Relative Root Mean Square Error Research Articles

Weight estimation models for commercial Pinus radiata wood in small felling stands based on UAV-LiDAR data

Uncrewed Aerial Vehicles (UAVs) equipped with Light Detection and Ranging (LiDAR) scanners have been adopted as an effective tool for conducting forest inventories, reducing field work and associated costs. These studies are based on obtaining information on volume, height and diameter at breast height (DBH). However, in the timber sector in Galicia (Spain)the variable used as the unit of purchase/sale is "weight". Therefore, this paper sets out to test different machine learning algorithms, such as multiple linear regression (MLR), MLR log-transformed (MRL-LT), Principal Component Analysis (PCA) and Random Forest (RF) to obtain a methodology applicable in the study area and replicable in other areas, with real utility in the forestry industry for determining the weight of Pinus radiata wood. These models are based on 73 observations and 19 predictors and have been developed and applied to a total of 33 Forest Cuts (FC) divided into 5204 tesserae. The models are validated by Fold Cross-Validation, with RMSE (relative root mean square error), R2 and MAE (mean absolute error) values being calculated. Of the four models studied, the PCA model performs best (R2=0.85, RMSE=1.84, MAE=1.46), followed by the MRL-LT which gives a value of R2=0.82 (RMSE=1.84, MAE=1.46). The actual figure for total Pinus radiata timber harvested was 35,440.54 t The PCA model estimated a total of 35,913.53 t (r = 0.98, R2=0.97, εr=9.35 %), while the MRL-LT model calculated 35,847.92 t (r = 0.99, R2=0.98, εr=8.85 %). On the other hand, the weight was underestimated by the MLR model and overestimated by the RF. The plain MLR model underestimated the "weight" of the wood, while the MRL-LT model provided the best result, with errors of less than 10 % in 72 % of the FCs. In conclusion, this study provides a powerful tool that will enable stakeholders in the community timber industry to accurately estimate the weight of timber in Pinus radiata stands, enhancing a more highly automated forest inventory that can optimise the number of field operations to be performed.

Efficient automated method to extract EOG artifact by combining Circular SSA with wavelet and unsupervised clustering from single channel EEG

The emergence of affordable single-channel electroencephalography (EEG) headbands has introduced new possibilities for applications in brain–computer interface (BCI) systems and health monitoring. However, these EEG signals are often contaminated by electrooculogram (EOG) activity caused by eyelid blinking. This poses a challenge, especially in portable EEG devices that typically have limited or single EEG channels. The presence of eye-blink artifacts can mislead the diagnosis of brain state activity. Consequently, there is a growing demand to extract eye-blink artifacts from single-channel EEG signals. However, during the process of removing these artifacts from contaminated EEG signals, low-frequency artifact components in non-artifact regions are also inadvertently eliminated. In this work, an automated, robust and efficient framework is presented by combining Circular Singular Spectral Analysis (Ci_SSA) with wavelet analysis and unsupervised clustering. This framework aims to remove artifact segments while preserving the low-frequency content in non-artifact regions. Simulations were carried out on both synthetic and real data, and the results were compared with alternative methods. The performance of the proposed method is evaluated by metrics such as Relative Root Mean Square Error (RRMSE), Mean Absolute Error (MAE), Correlation Coefficient (CC) and Artifact Rejection Ratio (ARR) for synthetic signals, as well as Signal-to-Error Ratio (SER) and Artifact-to-Residue Ratio (AReR) for real EEG signals. After applying the proposed algorithm to filter the contaminated EEG signal, a noticeable enhancement in the detection accuracy of driver fatigue is observed as compared to the pre-filtering stage.

Assessing the performance of several numerical methods for estimating Weibull parameters for Wind Energy Applications: A case study of Al-Hodeidah in Yemen

The estimation of wind potential is generally assessed using the two parameters of Weibull distribution (k, c). Relative Percentage Error (RPE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Relative Root Mean Square Error (RRMSE), Correlation Coefficient (R), and Index of Agreement (IA) are calculated to comparatively analyze five numerical methods of computing Weibull parameters. The five selected methods are (Empirical Justus (EMJ), Energy Pattern Factor (EPFM), Maximum Likelihood (MLM), Method of Moment (MOM), and L-moment Estimation Method (L-MOM)). With the daily wind speed dataset for the year 2014 measured at 10 m height, the five methods have been applied on the study site Al-Hodeidah city in Yemen. Therefore, compared to other methods, the EPFM method is the most accurate method for estimating the Weibull parameters, while the L-MOM method is the least accurate at 10, 30, and 50 m heights. Moreover, this study reveals that the parameter remains the same with height, while the c parameter increases with height. The values of the skewness and kurtosis of wind speed and power density do not change as height changes.

ChinaWheatYield30m: a 30 m annual winter wheat yield dataset from 2016 to 2021 in China

Abstract. Generating spatial crop yield information is of great significance for academic research and guiding agricultural policy. Existing public yield datasets have a coarse spatial resolution, spanning from 1 to 43 km. Although these datasets are useful for analyzing large-scale temporal and spatial change in yield, they cannot deal with small-scale spatial heterogeneity, which happens to be the most significant characteristic of the Chinese farmers' economy. Hence, we generated a 30 m Chinese winter wheat yield dataset (ChinaWheatYield30m) for major winter-wheat-producing provinces in China for the period 2016–2021 with a semi-mechanistic model (hierarchical linear model, HLM). The yield prediction model was built by considering the wheat growth status and climatic factors. It can estimate wheat yield with excellent accuracy and low cost using a combination of satellite observations and regional meteorological information (i.e., Landsat 8, Sentinel 2 and ERA5 data from the Google Earth Engine (GEE) platform). The results were validated using in situ measurements and census statistics and indicated a stable performance of the HLM based on calibration datasets across China, with a correlation coefficient (r) of 0.81 and a relative root mean square error (rRMSE) of 12.59 %. With regards to validation, the ChinaWheatYield30m dataset was highly consistent with in situ measurement data and statistical data (p<0.01), indicated by an r (rRMSE) of 0.72** (15.34 %) and 0.69** (19.16 %). The ChinaWheatYield30m is a sophisticated dataset with both high spatial resolution and excellent accuracy; such a dataset will provide basic knowledge of detailed wheat yield distribution, which can be applied for many purposes including crop production modeling and regional climate evaluation. The ChinaWheatYield30m dataset generated from this study can be downloaded from https://doi.org/10.5281/zenodo.7360753 (Zhao et al., 2022b).

Comparing analytical strategies for balancing site-level characteristics in stepped-wedge cluster randomized trials: a simulation study

BackgroundStepped-wedge cluster randomized trials (SWCRTs) are a type of cluster-randomized trial in which clusters are randomized to cross-over to the active intervention sequentially at regular intervals during the study period. For SWCRTs, sequential imbalances of cluster-level characteristics across the random sequence of clusters may lead to biased estimation. Our study aims to examine the effects of balancing cluster-level characteristics in SWCRTs.MethodsTo quantify the level of cluster-level imbalance, a novel imbalance index was developed based on the Spearman correlation and rank regression of the cluster-level characteristic with the cross-over timepoints. A simulation study was conducted to assess the impact of sequential cluster-level imbalances across different scenarios varying the: number of sites (clusters), sample size, number of cross-over timepoints, site-level intra-cluster correlation coefficient (ICC), and effect sizes. SWCRTs assumed either an immediate “constant” treatment effect, or a gradual “learning” treatment effect which increases over time after crossing over to the active intervention. Key performance metrics included the relative root mean square error (RRMSE) and relative mean bias.ResultsFully-balanced designs almost always had the highest efficiency, as measured by the RRMSE, regardless of the number of sites, ICC, effect size, or sample sizes at each time for SWCRTs with learning effect. A consistent decreasing trend of efficiency was observed by increasing RRMSE as imbalance increased. For example, for a 12-site study with 20 participants per site/timepoint and ICC of 0.10, between the most balanced and least balanced designs, the RRMSE efficiency loss ranged from 52.5% to 191.9%. In addition, the RRMSE was decreased for larger sample sizes, larger number of sites, smaller ICC, and larger effect sizes. The impact of pre-balancing diminished when there was no learning effect.ConclusionThe impact of pre-balancing on preventing efficiency loss was easily observed when there was a learning effect. This suggests benefit of pre-balancing with respect to impacting factors of treatment effects.

Mapping site index in coniferous forests using bi-temporal airborne laser scanning data and field data from the Swedish national forest inventory

Recent advancements in remote sensing of forests have demonstrated the capabilities of three-dimensional data acquired by airborne laser scanning (ALS) and, consequently, have become an integral part of enhanced forest inventories in Northern Europe. In Sweden, the first national laser scanning revolutionised forest management planning through low-cost production of large-scale and spatially explicit maps of forest attributes such as basal area, volume, and biomass, compared to the earlier practice based on field survey data. A second scanning at the national level was launched in 2019, and it provides conditions for the estimation of height growth and site index. Accurate and up-to-date information about site productivity is relevant for planning silvicultural treatments and for the prognosis of forest status and development over time. In this study, we explored the potential of bi-temporal ALS data and other auxiliary information to predict and map site productivity by site index according to site properties (SIS) of Norway spruce (Picea abies (L.) Karst) and Scots pine (Pinus sylvestris L.) in even-aged stands in Sweden. We linked ground survey data of SIS from more than 11,500 plots of the Swedish National Forest Inventory (NFI) to bi-temporal ALS data to predict and map site index using an area-based method and two regression modelling strategies: (1) a multiple linear regression (MLR) model with an ordinary least-squares parameter estimation method, and (2) a non-parametric random forests (RF) model optimised for hyper-parameter tuning. For model development, permanent plots were used, whereas the validation was done on the temporary plots of the Swedish NFI and an independent stand-level dataset. Species-specific models were developed, and the root mean square error (RMSE) metric was used to quantify the residual variability around model predictions. For both species, the MLR model gave precise and accurate estimates of SIS. The RMSE for SIS predictions was in the range of 1.96 – 2.11 m, and the relative RMSE was less than 10 % (7.68 – 9.49 %) of the reference mean value. Final predictors of site index include metrics of 90th percentile height and annual increment in the 95th percentile height, altitude, distance to coast, and soil moisture. Country-wide maps of SIS and the corresponding pixel-level prediction errors at a spatial resolution of 12.5 m grid cells were produced for the two species. Independent validations show the site index maps are suitable for use in operational forest management planning in Sweden.

A Reconstruction Method for Ionospheric foF2 Spatial Mapping over Australia

To improve the accuracy of predicting the ionospheric critical frequency of the F2 layer (foF2), a reconstruction method for the spatial map of the ionospheric foF2 based on modified geomagnetic dip coordinates is proposed. Based on the strong correlation between the ionospheric foF2 and geomagnetic coordinates, the variation function of ionospheric distance is built. In the end, the spatial map of the ionospheric foF2 is predicted by solving the Kriging equation. The results show that the regional characteristics of the ionospheric foF2 analyzed by the proposed method are consistent with the observations. Compared with the reconstructed value of foF2 using traditional geographic coordinates, the root-mean-square error (RMSE) in high solar activity years decreased by 0.43 MHz, and the relative RMSE decreased by 5.48%; The RMSE decreased by 0.35 MHz during low solar activity which is 5.99% lower to relative RMSE. The research results provide support for high-frequency communication frequency selection.

CFD Simulation of Air-Glass Beads Fluidized Bed Hydrodynamics

The hydrodynamic behaviour of air-glass beads bubbling fluidized bed reactor containing spherical glass beads is numerically studied, using OpenFoam v7 CFD software. Both Gidaspow and Syamlal-O'Brien drag models are used to calculate momentum exchange coefficients. Simulation predictions of pressure loss, bed expansion rate, and air volume fraction parameters were compared and validated using data, existing in the literature obtained experimentally and performed by other numerical softwares. Pressure loss and rate of bed expansion were calculated with relative root mean square error (RMSE) equal to 0.65 and 0.095 respectively; Syamlal-O'Brien model is considered more accurate than Gidaspow model. Hence, numerical model reliability developed on OpenFoam was also proved. The hydrodynamic aspect study of the fluidized bed reactor was then performed, to analyse the impact of inlet air velocity (U) on particles motion. It was revealed that with U increment, air and glass beads axial velocities increase in the reactor centre and decrease in the sidewalls. Thus, a greater particle bed expansion is induced and the solid particles accumulated highly on the reactor sidewalls. In general, with the increase of U, the solid volume fraction decreases from 0.63 to 0.58 observed at 0.065 m/s and 0.51 m/s, respectively.

Application of Machine Learning Algorithms to Describe the Characteristics of Dairy Sheep Lactation Curves.

In recent years, machine learning (ML) algorithms have emerged as powerful tools for predicting and modeling complex data. Therefore, the aim of this study was to evaluate the prediction ability of different ML algorithms and a traditional empirical model to estimate the parameters of lactation curves. A total of 1186 monthly records from 156 sheep lactations were used. The model development process involved training and testing models using ML algorithms. In addition to these algorithms, lactation curves were also fitted using the Wood model. The goodness of fit was assessed using correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and relative root mean square error (RRSE). SMOreg was the algorithm with the best estimates of the characteristics of the sheep lactation curve, with higher values of r compared to the Wood model (0.96 vs. 0.68) for the total milk yield. The results of the current study showed that ML algorithms are able to adequately predict the characteristics of the lactation curve, using a relatively small number of input data. Some ML algorithms provide an interpretable architecture, which is useful for decision-making at the farm level to maximize the use of available information.

Retrieving 3D distributions of atmospheric particles using Atmospheric Tomography with 3D Radiative Transfer – Part 2: Local optimization

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.

A New Estimator of Shannon Entropy with Application to Goodness-of-Fit Test to Normal Distribution

In this paper, a new estimator of the Shannon entropy of a random variable X having a probability density function \(\mathit{f}\)(\(\mathit{x}\)) is obtained based on window size spacings. Under the standard normal, standard exponential and uniform distributions, the estimator is shown to have relative low bias and low RMSE through extensive simulation study at sample sizes 10, 20, and 30. Based on the results, it is recommended as a good estimator of the entropy. Also, the new estimator is applied in goodness-of-fit test to normality. The statistic is affine invariant and consistent and the results show that it is a good statistic for assessing univariate normality of datasets.

Phase behaviour and physical properties of dimethyl ether (DME)/flue gas/water/heavy oil systems under reservoir conditions

The application of a mixture of dimethyl ether (DME) and flue gas (i.e., CO2 + N2) is a promising method to recover heavy oil; however, the phase behaviour and physical properties of DME/flue gas/water/heavy oil systems are not well quantified. In this study, theoretical and experimental techniques are developed to determine phase behaviour and physical properties of the aforementioned systems at pressures ranging from 2 MPa to 20 MPa and temperatures spanning from 352.15 K to 433.15 K. Experimentally, eight constant composition expansion (CCE) tests are carried out to obtain new experimental data for the DME/flue gas/water/heavy oil systems for the first time. Theoretically, a thermodynamic model that incorporates the Peng-Robinson equation of state (PR EOS), a modified α function, the Péneloux volume-translation strategy, and the Huron-Vidal (HV) mixing rule has been modified to reproduce the measured phase equilibria data. The tuned binary interaction parameters (BIPs) are utilized in conjunction with the thermodynamic model to accurately predict saturation pressure (Psat) and swelling factors (SFs) with a root-mean-squared relative error (RMSRE) of 3.32% and 0.57%, respectively. Furthermore, the newly proposed model demonstrates its high accuracy in forecasting the oleic/vapor (LV) two-phase boundaries for N2/heavy oil systems and DME/CO2/heavy oil systems with an RMSRE of 1.93% and 2.77%, respectively. Similarly, the accuracies of the predicted aqueous/oleic/vapor (ALV) three-phase boundaries for N2/water/heavy oil systems and DME/flue gas/water/heavy oil systems are 2.85% and 3.47%, respectively. Water is found to increase the phase boundaries for DME/CO2/heavy oil systems but decrease those of N2/heavy oil systems and DME/flue gas/heavy oil systems. Additionally, as the concentration of N2 and/or CO2 in the mixture is increased, its Psat is increased.

An active piezoelectric damping vibration control system for the sting used in wind tunnel

In wind tunnel tests, the cantilever sting supporting system often suffers from low-frequency and large-amplitude resonance due to its inherent low structural damping characteristic, resulting in the degradation of data quality and structural safety. To improve wind tunnel testing safety and data accuracy, this paper is dedicated to establish an active vibration control system using piezoelectric stack actuators. A novel methodology of vibration monitoring based on modal transformation, which uses measured strain and a Strain-to-Displacement Transformation (SDT) matrix to reconstruct dynamic displacement field, is proposed herein. Meanwhile, strain sensor positions are optimized by an improved Particle Swarm Optimization (PSO) algorithm to reduce systematic estimation errors of this method. Furthermore, a Back-Propagated Neutral Network (BPNN) is established to implement a self-adaptive control strategy. A series of verification tests are performed to demonstrate the validity of the proposed system. Experimental results indicate that the relative Root Mean Square Error (RMSE) between estimated vibration displacement and measured vibration displacement is less than 3%, and a vibration attenuation of over 14 dB/Hz is achieved in ground tests, proving the superiority of this intelligent active vibration suppression system.

Predicting California bearing ratio of HARHA-treated expansive soils using Gaussian process regression

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.

A similarity distance-based space-time random forest model for estimating PM2.5 concentrations over China

China has experienced persistent fine particulate matter (PM2.5) pollution for the past few years, which adversely affects both physical and mental health. The availability of high-accuracy and full-coverage PM2.5 products will be of substantial value in formulating effective policies to combat and regulate PM2.5 pollution. Therefore, we have developed a similarity distance-based space-time random forest (SDSTRF) model to estimate daily PM2.5 concentrations over China by integrating surface measurements, satellite aerosol products, meteorological data, and auxiliary information. The proposed model not only accounts for spatial-temporal heterogeneity, but also uses the similarity distance to avoid errors caused by outliers. It has undergone rigorous validation through three different cross-validation (CV) approaches and has shown high and stable accuracy, particularly in the site-based CV with a coefficient of determination (R2) of 0.87, and a root mean square error (RMSE) of 10.68 μg/m3, along with a relative RMSE (rRMSE) of 27.48%. In addition, the leave-out data are predicted to determine if the SDSTRF model is accurate in its predictive power, which achieves an impressive site-based CV R2 of 0.80 and an RMSE of 12.89 μg/m3, along with an rRMSE of 33.01%. The results from a variety of validation approaches strongly indicate that the SDSTRF model can provide accurate estimation of PM2.5 concentrations at different time scales and outperform many other space-time models by incorporating similarity distance. The proposed model would be a promising application in air pollution studies with remote sensing.

Estimation of subsurface salinity and analysis of Changjiang diluted water volume in the East China Sea

In the East China Sea (ECS), the sea surface salinity (SSS) changes as the Changjiang Diluted Water (CDW) propagates toward the Korean Peninsula via the ocean current and winds every summer annually. Although the vertical stratifications resulting from the CDW volume changes are important, it has not been analyzed yet. Therefore, in this study, we aimed to estimate the salinity at a depth of 10 m (S10m) using convolutional neural network (CNN) model based on multi-satellite measurements and analyze CDW volume variations. The main CDW mass in the ECS reaches approximately 10 m in depth; thus, the CNN model was developed using sea surface physical factors as input and in situ S10m obtained from the National Institute of Fisheries Science (NIFS) as ground truth data from 2015 to 2021. The CNN tests result showed a determination coefficient (R2) of 0.81, root mean square error (RMSE) of 0.63 psu, and relative RMSE (RRMSE) of 2.00%. Unlike the sea surface distribution, the spatial distribution of S10m showed that the CDW was predominantly present in the center of the ECS. From SHapley Additive exPlanations (SHAP) analysis, SSS exhibited a strong positive relationship with S10m, and the sea level anomaly showed a strong negative relationship. After calculating the volume of the CDW from the surface to a depth of 10 m, the maximum (3.01×1012 m3) and minimum volumes (1.31×1012 m3) were represented in 2016 and 2018, respectively. Finally, the warming effect induced by the CDW volume changes was analyzed in two different years: 2016 and 2018. Specifically, in 2016, the sea surface temperature increased by more than 4.79 °C in the Ieodo location, while in 2018, it increased by 2.19 °C. Thus, our findings can obtain information about the volume variation of the CDW and its effect on the ECS in summer.

Wholesale Food Price Index Forecasts with the Neural Network

Food price forecasts in the agricultural sector have always been a vital matter to a wide variety of market participants. In this work, we approach this forecast problem for the weekly wholesale food price index in the Chinese market during a 10-year period of January 1, 2010–January 3, 2020. To facilitate the analysis, we propose the use of the nonlinear auto-regressive neural network. Technically, we investigate forecast performance, based upon the relative root mean square error (RRMSE) as the evaluation metrics, corresponding to one hundred and twenty settings that cover different algorithms for model estimations, numbers of hidden neurons and delays, and ratios for splitting the data. Our experimental result suggests the construction of the neural network with three delays and 10 hidden neurons, which is trained through the Levenberg–Marquardt algorithm, as the forecast model. It leads to high accuracy and stabilities with the RRMSEs of 1.93% for the training phase, 2.16% for the validation phase, and 1.95% for the testing phase. Comparisons of forecast accuracy between the proposed model and some other machine learning models, as well as traditional time-series econometric models, suggest that our proposed model leads to statistically significant better performance. Our results could benefit different forecast users, such as policymakers and various market participants, in policy analysis and market assessments.

Crown Information Extraction and Annual Growth Estimation of a Chinese Fir Plantation Based on Unmanned Aerial Vehicle–Light Detection and Ranging

Forest biomass dynamics are important indicators of forest productivity and carbon sinks, which are useful for evaluating forest ecological benefits and management options. Rapid and accurate methods for monitoring forest biomass would serve this purpose well. This study aimed at measuring aboveground biomass (AGB) and stand growth from tree crown parameters derived using unmanned aerial vehicle–light detection and ranging (UAV–LiDAR). We focused on 17-year-old Chinese fir plantations in a subtropical area in China and monitored them using UAV–LiDAR from February 2019 to February 2020. Two effective crown height (ECH) detection methods based on drone discrete point clouds were evaluated using ground survey data. Based on the evaluation results, the voxel method based on point cloud segmentation (root-mean-squared error (RMSE) = 0.62 m, relative RMSE (rRMSE) = 4.26%) was better than the tree crown boundary pixel sum method based on canopy height segmentation (RMSE = 1.26 m, rRMSE = 8.63%). The effective crown area (ECA) of an individual tree extracted using ECH was strongly correlated with the annual biomass growth (coefficient of determination (R2) = 0.47). The estimation of annual growth of individual tree crowns based on annual tree height increase (ΔH) derived from LiDAR was statistically significant (R2 = 0.33, p < 0.01). After adding the crown projection area or ECA, the model accuracy R2 increased to 0.57 or 0.63, respectively. As the scale increased to the plot level, the direct model with ECA (RMSE = 1.59 Mg∙ha−1∙a−1, rRMSE = 15.02%) had a better performance than the indirect model using tree height and crown diameter (RMSE = 1.81 Mg∙ha−1∙a−1, rRMSE = 17.10%). The mean annual growth rate of AGB per middle-aged Chinese fir tree was determined to be 8.45 kg∙a−1 using ECA and ΔH, and the plot-level growth rate was 11.47 Mg∙ha−1∙a−1. We conclude that the rapid and accurate monitoring of the annual growth of Chinese fir can be achieved based on multitemporal UAV–LiDAR and effective crown information.

Radar Sensing of Displacement Motions With High Robustness Against Additive Noise

Doppler radar uses phase demodulation to extract the target displacement motion contained in the phase of the echo signal. The demodulation performance is vulnerable to the additive Gauss noise. Especially when the signal-to-noise ratio (SNR) is extremely low in the scenarios of long-range or subtle displacement motion sensing, it may be impossible to extract the correct phase information. In this article, a phase demodulation method with high robustness against additive noise is proposed for accurate displacement motion reconstruction. Mathematical derivations are performed to analyze the noise effect on phase demodulation, and it shows that the influence of phase noise is much smaller than the additive noise. Based on this finding, the key idea of the proposed method is to transform the additive noise of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$I$</tex-math> </inline-formula> / <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> signals into phase noise. The simulation results validate the noise analysis and verify the high robustness of the proposed method against additive noise. Furthermore, experiments were carried out to evaluate the proposed method under different radial distances and displacement amplitudes. The experimental results show that the proposed method enables accurate motion sensing even in low-SNR scenarios. In our experiments, we observe that the relative root-mean-square error (RRMSE) of the reconstructed displacement motion can be greatly reduced with the proposed method.

LXGB: a machine learning algorithm for estimating the discharge coefficient of pseudo-cosine labyrinth weir

One of the practical and financial solutions to increase the efficiency of weirs is to modify the geometry of the plan and increase the length of the weir to a specific width. This increases the discharge coefficient (Cd) of the weir. In this study, a new weir referred to pseudo-cosine labyrinth weir (PCLW) was introduced. A hybrid machine learning LXGB algorithm was introduced to estimate the Cd of the PCLW. The LXGB is a combination of the linear population size reduction history-based adaptive differential evolution (LSHADE) and extreme gradient boosting (XGB) algorithm. Seven different input scenarios were presented to estimate the discharge coefficient of the PCLW weir. To train and test the proposed method, 132 data series, including geometric and hydraulic parameters from PCLW1 and PCLW2 models were used. The root mean square error (RMSE), relative root mean square error (RRMSE), and Nash–Sutcliffe model efficiency coefficient (NSE) indices were used to evaluate the proposed approach. The results showed that the input variables were the ratio of the radius to the weir height (R/W), the ratio of the length of the weir to the weir height (L/W), and the ratio of the hydraulic head to the weir height (H/W), with the average values of RMSE = 0.009, RRMSE = 0.010, and NSE = 0.977 provided better results in estimating the Cd of PCLW1 and PCLW2 models. The improvement compared to SAELM, ANFIS-FFA, GEP, and ANN in terms of R2 is 2.06%, 3.09%, 1.03%, and 5.15%. In general, intelligent hybrid approaches can be introduced as the most suitable method for estimating the Cd of PCLW weirs.