Particulate matter (PM) is a widely used indicator of air quality. Satellite-derived aerosol products such as aerosol optical depth (AOD) have been a useful source of data for ground-level PM monitoring. However, satellite-based approaches for PM monitoring have limitations such as impacts of cloud cover. Recently, many studies have documented advances in modeling for monitoring PM over the globe. This review examines recent papers on ground-level PM monitoring for the past 10 years focusing on modeling techniques, sensor types, and areas. Satellite-based retrievals of AOD and commonly used approaches for estimating PM concentrations are also briefly reviewed. Research trends and challenges are discussed based on the review of 130 papers. The limitations and challenges include spatiotemporal scale issues, missing values in satellite-based variables, sparse distribution of ground stations for calibration and validation, unbalanced distribution of PM concentrations, and difficulty in the operational use of satellite-based PM estimation models. The literature review suggests there is room for further investigating: 1) the spatial extension of PM monitoring to global scale; 2) the synergistic use of satellite-derived products and numerical model output to improve PM estimation accuracy, gap-filling, and operational monitoring; 3) the use of more advanced modeling techniques including data assimilations; 4) the improvement of emission data quality; and 5) short-term (hours to days) PM forecasts through combining satellite data and numerical forecast model results.

Satellite altimeters have been used to monitor Arctic sea ice thickness since the early 2000s. In order to estimate sea ice thickness from satellite altimeter data, leads (i.e., cracks between ice floes) should first be identified for the calculation of sea ice freeboard. In this study, we proposed novel approaches for lead detection using two machine learning algorithms: decision trees and random forest. CryoSat-2 satellite data collected in March and April of 2011–2014 over the Arctic region were used to extract waveform parameters that show the characteristics of leads, ice floes and ocean, including stack standard deviation, stack skewness, stack kurtosis, pulse peakiness and backscatter sigma-0. The parameters were used to identify leads in the machine learning models. Results show that the proposed approaches, with overall accuracy >90%, produced much better performance than existing lead detection methods based on simple thresholding approaches. Sea ice thickness estimated based on the machine learning-detected leads was compared to the averaged Airborne Electromagnetic (AEM)-bird data collected over two days during the CryoSat Validation experiment (CryoVex) field campaign in April 2011. This comparison showed that the proposed machine learning methods had better performance (up to r = 0.83 and Root Mean Square Error (RMSE) = 0.29 m) compared to thickness estimation based on existing lead detection methods (RMSE = 0.86–0.93 m). Sea ice thickness based on the machine learning approaches showed a consistent decline from 2011–2013 and rebounded in 2014.

Long-term exposure to particulate matter (PM) with aerodynamic diameters < 10 (PM₁₀) and 2.5 µm (PM_2.5) has negative effects on human health. Although station-based PM monitoring has been conducted around the world, it is still challenging to provide spatially continuous PM information for vast areas at high spatial resolution. Satellite-derived aerosol information such as aerosol optical depth (AOD) has been frequently used to investigate ground-level PM concentrations. In this study, we combined multiple satellite-derived products including AOD with model-based meteorological parameters (i.e., dew-point temperature, wind speed, surface pressure, planetary boundary layer height, and relative humidity) and emission parameters (i.e., NO, NH₃, SO₂, primary organic aerosol (POA), and HCHO) to estimate surface PM concentrations over South Korea. Random forest (RF) machine learning was used to estimate both PM₁₀ and PM_2.5 concentrations with a total of 32 parameters for 2015–2016. The results show that the RF-based models produced good performance resulting in R² values of 0.78 and 0.73 and root mean square errors (RMSEs) of 17.08 and 8.25 µg m⁻³ for PM₁₀ and PM_2.5, respectively. In particular, the proposed models successfully estimated high PM concentrations. AOD was identified as the most significant for estimating ground-level PM concentrations, followed by wind speed, solar radiation, and dew-point temperature. The use of aerosol information derived from a geostationary satellite sensor (i.e., Geostationary Ocean Color Imager, GOCI) resulted in slightly higher accuracy for estimating PM concentrations than that from a polar-orbiting sensor system (i.e., the Moderate Resolution Imaging Spectroradiometer, MODIS). The proposed RF models yielded better performance than the process-based approaches, particularly in improving on the underestimation of the process-based models (i.e., GEOS-Chem and the Community Multiscale Air Quality Modeling System, CMAQ).

Researchers constantly seek more efficient detection techniques to better utilize enhanced image resolution in accurately detecting and monitoring land cover. Recently, convolutional neural networks (CNNs) have shown high performances comparable to or even better than widely used and adopted machine learning techniques. The aim of this study is to investigate the application of CNNs for land cover classification by using two-dimensional (2-D) spectral curve graphs from multispectral satellite images. The land cover classification was conducted in Concord, New Hampshire, USA, and South Korea by using multispectral images acquired from 30-m Landsat-8 and 500-m Geostationary Ocean Color Imager images. For the construction of input data specific to CNNs, two seasons (winter and summer) of multispectral bands were transformed into 2-D spectral curve graphs for each class. Land cover classification results of CNNs were compared with the results of support vector machines (SVMs) and random forest (RFs). The CNNs model showed higher performance than RFs and SVMs in both study sites. The examination of land cover classification maps demonstrates a good agreement with reference maps, Google Earth images, and existing global scale land cover map, especially for croplands. Using the spectral curve graph could incorporate the phenological cycles on classifying the land cover types. This study shows that the use of a new transformation of spectral bands into a 2-D form for application in CNNs can improve land cover classification performance.

This study compares some different types of spectral domain transformations for convolutional neural network (CNN)-based land cover classification. A novel approach was proposed, which transforms one-dimensional (1-D) spectral vectors into two-dimensional (2-D) features: Polygon graph images (CNN-Polygon) and 2-D matrices (CNN-Matrix). The motivations of this study are that (1) the shape of the converted 2-D images is more intuitive for human eyes to interpret when compared to 1-D spectral input; and (2) CNNs are highly specialized and may be able to similarly utilize this information for land cover classification. Four seasonal Landsat 8 images over three study areas—Lake Tapps, Washington, Concord, New Hampshire, USA, and Gwangju, Korea—were used to evaluate the proposed approach for nine land cover classes compared to several other methods: Random forest (RF), support vector machine (SVM), 1-D CNN, and patch-based CNN. Oversampling and undersampling approaches were conducted to examine the effect of the sample size on the model performance. The CNN-Polygon had better performance than the other methods, with overall accuracies of about 93%–95 % for both Concord and Lake Tapps and 80%–84% for Gwangju. The CNN-Polygon particularly performed well when the training sample size was small, less than 200 per class, while the CNN-Matrix resulted in similar or higher performance as sample sizes became larger. The contributing input variables to the models were carefully analyzed through sensitivity analysis based on occlusion maps and accuracy decreases. Our result showed that a more visually intuitive representation of input features for CNN-based classification models yielded higher performance, especially when the training sample size was small. This implies that the proposed graph-based CNNs would be useful for land cover classification where reference data are limited.

Prolonged exposure to high concentrations of nitrogen dioxide (NO2) and ozone (O3) at ground level could be harmful to human health. In-situ air pollutant concentration data observed from ground monitoring stations are limited in providing spatially continuous information. Since there are only a few stations installed above the sea, it is difficult to monitor the concentrations of air pollutants over the sea. In this study, machine learning-based models were developed to estimate ground-level NO2 and O3 concentrations using satellite-based remote sensing data and model-based meteorological and emission data over East Asia during 2015-2017, to overcome such limitations. NO2 and O3 vertical column density products from the Aura Ozone Monitoring Instrument (OMI) were used as essential predictors to estimate NO2 and O3 concentrations. Missing pixels of OMI products due to row anomalies were filled using a temporal convolution approach to generate the spatiotemporally continuous distribution of NO2 and O3 concentrations. In order to estimate the air pollutant concentrations in both land and ocean, specific values were assigned to the ocean for land-only variables. Random forest (RF) was used to develop the estimation models for NO2 and O3 concentrations. The RF-based models showed the results with R2 values of 0.72 and 0.75, and RMSEs of 6.24 ppb and 10.56 ppb for NO2 and O3, respectively. The estimated results over the ocean were validated using coastal stations that are located within a 1 km distance from the coast. Compared to the model without land-only variables, the models using all variables had slightly better results. The satellite-based NO2 and O3 vertical column density were identified as significant variables in both models. Besides, urban land cover ratio, wind-related variables such as wind vectors, and stacked maximum wind speed had relatively high variable importance. The spatial variation of NO2 and seasonal variation of O3 were well shown in the estimated spatiotemporal distribution.