A Fourier Neural Operator-enhanced parabolic equation framework for highly efficient underwater acoustic field prediction

The integration of solar photovoltaic (SPV) system to the grid has introduced a new source of intermittency in the grid, and the grid has to react smartly to the changes that occur in the penetration of SPV power. Accurate modeling of weather-dependent SPV power will be helpful in forecasting the penetration of SPV power into the grid. An SPV power output forecasting model has been developed based on artificial neural network (ANN) approach. Two forecasters, namely ANN forecaster and two-stage hybrid-ANN forecaster, are developed with operational and weather parameters. The historical data of SPV power (P), hours of operation of SPV system (to), daily global solar radiation (H), and ambient temperature(T) are used as modeling parameters. The combination of modeling parameters {P, H, T, to} is identified as the best combination that influences the forecasting of day-ahead power output. A relative root mean square error (RRMSE) of 5.74% was obtained with the combination of {P, H, T, to}. An RRMSE of 6.04% was observed with the combination of {P, H, T} as inputs, and the hours of operation of the SPV plant could be ignored in the model. The historical power data of the SPV plant is identified as the crucial parameter in the SPV power forecast model and has given an RRMSE of 7.25%. The models developed with temperature and radiation as modeling parameters have resulted in good forecasting accuracy, which could be best suitable for feasibility studies of SPV plant at a particular location. Solar radiation prediction models are used in the development of hybrid-ANN forecaster. It has produced an RRMSE of 7.35% with four inputs. The hybrid-ANN forecaster with predicted radiations as modeling input will eliminate the need of a costly pyranometer. The models developed in the present study have utilized readily available parameters as modeling parameters, thereby cost of the forecasting system has been decreased. The developed models will be useful for energy scheduling and energy management in the smart grid. Abbreviations: GSR, Global Solar Radiation; ANN, Artificial Neural networks; SPV, Solar Photovoltaics; MAPE, Mean Absolute Percentage Error; RRMSE, Relative Root Mean Square Error; MSE, Mean Square Error.

Purpose: This study examines Clements’ Approach (CA), Box-Cox transformation (BCT), and Johnson transformation (JT) methods for process capability assessments through Weibull-distributed data with different parameters to figure out the effects of the tail behaviours on process capability and compares their estimation performances in terms of accuracy and precision.Design/methodology/approach: Usage of process performance index (PPI) Ppu is handled for process capability analysis (PCA) because the comparison issues are performed through generating Weibull data without subgroups. Box plots, descriptive statistics, the root-mean-square deviation (RMSD), which is used as a measure of error, and a radar chart are utilized all together for evaluating the performances of the methods. In addition, the bias of the estimated values is important as the efficiency measured by the mean square error. In this regard, Relative Bias (RB) and the Relative Root Mean Square Error (RRMSE) are also considered.Findings: The results reveal that the performance of a method is dependent on its capability to fit the tail behavior of the Weibull distribution and on targeted values of the PPIs. It is observed that the effect of tail behavior is more significant when the process is more capable.Research limitations/implications: Some other methods such as Weighted Variance method, which also give good results, were also conducted. However, we later realized that it would be confusing in terms of comparison issues between the methods for consistent interpretations.Practical implications: Weibull distribution covers a wide class of non-normal processes due to its capability to yield a variety of distinct curves based on its parameters. Weibull distributions are known to have significantly different tail behaviors, which greatly affects the process capability. In quality and reliability applications, they are widely used for the analyses of failure data in order to understand how items are failing or failures being occurred. Many academicians prefer the estimation of long term variation for process capability calculations although Process Capability Indices (PCIs) Cp and Cpk are widely used in literature. On the other hand, in industry, especially in automotive industry, the PPIs Pp and Ppk are used for the second type of estimations.Originality/value: Performance comparisons are performed through generating Weibull data without subgroups and for this reason, process performance indices (PPIs) are executed for computing process capability rather than process capability indices (PCIs). Box plots, descriptive statistics, the root-mean-square deviation (RMSD), which is used as a measure of error, and a radar chart are utilized all together for evaluating the performances of the methods. In addition, the bias of the estimated values is important as the efficiency measured by the mean square error. In this regard, Relative Bias (RB) and the Relative Root Mean Square Error (RRMSE) are also considered. To the best of our knowledge, all these issues including of execution of PPIs are performed all together for the first time in the literature.

Abstract. This study evaluates three different metrics of water content of an herbaceous cover in a Mediterranean wooded grassland (dehesa) ecosystem. Fuel moisture content (FMC), equivalent water thickness (EWT) and canopy water content (CWC) were estimated from proximal sensing and MODIS satellite imagery. Dry matter (Dm) and leaf area index (LAI) connect the three metrics and were also analyzed. Metrics were derived from field sampling of grass cover within a 500 m MODIS pixel. Hand-held hyperspectral measurements and MODIS images were simultaneously acquired and predictive empirical models were parametrized. Two methods of estimating FMC and CWC using different field protocols were tested in order to evaluate the consistency of the metrics and the relationships with the predictive empirical models. In addition, radiative transfer models (RTM) were used to produce estimates of CWC and FMC, which were compared with the empirical ones. Results revealed that, for all metrics spatial variability was significantly lower than temporal. Thus we concluded that experimental design should prioritize sampling frequency rather than sample size. Dm variability was high which demonstrates that a constant annual Dm value should not be used to predict EWT from FMC as other previous studies did. Relative root mean square error (RRMSE) evaluated the performance of nine spectral indices to compute each variable. Visible Atmospherically Resistant Index (VARI) provided the lowest explicative power in all cases. For proximal sensing, Global Environment Monitoring Index (GEMI) showed higher statistical relationships both for FMC (RRMSE = 34.5 %) and EWT (RRMSE = 27.43 %) while Normalized Difference Infrared Index (NDII) and Global Vegetation Monitoring Index (GVMI) for CWC (RRMSE = 30.27 % and 31.58 % respectively). When MODIS data were used, results showed an increase in R2 and Enhanced Vegetation Index (EVI) as the best predictor for FMC (RRMSE = 33.81 %) and CWC (RRMSE = 27.56 %) and GEMI for EWT (RRMSE = 24.6 %). Differences in the viewing geometry of the platforms can explain these differences as the portion of vegetation observed by MODIS is larger than when using proximal sensing including the spectral response from scattered trees and its shadows. CWC was better predicted than the other two water content metrics, probably because CWC depends on LAI, that shows a notable seasonal variation in this ecosystem. Strong statistical relationship was found between empirical models using indices sensible to chlorophyll activity (NDVI or EVI which are not directly related to water content) due to the close relationship between LAI, water content and chlorophyll activity in grassland cover, which is not true for other types of vegetation such as forest or shrubs. The empirical methods tested outperformed FMC and CWC products based on radiative transfer model inversion.

Modeling luminous efficacy of daylight for Yongin, South Korea

The California bearing ratio (CBR) is one of the basic subgrade strength characterization properties in road pavement design for evaluating the bearing capacity of pavement subgrade materials. In this research, a new model based on the Gaussian process regression (GPR) computing technique was trained and developed to predict CBR value of hydrated lime-activated rice husk ash (HARHA) treated soil. An experimental database containing 121 data points have been used. The dataset contains input parameters namely HARHA—a hybrid geometrical binder, liquid limit, plastic limit, plastic index, optimum moisture content, activity and maximum dry density while the output parameter for the model is CBR. The performance of the GPR model is assessed using statistical parameters, including the coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), Relative Root Mean Square Error (RRMSE), and performance indicator (ρ). The obtained results through GPR model yield higher accuracy as compare to recently establish artificial neural network (ANN) and gene expression programming (GEP) models in the literature. The analysis of the R2 together with MAE, RMSE, RRMSE, and ρ values for the CBR demonstrates that the GPR achieved a better prediction performance in training phase with (R2 = 0.9999, MAE = 0.0920, RMSE = 0.13907, RRMSE = 0.0078 and ρ = 0.00391) succeeded by the ANN model with (R2 = 0.9998, MAE = 0.0962, RMSE = 4.98, RRMSE = 0.20, and ρ = 0.100) and GEP model with (R2 = 0.9972, MAE = 0.5, RMSE = 4.94, RRMSE = 0.202, and ρ = 0.101). Furthermore, the sensitivity analysis result shows that HARHA was the key parameter affecting the CBR.

Application of firefly algorithm-based support vector machines for prediction of field capacity and permanent wilting point

Abstract. Our global understanding of clouds and aerosols relies on the remote sensing of their optical, microphysical, and macrophysical properties using, in part, scattered solar radiation. Current retrievals assume clouds and aerosols form plane-parallel, homogeneous layers and utilize 1D radiative transfer (RT) models. These assumptions limit the detail that can be retrieved about the 3D variability in the cloud and aerosol fields and induce biases in the retrieved properties for highly heterogeneous structures such as cumulus clouds and smoke plumes. In Part 1 of this two-part study, we validated a tomographic method that utilizes multi-angle passive imagery to retrieve 3D distributions of species using 3D RT to overcome these issues. That validation characterized the uncertainty in the approximate Jacobian used in the tomographic retrieval over a wide range of atmospheric and surface conditions for several horizontal boundary conditions. Here, in Part 2, we test the algorithm's effectiveness on synthetic data to test whether the retrieval accuracy is limited by the use of the approximate Jacobian. We retrieve 3D distributions of a volume extinction coefficient (σ3D) at 40 m resolution from synthetic multi-angle, mono-spectral imagery at 35 m resolution derived from stochastically generated cumuliform-type clouds in (1 km)3 domains. The retrievals are idealized in that we neglect forward-modelling and instrumental errors, with the exception of radiometric noise; thus, reported retrieval errors are the lower bounds. σ3D is retrieved with, on average, a relative root mean square error (RRMSE) < 20 % and bias < 0.1 % for clouds with maximum optical depth (MOD) < 17, and the RRMSE of the radiances is < 0.5 %, indicating very high accuracy in shallow cumulus conditions. As the MOD of the clouds increases to 80, the RRMSE and biases in σ3D worsen to 60 % and −35 %, respectively, and the RRMSE of the radiances reaches 16 %, indicating incomplete convergence. This is expected from the increasing ill-conditioning of the inverse problem with the decreasing mean free path predicted by RT theory and discussed in detail in Part 1. We tested retrievals that use a forward model that is not only less ill-conditioned (in terms of condition number) but also less accurate, due to more aggressive delta-M scaling. This reduces the radiance RRMSE to 9 % and the bias in σ3D to −8 % in clouds with MOD ∼ 80, with no improvement in the RRMSE of σ3D. This illustrates a significant sensitivity of the retrieval to the numerical configuration of the RT model which, at least in our circumstances, improves the retrieval accuracy. All of these ensemble-averaged results are robust in response to the inclusion of radiometric noise during the retrieval. However, individual realizations can have large deviations of up to 18 % in the mean extinction in clouds with MOD ∼ 80, which indicates large uncertainties in the retrievals in the optically thick limit. Using less ill-conditioned forward model tomography can also accurately infer optical depths (ODs) in conditions spanning the majority of oceanic cumulus fields (MOD < 80), as the retrieval provides ODs with bias and RRMSE values better than −8 % and 36 %, respectively. This is a significant improvement over retrievals using 1D RT, which have OD biases between −30 % and −23 % and RRMSE between 29 % and 80 % for the clouds used here. Prior information or other sources of information will be required to improve the RRMSE of σ3D in the optically thick limit, where the RRMSE is shown to have a strong spatial structure that varies with the solar and viewing geometry.

ABSTRACTThe normalized difference vegetation index (NDVI) is a commonly used index for monitoring crop growth status. Previous studies have shown that the leaf area index (LAI) estimation based on NDVI is limited by saturation that occurs under conditions of relatively dense canopies (LAI > 2 m2 m–2). To reduce the saturation effect, we suggested new spectral indices through the spectral indices approach. The results suggested that the two-band normalized difference spectral index (NDSI = ((ρ940 – ρ730) /(ρ940 + ρ730))) resulted from the two-band spectral indices approach and the three-band modified normalized difference spectral index (mNDSI = ((ρ940 – 0.8 × ρ950) – ρ730) /((ρ940 – 0.8 × ρ950) + ρ730)) resulted from the three-band spectral indices approach, and they were able to mitigate saturation and improve the LAI prediction with a determination coefficient (R2) of 0.77 and 0.78, respectively. In the validation based on data from independent experiments, these new indices exhibited an accuracy with relative root mean square error (RRMSE) lower than 23.38% and bias higher than –0.40. These accuracies were significantly higher than those obtained with some existing indices with good performance in LAI estimation, such as the enhanced vegetation index (EVI) (RRMSE = 30.19%, bias = –0.34) and the modified triangular vegetation index 2 (MTVI2) (RRMSE = 29.30%, bias = –0.28), and the indices with the ability to mitigate the saturation, such as the wide dynamic range vegetation index (WDRVI) (RRMSE = 31.37%, bias = –0.54), the red-edge wide dynamic range vegetation index (red-edge WDRVI) (RRMSE = 26.34%, bias = –0.54), and the normalized difference red-edge index (NDRE) (RRMSE = 28.41%, bias = –0.56). Additionally, these new indices were more sensitive under moderate to high LAI conditions (between 2 and 8 m2 m–2). Between these two new developed spectral indices, there was no significant difference in the accuracy and sensitivity assessments. Considering the index structure and convenience in application, we demonstrated that the two-band spectral index NDSI((ρ940 – ρ730) /(ρ940 + ρ730)) is efficient in mitigating saturation and has considerable potential for estimating the LAI of canopies throughout the entire growing season of wheat (Triticum aestivum L.), whereas the three-band spectral index contributes lesser in the saturation mitigation provided the red-edge band has been contained.

The mathematics used for urea kinetic modeling are currently based on a single-pool distribution of urea throughout the body. In this study, we evaluated which one of a single- or a two-pool model would be more appropriate for the prediction of directly measured urea decay during hemodialysis. A numerical method was used which minimizes the relative root mean square (RMS) error between a calculated single- or two-pool urea decay curve and the measured intradialysis decay in 13 equilibrated dialysis patients. Using a two-pool model, the RMS error was markedly lower (1.27 +/- 0.72%) than the values obtained with a single-pool model, either based on multiple urea concentrations (RMS error 3.14 +/- 1.36%; p < 0.01 vs. two-pool model) or only on pre- and postdialysis urea (RMS error 5.00 +/- 2.38%; p < 0.001). This resulted for the single-pool model in an overall underestimation of urea generation, distribution volume (V) and protein catabolic rate and in an overestimation of Kt/V versus the two-pool model. In individual cases, the difference reached up to 18.7%. Comparison of V calculated from the two-pool model versus V values determined from anthropometric formulae (Watson) resulted in similar mean values (34.05 +/- 4.87 vs. 33.09 +/- 4.19 liters; p = NS), with a weak correlation (n = 13, r = 0.75, p = 0.003). Individual values, however, again differed by up to more than 20%. In conclusion, the use of single-pool kinetic models, as well as of anthropometric estimations of V, should be regarded with care, especially when individual patients are considered instead of groups. The two-pool model follows the directly measured urea decay more exactly which results in substantial differences in calculated kinetic parameters.

High-resolution airflow monitoring in urban environments requires deployment of a large number of anemometers with precise measurement capability of both wind speed and direction in two or three dimensions. Existing sensors are too expensive and/or bulky for this application. It is known that microelectromechanical systems (MEMS) sensor-based anemometers can be low in cost for mass production. And due to its ultra-thin filaments and fine structure, a MEMS-based hot-film sensor also has the potential to outperform traditional hot-wire or hot-film sensors. Existing MEMS-based anemometers that integrate multiple sensing elements on a chip for detection of airflow speed and direction show low sensitivity due to their in-plane structure, which cannot harvest wind energy efficiently. In this paper, we develop an anemometer having a probe structure mounted with three MEMS-based hot-film sensor chips, which can detect both airflow speed and direction with high sensitivity while keeping a compact size for the probe (6-mm diameter). The prototype anemometer is calibrated for detection of wind speed with accuracy of 3.6% [relative root mean square (RMS) error] in a range of 0.1-10 m/s, and wind direction from 0° to 360°, with an accuracy of 1.20 degree (RMS error). We field-test the MEMS based 2-D anemometer at urban wind monitoring points and the results agree well with monitoring data of nearby commercial 2-D ultrasonic anemometers.

Synergistic use of Sentinel-1, Sentinel-2, and Landsat 8 in predicting forest variables

The knowledge of the ground electrical resistivity is essential to ensure the protection of electrical and telecommunications networks. However, the monitoring of its values is an expensive task which takes long time. Therefore, its prediction is important. This study investigates on predicting soil electrical resistivity using Artificial Neural Networks. Nine sites of our city (Lome, TOGO) were considered. After characterization of the resistivity data collected on these sites, two models have been developed: Multilayer Perceptron (MLP) and Radial Basis Function (RBF) networks. Relative Root Mean Square Error (RRMSE) and R2 (Linear Correlation Coefficient) have been used to evaluate each model performance. For the MLP model, the configuration [ABCDEF] is the most efficient with the RRMSE = 12.00%, R2 = 81.91% and 70 neurons under the hidden layer. For the RBF model, the configuration [BCDEF] is the most efficient with the RRMSE = 16.07%, R2 = 69.97% and 100 neurons under the hidden layer. In general, the results exhibit that the MLP outcome configuration [ABCDEF] is the most efficient with the best RRMSE = 16.07% and R2 = 69.97%. The letter A, B and C are the weather parameters and D, E, F are the geo-referenced coordinates of the measuring point. So far, research has not focused on predicting the electrical resistivity of the soil at a given location. Thus, the results of this study show that from meteorological data, it’s possible to predict this electrical resistivity.

ABSTRACTCombining surface evaporation and plant transpiration, evapotranspiration (ET) is critical to surface water and heat balances as it links water, carbon cycles and energy exchanges. Many models have been developed and are presently used to estimate terrestrial ET. However, there are large model uncertainties among the different models, which present a problem. By combining meteorological reanalysis data from the China Meteorological Forcing Dataset (CMFD) with remote sensing data and observational data during 2002–2009, two semi-physical models, the modified satellite-based Priestley-Taylor (MS-PT) model and a semi-empirical Penman equation-based (SE-PM) model, are used to estimate ET and are validated using in situ measurements collected at 22 flux tower sites in China. Then support vector machine (SVM) method is used to integrate these two semi-physical models to improve the accuracy of ET estimates for eight different vegetation types separately, as well as all of these types together. The integrated model likely explains 56–94% of the land surface ET changes indicated by the observations collected at the flux tower sites. The ET predictions obtained by driving the models with the reanalysis data (for which the relative bias and the relative root mean square error (RMSE) for all types of the SVM were 6 and 51 W m–2, respectively, and the maximum decrease of the relative RMSE for different types is nearly 20 W m–2) are less accurate than those obtained by driving the models with the observational data (for which the relative bias and the relative RMSE for all types of the SVM are 4 and 43 W m–2, respectively). Compared to the individual semi-physical models, the results produced by the integrated model display significantly decreased bias (less than 5 W m–2 for all types) and RMSE (for which the maximum decrease is nearly 71 W m–2) in the validation.

Estimation of As and Cu Contamination in Agricultural Soils Around a Mining Area by Reflectance Spectroscopy: A Case Study

Abstract. This paper examines various geometric shapes to determine the most suitable one for calculating tree crown area in field measurements. The study was conducted in an Eldarica pine plantation forest, which was digitally mapped using RGB images captured by a Phantom 4 Pro drone. Tree crowns were manually digitized (MD) from these images to serve as reference data. Field measurements, including the large and small crown diameters, were collected to evaluate crown areas derived from different geometric shapes. The geometric shapes considered were: Oval with Both Diameters (OBD), Circle with Small Diameter (CSD), Circle with Large Diameter (CLD), and Circle with Mean Diameters (CMD). Three analyses were performed to assess the results: correlation analysis (R2), relative root mean square error (RRMSE), and shape analysis, which included overestimation (OverID) and underestimation (UnderID) indices. The results revealed that the choice of geometric shape significantly impacts the accuracy of crown area calculations. The OBD model based on the outer boundary diameter yielded the best results with RRMSE = 0.29, R2 = 0.84, OverID = 0.18, and UnderID = 0.23, followed closely by the CMD method. In contrast, the CSD and CLD models performed less effectively, with RRMSE = 0.52, R2 = 0.42, OverID = 0.11, UnderID = 0.35 (CSD), and RRMSE = 0.59, R2 = 0.37, OverID = 0.46, UnderID = 0.22 (CLD). These differences in performance are likely due to the inclusion of empty spaces within the crown area in some models. However, the findings of this study are not universally applicable to all tree crown area calculations. The geometric shape used for crown area estimation must align with the structural characteristics of the forest and the specific geometry of the tree species under consideration.