Using process-oriented model output to enhance machine learning-based soil organic carbon prediction in space and time.

Monitoring and modelling soil organic carbon (SOC) in space and time can help us to better understand soil carbon dynamics and is of key importance to support climate change research and policy. Although machine learning (ML) has attracted a lot of attention in the digital soil mapping (DSM) community for its powerful ability to learn from data and predict soil properties, such as SOC, it is better at capturing soil spatial variation than soil temporal dynamics. By contrast, process-oriented (PO) models benefit from mechanistic knowledge to express physiochemical and biological processes that govern SOC temporal changes. Therefore, integrating PO and ML models seems a promising means to represent physically plausible SOC dynamics while retaining the spatial prediction accuracy of ML models. In this study, a hybrid modelling framework was developed and tested for predicting topsoil SOC stock in space and time for a regional cropland area located in eastern China. In essence, the hybrid model uses predictions of the PO model in unsampled years as additional training data of the ML model, with a weighting parameter assigned to balance the importance of SOC values from the PO model and real measurements. The results indicated that temporal trends of SOC stock modelled by PO and ML models were largely different, while they were notably similar between the PO and hybrid models. Cross-validation showed that the hybrid model had the best performance (RMSE = 0.29 kg m-2), with a 19 % improvement compared with the ML model. We conclude that the proposed hybrid framework not only enhances space-time soil carbon mapping in terms of prediction accuracy and physical plausibility, it also provides insights for soil management and policy decisions in the face of future climate change and intensified human activities.

Predicting isoscapes based on an environmental similarity model for the geographical origin of Chinese rice.

The authentication of geographical origin of food is important using stable isotope analysis. However, the isotopic databank is still short of comprehensive. The isoscapes model based on environmental similarity is used for the first time to predict the geospatial distribution of δ13C, δ2H and δ18O in Chinese rice in 2017 and 2018. 794 rice samples in 2017 were used to build isoscapes model. Independent verification shows that the predicted isotope distribution from this new approach is of high accuracy, with a root mean square error (RMSE) of 0.51 ‰, 7.09 ‰ and 2.06 ‰ for δ13C, δ2H and δ18O values for 2017, respectively. Our results indicate that it is possible to predict the spatial distribution of stable isotopes in rice using an isoscapes model based on environmental similarity. This novel strategy can enrich and complement a stable isotope reference database for rice origin identification at regional scale.

Evaluation of NOx emissions before, during, and after the COVID-19 lockdowns in China: A comparison of meteorological normalization methods.

Meteorological normalization refers to the removal of meteorological effects on air pollutant concentrations for evaluating emission changes. There currently exist various meteorological normalization methods, yielding inconsistent results. This study aims to identify the state-of-the-art method of meteorological normalization for characterizing the spatiotemporal variation of NOx emissions caused by the COVID-19 pandemic in China. We obtained the hourly data of NO2 concentrations and meteorological conditions for 337 cities in China from January 1, 2019, to December 31, 2020. Three random-forest based meteorological normalization methods were compared, including (1) the method that only resamples meteorological variables, (2) the method that resamples meteorological and temporal variables, and (3) the method that does not need resampling, denoted as Resample-M, Resample-M&T, and Resample-None, respectively. The comparison results show that Resample-M&T considerably underestimated the emission reduction of NOx during the lockdowns, Resample-None generates widely fluctuating estimates that blur the emission recovery trend during work resumption, and Resample-M clearly delineates the emission changes over the entire period. Based on the Resample-M results, the maximum emission reduction occurred during January to February 2020, for most cities, with an average decrease of 19.1 ± 9.4% compared to 2019. During April of 2020 when work resumption initiated to the end of 2020, the emissions rapidly bounced back for most cities, with an average increase of 12.6 ± 15.8% relative to those during the strict lockdowns. Consequently, we recommend using Resample-M for meteorological normalization, and the normalized NO2 concentration dynamics for each city provide important implications for future emission reduction.

A robust approach to deriving long-term daily surface NO2 levels across China: Correction to substantial estimation bias in back-extrapolation.

BACKGROUND: Long-term surface NO2 data are essential for retrospective policy evaluation and chronic human exposure assessment. In the absence of NO2 observations for Mainland China before 2013, training a model with 2013-2018 data to make predictions for 2005-2012 (back-extrapolation) could cause substantial estimation bias due to concept drift. OBJECTIVE: This study aims to correct the estimation bias in order to reconstruct the spatiotemporal distribution of daily surface NO2 levels across China during 2005-2018. METHODS: On the basis of ground- and satellite-based data, we proposed the robust back-extrapolation with a random forest (RBE-RF) to simulate the surface NO2 through intermediate modeling of the scaling factors. For comparison purposes, we also employed a random forest (Base-RF), as a representative of the commonly used approach, to directly model the surface NO2 levels. RESULTS: The validation against Taiwan's NO2 observations during 2005-2012 showed that RBE-RF adequately corrected the substantial underestimation by Base-RF. The RMSE decreased from 10.1 to 8.2 µg/m3, 7.1 to 4.3 µg/m3, and 6.1 to 2.9 µg/m3 in predicting daily, monthly, and annual levels, respectively. For North China with the most severe pollution, the population-weighted NO2 ([NO2]pw) during 2005-2012 was estimated as 40.2 and 50.9 µg/m3 by Base-RF and RBE-RF, respectively, i.e., 21.0% difference. While both models predicted that the national annual [NO2]pw increased during 2005-2011 and then decreased, the interannual trends were underestimated by >50.2% by Base-RF relative to RBE-RF. During 2005-2018, the nationwide population that lived in the areas with NO2 > 40 µg/m3 were estimated as 259 and 460 million by Base-RF and RBE-RF, respectively. CONCLUSION: With RBE-RF, we corrected the estimation bias in back-extrapolation and obtained a full-coverage dataset of daily surface NO2 across China during 2005-2018, which is valuable for environmental management and epidemiological research.

A nonparametric approach to filling gaps in satellite-retrieved aerosol optical depth for estimating ambient PM2.5 levels.

Satellite-retrieved aerosol optical depth (AOD) is commonly used to estimate ambient levels of fine particulate matter (PM2.5), though it is important to mitigate the estimation bias of PM2.5 due to gaps in satellite-retrieved AOD. A nonparametric approach with two random-forest submodels is proposed to estimate PM2.5 levels by filling gaps in satellite-retrieved AOD. This novel approach was employed to estimate the spatiotemporal distribution of daily PM2.5 levels during 2013-2015 in the Sichuan Basin of Southwest China, where the coverage rate of composite AOD retrieved by the Terra and Aqua satellites was only 11.7%. Based on the retrieved AOD and various covariates (including meteorological conditions and land use types), the first random-forest submodel (named AOD-submodel) was trained to fill the gaps in the AOD dataset, giving a cross-validation R2 of 0.95. Subsequently, the second random-forest submodel (named PM2.5-submodel) was trained to estimate the PM2.5 levels for unmonitored areas/days based on the gap-filled AOD, ground-monitored PM2.5 levels, and the covariates, and achieved a cross-validation R2 of 0.86. By comparing the complete and incomplete (i.e., without the days when AOD data were missing) estimates, we found that the monthly PM2.5 levels could be overestimated by 34.6% if the PM2.5 values coincident with AOD gaps were not considered. The newly developed approach is valuable for deriving the complete spatiotemporal distribution of daily PM2.5 from incomplete remote-sensing data, which is essential for air quality management and human exposure assessment.

Satellite-Based Estimates of Daily NO2 Exposure in China Using Hybrid Random Forest and Spatiotemporal Kriging Model.

A novel model named random-forest-spatiotemporal-kriging (RF-STK) was developed to estimate the daily ambient NO2 concentrations across China during 2013-2016 based on the satellite retrievals and geographic covariates. The RF-STK model showed good prediction performance, with cross-validation R2 = 0.62 (RMSE = 13.3 µg/m3) for daily and R2 = 0.73 (RMSE = 6.5 µg/m3) for spatial predictions. The nationwide population-weighted multiyear average of NO2 was predicted to be 30.9 ± 11.7 µg/m3 (mean ± standard deviation), with a slowly but significantly decreasing trend at a rate of -0.88 ± 0.38 µg/m3/year. Among the main economic zones of China, the Pearl River Delta showed the fastest decreasing rate of -1.37 µg/m3/year, while the Beijing-Tianjin Metro did not show a temporal trend ( P = 0.32). The population-weighted NO2 was predicted to be the highest in North China (40.3 ± 10.3 µg/m3) and lowest in Southwest China (24.9 ± 9.4 µg/m3). Approximately 25% of the population lived in nonattainment areas with annual-average NO2 > 40 µg/m3. A piecewise linear function with an abrupt point around 100 people/km2 characterized the relationship between the population density and the NO2, indicating a threshold of aggravated NO2 pollution due to urbanization. Leveraging the ground-level NO2 observations, this study fills the gap of statistically modeling nationwide NO2 in China, and provides essential data for epidemiological research and air quality management.

Spatiotemporal prediction of daily ambient ozone levels across China using random forest for human exposure assessment.

In China, ozone pollution shows an increasing trend and becomes the primary air pollutant in warm seasons. Leveraging the air quality monitoring network, a random forest model is developed to predict the daily maximum 8-h average ozone concentrations ([O3]MDA8) across China in 2015 for human exposure assessment. This model captures the observed spatiotemporal variations of [O3]MDA8 by using the data of meteorology, elevation, and recent-year emission inventories (cross-validation R2 = 0.69 and RMSE = 26 µg/m3). Compared with chemical transport models that require a plenty of variables and expensive computation, the random forest model shows comparable or higher predictive performance based on only a handful of readily-available variables at much lower computational cost. The nationwide population-weighted [O3]MDA8 is predicted to be 84 ± 23 µg/m3 annually, with the highest seasonal mean in the summer (103 ± 8 µg/m3). The summer [O3]MDA8 is predicted to be the highest in North China (125 ± 17 µg/m3). Approximately 58% of the population lives in areas with more than 100 nonattainment days ([O3]MDA8>100 µg/m3), and 12% of the population are exposed to [O3]MDA8>160 µg/m3 (WHO Interim Target 1) for more than 30 days. As the most populous zones in China, the Beijing-Tianjin Metro, Yangtze River Delta, Pearl River Delta, and Sichuan Basin are predicted to be at 154, 141, 124, and 98 nonattainment days, respectively. Effective controls of O3 pollution are urgently needed for the highly-populated zones, especially the Beijing-Tianjin Metro with seasonal [O3]MDA8 of 140 ± 29 µg/m3 in summer. To the best of the authors' knowledge, this study is the first statistical modeling work of ambient O3 for China at the national level. This timely and extensively validated [O3]MDA8 dataset is valuable for refining epidemiological analyses on O3 pollution in China.

Soil organic carbon of an intensively reclaimed region in China: Current status and carbon sequestration potential.

Land reclamation has been highly intensive in China, resulting in a large amount of soil organic carbon (SOC) loss to the atmosphere. Evaluating the factors which drive SOC dynamics and carbon sequestration potential in reclaimed land is critical for improving soil fertility and mitigating global warming. This study aims to determine the current status and factors important to the SOC density in a typical reclaimed land located in Eastern China, where land reclamation has been undergoing for centuries. A total of 4746 topsoil samples were collected from 2007 to 2010. The SOC density of the reclaimed land (3.18±0.05kgCm(-2); mean±standard error) is significantly lower than that of the adjacent non-reclaimed land (5.71±0.04kgCm(-2)) (p<0.05). A Random Forest model is developed and it captures the relationships between the SOC density and the environmental/anthropogenic factors (R(2)=0.59). The soil pH, land use, and elevation are the most important factors for determining SOC dynamics. In contrast, the effect of the reclamation age on the SOC density is negligible, where SOC content in the land reclaimed during years 1047-1724 is as low as that reclaimed during years 1945-2004. The scenario analysis results indicate that the carbon sequestration potential of the reclaimed lands may achieve a maximum of 5.80±1.81kgCO2m(-2) (mean±SD) when dryland is converted to flooded land with vegetable-rice cropping system and soil pH of ~5.9. Note that in some scenarios the methane emission substantially offsets the carbon sequestration potential, especially for continuous rice cropping system. With the optimal setting for carbon sequestration, it is estimated that the dryland reclaimed in the last 50years in China is able to sequester 0.12milliontons CO2 equivalent per year.

Estimating Emissions and Environmental Fate of Di-(2-ethylhexyl) Phthalate in Yangtze River Delta, China: Application of Inverse Modeling.

A georeferenced multimedia model was developed for evaluating the emissions and environmental fate of di-2-ethylhexyl phthalate (DEHP) in the Yangtze River Delta (YRD), China. Due to the lack of emission inventories, the emission rates were estimated using the observed concentrations in soil as inputs for the multimedia model solved analytically in an inverse manner. The estimated emission rates were then used to evaluate the environmental fate of DEHP with the regular multimedia modeling approach. The predicted concentrations in air, surface water, and sediment were all consistent with the ranges and spatial variations of observed data. The total emission rate of DEHP in YRD was 13.9 thousand t/year (95% confidence interval: 9.4-23.6), of which urban and rural sources accounted for 47% and 53%, respectively. Soil in rural areas and sediment stored 79% and 13% of the total mass, respectively. The air received 61% of the total emissions of DEHP but was only associated with 0.2% of the total mass due to fast degradation and intensive deposition. We suggest the use of an inverse modeling approach under a tiered risk assessment framework to assist future development and refinement of DEHP emission inventories.