Author: Latest Results

Abstract

Atmospheric boundary layer (ABL) structure and dynamics are important aspects to consider in human health. The ABL is characterized by a high degree of spatial and temporal variability that hinders their understanding. This paper aims to provide a comprehensive overview of machine learning (ML) methodologies, encompassing deep learning and ensemble approaches, within the scope of ABL research. The goal is to highlight the challenges and opportunities of using ML in turbulence modeling and parameterization in areas such as atmospheric pollution, meteorology, and renewable energy. The review emphasizes the validation of results to ensure their reliability and applicability. ML has proven to be a valuable tool for understanding and predicting how ABL spatial and seasonal variability affects pollutant dispersion and public health. In addition, it has been demonstrated that ML can be used to estimate several variables and parameters, such as ABL height, making it a promising approach to enhance air quality management and urban planning.

Abstract

In this research, the impact of climate change on annual maximum daily precipitation (AMP) during the period 2024-2050 and the evaluation of flood risk in Ilam province have been investigated using the outputs of CMIP6 models. After identifying the top-performing CMIP6 models, the annual maximum daily precipitation for return periods of 2, 10, 100, and 1000 years was determined based on fitting 65 probability distributions, considering the 1992-2018 observational period and future periods (SSP1-2.6 and SSP5-8.5). The study also integrates hazard, vulnerability, and exposure components to assess flood risk at various return periods (2, 10, 100, and 1000 years). Vulnerability and exposure assessment involved the selection of indicators such as hamlet density (HD), land use (LU), population density (PD), land cover (LC), SAVI vegetation index, digital elevation model (DEM), slope, soil erodibility (SE), drainage density (DD), and distance from drainage (DFD). The AHP-Entropy weight method was employed to determine the relative importance of each component. The results indicated that changes in annual maximum daily precipitation and flood risk under the SSP1 scenario did not differ significantly from the observational period, exhibiting similar trends and patterns. However, conditions under the SSP5 scenario differed, showing significant fluctuations in annual maximum daily precipitation, particularly for the 1000-year return period, resulting in increased high-risk areas. For instance, in the SSP5-8.5 scenario, the moderate-risk area for the 1000-year return period expanded from 7% to over 13%, and a new high-risk classification arose, covering 5% of the province’s area, which is unprecedented in the other scenarios.

Abstract

In this study, the performances of 40 Coupled Model Intercomparison Project Phase 6 are evaluated against observational data at synoptic stations in Iran using various evaluation criteria. The results reveal diverse model accuracy across different climate conditions and criteria, emphasizing particularly notable disparities in the nonstationarity R criterion compared to others. Although according to the ranking of the raw and bias-corrected outputs of CMIP6 GCMs for Iran, the NorESM2-MM, AWI-ESM-1-1-LR, and MPI-ESM1-2-LR models are consistently among the top six ranked models for precipitation in both raw and corrected outputs. For temperature, MPI-ESM1-2-LR, TaiESM1, INM-CM4-8, and IITM-ESM are consistently among the top six models for both the raw and bias-corrected outputs of CMIP6 GCMs. The Bias correction methods, including quantile mapping and linear scaling, integrated with Bayesian model averaging, were applied. While quantile mapping demonstrates superior performance and less disparity than linear scaling, it proves ineffective for correcting biases at stations with bias nonstationarity over time. The RMSE for monthly precipitation ranges from almost 0 to 200 mm, with a large RMSE value related to the high precipitation stations, and the monthly temperature exhibits a range of 0 to 4 °C. The use of a multi-model ensemble improves accuracy compared to individual models, resulting in a reduction in the differences between the minimum and maximum RMSE values from 178.6 to 91.0. Additionally, the range for mean absolute error decreases from 126.9 to 93.3, and the difference in the correlation coefficient narrows from 0.9 to 0.42. Averaging models after bias correction prevents significant fluctuations while maintaining higher accuracy, in contrast to the second method, which involves bias-correcting models after averaging.

Abstract

Leaf Area Index (LAI) is a critical parameter in terrestrial ecosystems, with high spatial resolution data being extensively utilized in various research studies. However, LAI data under future scenarios are typically only available at 1° or coarser spatial resolutions. In this study, we generated a dataset of 0.05° LAI (F0.05D-LAI) from 1983–2100 in a high spatial resolution using the LAI Downscaling Network (LAIDN) model driven by inputs including air temperature, relative humidity, precipitation, and topography data. The dataset spans the historical period (1983–2014) and future scenarios (2015–2100, including SSP-126, SSP-245, SSP-370, and SSP-585) with a monthly interval. It achieves high accuracy (R² = 0.887, RMSE = 0.340) and captures fine spatial details across various climate zones and terrain types, indicating a slightly greening trend under future scenarios. F0.05D-LAI is the first high-resolution LAI dataset and reveals the potential vegetation variation under future scenarios in China, which benefits vegetation studies and model development in earth and environmental sciences across present and future periods.

Abstract

Due to the length and complexity of supply chains, changes in food consumption patterns in one metropolitan region can transform production patterns in other sectors and countries. Therefore, they cause complex synergies and trade-offs between environmental and socioeconomic goals at the local and global level. We argue that the dissemination of cross-scale consumption-based simulation models is crucial to investigate these complex multilevel effects and promote sustainable food systems.

Abstract

Comprehensively analyzing carbon emissions in the Central Plains Urban Agglomeration (CPUA) of China is an effective case study for promoting sustainable development and supporting China in achieving its carbon peak targets. This study applies an energy balance sheet downscaling method to estimate the carbon emissions of 30 cities in the CPUA from 2000 to 2021, examining trends in carbon emissions and land carbon sequestration. Key influencing factors of carbon emissions are identified using knowledge graph technology, and the spatiotemporal effects of these factors are analyzed using Geographically and Temporally Weighted Regression Geographically Weighted Regression and Multiscale Geographically Weighted Regression models. The study shows that carbon emissions in the CPUA increased from 452.639 million tons in 2000 to 1737.107 million tons in 2021, with a growth rate that declined from 24.18% to 3.06%. Fossil fuel consumption and cultivated land were major carbon sources, while forest land was a significant carbon sink. The spatial pattern of carbon emissions predominantly showed lower values in the south and higher values in the north, with significant clustering in high emission areas. Population size, per capita gross domestic product, technological progress, and energy consumption intensity had significant impacts on the urban agglomeration’s carbon emissions. However, the impact was influenced by fluctuations driven by government policies, industrial and energy structures, and other factors. This study not only provides critical insights for China’s low-carbon development but also offers valuable lessons for other developing countries facing similar challenges. Urban agglomeration planning should focus on optimizing energy and industrial structures, promoting green technology, and designing tailored carbon reduction policies to achieve sustainable and green development.

This report summarises the main outcomes of the 4th edition of the workshop on Machine Learning (ML) for Earth System Observation and Prediction (ESOP / ML4ESOP) co-organised by the European Space Agency (ESA) and the European Centre for Medium-Range Weather Forecasts (ECMWF). The 4-day workshop was held on 7-10 May 2024 in a hybrid format at the ESA Frascati site with an interactive online component, featuring over 46 expert talks with a record number of submissions and about 800 registrations. The workshop offered leading experts a platform to exchange on the current opportunities, challenges and future directions for applying ML methodology to ESOP. To structure the presentations and discussions, the workshop featured five main thematic areas covering key topics and emerging trends. The most promising research directions and significant outcomes were identified by each thematic area’s Working Group and are the focus of this document.

Abstract

As the world’s largest energy consumer and carbon emitter, the task of carbon emission reduction is imminent. In order to realize the dual-carbon goal at an early date, it is necessary to study the key factors affecting China’s carbon emissions and their non-linear relationships. This paper compares the performance of six machine learning algorithms to that of traditional econometric models in predicting carbon emissions in China from 2011 to 2020 using panel data from 254 cities in China. Specifically, it analyzes the comparative importance of domestic economic, external economic, and policy uncertainty factors as well as the nonparametric relationship between these factors and carbon emissions based on the Extra-trees model. Results show that energy consumption (ENC) remains the root cause of increased carbon emissions among domestic economic factors, although government intervention (GOV) and digital finance (DIG) can significantly reduce it. Next, among the external economic and policy uncertainty factors, foreign direct investment (FDI) and economic policy uncertainty (EPU) are important factors influencing carbon emissions, and the partial dependence plots (PDPs) confirm the pollution haven hypothesis and also reveal the role of EPU in reducing carbon emissions. The heterogeneity of factors affecting carbon emissions is also analyzed under different city sizes, and it is found that ENC is a common driving factor in cities of different sizes, but there are some differences. Finally, appropriate policy recommendations are proposed by us to help China move rapidly towards a green and sustainable development path.

Abstract

Hydrological models are used to assess natural and man-made changes in watersheds worldwide. Proper input data collection and handling are essential to reduce simulation uncertainty. Thus, this study reviews the sources of physical and hydroclimatic data, used in the last 5 years, from 55 articles that applied the SWAT model in Brazil. Most studies took place in the Atlantic Forest biome (20), followed by Cerrado (14), Amazon (11), and Caatinga (10). Worth noting that there are no studies published in the Pantanal and Pampa biomes. National databases (INPE, INMET, EMPRAPA, and ANA) are the most used in data acquisition process, followed by regional databases, more applied in smaller basins. Global databases are more sought after in studies of large basins due to their low spatial resolution. National climate data have low spatial density and are only available in five states at the regional level, so satellite data and reanalysis are viable alternatives in regions with little climate monitoring. Future research directions include (1) evaluating and comparing available data, (2) using high-resolution imagery to map land use in small catchments, (3) expanding the model’s database of vegetation parameters to cover all classes identified in high-resolution images, (4) create a database at regional level in the states, (5) develop software to manage hydroclimatic information, and (6) continuously monitor the quality of water bodies.

Abstract

There are millions of river barriers worldwide, ranging from wooden locks to concrete dams, many of which form associated impoundments to store water in small ponds or large reservoirs. Besides their benefits, there is growing recognition of important environmental and social trade-offs related to these artificial structures. However, global datasets describing their characteristics and geographical distribution are often biased towards particular regions or specific applications, such as hydropower dams affecting fish migration, and are thus not globally consistent. Here, we present a new river barrier and reservoir database developed by the Global Dam Watch (GDW) consortium that integrates, harmonizes, and augments existing global datasets to support large-scale analyses. Data curation involved extensive quality control processes to create a single, globally consistent data repository of instream barriers and reservoirs that are co-registered to a digital river network. Version 1.0 of the GDW database contains 41,145 barrier locations and 35,295 associated reservoir polygons representing a cumulative storage capacity of 7,420 km³ and an artificial terrestrial surface water area of 304,600 km².