Soil organic carbon (SOC) is a key component of the global carbon cycle yet it is not well represented in Earth system models to accurately predict global carbon dynamics in response to climate change. This novel study integrated deep learning, data assimilation, 25,444 vertical soil profiles, and the Community Land Model version 5 (CLM5) to optimize the model representation of SOC over the conterminous United States. We firstly constrained parameters in CLM5 using observations of vertical profiles of SOC in both a batch mode (i.e., using all individual soil layers in one batch) and at individual sites (i.e., site-by-site). The estimated parameter values from the site-by-site method were then either randomly sampled (i.e., random-sampling) to generate continentally homogeneous (i.e., constant) parameter values or maximally preserved for their spatially heterogeneous distributions (i.e., varying parameter values to match the spatial patterns from the site-by-site method) so as to optimize spatial representation of SOC in CLM5 through a deep learning technique (neural networking) over the conterminous United States. Comparing modeled spatial distributions of SOC by CLM5 to observations yielded increasing predictive accuracy from default CLM5 settings (R2 = 0.32) to randomly sampled (0.36), one-batch estimated (0.43), and deep learning optimized (0.62) parameter values. While CLM5 with parameter values derived from random-sampling and one-batch methods substantially corrected the overestimated SOC storage by that with default model parameters, there were still considerable geographical biases. CLM5 with the spatially heterogeneous parameter values optimized from the neural networking method had the least estimation error and less geographical biases across the conterminous U.S. Our study indicated that deep learning in combination with data assimilation can significantly improve the representation of SOC by complex land biogeochemical models.
28 September 2020 in Proceedings of the National Academy of Sciences
Significance: By linking seasonality of climate and changing human behavior, we demonstrate that collaboration on global efforts for prompt and intensive intervention is fundamental to coping with future pandemic waves of COVID-19. We propose that this collaboration can be started in locations with typically high population density and international travel, followed by other high-risk locations. We believe this tiered intervention strategy can greatly integrate global efforts and is effective and practical to improve the global emergency response to COVID-19 and many other infectious diseases.
The increasingly frequent flooding imposes tremendous and long-lasting damages to lives and properties in impoverished rural areas. Rapid, accurate, and large-scale flood mapping is urgently needed for flood management, and to date has been successfully implemented benefiting from the advancement in remote sensing and cloud computing technology. Yet, the effects of agricultural emergency response to floods have been limitedly evaluated by satellite-based remote sensing, resulting in biased post-flood loss assessments. Addressing this challenge, this study presents a method for monitoring post-flood agricultural recovery using Sentinel-1/2 imagery, tested in three flood-affected main grain production areas, in the middle and lower Yangtze and Huai River, China. Our results indicated that 33~72% of the affected croplands were replanted and avoided total crop failures in summer 2020. Elevation, flood duration, crop rotation scheme, and flooding emergency management affect the post-flood recovery performance. The findings also demonstrate rapid intervention measures adjusted to local conditions could reduce the agricultural failure cost from flood disasters to a great extent. This study provides a new alternative for comprehensive disaster loss assessment in flood-prone agricultural regions, which will be insightful for worldwide flood control and management.
Nighttime light remote sensing has aroused great popularity because of its advantage in estimating socioeconomic indicators and quantifying human activities in response to the changing world. Despite many advances that have been made in method development and implementation of nighttime light remote sensing over the past decades, limited studies have dived into answering the question: Where does nighttime light come from? This hinders our capability of identifying specific sources of nighttime light in urbanized regions. Addressing this shortcoming, here we proposed a parcel-oriented temporal linear unmixing method (POTLUM) to identify specific nighttime light sources with the integration of land use data. Ratio of root mean square error was used as the measure to assess the unmixing accuracy, and parcel purity index and source sufficiency index were proposed to attribute unmixing errors. Using the Visible Infrared Imaging Radiometer Suite (VIIRS) nighttime light dataset from the Suomi National Polar-Orbiting Partnership (NPP) satellite and the newly released Essential Urban Land Use Categories in China (EULUC-China) product, we applied the proposed method and conducted experiments in two China cities with different sizes, Shanghai and Quzhou. Results of the POTLUM showed its relatively robust applicability of detecting specific nighttime light sources, achieving an rRMSE of 3.38% and 1.04% in Shanghai and Quzhou, respectively. The major unmixing errors resulted from using impure land parcels as endmembers (i.e., parcel purity index for Shanghai and Quzhou: 54.48%, 64.09%, respectively), but it also showed that predefined light sources are sufficient (i.e., source sufficiency index for Shanghai and Quzhou: 96.53%, 99.55%, respectively). The method presented in this study makes it possible to identify specific sources of nighttime light and is expected to enrich the estimation of structural socioeconomic indicators, as well as better support various applications in urban planning and management.