The spatial distribution of soil organic carbon (SOC) serves as critical geographic information for assessing ecosystem services, climate change mitigation, and optimal agriculture management. Digital mapping of SOC is challenging due to the complex relationships between the soil and its environment. Except for the well-known terrain and climate environmental covariates, vegetation that interacts with soils influences SOC significantly over long periods. Although several remote-sensing-based vegetation indices have been widely adopted in digital soil mapping, variables indicating long term vegetation growth have been less used. Vegetation phenology, an indicator of vegetation growth characteristics, can be used as a potential time series environmental covariate for SOC prediction. A CNN-LSTM model was developed for SOC prediction with inputs of static and dynamic environmental variables in Xuancheng City, China. The spatially contextual features in static variables (e.g., topographic variables) were extracted by the convolutional neural network (CNN), while the temporal features in dynamic variables (e.g., vegetation phenology over a long period of time) were extracted by a long short-term memory (LSTM) network. The ten-year phenological variables derived from moderate-resolution imaging spectroradiometer (MODIS) observations were adopted as predictors with historical temporal changes in vegetation in addition to the commonly used static variables. The random forest (RF) model was used as a reference model for comparison. Our results indicate that adding phenological variables can produce a more accurate map, as tested by the five-fold cross-validation, and demonstrate that CNN-LSTM is a potentially effective model for predicting SOC at a regional spatial scale with long-term historical vegetation phenology information as an extra input. We highlight the great potential of hybrid deep learning models, which can simultaneously extract spatial and temporal features from different types of environmental variables, for future applications in digital soil mapping.

Coronavirus disease 2019 (COVID-19) has strongly impacted society since it was first reported in mainland China in December 2020. Understanding its spread and consequence is crucial to pandemic control, yet difficult to achieve because we deal with a complex context of social environment and variable human behaviour. However, few efforts have been made to comprehensively analyse the socio-economic influences on viral spread and how it promotes the infection numbers in a region. Here we investigated the effect of socio-economic factors and found a strong linear relationship between the gross domestic product (GDP) and the cumulative number of confirmed COVID-19 cases with a high value of R2 (between 0.57 and 0.88). Structural equation models were constructed to further analyse the social-economic interaction mechanism of the spread of COVID-19. The results show that the total effect of GDP (0.87) on viral spread exceeds that of population influx (0.58) in the central cities of mainland China and that the spread mainly occurred through its interplay with other factors, such as socio-economic development. This evidence can be generalized as socio-economic factors can accelerate the spread of any infectious disease in a megacity environment. Thus, the world is in urgent need of a new plan to prepare for current and future pandemics.