, soil and plant characteristics, topography, and hydrogeology. The model showed higher performance (adjusted R2: 0.702, RMSE: 193.35 mm yr−1) than a recent global process-based model in predicting groundwater recharge. Using XAI methods as individual conditional expectations and Shapley Additive Explanation interaction values, the model behavior was analyzed and possible linear and non-linear relationships between the predictors and the groundwater recharge rate were found. Long-term averaged precipitation and enhanced vegetation index showed non-linear relationships with groundwater recharge rate, while slope, compound topographic index, and water table depth showed low importance to the model results. Most model behaviors followed the domain knowledge, while multi-correlation between predictors and data skewness hindered the model from learning.