Reduction In Root Mean Square Error Research Articles

Generation of Virtual Ground Control Points Using a Binocular Camera

This paper presents a methodology for generating virtual ground control points (VGCPs) using a binocular camera mounted on a drone. We compare the measurements of the binocular and monocular cameras between the classical method and the proposed one. This work aims to decrease human processing times while maintaining a reduced root mean square error (RMSE) for 3D reconstruction. Additionally, we propose utilizing COLMAP to enhance reconstruction accuracy by solely utilizing a sparse point cloud. The results demonstrate that implementing COLMAP for pre-processing reduces the RMSE by up to 16.9% in most cases. We prove that VGCPs further reduce the RMSE by up to 61.08%.

Enhancing Soil Moisture Active–Passive Estimates with Soil Moisture Active–Passive Reflectometer Data Using Graph Signal Processing

The Soil Moisture Active–Passive (SMAP) mission has greatly contributed to the use of remote sensing technologies for monitoring the Earth’s land surface and estimating geophysical parameters that influence the climate system. Since the SMAP mission switched its radar receiver to allow the reception of Global Positioning System (GPS) signals, Global Navigation Satellite System Reflectometry (GNSS-R) configuration has been enabled, providing full polarimetric forward scattering measurements of the Earth’s surface, also known as SMAP Reflectometry or SMAP-R. Polarimetric GNSS-R is beneficial for sensing land surface properties, especially for more accurate estimations of soil moisture (SM) in densely vegetated areas. In this study, we explore the opportunity to enhance SMAP mission soil moisture estimates using reflected GNSS signals. We achieve this by interpolating the sparse reflectivity data with terrain information to disaggregate radiometer brightness temperatures. Our main objective is to present a novel algorithm based on Graph Signal Processing (GSP) that uses reflectometry data to enhance SMAP radiometer observations and ultimately improve SM retrievals. By implementing methods from the GSP field, we formulate the reflectivity interpolation problem as a signal reconstruction on a graph, where the weights of the edges between the nodes are chosen as a function of geophysical information. Subsequently, using the retrieved reflectivity maps, we increase the resolution of the brightness temperature data, leading to an improvement in the SM estimates. Initial findings indicate that our GSP method presents a promising alternative for analyzing sparse remote sensing observations, leveraging Earth’s surface geophysical information. This approach results in a notable improvement, with a reduced Root Mean Square Error (RMSE) of 11.8% compared to SMAP data and a reduction in unbiased RMSE (uRMSE) by 14.7% over vegetated areas.

Variable-Dependent and Selective Multivariate Localization for Ensemble–Variational Data Assimilation in the Tropics

Abstract Two aspects of ensemble localization for data assimilation are explored using the simplified nonhydrostatic ABC model in a tropical setting. The first aspect (i) is the ability to prescribe different localization length scales for different variables (variable-dependent localization). The second aspect (ii) is the ability to control (i.e., to knock out by localization) multivariate error covariances (selective multivariate localization). These aspects are explored in order to shed light on the cross-covariances that are important in the tropics and to help determine the most appropriate localization configuration for a tropical ensemble–variational (EnVar) data assimilation system. Two localization schemes are implemented within the EnVar framework to achieve (i) and (ii). One is called the isolated variable-dependent localization (IVDL) scheme and the other is called the symmetric variable-dependent localization (SVDL) scheme. Multicycle observation system simulation experiments are conducted using IVDL or SVDL mainly with a 100-member ensemble, although other ensemble sizes are studied (between 10 and 1000 members). The results reveal that selective multivariate localization can reduce the cycle-averaged root-mean-square error (RMSE) in the experiments when cross-covariances associated with hydrostatic balance are retained and when zonal wind/mass error cross-covariances are knocked out. When variable-dependent horizontal and vertical localization are incrementally introduced, the cycle-averaged RMSE is further reduced. Overall, the best performing experiment using both variable-dependent and selective multivariate localization leads to a 3%–4% reduction in cycle-averaged RMSE compared to the traditional EnVar experiment. These results may inform the possible improvements to existing tropical numerical weather prediction systems that use EnVar data assimilation.

Lung CT harmonization of paired reconstruction kernel images using generative adversarial networks.

The kernel used in CT image reconstruction is an important factor that determines the texture of the CT image. Consistency of reconstruction kernel choice is important for quantitative CT-based assessment as kernel differences can lead to substantial shifts in measurements unrelated to underlying anatomical structures. In this study, we investigate kernel harmonization in a multi-vendor low-dose CT lung cancer screening cohort and evaluate our approach's validity in quantitative CT-based assessments. Using the National Lung Screening Trial, we identified CT scan pairs of the same sessions with one reconstructed from a soft tissue kernel and one from a hard kernel. In total, 1000 pairs of five different paired kernel types (200 each) were identified. We adopt the pix2pix architecture to train models for kernel conversion. Each model was trained on 100 pairs and evaluated on 100 withheld pairs. A total of 10 models were implemented. We evaluated the efficacy of kernel conversion based on image similarity metrics including root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) as well as the capability of the models to reduce measurement shifts in quantitative emphysema and body composition measurements. Additionally, we study the reproducibility of standard radiomic features for all kernel pairs before and after harmonization. Our approach effectively converts CT images from one kernel to another in all paired kernel types, as indicated by the reduction in RMSE (p<0.05) and an increase in the PSNR (p<0.05) and SSIM (p<0.05) for both directions of conversion for all pair types. In addition, there is an increase in the agreement for percent emphysema, skeletal muscle area, and subcutaneous adipose tissue (SAT) area for both directions of conversion. Furthermore, radiomic features were reproducible when compared with the ground truth features. Kernel conversion using deep learning reduces measurement variation in percent emphysema, muscle area, and SAT area.

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion

Stereoscopic display technology plays a significant role in industries, such as film, television and autonomous driving. The accuracy of depth estimation is crucial for achieving high-quality and realistic stereoscopic display effects. In addressing the inherent challenges of applying Transformers to depth estimation, the Stereoscopic Pyramid Transformer-Depth (SPT-Depth) is introduced. This method utilizes stepwise downsampling to acquire both shallow and deep semantic information, which are subsequently fused. The training process is divided into fine and coarse convergence stages, employing distinct training strategies and hyperparameters, resulting in a substantial reduction in both training and validation losses. In the training strategy, a shift and scale-invariant mean square error function is employed to compensate for the lack of translational invariance in the Transformers. Additionally, an edge-smoothing function is applied to reduce noise in the depth map, enhancing the model's robustness. The SPT-Depth achieves a global receptive field while effectively reducing time complexity. In comparison with the baseline method, with the New York University Depth V2 (NYU Depth V2) dataset, there is a 10% reduction in Absolute Relative Error (Abs Rel) and a 36% decrease in Root Mean Square Error (RMSE). When compared with the state-of-the-art methods, there is a 17% reduction in RMSE.

Enhancing Image Alignment in Time-Lapse-Ground-Penetrating Radar through Dynamic Time Warping

Ground-penetrating radar (GPR) is a rapid and non-destructive geophysical technique widely employed to detect and quantify subsurface structures and characteristics. Its capability for time lapse (TL) detection provides essential insights into subsurface hydrological dynamics, including lateral flow and soil water distribution. However, during TL-GPR surveys, field conditions often create discrepancies in surface geometry, which introduces mismatches across sequential TL-GPR images. These discrepancies may generate spurious signal variations that impede the accurate interpretation of TL-GPR data when assessing subsurface hydrological processes. In responding to this issue, this study introduces a TL-GPR image alignment method by employing the dynamic time warping (DTW) algorithm. The purpose of the proposed method, namely TLIAM–DTW, is to correct for geometric mismatch in TL-GPR images collected from the identical survey line in the field. We validated the efficacy of the TLIAM–DTW method using both synthetic data from gprMax V3.0 simulations and actual field data collected from a hilly, forested area post-infiltration experiment. Analyses of the aligned TL-GPR images revealed that the TLIAM–DTW method effectively eliminates the influence of geometric mismatch while preserving the integrity of signal variations due to actual subsurface hydrological processes. Quantitative assessments of the proposed methods, measured by mean absolute error (MAE) and root mean square error (RMSE), showed significant improvements. After performing the TLIAM–DTW method, the MAE and RMSE between processed TL-GPR images and background images were reduced by 96% and 78%, respectively, in simple simulation scenarios; in more complex simulations, MAE declined by 27–31% and RMSE by 17–43%. Field data yielded reductions in MAE and RMSE of &gt;82% and 69%, respectively. With these substantial improvements, the processed TL-GPR images successfully depict the spatial and temporal transitions associated with subsurface lateral flows, thereby enhancing the accuracy of monitoring subsurface hydrological processes under field conditions.

Bias Correction of IMERG Data in the Mountainous Areas of Sumatra Based on A Single Gauge Observation

The performance of surface precipitation data from satellite precipitation products (SPPs) in mountainous areas has greater error and bias than in plain areas. In this study, linear scaling (LS), local intensity (LOCI), power transformation (PT), and cumulative distribution function (CDF) methods are used to correct the bias of Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG) data in the mountainous region of Sumatra based on long-term and high-resolution optical rain gauge (ORG) observations. The ORG is installed at Equatorial Atmospheric Observatory (EAO) in Kototabang, West Sumatra, Indonesia (100.32 °E, 0.20 °S, 865 m above sea level (ASL) with an observation period from 2002 to 2016. The impact of the bias correction method is tested based on accuracy and capability detection tests. The bias correction method is more effective at the daily resolution than the hourly resolution of the IMERG data in the mountainous region of Sumatra. The LS method exhibited the best improvement in accuracy with reduced root-mean-square error (RMSE) and relative bias (RB), although there was no significant increase in coefficient correlation (CC) values. However, the accuracy improvement was not observed in the bias correction for hourly data. The lack of improvement in the accuracy of the hourly IMERG data is due to the high local variability of rainfall in the mountainous area of Sumatra. The high data variability causes large differences in the mean and variance of the IMERG calibration and evaluation data periods. On the other hand, the LOCI, PT, and CDF methods were successfully improved the rain detection capability of IMERG, as indicated by the better critical succession index (CSI) values compared to the original hourly and daily IMERG data. It increased the CSI value by reducing false alarms for rain with intensity below 2 mm/h. Furthermore, the CDF method can improve the analysis of extreme rainfall in the mountainous region of Sumatra by improving the estimation of the extreme rainfall index. Therefore, these methods can be applied to improve the accuracy and detectability of IMERG data in the mountainous region of Sumatra. However, the scale factor and transfer function constructed in this study need to be further evaluated on other rain gauge observation data in Sumatra’s mountainous region to improve performance. HIGHLIGHTS The LS method shows the best improvement in the accuracy of IMERG data in the mountainous area of Sumatera compared to the LOCI, PT, and CDF methods, as indicated by the largest decrease in RMSE and RB values CSI values prove that LOCI, PT, and CDF methods successfully improve the detection capability of IMERG hourly and daily data in the mountainous region of Sumatra The CDF method shows the best quality in improving extreme rainfall observations in the mountainous region of Sumatra GRAPHICAL ABSTRACT

Enhancing data-driven soil moisture modeling with physically-guided LSTM networks

In recent years, deep learning methods have shown significant potential in soil moisture modeling. However, a prominent limitation of deep learning approaches has been the absence of physical mechanisms. To address this challenge, this study introduces two novel loss functions designed around physical mechanisms to guide deep learning models in capturing physical information within the data. These two loss functions are crafted to leverage the monotonic relationships between surface water variables and shallow soil moisture as well as deep soil water. Based on these physically-guided loss functions, two physically-guided Long Short-Term Memory (LSTM) networks, denoted as PHY-LSTM and PHYs-LSTM, are proposed. These networks are trained on the global ERA5-Land dataset, and the results indicate a notable performance improvement over traditional LSTM models. When used for global soil moisture forecasting for the upcoming day, PHY-LSTM and PHYs-LSTM models exhibit closely comparable results. In comparison to conventional data-driven LSTM models, both models display a substantial enhancement in various evaluation metrics. Specifically, PHYs-LSTM exhibits improvements in several key performance indicators: an increase of 13.6% in Kling-Gupta Efficiency (KGE), a 20.7% increase in Coefficient of Determination (R2), an 8.2% reduction in Root Mean Square Error (RMSE), and a 4.4% increase in correlation coefficient (R). PHY-LSTM also demonstrates improvements, with a 14.8% increase in KGE, a 19.6% increase in R2, an 8.2% reduction in RMSE, and a 4.4% increase in R. Additionally, both models exhibit enhanced physical consistency over a wide geographical area. Experimental results strongly emphasize that the incorporation of physical mechanisms can significantly bolster the predictive capabilities of data-driven soil moisture models.

Optimizing Lithium-Ion Battery Modeling: A Comparative Analysis of PSO and GWO Algorithms

In recent years, the modeling and simulation of lithium-ion batteries have garnered attention due to the rising demand for reliable energy storage. Accurate charge cycle predictions are fundamental for optimizing battery performance and lifespan. This study compares particle swarm optimization (PSO) and grey wolf optimization (GWO) algorithms in modeling a commercial lithium-ion battery, emphasizing the voltage behavior and the current delivered to the battery. Bio-inspired optimization tunes parameters to reduce the root mean square error (RMSE) between simulated and experimental outputs. The model, implemented in MATLAB/Simulink, integrates electrochemical parameters and estimates battery behavior under varied conditions. The assessment of terminal voltage revealed notable enhancements in the model through both the PSO and GWO algorithms compared to the non-optimized model. The GWO-optimized model demonstrated superior performance, with a reduced RMSE of 0.1700 (25 °C; 3.6 C, 455 s) and 0.1705 (25 °C; 3.6 C, 10,654 s) compared to the PSO-optimized model, achieving a 42% average RMSE reduction. Battery current was identified as a key factor influencing the model analysis, with optimized models, particularly the GWO model, exhibiting enhanced predictive capabilities and slightly lower RMSE values than the PSO model. This offers practical implications for battery integration into energy systems. Analyzing the execution time with different population values for PSO and GWO provides insights into computational complexity. PSO exhibited greater-than-linear dynamics, suggesting a polynomial complexity of O(nk), while GWO implied a potential polynomial complexity within the range of O(nk) or O(2n) based on execution times from populations of 10 to 1000.

On the performance of streamflow gauging using CCTV-integrated LSPIV in diverse hydro-environmental conditions.

Addressing the critical need for precise streamflow measurements in hydro-environmental research, this study evaluates large-scale particle image velocimetry (LSPIV) using cost-effective closed-circuit television (CCTV) cameras, providing a detailed sensitivity analysis in both laboratory and real-world canal settings. In laboratory conditions, a 45° camera angle notably enhanced performance, exhibiting a 12% decrease in MAE and a remarkable 40% reduction in RMSE compared to the performance of orthographic form. Tracer particles further enhanced LSPIV accuracy, decreasing both mean absolute error (MAE) and root mean square error (RMSE) by around 0.05 m/s. Optimal velocity coefficients for the lab ranged between 0.85 and 0.90. Nighttime measurements, using projection-based illumination, showed a minor 3% MAE variation and 0.02 RMSE difference versus daytime. In field experiments, a 45° upstream CCTV camera configuration notably improved LSPIV accuracy, achieving a 3% MAE and 0.055 m/s RMSE. For best results across different turbidity levels, we recommend a velocity coefficient range of 0.84 to 0.88. This study highlights the robustness and cost-efficiency of LSPIV as a transformative method for streamflow gauging, demonstrating its wide applicability in diverse hydro-environmental scenarios.

Quantitative Analysis of Near-Infrared Spectroscopy Using the BEST-1DConvNet Model

In the quest for enhanced precision in near-infrared spectroscopy (NIRS), in this study, the application of a novel BEST-1DConvNet model for quantitative analysis is investigated against conventional support vector machine (SVM) approaches with preprocessing such as multiplicative scatter correction (MSC) and standard normal variate (SNV). We assessed the performance of these methods on NIRS datasets of diesel, gasoline, and milk using a Fourier Transform Near-Infrared (FT-NIR) spectrometer having a wavelength range of 900–1700 nm for diesel and gasoline and 4000–10,000 nm for milk, ensuring comprehensive spectral capture. The BEST-1DConvNet’s effectiveness in chemometric predictions was quantitatively gauged by improvements in the coefficient of determination (R2) and reductions in the root mean square error (RMSE). The BEST-1DConvNet model achieved significant performance enhancements compared to the MSC + SNV + 1D + SVM model. Notably, the R2 value for diesel increased by approximately 48.85% despite a marginal RMSE decrease of 0.92%. R2 increased by 11.30% with a 3.32% RMSE reduction for gasoline, and it increased by 8.71%, accompanied by a 3.51% RMSE decrease for milk. In conclusion, the BEST-1DConvNet model demonstrates superior predictive accuracy and reliability in NIRS data analysis, marking a substantial leap forward in spectral analysis technology. This advancement could potentially streamline their integration into various industrial applications and highlight the role of convolutional neural networks in future chemometric methodologies.

Modeling transpiration using solar-induced chlorophyll fluorescence and photochemical reflectance index synergistically in a closed-canopy winter wheat ecosystem

The joint use of solar-induced chlorophyll fluorescence (SIF) and the photochemical reflectance index (PRI) has been shown to improve gross primary productivity (GPP) estimation across various plant functional types. However, the utility of PRI in combination with SIF for transpiration (T) estimation has not yet been explored. Additionally, current SIF-driven transpiration models including linear models, semi-mechanical models (combination of canopy conductance, gC, derived from a SIF and vapor pressure deficit, VPD, driven linear model with the Penman-Monteith model), and hybrid models (combination of gC derived from a SIF and VPD driven machine learning model with the Penman-Monteith model) have rarely been mutually assessed. Based on concurrent remotely sensed SIF and PRI, and eddy covariance flux measurements during one growing season for a winter wheat ecosystem in northern China, we investigated the mediating effect of PRI on SIF-driven T estimation under different VPD conditions and compared the performance of linear, semi-mechanical, and hybrid models in estimating T. Our results showed that the mediating effect of PRI on T described in the SIF-driven linear, semi-mechanistic, and hybrid models was significant under high VPD conditions rather than under low VPD conditions. Specifically, based on T partitioned using an underlying water use efficiency method as a benchmark, the root mean square error (RMSE) value of the PRI-mediated linear, semi-mechanistic, and hybrid models was 28.01 W/m2, 22.25 W/m2, and 28.71 W/m2 lower, respectively, than those of the corresponding models without PRI when VPD was >1.5 kPa. Based on T partitioned using a transpiration estimation algorithm as a benchmark, these three models also exhibited a significant reduction in RMSE under high VPD conditions after considering PRI. The main rationale behind the PRI improvement is that PRI can track photosynthetic dynamics under high VPD conditions. Based on the simulation results of the Soil-Canopy-Observation of Photosynthesis and Energy fluxes (SCOPE) model, PRI can serve as an indicator for non-photochemical quenching (NPQ) within this ecosystem. Consequently, PRI can enhance the capability of SIF to characterize the energy dissipation of photosynthetically active radiation and help SIF to yield more accurate information on GPP and gc under high VPD conditions. Finally, the order of model performance in estimating T was generally hybrid model > semi-mechanistic model > linear model. Our findings show the effectiveness of PRI for improving SIF-driven transpiration estimation under high VPD conditions and provide a new hybrid model for estimating T from SIF.

Can a Sparse Network of Cosmic Ray Neutron Sensors Improve Soil Moisture and Evapotranspiration Estimation at the Larger Catchment Scale?

AbstractCosmic‐ray neutron sensors (CRNS) fill the gap between locally measured in‐situ soil moisture (SM) and remotely sensed SM by providing accurate SM estimation at the field scale. This is promising for improving hydrologic model predictions, as CRNS can provide valuable information on SM in the root zone at the typical scale of a model grid cell. In this study, SM measurements from a network of 12 CRNS in the Rur catchment (Germany) were assimilated into the Terrestrial System Modeling Platform (TSMP) to investigate its potential for improving SM, evapotranspiration (ET) and river discharge characterization and estimating soil hydraulic parameters at the larger catchment scale. The data assimilation (DA) experiments (with and without parameter estimation) were conducted in both a wet year (2016) and a dry year (2018) with the ensemble Kalman filter (EnKF), and later verified with an independent year (2017) without DA. The results show that SM characterization was significantly improved at measurement locations (with up to 60% root mean square error (RMSE) reduction), and that joint state‐parameter estimation improved SM simulation more than state estimation alone (more than 15% additional RMSE reduction). Jackknife experiments showed that SM at verification locations had lower and different improvements in the wet and dry years (an RMSE reduction of 40% in 2016 and 16% in 2018). In addition, SM assimilation was found to improve ET characterization to a much lesser extent, with a 15% RMSE reduction of monthly ET in the wet year and 9% in the dry year.

An Empirical Modal Decomposition-Improved Whale Optimization Algorithm-Long Short-Term Memory Hybrid Model for Monitoring and Predicting Water Quality Parameters

Prediction of water quality parameters is a significant aspect of contemporary green development and ecological restoration. However, the conventional water quality prediction models have limited accuracy and poor generalization capability. This study aims to develop a dependable prediction model for ammonia nitrogen concentration in water quality parameters. Based on the characteristics of the long-term dependence of water quality parameters, the unique memory ability of the Long Short-Term Memory (LSTM) neural network was utilized to predict water quality parameters. To improve the accuracy of the LSTM prediction model, the ammonia nitrogen data were decomposed using Empirical Modal Decomposition (EMD), and then the parameters of the LSTM model were optimized using the Improved Whale Optimization Algorithm (IWOA), and a combined prediction model based on EMD-IWOA-LSTM was proposed. The study outcomes demonstrate that EMD-IWOA-LSTM displays improved prediction accuracy with reduced RootMean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) in comparison to the LSTM and IWOA-LSTM approaches. These research findings better enable the monitoring and prediction of water quality parameters, offering a novel approach to preventing water pollution rather than merely treating it afterwards.

Evaluating data-driven and hybrid modeling of terrestrial actual evapotranspiration based on an automatic machine learning approach

The performances of physics-based, data-driven, and hybrid models for estimating terrestrial actual evapotranspiration (ETa) is currently under debate, which requires thorough evaluations of those models particularly with recent developments in automatic machine learning (AML) techniques. In this study, six AML-based models were first constructed using the H2O-AML platform, from which an optimal (AML-OP) model was selected for estimating daily ETa at ecosystem scales. In addition, hybrid models were developed by combining the six AML models with surface conductance (Gs) inverted from the Penman-Monteith equation and an optimal (PM-OP) model was also selected. With 15 predictor variables as model inputs that were compiled from various data sources, the performances of those models for estimating daily ETa were evaluated using observed data from the FLUXNET2015 dataset. The results revealed that no models showed consistently low noise levels across different ecosystem types, making it necessary to use AML techniques for selecting ecosystem-specific models. Interestingly, the AML-OP models (root mean square error (RMSE) and symmetric mean absolute percentage error (SMAPE) were 0.16–0.31 mm d-1 and 9 %–36 % respectively) showed slightly better predictive results than the PM-OP models (RMSE and SMAPE were 0.23–0.36 mm d-1 and 15 %–68 % respectively), likely owing to model parameter uncertainties and tight constraints of physical models on application condition. Secondly, as ETa nonlinearly responds to environmental variables, model predictability under extreme weather (drought and heatwave) conditions was examined. The results showed that the prediction of the AML-OP and PM-OP models expectedly worsened (RMSE and SMAPE increased by 0.06–0.77 mm d-1 and −19 % to 79 %, respectively); however, the AML-OP model still outperformed the PM-OP model in most ecosystems, further underscoring the need to understand ETa regulation mechanisms under varying climatic conditions. Finally, the PM-OP models developed here provided better daily ETa estimates compared to other recently proposed hybrid models (RMSE reduced by 0.98–1.80 mm d-1). Both models can be better applied to wetlands that have been less frequently evaluated previously (RMSE reduction of 0.22 mm d-1 and 0.18 mm d-1 for the AML-OP and PM-OP models).

An Improved Carrier-Smoothing Code Algorithm for BDS Satellites with SICB

Carrier Smoothing Code (CSC), as a low-pass filter, has been widely used in GNSS positioning processing to reduce pseudorange noise via carrier phases. However, current CSC methods do not consider the systematic bias between the code and carrier phase observation, also known as Satellite-induced Code Bias (SICB). SICB has been identified in the BDS-2 and the bias will reduce the accuracy or reliability of the CSC. To confront bias, an improved CSC algorithm is proposed by considering SICB for GEO, IGSO, and MEO satellites in BDS constellations. The correction model of SICB for IGSO/MEO satellites is established by using a 0.1-degree interval piecewise weighted least squares Third-order Curve Fitting Method (TOCFM). The Variational Mode Decomposition combined with Wavelet Transform (VMD-WT) is proposed to establish the correction model of SICB for the GEO satellite. To verify the proposed method, the SICB model was established by collecting 30 Multi-GNSS Experiment (MGEX) BDS stations in different seasons of a year, in which the BDS data of ALIC, KRGG, KOUR, GCGO, GAMG, and SGOC stations were selected for 11 consecutive days to verify the effectiveness of the algorithm. The results show that there is obvious SICB in the BDS-2 Multipath (MP) combination, but the SICB in the BDS-3 MP is smaller and can be ignored. Compared with the modeling in the references, TOCFM is more suitable for IGSO/MEO SICB modeling, especially for the SICB correction at low elevation angles. After the VMD-WT correction, the Root Mean Square Error (RMSE) of SICB of B1I, B2I, and B3I in GEO satellites is reduced by 53.35%, 63.50%, and 64.71% respectively. Moreover, we carried out ionosphere-free Single Point Positioning (IF SPP), Ionosphere-free CSC SPP (IF CSC SPP), CSC single point positioning with the IGSO/MEO SICB Correction based on the TOCFA Method (IGSO/MEO SICB CSC), and CSC single point positioning with the IGSO/MEO/GEO SICB correction based on VMD-WT and TOCFA (IGSO/MEO/GEO SICB CSC), respectively. Compared to IF SPP, the average improvement of the IGSO/MEO/GEO SICB CSC algorithm in the north, east, and up directions was 24.42%, 27.94%, and 24.98%, respectively, and the average reduction in 3D RMSE is 24.54%. Compared with IF CSC SPP, the average improvement of IGSO/MEO/GEO SICB CSC is 7.03%, 6.50%, and 10.48% in the north, east, and up directions, respectively, while the average reduction in 3D RMSE was 9.86%. IGSO/MEO SICB mainly improves the U direction positioning accuracy, and GEO SICB mainly improves the E and U direction positioning accuracy. After the IGSO/MEO/GEO SICB correction, the overall improvement was about 10% and positioning improved to a certain extent.

Improving Polarimetric Radar-Based Drop Size Distribution Retrieval and Rain Estimation Using a Deep Neural Network

Abstract Raindrop size distributions (DSD) and rain rate have been estimated from polarimetric radar data using different approaches with the accuracy depending on the errors both in the radar measurements and the estimation methods. Herein, a deep neural network (DNN) technique was utilized to improve the estimation of the DSD and rain rate by mitigating these errors. The performance of this approach was evaluated using measurements from a two-dimensional video disdrometer (2DVD) at the Kessler Atmospheric and Ecological Field Station in Oklahoma as ground truth with the results compared against conventional estimation methods for the period 2006–17. Physical parameters (mass-/volume-weighted diameter and liquid water content), rain rate, and polarimetric radar variables (including radar reflectivity and differential reflectivity) were obtained from the DSD data. Three methods—physics-based inversion, empirical formula, and DNN—were applied to two different temporal domains (instantaneous and rain-event average) with three diverse error assumptions (fitting, measurement, and model errors). The DSD retrievals and rain estimates from 18 cases were evaluated by calculating the bias and root-mean-squared error (RMSE). DNN produced the best performance for most cases, with up to a 5% reduction in RMSE when model errors existed. DSD and rain estimated from a nearby polarimetric radar using the empirical and DNN methods were well correlated with the disdrometer observations; the rain-rate estimate bias of the DNN was significantly reduced (3.3% in DNN vs 50.1% in empirical). These results suggest that DNN has advantages over the physics-based and empirical methods in retrieving rain microphysics from radar observations.

Improving the Intensity Forecast of Tropical Cyclones in the Hurricane Analysis and Forecast System

Abstract A modification to the mixing length formulation in a planetary boundary layer (PBL) scheme is introduced to improve the intensity forecast of tropical cyclones (TCs) in a basin-scale Hurricane Analysis and Forecast System (HAFS) for the real-time experiment in 2021. The 2020 basin-scale HAFS with the physics suite of the NCEP operational Global Forecast System performs well in terms of the reduced root-mean-square (RMS) errors in track and intensity except for the mean intensity bias, compared with NCEP operational hurricane models. To address the large intensity bias issue, the vertical mixing length near the surface used in the PBL scheme is increased to follow the similarity theory, consistent with that used in the surface layer scheme. Test results show that the RMS error and bias in intensity are further reduced without the degradation of the track forecast. An idealized one-dimensional TC PBL model is used to understand the model response to the modification, indicating that the radial wind is strengthened to dynamically balance the enhanced downward momentum mixing. This is also exhibited in the case study of a three-dimensional HAFS simulation, with the improved vertical distribution of the simulated wind speed in the eyewall area. Given the improvement, the modification has been implemented in one of the configurations of the first version of the operational HAFS at NCEP. Finally, the adjustment of the parameterization of diffusion and mixing in TC simulations is discussed. Significance Statement A modification to the mixing length formulation in a PBL scheme is described, which improves the intensity forecast of tropical cyclones simulated in the Hurricane Analysis and Forecast System (HAFS). Retrospective tests indicate that the modification can reduce the root-mean-square error and bias of the simulated TC intensity by 5%–10% and 50%, respectively. This modification has been implemented in one of the operational configurations of HAFS, version 1, at NCEP, improving the hurricane model guidance.

Prediction of body composition in growing-finishing pigs using ultrasound based back-fat depth approach and machine learning algorithms

Timely monitoring and precise estimation of body composition parameters, such as fat mass (FM) and fat-free mass (FFM), are crucial for pig production. Therefore, this study aimed to utilize three machine learning models, namely multiple linear regression (MLR), random forest regression (RFR), and support vector regression (SVR), to predict FM and FFM in growing-finishing pigs using four input combinations of three variables, i.e., mass of pigs, feed intake, and surface temperature of pigs. An ultrasound-based back-fat depth measurement approach was used to determine FM and FFM, and these measurements were compared with reference measurements obtained from slaughtered pigs. Data from two experimental periods in 2021 and 2022 were used for training and testing these models. Performance metrics, including the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE), were used to evaluate the models' performance and stability. The results showed that the SVR model had the highest accuracy in predicting FM and FFM, with the ability to explain the relationship between input and target variables up to 94.4% in FM and 94.6% in FFM prediction. Additionally, the SVR model consistently outperformed the RFR and MLR models in predicting FM, with an increase in R2 of up to 6.72% and 27.96%, respectively, and a reduction in RMSE of up to 24.06% and 36.82%, respectively, across different input combinations. Similar results were obtained in FFM prediction, where the SVR model showed an increase in R2 of up to 6.47% and 22.45%, and a reduction in RMSE of up to 23.96% and 36.57% compared to RFR and MLR models, respectively. Moreover, the SVR model demonstrated the highest stability, with only 2.9% to 3.3% decrease in R2 during the testing phase compared to the training phase, while the RFR model exhibited the worst stability. Findings of the present study suggested that the SVR model was the most stable and reliable, along with the ultrasound-based back-fat depth approach for measuring FM and FFM in growing-finishing pigs. This approach could aid in monitoring meat quality and providing a rapid overview of body composition for pig farmers.

Community-Based Matrix Factorization (CBMF) Approach for Enhancing Quality of Recommendations.

Matrix factorization is a long-established method employed for analyzing and extracting valuable insight recommendations from complex networks containing user ratings. The execution time and computational resources demanded by these algorithms pose limitations when confronted with large datasets. Community detection algorithms play a crucial role in identifying groups and communities within intricate networks. To overcome the challenge of extensive computing resources with matrix factorization techniques, we present a novel framework that utilizes the inherent community information of the rating network. Our proposed approach, named Community-Based Matrix Factorization (CBMF), has the following steps: (1) Model the rating network as a complex bipartite network. (2) Divide the network into communities. (3) Extract the rating matrices pertaining only to those communities and apply MF on these matrices in parallel. (4) Merge the predicted rating matrices belonging to communities and evaluate the root mean square error (RMSE). In our experimentation, we use basic MF, SVD++, and FANMF for matrix factorization, and the Louvain algorithm is used for community division. The experimental evaluation on six datasets shows that the proposed CBMF enhances the quality of recommendations in each case. In the MovieLens 100K dataset, RMSE has been reduced to 0.21 from 1.26 using SVD++ by dividing the network into 25 communities. A similar reduction in RMSE is observed for the datasets of FilmTrust, Jester, Wikilens, Good Books, and Cell Phone.