Spatiotemporal Graph Neural Networks for PM2.5 Concentration Forecasting

ABSTRACTAccurate estimation of precipitation is crucial for crop yield assessment, flood and drought monitoring, and water structures management. Precipitation is subject to both temporal and spatial variability. While recording rain gauges support temporal resolution, they measure point rainfall and require dense network and application of interpolation techniques to provide spatial dimension. On the other hand, remote-sensing products cover regional and global spatial scales. Building upon the Tropical Rainfall Measuring Mission (TRMM) heritage, the Global Precipitation Measurement (GPM) mission is an international net of satellites that present the next-generation global observations of rain and snow at a spatial resolution of 0.1° × 0.1° with a half-hour temporal resolution. In this study, March–December 2014 3-hourly TRMM data (3B42V7) and half-hourly Integrated Multi-satellite Retrievals for GPM (IMERG) data are compared with the 3-hourly rain gauges data in Khorasan Razavi province, located in northwest of Iran. Coefficient of determination (R2), Bias, MBias, RBias, mean absolute error (MAE), root mean square error (RMSE) as well as probability of detection (POD), false alarm ratio (FAR), and critical success index (CSI) metrics were measured for validation purposes. The result showed that correlation between IMERG data and rain gauge rainfall data is higher than those of 3B42V7 data. In addition, the values of MBias, Bias, and RBias confirmed that both of 3B42V7 and IMERG underestimated rainfall over the study area, whereas MBias of IMERG was higher than 3B42V7. Furthermore, MAE and RMSE values of 3B42V7 and IMERG were similar while IMERG evaluation turned out a better correlation coefficient (r) and POD than 3B42V7. This study showed that IMERG generally had reasonable agreement with the gauge data.

The limitations of good rainfall data due to constraints on direct measurements can be overcome by using satellite data or reanalysis data. The use of this data must, of course, go through a validation process first. This research aims to evaluate daily data from the Tropical Rainfall Measurement Mission (TRMM) version 3B42RT (TRMM_3B42RT) and European Center for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5 (ERA5) data against data collected from 17 rain gauges in the Sumatra region South. Evaluation is carried out based on the Correlation Coefficient (CC), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Bias Error (MBE) values between the data. In addition, the estimation capabilities of TRMM_3B42RT and ERA5 were evaluated based on the Probability of Detection (POD), False Alarm Ratio (FAR), and Critical Success Index (CSI) values. The results show a very high correlation between TRMM_3B42RT and ERA5 with rain gauge data, especially in terms of monthly data. These values (monthly data) for TRMM_3B42RT and ERA5 data are 0.3-0.9 and 0.2-0.9, respectively. The RMSE values of TRMM_3B42RT and ERA5 data in monthly analysis are 75-250mm/month and 100-180mm/month, respectively. The forecasting performance of TRMM_3B42RT and ERA5 shows good results, especially for moderate rainfall in daily data and heavy rainfall in monthly data. The results of this analysis show tha the monthly data TRMM_3B42RT is more in line with the station data and can be used in further research.

Droughts severely impact agriculture, food security, and water resources, particularly in data scarce regions like the Genale Dawa River Basin (GDRB). This study evaluates the performance of five satellite rainfall products including CHIRPSv2.0, RFE2.0, TAMSATv3.1, PERSIANN-CDR, and ARC2 over 2001-2020 using metrics such as Mean Bias, Absolute Error (MAE), Root Mean Square Error (RMSE), Correlation Coefficient (CC), Probability of Detection (POD), False Alarm Ratio (FAR), and Critical Success Index (CSI). Furthermore, the studies examined the relationship between climate indices including the Pacific Decadal Oscillation (PDO), North Atlantic Oscillation (NAO), El Niño Southern Oscillation (ENSO), and Atlantic Multidecadal Oscillation (AMO) and drought variability. CHIRPSv2.0 demonstrated the highest accuracy, especially at Ginir (CC = 0.98) and Chewbet (CC = 0.75), and the lowest errors at Teferekella (MAE = 45, RMSE = 65). Based on a multi-criterion ranking approach, CHIRPSv2.0 was identified as the most reliable satellite-based product for daily rainfall estimation across the entire basin, exhibiting strong performance metrics (Lp = 0.433, CC = 0.84, POD = 0.85, CSI = 0.46). CHIRPSv2.0 was used to analyze drought spatiotemporal patterns using SPI-3 and SPI-6. Drought severity, frequency, and duration were highest in the west-central and northern GDRB, with major events occurring in 1988, 1991-1993, 2000, 2004, 2011, and 2012. Climate index analysis showed that AMO and NAO positive phases were associated with wetter conditions, while negative PDO and ENSO phases corresponded with drier periods, especially in central and eastern areas. These findings highlight CHIRPSv2.0's reliability for drought monitoring and its value for early warning and mitigation planning in the GDRB.

Long-term measurements of planetary boundary layer height and interactions with PM2.5 in Shanghai, China

Error magnitude is a measurement commonly used in forecast evaluation. However, the purpose of forecasting air quality is to maintain the air quality within assigned guidelines. Thus, the index measurement is important to be considered. But, the problem arises when the index is used to gauge the values of different offices and these measurements are found to be degenerate in commonly occurring situations. Therefore, this study aims to overcome both of the limitations. The daily air pollutant index (API) data from year 2005 to 2011 was used to compare the forecast performance between Box-Jenkins methods, artificial neural networks (ANN) and hybrid method. The forecast accuracy measurements used include mean absolute percentage error (MAPE), root mean squared error (RMSE), mean absolute deviation (MAD), true predicted rate (TPR), false positive rate (FPR), false alarm rate (FAR) and successful index (SI) including the proposed index measurement, combination index (CI). It is found that the index measurement enhance the ability to measure the air quality forecast performance in choosing the best forecast method with CI significantly overcome the limitation of existing index measurement. Thus, this study suggests to use the appropriate measurement in accordance to the purpose of forecasting.Error magnitude is a measurement commonly used in forecast evaluation. However, the purpose of forecasting air quality is to maintain the air quality within assigned guidelines. Thus, the index measurement is important to be considered. But, the problem arises when the index is used to gauge the values of different offices and these measurements are found to be degenerate in commonly occurring situations. Therefore, this study aims to overcome both of the limitations. The daily air pollutant index (API) data from year 2005 to 2011 was used to compare the forecast performance between Box-Jenkins methods, artificial neural networks (ANN) and hybrid method. The forecast accuracy measurements used include mean absolute percentage error (MAPE), root mean squared error (RMSE), mean absolute deviation (MAD), true predicted rate (TPR), false positive rate (FPR), false alarm rate (FAR) and successful index (SI) including the proposed index measurement, combination index (CI). It is found that the index measurement...

A statistical-empirical decision aid for forecasting morning fogs at Mount Gambier Airport based on pre-dawn data is presented. Of main concern are those fog events significantly impacting on aviation operations, although the model is applicable to other fog events of lesser impact. The aid is restricted to precipitation-absent fogs. The probability of fog occurrence was modelled on a ten-year dependent dataset using the logistic equation. By converting probabilistic forecasts to categorical forecasts of fog events, skill scores of Probability of Detection, False Alarm Rate and Critical Success Index were determined based upon three years of independent data. For operationally significant fogs, the Probability of Detection, False Alarm Rate and Critical Success Index were 73%, 23% and 60% respectively on the independent data. These scores were very similar to those obtained from the dependent dataset of ten years. When fog events were defined less stringently as either fogs per se or shallow fogs, the respective skill scores on the independent data were 84%, 20% and 70%; again with similar scores on the dependent data.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

This article uses machine learning techniques as fuzzy and neuro-fuzzy ANFISs, to develop and compare prediction models capable of relating pregnant women’s exposure to air pollutants, such as Nitrogen Dioxide and Particulate Matter, the mother’s age, and the number of prenatal consultations to the incidence of premature birth. In the current literature, studies can be found that relate prematurity to the exposure of pregnant women to NO2, O3, and PM10; to Toluene and benzene, mainly in the window 5 to 10 days before birth; and to PM10 in the week before birth. Both models used logistic regression to quantify the effects of pollutants as a result of premature birth. Datasets from Brazil—Departamento de Informatica do Sistema Único de Saúde (DATASUS) and Companhia Ambiental do Estado de São Paulo (CETESB)—were used, covering the period from 2016 to 2018 and comprising women living in the city of São José dos Campos (SP), Brazil. In order to evaluate and compare the different techniques used, evaluation metrics were calculated, such as correlation (r), coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and Mean Absolute Error (MAE). These metrics are widely used in the literature due to their ability to evaluate the robustness and efficiency of prediction models. For the RMSE, MAPE, MSE, and MAE metrics, lower values indicate that prediction errors are smaller, demonstrating better model accuracy and confidence. In the case of (r) and R2, a positive and strong result indicates alignment and better performance between the real and predicted data. The neuro-fuzzy ANFIS model showed superior performance, with a correlation (r) of 0.59, R2 = 0.35, RMSE = 2.83, MAPE = 5.35%, MSE = 8.00, and MAE = 1.70, while the fuzzy model returned results of r = 0.20, R2 = 0.04, RMSE = 3.29, MSE = 10.81, MAPE = 6.67%, and MAE = 2.01. Therefore, the results from the ANFIS neuro-fuzzy system indicate greater prediction capacity and precision in relation to the fuzzy system. This superiority can be explained by integration with neural networks, allowing data learning and, consequently, more efficient modeling. In addition, the findings obtained in this study have potential for the formulation of public health policies aimed at reducing the number of premature births and promoting improvements in maternal and neonatal health.

Using spectral indices and terrain attribute datasets and their combination in the prediction of cadmium content in agricultural soil

Air pollution, Asthma, and Gross Domestic Product (GDP) are very important indicators to human life and development and it has been found that air pollution has a big effect on the latter two. In this paper, we find the correlation factor and to what extent air pollution has an effect on those two. For this, we chose 20 American states, handpicked the ones having unique features with respect to pollution levels, asthma cases, GDP numbers, and the datasets for the past 20 years of each state were taken. We chose 6 toxic pollutants, namely PM2.5, Carbon Monoxide, Sulfur Dioxide, PM10, Ozone, and Nitrogen Dioxide with each dataset including daily readings of these pollutants for the past 20 years in each state. The idea behind our model is to use all these data and find the extent to which air pollution is related to the asthma cases and the GDP of a state. For this, we use 4 models, namely Neural Network (NN), Random Forest (RFC), Support Vector Machines (SVM) and K-Nearest Neighbors (KNN). We use metrics like Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R-Squared to evaluate our results. We observed a positive correlation between rates of asthma and GDP and pollution data. NN gave the best prediction accuracy especially for GDP (Average: 76%) followed closely by SVM. SVM's also had the least MAE while RFC had the least RMSE.

A hybrid air quality early-warning framework: An hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms

Regionalization of the summertime planetary boundary layer height in comparison with various reanalysis datasets over China

ABSTRACTIn this paper, we have proposed a method of sea fog prediction using model sea surface wind (SSW) data and hourly optical satellite data with 500 m spatial resolution. Three sea fog cases in the Yellow Sea were selected from Geostationary Ocean Color Imager (GOCI) images, and their shifts were determined from the fog cluster centroid displacements at successive hours. The 4 km resolution Weather Research and Forecasting (WRF) model SSW were used to predict sea fog shifts. The sea fog prediction results were verified using validation indices like probability of detection (POD), false alarm ratio (FAR), and critical success index (CSI). The predictions started with high initial skill scores (POD = 0.76, FAR = 0.18, and CSI = 0.66), and showed values 0.59, 0.30, and 0.46 for POD, FAR, and CSI, respectively for predictions after two hours. After three hours their values still remained close to the medians though decreased, but afterwards decreased considerably for POD and CSI. Thus the method is found suitable for short-term prediction of sea fog. Additionally, trajectory sensitivities were compared between 20 and 4 km resolution WRF which, in general, resulted in less errors for 4 km WRF model SSW.

Deep convective clouds, such as towering cumulus and Cumulonimbus, can endanger lives and property, also being a major hazard to aviation. This study presents the convective index (IndexCON) used operationally at the Portuguese Meteorological Watch Office. Moreover, IndexCON is evaluated against lightning and precipitation data for two years, between January 2022 and December 2023, over mainland Portugal and its surrounding areas. This index combines several European Center for Medium-Range Weather Forecasts (ECMWF) prognostic variables, such as stability indices, cloud water content, relative humidity and vertical velocity, using a fuzzy-logic approach. IndexCON performs well in the warm season (May–October), with a probability of detection (POD) of 70%, a false alarm ratio (FAR) of 30% and a probability of false detection (POFD) less than 5%, leading to a Critical Success Index (CSI) above 0.55. However, IndexCON performs worse in the cold season (November–April), when dynamical drivers are more relevant, mainly due to overestimating the convective activity, resulting in CSI and Heidke Skill Score (HSS) values below 0.3. Optimizing the membership functions partially reduces this overestimation. Finally, the added value of IndexCON was illustrated in detail for a thunderstorm episode, using satellite products, lightning and precipitation data.

Haze caused by forest and land fires is a serious problem in South Sumatra Province. One mitigation effort that can be made is to improve the accuracy of rainfall predictions, because rain plays an important role in reducing the potential for fires. This study implements machine learning methods, namely XGBoost and ConvLSTM, to predict spatiotemporal rainfall in areas prone to haze. The results show that ConvLSTM is capable of providing better predictions than the baseline, especially during periods of haze, by considering missing data imputation and masking techniques for disrupted satellite conditions. Increasingly apparent climate change in tropical regions has had a significant impact on rainfall patterns, particularly in South Sumatra, which is one of Indonesia's main agricultural and plantation centers. High rainfall variability can lead to the risk of flooding and drought, as well as disrupting productivity in the education, health, and economic sectors. Therefore, a more accurate rainfall prediction approach is needed to support climate adaptation planning and disaster risk mitigation. This study aims to compare the performance of three approaches to daily rainfall prediction, namely the ConvLSTM-based method, XGBoost, and Persistence, using daily observation data from BMKG for the South Sumatra region for the period 1981–2020. The input variables include average air temperature (Tavg), humidity, sunshine duration, and wind speed, while rainfall is used as the prediction target. The analysis was conducted through a time series approach, statistical distribution, and model performance evaluation using the quantitative metrics Root Mean Square Error (RMSE) and Critical Success Index (CSI). The results show that the ConvLSTM model produced the highest accuracy with an average RMSE of 10 mm/day and a CSI of 0.53, which is better than XGBoost (RMSE 12 mm/day; CSI 0.48) and the persistence method (RMSE 15 mm/day; CSI 0.40). Distribution analysis indicates that light to moderate rainfall occurs more frequently, while extreme rainfall occurs sporadically. The correlation heatmap shows that rainfall has a moderate positive relationship with humidity and a negative relationship with solar radiation, while average temperature and wind play a smaller role. The main contribution of this study is to provide empirical evidence that spatiotemporal deep learning methods such as ConvLSTM are superior in modeling the complexity of tropical rainfall dynamics compared to classical machine learning approaches and simple models. These findings can serve as a basis for the development of early warning systems and interactive climate dashboards at the regional level, while enriching the literature on rainfall prediction in tropical regions using an integrative approach.