bLS Model Research Articles

A NIRS-based recognition of coal and rock using convolution-multiview broad learning system

Achieving high production in the top coal caving process from thick coal seams is crucial. Thus, the timely decision of when to stop caving poses an urgent challenge to impact the mining loss rate and cost recovery. To address this issue, an innovative recognition system has been developed using Near-Infrared Spectroscopy (NIRS) technology. It stands out for its on-site usability, it enables rapid data collection and local recognition at the longwall face. Furthermore, to overcome the limitations of existing methods in adapting to variations in spectral data quality during on-site collection and the lack of integration of spectral data across different feature processing stages, a coal-rock recognition method has been developed which can ignore the influence of acquisition factors(granularity, light source angle, and detection sensor angle). This method incorporates the features of convolution and multi-view into the BLS model, the designed model structure exhibits a remarkable recognition accuracy of 99.78 %. The model was deployed into the recognition system, and experimental tests were conducted on the working face. The results showed that the recognition system can effectively identify the entire coal-caving process and achieve a recognition accuracy of 92.3 %. This capability is crucial for determining the optimal point to stop roof caving.

Estimation of full-scale performance of energy-saving devices using Boundary Layer Similarity model

AbstractThe recent global trend toward decarbonization is also occurring in the maritime industry and there is an urgent need to improve the fuel efficiency of ships. Various energy-saving devices (ESDs) are adopted for this purpose. However, because of the difference in the boundary layer thickness between full-scale and model-scale, it is difficult to estimate the actual performance of ESDs in a tank test. As a solution to overcome this difficulty, the Boundary Layer Similarity model (BLS model) is proposed in which only the stern part of the hull is extracted to shorten the model length and to make its boundary layer thickness equivalent to that of a full-scale ship. By using this BLS model, the performance of ESDs on a full-scale can be estimated in a model test. In the present paper, the applicability of the BLS model is investigated by CFD (Computational Fluid Dynamics) simulations of performance estimation of an energy-saving fin in different locations for a bulk carrier. It is found that the BLS model is capable of predicting the full-scale performance of the fins by the model-scale simulations. Moreover, the flow fields affected by the fins with the BLS model are similar to those of full-scale. It is expected that the use of the BLS model enables the prediction of the full-scale performance of ESDs in a model test.

Artistic Guidance and Emotional Expression Pathways in Piano Performance - Based on Deep Score Characterization Fusion

Abstract In the evolving domain of artificial intelligence and deep learning, the pedagogical applications of piano performance— specifically its artistic instruction and emotional expressiveness—have garnered increasing scholarly attention. This research leverages MIDI music file formats to mine necessary data, engaging in a detailed examination of the structural and characteristic elements of MIDI files. To optimize the precision of mathematical models applied in this study, MIDI music data underwent preliminary preprocessing steps, including hexadecimal encoding and feature filtering, which facilitated the transformation of MIDI features into vectors representing emotional attributes. The study introduced the development of a BiLSTM_BLS model tailored to articulate the nuances of piano performance and emotional expression. This model synthesis integrates features reflective of emotional states induced by piano playing. A mathematically derived loss function was utilized to gauge the model’s fidelity, thereby enabling an assessment of its efficacy in the realms of artistic instruction and emotional conveyance in piano performance. Findings indicate a proximity between the emotional states of Anger (0.392) and Stress (0.385), with Depressed (0.422) presenting a slightly elevated distance from these states. Moreover, the BiLSTM_BLS model achieved a performance score of 3.214 in the evaluation of artistic expression, which corresponds to 64.28 on a standardized 100-point scale. This investigation contributes to the enhancement of musical skills and theoretical knowledge among pianists, promotes cognitive development, augments emotional expression, and nurtures creativity.

Wind Speed Prediction Based on VMD-BLS and Error Compensation

As one of the fastest-growing new energy sources, wind power technology has attracted widespread attention from all over the world. In order to improve the quality of wind power generation, wind speed prediction is an indispensable task. In this paper, an error correction-based Variational Mode Decomposition and Broad Learning System (VMD-BLS) hybrid model is proposed for wind speed prediction. First, the wind speed is decomposed into multiple components by the VMD algorithm, and then an ARMA model is established for each component to find the optimal number of sequence divisions. Second, the BLS model is used to predict each component, and the prediction results are summed to obtain the wind speed forecast value. However, in some traditional methods, there is always time lag, which will reduce the forecast accuracy. To deal with this, a novel error correction technique is developed by utilizing BLS. Through verification experiment with actual data, it proves that the proposed method can reduce the phenomenon of prediction lag, and can achieve higher prediction accuracy than traditional approaches, which shows our method’s effectiveness in practice.

Calculation of NH3 Emissions, Evaluation of Backward Lagrangian Stochastic Dispersion Model and Aerodynamic Gradient Method

Two campaigns measuring ammonia (NH3) emissions with different measurement techniques were performed on a large grass field (26 ha) after the application of liquid animal manure. The aim was to compare emissions from a confined area estimated from either (i) concentration measurements, both point and line-integrated measurements, combined with backward Lagrangian stochastic (bLS) dispersion modeling or by (ii) estimation of the vertical flux by the aerodynamic gradient method (AGM) with and without footprint correction approximated by the bLS model estimates of the flux footprint. The objective of the comparison is to establish the best practice to derive NH3 emissions from a large field. NH3 emissions derived from bLS agreed well when comparing point and line-integrated measurements. Simple point measurements combined with bLS yield good emission estimations for the confined area. Without footprint correction, the AGM underestimates the emissions by up to 9% compared to the footprint-corrected AGM results. The sensitivity of the measurement methods makes it possible to quantify NH3 emissions with diurnal patterns even five days after a field application of liquid animal manure under wet conditions. The bLS model proves to be a strong tool to determine the NH3 emissions from point concentration measurements inside a large field after a slurry application.

Uncertainty in using dispersion models to estimate methane emissions from manure lagoons in dairies

Manure lagoons in dairies make significant contributions to emissions of methane, a major greenhouse gas; however, there is a high level of uncertainty in these emissions. In this paper, we apply dispersion models in combination with a unique sampling strategy, which involves stationary measurements at multiple points around the lagoons to estimate methane emissions from manure lagoons located in two dairies, one in Southern California and the other in Central California. We then estimate the uncertainty associated with the results from this approach by interpreting our measurements with two dispersion models, a numerical Eulerian model (EN) and a backward Lagrangian stochastic (bLS) model. The range of emissions inferred from these two models is a measure of uncertainty related to differences in the formulation of these models. We also estimate 95% confidence intervals for the emission estimates from each of the models by bootstrapping the residuals between model estimates and measurements. Both models explain more than 85% of the variance of the methane concentrations measured at the two dairies. For the Southern California dairy (1066 milking cows), the 95% confidence interval of the emission rate inferred by the EN model is 282 kg/d to 482 kg/d. The corresponding interval for the bLS model is 174 kg/d to 246 kg/d. The best fit value from the EN model is about 1.9 times that from the bLS model. For the Central California dairy (3200 milking cows), the best emission rates from the two models differ by about 10%. The emission rate inferred by the EN model ranges from 3198 kg/d to 5312 kg/d, and that from the bLS ranges from 2943 kg/d to 4977 kg/d. Our results are consistent with methane emissions derived from information on dairy cow population and manure management practices at these two dairies. These results suggest this measurement technique is easily deployed and effective at quantifying uncertainties associated with methane emissions from manure lagoons.

Comparisons of forward-in-time and backward-in-time Lagrangian stochastic dispersion models for micro-scale atmospheric dispersion

ABSTRACTLagrangian stochastic dispersion models are sometimes run in backward mode to estimate air emissions from different types of sources including area sources. The forward-in-time and backward-in-time Lagrangian stochastic (fLS and bLS) dispersion models may not result in the same estimates. The two models were compared under different atmospheric conditions in micro-scale applications. They are equivalent in a steady-state and horizontally homogeneous atmosphere in many features including estimating concentration at a point, using surface receptor, and prerunning the models. Although bLS shows better computational efficiency, it has a larger uncertainty in results due to the use of surface receptors. In a non-steady-state wind field, the two models show opposite transition trends when the wind fields experience a step change. Under sinusoidal-varying winds, the two models show different shapes of the predicated concentration curves. The normalized differences of the mean concentrations mainly increase with the receptor height when the source-receptor distance is fixed. A controlled methane release experiment was conducted to investigate the behaviors of the two models driven by real wind fields. The correlation coefficient between model-predicted concentrations is 0.95. The model-predicted (forward model) and measured concentrations show similar trend with a correlation coefficient of 0.70. The bLS model estimates larger peak concentrations than that fLS model under the same emission rate. The best-fitted results of the fLS and bLS models give recovery ratios of 1.1558 and 0.9675, respectively, which are better than that using a constant 15-min averaged wind (0.7922).Implications: There are large uncertainties and difficulties in quantification of fugitive air emissions from area sources such as landfills, agriculture, and industry sections. Lagrangian stochastic dispersion model is a versatile tool for these applications with the capability of near-field description and good efficiency. Backward models are usually used to estimate emission rates from area sources due to high computing efficiencies. But they may not result in the same estimate as the forward models due to factors involving model realization and input parameters. It is necessary to investigate the discrepancies to select the best model with minimal uncertainty in the results.

Ammonia emissions from irrigated pastures on Solonetz in Victoria, Australia

This paper reports ammonia (NH3) emissions from irrigated, fertilized pastures grazed intensively by dairy cattle in Victoria, Australia. Irrigation bays (65 × 365 m) were grazed in rotation by 315 dairy cattle and daily emissions were measured in summer and autumn. After grazing for a few days, the bays were fertilized with urea at 50 kg N ha−1 and irrigated with 50 mm of water. Passive NH3 samplers were used to measure horizontal fluxes of NH3 from different sectors of the bays directly and the corresponding surface emissions were calculated from the sampler data using a backward Lagrangian stochastic (bLs) model of atmospheric dispersion. Ammonia emissions from the whole herd during the grazing phases were 14.8 kg NH3−N in summer, but only 2.0 kg NH3−N in autumn, corresponding to emission factors of 12% and 1% for an assumed annual input of nitrogen (N) in excreta of 150 kg N head−1 yr−1. Only 1% of the urea-N was lost through NH3 volatilization when irrigation followed fertilization immediately, but 6% was lost when irrigation was delayed for 3 days. The bLs model appears to be a useful tool for assessing gas emissions from dairy farm operations.

BLS모형 기반 2028년 스포츠건강 고용시장 예측

BLS모형 기반 2028년 스포츠건강 고용시장 예측

Comparing methane emissions estimated using a backward-Lagrangian stochastic model and the eddy covariance technique in a beef cattle feedlot

Accurate methodologies to measure emissions of greenhouse gases (GHG) from livestock systems are necessary to improve the emission coefficients used in national GHG inventories and to evaluate mitigation strategies. The objective of this study was to compare methane (CH4) emissions estimated using the eddy covariance (EC) technique and a backward-Lagrangian stochastic (bLS) model. A closed-path EC system was used to measure CH4 fluxes in a commercial beef cattle feedlot. The EC fluxes were scaled from the feedlot to the animal scale using a footprint analysis. The EC measurements of CH4 concentration and wind data were used with the bLS model to infer CH4 emissions. The average CH4 emissions (±standard deviation) during the experiment were 87 (±30) g animal−1 d−1 and 85 (± 27) g animal−1 d−1 for EC and bLS techniques, respectively. These values are consistent with the results from previous studies with similar animal and feed characteristics. Both techniques were able to capture a pronounced daytime and nighttime variation in CH4 emissions, with higher CH4 emissions during the day and lower emissions at night. Our results indicate that the eddy covariance technique combined with footprint models can be successfully used to accurately measure enteric CH4 from cattle.

Ammonia emissions from an anaerobic digestion plant estimated using atmospheric measurements and dispersion modelling

Anaerobic digestion (AD) is becoming increasingly implemented within organic waste treatment operations. The storage and processing of large volumes of organic wastes through AD has been identified as a significant source of ammonia (NH3) emissions, however the totality of ammonia emissions from an AD plant have not been previously quantified. The emissions from an AD plant processing food waste were estimated through integrating ambient NH3 concentration measurements, atmospheric dispersion modelling, and comparison with published emission factors (EFs). Two dispersion models (ADMS and a backwards Lagrangian stochastic (bLS) model) were applied to calculate emission estimates. The bLS model (WindTrax) was used to back-calculate a total (top-down) emission rate for the AD plant from a point of continuous NH3 measurement downwind from the plant. The back-calculated emission rates were then input to the ADMS forward dispersion model to make predictions of air NH3 concentrations around the site, and evaluated against weekly passive sampler NH3 measurements.As an alternative approach emission rates from individual sources within the plant were initially estimated by applying literature EFs to the available site parameters concerning the chemical composition of waste materials, room air concentrations, ventilation rates, etc. The individual emission rates were input to ADMS and later tuned by fitting the simulated ambient concentrations to the observed (passive sampler) concentration field, which gave an excellent match to measurements after an iterative process. The total emission from the AD plant thus estimated by a bottom-up approach was 16.8±1.8mgs−1, which was significantly higher than the back-calculated top-down estimate (7.4±0.78mgs−1). The bottom-up approach offered a more realistic treatment of the source distribution within the plant area, while the complexity of the site was not ideally suited to the bLS method, thus the bottom-up method is believed to give a better estimate of emissions. The storage of solid digestate and the aerobic treatment of liquid effluents at the site were the greatest sources of NH3 emissions.

Footprint methods to separate N2O emission rates from adjacent paddock areas.

Using micrometeorological techniques to measure greenhouse gas emissions from differently treated adjacent plots is a promising avenue to verify the effect of mitigation strategies at the field scale. In pursuing such an approach, it is crucial to accurately characterize the source area of the fluxes measured at each sampling point. Hence, a comprehensive footprint analysis method is required so that emission rates can be obtained for a specific field within a biochemically heterogeneous area. In this study, a footprint analysis method is developed to estimate the emission for an experiment where the flux of N2O is measured from several control and treated plots. The emission rate of an individual plot is estimated using an inverse footprint fraction approach where the footprint fractions are obtained from an analytical footprint model. A numerical solution for obtaining the background flux for such a multiplot measurement system is also provided. Results of the footprint analysis method are assessed, first, by comparing footprint fractions obtained from both an analytical footprint model and a "forward" simulation of a backward Lagrangian stochastic (bLs) model; and second, by comparing the emission rates of a control plot obtained from the footprint analysis method and from the "backward" simulation of the bLs model. It is found that the analytical footprint fractions compare well with the values obtained from the bLs model (correlation coefficient of 0.58 and 0.66 within p value <0.001). An average of 4.3% of the measured fluxes is found to be contributed by sources outside the measured area and, excluding this outside area contribution to the measured flux, footprint corrected emission rates within the defined domain are found to increase by 2.1 to 5.8% of the measured flux. Also, the proposed method of emission rate estimation is found to work well under a wide range of atmospheric stability.

Assessment of the backward Lagrangian Stochastic dispersion technique for continuous measurements of CH 4 emissions

Continuous measurements of methane (CH 4) emissions from agricultural facilities over a period of several days are needed to assess the mitigation effectiveness of management practices. In this study, we examined the feasibility of using an inverse dispersion technique (backward Lagrangian Stochastic model, bLS) for obtaining 15-min averages of CH 4 emissions over a period of 5 days in the Ottawa area. Using two open-path lasers and pan-tilt scanning units, a ground level source was enclosed to measure the CH 4 emissions ( Q) with any wind direction. After application of the recommended data quality criteria screening for low friction velocity and extreme atmospheric stability, the average recovery (ratio of estimates Q bLS to Q) was 1.09 with a standard deviation of 0.45. We observed a tendency in the recovery results toward underestimation during unstable stratification and overestimation during stable stratification. Using a test on developed turbulence instead of a fixed friction velocity threshold improved the accuracy of the emission estimates slightly. An additional data quality criterion based on the standard deviation output of the bLS model led to a significant improvement with a recovery of 1.00 and a standard deviation of 0.30. A strategy for averaging the resulting incomplete dataset is discussed. An assessment of the applicability of this approach to farm-size facilities led to the conclusion that this technique is suitable to determine emissions from realistic CH 4 sources, such as dairy cattle barns, continuously in order to characterize both seasonal and diurnal characteristics of CH 4 emissions.

Estimating Gas Emissions from Multiple Sources Using a Backward Lagrangian Stochastic Model

Manure storage tanks and animals in barns are important agricultural sources of methane. To examine the possibility of using an inverse dispersion technique based on a backward Lagrangian Stochastic (bLS) model to quantify methane (CH4) emissions from multiple on-farm sources, a series of tests were carried out with four possible source configurations and three controlled area sources. The simulated configurations were: (C1) three spatially separate ground-level sources, (C2) three spatially separate sources with wind-flow disturbance, (C3) three adjacent ground-level sources to simulate a group of adjacent sources with different emission rates, and (C4) a configuration with a ground level and two elevated sources. For multiple ground-level sources without flow obstructions (C1 and C3), we can use the condition number (k, the ratio of the uncertainty in the calculated emission rate to the uncertainty in the predicted ratio of concentration to emission rate) to evaluate the applicability of this inverse dispersion technique and a preliminary threshold of k < 10 is recommended. For multiple sources with wind disturbance (C2) or an even more complex configuration including ground level and elevated sources (C4), a low k is not sufficient to provide reasonable discrete and total emission rates. The effect of flow obstructions can be neglected as long as the distance between the source and the measurement location is greater than approximately 10 times the height of the flow obstructions. This study shows that the bLS model has the potential to provide accurate discrete emission rates from multiple on-farm emissions of gases provided that certain conditions are met.

The evaluation of a backward Lagrangian stochastic (bLS) model to estimate greenhouse gas emissions from agricultural sources using a synthetic tracer source

Presented are the results of a field trial designed to test the accuracy of a backward Lagrangian stochastic (bLS) model. The accuracy of the bLS model was determined by comparing estimated CH 4 emission rates ( Q bLS) to measured CH 4 emission rates ( Q) for four different experimental set-up. Releases of CH 4 (99% purity) were made from a ground level grid (3 m × 3 m), as well as an elevated grid (1 m × 3 m) that was suspended 1.2 m above the surface. The bLS model was used to obtain emission estimates using concentration measurements and turbulence data obtained from an open-path laser and a three-dimensional sonic anemometer, respectively. The comparisons suggest that the bLS model can be used effectively in an agricultural setting provided the surface layer is homogeneous and the atmosphere can be described by Monin-Obukhov similarity theory. Under ideal conditions the average value of Q bLS/ Q was found to be 1.06 with a standard deviation ( σ bLS) = 0.16 and a standard error ( σ x ¯ ) = 0.02 . Obstructions upwind of the concentration and wind sensors were determined to have little impact on the estimated emissions provided the distance between the sensors and the obstructions was at least 25 times the height of the obstruction. For an elevated source ( z = 1.2 m) the average value of Q bLS/ Q over a homogenous terrain was 0.99, with σ bLS = 0.20 and σ x ¯ = 0.06 . The accuracy of the model varied with the sampling height, z m, suggesting that an ideal measurement height that is insensitive to atmospheric stability might exist.

Estimating gas emissions from a farm with an inverse-dispersion technique

We use an inverse–dispersion technique to diagnose gas emissions (ammonia) from a swine farm. A backward Lagrangian stochastic (bLS) model gives the emission-concentration relationship, so that downwind gas concentration establishes emissions. The bLS model takes as input the average wind velocity and direction, surface roughness, and atmospheric stability. Despite ignoring windcomplexity andassuming a simplifiedsource configuration in the mod el calculations, we argue that with concentration andwindmeasuredsufficiently far from the farm the errors can be relatively small. An important part of our analysis was identifying periods likely to give erroneous results. The resulting emission calculations (6.5 and16 g animal � 1 day � 1 in March andJuly, respectively) are plausible in the light of

Deducing Ground-to-Air Emissions from Observed Trace Gas Concentrations: A Field Trial with Wind Disturbance

AbstractInverse-dispersion techniques allow inference of a gas emission rate Q from measured air concentration. In “ideal surface layer problems,” where Monin–Obukhov similarity theory (MOST) describes the winds transporting the gas, the application of the technique can be straightforward. This study examines the accuracy of an ideal MOST-based inference, but in a nonideal setting. From a 6 m × 6 m synthetic area source surrounded by a 20 m × 20 m square border of a windbreak fence (1.25 m tall), Q is estimated. Open-path lasers gave line-averaged concentration CL at positions downwind of the source, and an idealized backward Lagrangian stochastic (bLS) dispersion model was used to infer QbLS. Despite the disturbance of the mean wind and turbulence caused by the fence, the QbLS estimates were accurate when ambient winds (measured upwind of the plot) were assumed in the bLS model. In the worst cases, with CL measured adjacent to a plot fence, QbLS overestimated Q by an average of 50%. However, if these near-fence locations are eliminated, QbLS averaged within 2% of the true Q over 61 fifteen-minute observations (with a standard deviation σQ/Q = 0.20). Poorer accuracy occurred when in-plot wind measurements were used in the bLS model. The results show that when an inverse-dispersion technique is applied to disturbed flows without accounting for the disturbance, the outcome may still be of acceptable accuracy if judgment is applied in the placement of the concentration detector.