Search

The dynamic and non-linear nature of complex chemical processes often leads to low prediction accuracy of key quality variables by traditional soft sensors, thus affecting the overall system control accuracy and operational efficiency. Therefore, this paper proposes a semi-supervised soft sensor modelling method based on improved the northern goshawk optimization (INGO)-variable mode decomposition (VMD)-echo state network (ESN). Firstly, a new semi-supervised fusion method is proposed to address the problem of model training difficulty due to the scarcity of labelled samples and process dynamics, which reconstructs the sample dataset by fusing labelled and unlabelled samples into more representative new samples, improving the model's generalization ability. Secondly, for the noise interference present in the reconstructed data, the input data is denoised using the VMD method to improve the quality of data. Then, a soft sensor model is built based on ESN. Additionally, the denoising and prediction performance of VMD and ESN is significantly affected by parameters, therefore the paper utilizes the INGO algorithm to achieve parameter rectification for VMD and ESN. Finally, the method is validated based on actual sulphur recovery data from a refinery. The results demonstrate that the method effectively mitigates the impact of dynamics and nonlinearity in the complex chemical process which enhances prediction accuracy. [ABSTRACT FROM AUTHOR]

In this study, we investigated the urbanization‐induced summer rainfall changes in the Yangtze River Delta (YRD) by analyzing long‐term observations and numerical simulations. The observation‐based analysis showed that long‐term urbanization increased the region's summer rainfall, particularly through the intensification of heavy rainfall, which is noted as the urban rain island (URI) effect. A series of numerical sensitivity experiments with three historical land use and land cover scenarios (1990, 2000, and 2010) were designed to further understand the urbanization impacts on rainfall. The observed URI effect was well reproduced by the numerical simulations, and on average, urban expansion during 1990–2010 increased summer rainfall over urban areas by 51.91 mm. The URI effect slightly weakened in the late stage of urbanization (2000–2010) compared to the early stage (1990–2000). We conclude that the strengthening of precipitation‐inhibiting effects during the late period offset the precipitation‐enhancing effects, which led to the weakening of the URI effect. Plain Language Summary: In this study, urbanization‐induced summertime precipitation changes over the Yangtze River Delta (YRD) region were investigated using both long‐term observational data and numerical model experiments. Observations showed that over the past decades, the summer precipitation over the YRD region has generally experienced a significant increasing trend, which was mainly caused by the intensification of strong‐intensity rainfalls. We further showed that urbanization in the region has played key roles in the trend by an urban rain island (URI) effect. The URI effect was found to have slightly weakened in the late stage of the study period (2000–2010) compared to the early stage (1990–2000). We also found that precipitation‐inhibiting effects (e.g., atmospheric humidity loss), overshadowed the precipitation‐enhancing effects (e.g., the urban heat island effect), which resulted in the weakened URI effect in the late stage. Key Points: The urban modification on summertime rainfall in YRD was investigated based on both long‐term observations and numerical experimentsLong‐term urbanization increased summer rainfall, yet the urban rain island (URI) effect slightly weakened in the late stage of urbanizationPrecipitation‐inhibiting effects strengthened in the late stage of urbanization and led to a weakened URI effect [ABSTRACT FROM AUTHOR]

This study uses dynamical and statistical methods to understand end‐of‐century mean changes to Sierra Nevada snowpack. Dynamical results reveal that middle‐elevation watersheds experience considerably more rain than snow during winter, leading to substantial snowpack declines by spring. Despite some high‐elevation watersheds receiving slightly more snow in January and February, the warming signal still dominates across the wet season and leads to notable declines by springtime. A statistical model is created to mimic dynamical results for 1 April snowpack, allowing for an efficient downscaling of all available general circulation models from the Coupled Model Intercomparison Project phase 5. For all general circulation models and emission scenarios, dramatic 1 April snowpack loss occurs at elevations below 2,500 m, despite increased precipitation in many general circulation models. Only 36% (±12%) of historical 1 April total snow water equivalent volume remains at the century's end under a "business‐as‐usual" emission scenario, with 70% (±12%) remaining under a realistic "mitigation" scenario. Plain Language Summary: The Sierra Nevada is one of California's most beloved natural treasures, and mountain snowpack snow is an important water resource. As climate change continues, scientists and water managers have become increasingly concerned about the future of the frozen reservoir Californian depend on. Global climate models are the best tools we have for projecting future climate change. But they are too coarse in spatial resolution to accurately simulate future climate in topographically complex areas like the Sierra Nevada, where different elevations experience different climatic conditions. This study utilizes an innovative hybrid high‐resolution downscaling method to understand spatial and temporal patterns of snowpack changes for certain watersheds and different elevations in the Sierra Nevada. A full range of global climate models and future greenhouse emission scenarios are investigated to quantify the uncertainties. Dramatic decreases in total Sierra Nevada snowpack are projected by century's end, even under a realistic mitigation emission scenario. The results are intended to provide water resource and management agencies information to help plan for the impacts of future climate change on the reliability and inhomogeneity of water supplies. Key Points: Dynamically downscaled projections are used to understand spatial and temporal patterns of snowpack changes for Sierra Nevada watershedsA hybrid dynamical‐statistical downscaling technique is developed to project 1 April snowpack change by century's end for all GCMs and RCPsDramatic decreases in total snowpack volume are projected by century's end, even under a realistic mitigation emission scenario [ABSTRACT FROM AUTHOR]

The dynamic character of an enstrophy-based diagnostic, previously used in the study of atmospheric blocking, is examined here, in near-term future simulations from the Institut Pierre Simon Laplace Climate Model version 4 (IPSL-CM4) and version 5 (IPSL-CM5) climate models of the Northern Hemisphere flow for moderate climate change scenarios. Previous research has shown that integrated regional enstrophy (IE) increases during blocking onset and decay, which is a reflection of planetary-scale instability. In addition, IE has been shown previously to increase during flow regime transitions in general, even those not associated with blocking events. Here, a 31-year IE diagnostic time series is examined for changes in short term (5-40 days) planetary-scale variability that may correspond flow regime changes in an increased carbon dioxide environment. The time-series analysis herein indicates that the IE diagnostic provides evidence for approximately 30-35 atmospheric flow regime transitions per year in a warmer climate, which is similar to that of the control run and the latest 30-year observed climate, as derived from re-analyses. This result has implications regarding the predictability of weather in a warmer world. [ABSTRACT FROM AUTHOR]

In this study (Part I), the mid-twenty-first-century surface air temperature increase in the entire CMIP5 ensemble is downscaled to very high resolution (2 km) over the Los Angeles region, using a new hybrid dynamical-statistical technique. This technique combines the ability of dynamical downscaling to capture finescale dynamics with the computational savings of a statistical model to downscale multiple GCMs. First, dynamical downscaling is applied to five GCMs. Guided by an understanding of the underlying local dynamics, a simple statistical model is built relating the GCM input and the dynamically downscaled output. This statistical model is used to approximate the warming patterns of the remaining GCMs, as if they had been dynamically downscaled. The full 32-member ensemble allows for robust estimates of the most likely warming and uncertainty resulting from intermodel differences. The warming averaged over the region has an ensemble mean of 2.3°C, with a 95% confidence interval ranging from 1.0° to 3.6°C. Inland and high elevation areas warm more than coastal areas year round, and by as much as 60% in the summer months. A comparison to other common statistical downscaling techniques shows that the hybrid method produces similar regional-mean warming outcomes but demonstrates considerable improvement in capturing the spatial details. Additionally, this hybrid technique incorporates an understanding of the physical mechanisms shaping the region's warming patterns, enhancing the credibility of the final results. [ABSTRACT FROM AUTHOR]