Relative Root Mean Square Error Research Articles

Dynamic Prediction Model for Progressive Surface Subsidence Based on MMF Time Function

It is imperative to timely and accurately predict the progressive surface subsidence caused by coal mining in the context of precision coal mining. However, the existing dynamic prediction methods that use time functions still have limitations, especially in the description of the moments of initiation and maximum subsidence velocity, which hinder their wide application. In this study, we proposed the MMF (Morgan–Mercer–Flodin) time function for predicting progressive surface subsidence based on the model assumptions and formula derivations. MMF time function can resolve the limitations in the description of the moments of initiation and maximum subsidence velocity perfectly. Afterward, we established the dynamic prediction model by combining the probability integral method with the MMF time function. Finally, using the measured subsidence data of working panel 22101 as an example, the accuracy and reliability of the dynamic prediction model was verified. The average RMSE and average relative RMSE (RRMSE) of prediction progressive subsidence using MMF time function are 46.65 mm and 4.63%, respectively. The accuracy is optimal compared with other time functions (for the average RMSE, Logistic time function is 80.57 mm, Gompertz time function is 79.77 mm, and Weibull time function is 90.61 mm; for the average RRMSE, Logistic time function is 7.66%, Gompertz time function is 7.73%, and Weibull time function is 8.62%). The results show that the method proposed in this paper can fully meet the requirements of practical engineering applications, achieve accurate dynamic prediction during the coal mining process, and provide good guidance for surface deformation and building protection.

Can meteorological data improve the short-term prediction of individual milk yield in dairy cows?

Many farms document daily milk yields of individual cows because these are a good indicator of cow well-being. It is established that extreme meteorological conditions influence the milk yields by causing heat and cold stress, whereas less is known about the effects of moderate changes in meteorological conditions. Thus, the aim of the present study was to evaluate whether individual daily milk yield predictions can be improved by considering such changes. We evaluated 8 years of milking and meteorological data from Eastern Switzerland with a total of 33,938 daily milkings from 145 Brown Swiss and 64 Swiss Fleckvieh cows. The cows were aged between 1.9 and 13.5 years at parturition. The data set was split into 7 periods according to the days in milk (DIM) and subsequently filtered into subsets by breed and parity. We applied Gaussian process regression to predict individual daily milk yield. We compared different models including DIM, lagged milk yield, and meteorological variables as features and found that models including the lagged milk yield performed best. Within the period of 5 to 90 DIM, we were able to predict individual next-day milk yield from the cow's last milkings with a root mean squared error (RMSE) of 2.1 kg. In contrast, without information on the previous milk yield, accuracy of milk yield prediction was lower, with an RMSE close to 8 kg. The models holding information about previous milk yields showed a substantial increase in performance. Within a more homogeneous data subset filtered by breed or parity or both, predictions were even better, with a relative RMSE of 4.3% for first-parity Fleckvieh cows. However, we found that including meteorological features, such as temperature, rainfall, wind speed, temperature humidity index, cooling degree, and barometric pressure, did not improve the predictions in any of the evaluated periods. This finding indicates that considering meteorological features in daily milk yield prediction models is not useful in moderate climates; considering lagged milk yield is sufficient. We hypothesize that this meteorological information, among other influences, is indirectly contained in the lagged milk yield.

A dynamic shelf-life prediction method considering actual uncertainty: Application to fresh fruits in long-term cold storage

Shelf-life is an important tool for visually conveying remaining food quality. However, the traditional printed shelf-life is a fixed value based on a stable environment, whereas food supplies undergo long-term dynamic conditions. Moreover, the accumulating effects of real-world uncertainty will lead to stochastic changes in remaining shelf-life in a probabilistic manner. Therefore, we proposed a novel dynamic shelf-life prediction method integrating the kinetic reaction and stochastic process. First, to predict practical changes in food quality indices (FQIs), we established the stochastic kinetic model, which combines basic deterministic modeling with zero-order reaction and the Arrhenius equation, and stochastic factor modeling with the Wiener process. Second, we conducted real-time probability analysis of remaining shelf-life to quantify the potential degeneration of food quality based on the established model. By using datasets monitoring firmness and Vitamin C of Kiwifruit in long-term cold storage to verify the performance of our proposed integrated model, we showed that our method was more accurate in modeling stochastic changes in FQIs than the traditional reaction model, resulting in mean absolute error, mean absolute percentage error, and root mean squared error (RMSE) less than 0.2136, 0.0162, and 0.7402, respectively. Furthermore, the shelf-life probability analysis was efficient, with relative RMSE 5.26% and computing time 0.047 s. This valuable food quality information can be provided to managers or customers to reduce food loss and waste.

The Performance of Sensitivity-Maps Method in Reconstructing Low Contrast and Multi-Contrast Objects for Microwave Imaging Applications

The microwave imaging system for breast tumor/cancer detection requires high sensitivity to detect abnormal tissue that has little contrast in high-density breasts. This paper proposes a qualitative microwave imaging system simulation based on inverse scattering using the sensitivity-maps method. This method utilizes two measurement types for system calibration: a reference object as a scatterer-free background and a calibration object to obtain the system's impulse response. The object under test (OUT) consists of an object with low dielectric contrast and a phantom with multiple low dielectric contrasts (multi-contrast). Reconstruction is carried out on three types of S-parameter measurement data, namely S_11,〖 S〗_21, and a combination of both. S-parameters are measured at several frequencies, which are 3, 10, 14, 15, 16, 20 GHz, and the combination of all those frequencies (multifrequency). Reconstructed images show that the system is capable of reconstructing dielectric objects accurately. Quantitatively, the results show that the multifrequency S_21 measurement yields the best image quality with relative root mean squared error (RRMSE) values of 0.1272 and structural similarity index (SSIM) of 0.9076. The designed imaging system also successfully reconstructs multi-contrast phantom accurately with RRMSE of 0.1434 and SSIM of 0.4609.

Comparison between deep learning architectures for the 1 km, 10/15-min estimation of downward shortwave radiation from AHI and ABI

The retrieval of downward shortwave radiation (DSR) with high spatiotemporal resolution and short latency is critical. It is the fundamental driving force of surface energy, carbon, and hydrological circulations, and a key energy source for photovoltaic electricity. However, existing methods face significant challenges owing to cloud heterogeneity and their reliance on other satellite-derived products, which hinder the retrieval of accurate and timely DSR with high spatiotemporal resolution. In addition to the spectral features used in traditional approaches, deep learning (DL) can incorporate the spatial and temporal features of satellite data. This study developed and compared three DL methods, namely the DenseNet, the bidirectional gated recurrent unit without surface albedo as inputs (BiGRUnor), and the convolutional neural network with gated recurrent unit without surface albedo as inputs (CNNGRUnor). These methods were used to estimate DSR at 1 km and 10/15 min resolutions directly from top-of-atmosphere reflectance over the Advanced Himawari Imager (AHI) onboard Himawari-8 and the Advanced Baseline Imager (ABI) onboard GOES-16 coverage, achieving high accuracies. The instantaneous root mean square error (RMSE) and relative RMSE for the three models were 68.4 (16.1%), 69.4 (16.3%), and 67.1 (15.7%) W/m2, respectively, which are lower than the baseline machine learning method, the multilayer perceptron model (MLP), with RMSE at 76.8 W/m2 (18.0%). Hourly accuracies for the three DL methods were 58.6 (14.1%), 57.8 (14.0%), and 57.3 (13.8%) W/m2, which are within the DSR RMSEs that we estimated for existing datasets of the Earth's Radiant Energy System (CERES) (88.8 W/m2, 21.4%) and GeoNEX (77.8 W/m2, 18.8%). The study illustrates that DL models that incorporate temporal information can eliminate the need for surface albedo as an input, which is crucial for timely monitoring and nowcasting of DSR. Incorporating spatial information can enhance retrieval accuracy in overcast conditions, and incorporating infrared bands can further improve the accuracy of DSR estimation.

Boosting the prediction accuracy of a process-based greenhouse climate-tomato production model by particle filtering and deep learning

By generating high quality data without the big time investment and economic cost of real experiments, dynamic greenhouse climate and crop simulation models can support decisions on greenhouse climate control, crop management and greenhouse design. The reliability of simulation-based decisions depends on both the prediction accuracy and interpretability of simulation models. The prediction accuracy of these simulation models can be increased by: 1) improving mechanisms in process-based models; 2) calibrating process-based model parameters; 3) deriving black-box relationships from data. Considering the descending interpretability from (1) to (3), this study presents a knowledge-based data-driven modelling approach where firstly a process-based model is selected and modified based on domain knowledge, then data-driven improvement is applied including two steps: parameter value estimation by particle filter (PF) and further black-box improvement by deep neural networks (DNN). The approach was tested with an example of greenhouse climate-tomato production system modelling. Modules from GreenLight (Katzin et al., 2020) and TOMSIM (Heuvelink, 1995, 1996) were selected, modified and integrated into a process-based greenhouse climate-tomato model. Validation showed that PF-calibration of five greenhouse parameters decreased the seasonal relative root mean squared error (RRMSE) of indoor air vapor pressure predictions from 40.7% of that before PF-calibration to 16.4%, while it did not decrease the RRMSE of indoor air temperature predictions. Combining the PF-calibrated model with a DNN trained on a season of data decreased the RRMSE of indoor air temperature from 15.0% without DNN to 6.7%, and decreased the RRMSE of indoor air vapor pressure to 12.6%. The knowledge-based data-driven greenhouse climate-tomato model had a relative error of 0.9% for seasonal total fresh yield, and an RRMSE of 6.6% for the cumulative yield throughout the season. If process-based model parameters were not calibrated before combining the model with DNNs, the required amount and diversity of DNN training data increased because more information needed to be learnt from data by the DNNs. Without PF-calibration, combining a DNN trained on 50 days of data with the process-based model resulted in RRMSEs of 44.8% and 31.8% for indoor air temperature and vapor pressure prediction, respectively; with PF-calibration, the RRMSEs were decreased to 13.1% and 17.9%. The proposed three-step knowledge-based data-driven approach can not only improve the model prediction accuracy, but can also help to track and interpret the improvements.

A Ground Point Fitting Method for Winter Wheat Height Estimation Using UAV-Based SfM Point Cloud Data

Height is a key factor in monitoring the growth status and rate of crops. Compared with large-scale satellite remote sensing images and high-cost LiDAR point cloud, the point cloud generated by the Structure from Motion (SfM) algorithm based on UAV images can quickly estimate crop height in the target area at a lower cost. However, crop leaves gradually start to cover the ground from the beginning of the stem elongation stage, making more and more ground points below the canopy disappear in the data. The terrain undulations and outliers will seriously affect the height estimation accuracy. This paper proposed a ground point fitting method to estimate the height of winter wheat based on the UAV SfM point cloud. A canopy slice filter was designed to reduce the interference of middle canopy points and outliers. Random Sample Consensus (RANSAC) was applied to obtain the ground points from the valid filtered point cloud. Then, the missing ground points were fitted according to the known ground points. Furthermore, we achieved crop height monitoring at the stem elongation stage with an R2 of 0.90. The relative root mean squared error (RRMSE) of height estimation was 5.9%, and the relative mean absolute error (RMAE) was 4.6% at the stem elongation stage. This paper proposed the canopy slice filter and fitting missing ground points. It was concluded that the canopy slice filter successfully optimized the extraction of ground points and removed outliers. Fitting the missing ground points simulated the terrain undulations effectively and improved the accuracy.

A copula-supported Bayesian framework for spatial downscaling of GRACE-derived terrestrial water storage flux

The GRACE and GRACE-FO satellite missions provide mass variations as a fundamentally new observation type for a broad spectrum of novel applications in Earth science disciplines, including oceanography, geophysics, hydrology, and hydrometeorology. Despite all the key findings in hydrology, the utility of GRACE-derived Terrestrial Water Storage Anomaly (TWSA) and its time derivative Terrestrial Water Storage Flux (TWSF) have mainly been limited to large catchments due to their coarse spatial resolution. Here, we propose a method to downscale TWSF by incorporating available finer-resolution data. We determine the downscaled TWSF and its uncertainty within a proposed Bayesian framework by incorporating the fine-scale data of TWSF and Soil Moisture Change (SMC) from different available sources. For the Bayesian ingredients, we rely on GRACE data to obtain the prior and rely on copula models to obtain nonparametric likelihood functions based on the statistical relationship between GRACE TWSF with fine-scale TWSF data and SMC. We apply our method to the Amazon Basin and assess the performances of our products from various fine-scale input datasets of TWSFs and SMCs. Given the lack of ground truth for TWSF, we validate our results against space-based Surface Water Storage Change (SWSC) in the Amazon river system and also against the Vertical Crustal Displacements Rate (VCDR) observed by the Global Positioning System (GPS). Overall, the results show that the proposed method is able to estimate a downscaled TWSF, which is informed by GRACE and fine-scale data. Validation shows that our downscaled products are better anticorrelated with VCDR (−0.81) than fine-scale TWSF (−0.73) and show a mean relative RMSE of 26% with SWSC versus 70% for fine-scale TWSF. The proposed methodology can be extended to other coarse scale datasets, which are crucial for hydrological application at regional and local scales.

A theoretical approach for water saturation estimation in shaly sandstones

The process of quantitative reservoir characterization is a crucial component spanning from the initial estimation of in-place reserves to the optimization of production design. Water saturation is a critical parameter in quantitative reservoir characterization that directly impacts the in-place reserve estimates. In the case of shale-free sandstones, the computation of water saturation using Archie's equation yields fairly accurate results. However, in shaly sandstone reservoirs, the presence of multiple conductive entities in the rock poses additional complexities. Currently, various empirical, semi-empirical and theoretical equations are available in literature to estimate water saturation; nevertheless, none of these models is such that it is both theoretically sound and practically applicable.In this study, we present a novel approach that is both theoretically sound and practically applicable in computing water saturation in shaly sandstones. The fluid-saturated rocks are treated as a system consisting of two interlocked lattice-like structures, namely grains and fluid in the interconnected pores. The composite fluid comprising water and hydrocarbon is modeled using the general mixture rule, while the Hanai-Bruggeman equation is employed to model the electrical conductivity of this system. The resulting electrical conductivity equation is then utilized to compute water saturation in shaly sandstones.The proposed equation was effectively validated using the published core data. Furthermore, we compare the new model with other grain conductivity-based models such as Mixing model and Berg's model. Our findings show that while describing core data the proposed equation gives a lower average Relative Root Mean Squared Error (RRMSE) of 2.05% as compared to 7.56% and 5.58% for the Mixing and Berg's model available in literature, respectively. Moreover, the range of porosity and water conductivity for which the proposed model is applicable, surpasses that of the current models. We also suggest that this equation can be extended to other systems with a similar two interlocked lattice-like structure, such as carbonates.

Investigation of Campbell mode with automatic calibration operated in fission chamber-based neutron flux monitoring system on EAST

To satisfy the wide-range requirement for the fission chamber-based neutron flux monitoring (NFM) system on experimental advanced superconducting tokamak (EAST), the pulse-counting and Campbell modes were combined to expand the measurement range. However, to obtain the neutron yields, the results of the Campbell mode should first be converted into neutron count rates via linear calibration. During the plasma experiment, the non-neutron backgrounds vary with respect to different experimental conditions, which leads to a baseline dynamic change in the Campbell mode. In future research, NFM system need provide real-time feedback parameters regarding the operational status of the fusion device. Therefore, an automatic calibration method was developed to automatically deduct various baselines of the Campbell mode and obtain the neutron yields in real time. This method continuously updates the average value of each sub-interval (multiple sub-intervals are set in the calibration region) using a linear superposition averaging method. In addition, to optimize the dual-mode switching threshold, ensure the calibration region and define the upper limit of Campbell mode, a simulated neutron signal generator was designed and applied. The switching threshold of the dual modes was set to 400 kcps, the calibration region of the Campbell mode was selected as 50–500 kcps, and the upper limit of the equivalent count rate in the Campbell mode reached to 108cps with a relative error of<4%. Finally, the automatic calibration method was tested using experimental data from the NFM system on EAST. The automatic calibration results basically overlapped with the reference results and superior to the offline fixed calibration results. Under different experimental conditions, the relative root mean square error (RRMSE) values of the automatic calibration results were lower than those of the offline fixed calibration results. Therefore, the proposed automatic calibration method is accurate and reliable, and can satisfy the real-time measurement requirements of wide-range NFM system.

Prediction of quality-adjusted life years (QALYs) after bariatric surgery using regularized linear regression models: results from a Swedish nationwide quality register

PurposeTo investigate whether the quality-adjusted life years (QALYs) of the patients who underwent bariatric surgery could be predicted using their baseline information.Materials and MethodsAll patients who received bariatric surgery in Sweden between January 1, 2011 and March 31, 2019 were obtained from the Scandinavian Obesity Surgery Registry (SOReg). Baseline information included patients’ sociodemographic characteristics, details regarding the procedure, and postsurgical conditions. QALYs were assessed by the SF-6D at follow-up years 1 and 2. The general and regularized linear regression models were used to predict postoperative QALYs.ResultsAll regression models demonstrated satisfactory and comparable performance in predicting QALYs at follow-up year 1, with R2 and relative root mean squared error (RRMSE) values of about 0.57 and 9.6%, respectively. The performance of the general linear regression model increased with the number of variables; however, the improvement was ignorable when the number of variables was more than 30 and 50 for follow-up years 1 and 2, respectively. Although minor L1 and L2 regularization provided better prediction ability, the improvement was negligible when the number of variables was more than 20. All the models showed poorer performance for predicting QALYs at follow-up year 2.ConclusionsPatient characteristics before bariatric surgery including health related quality of life, age, sex, BMI, postoperative complications within six weeks, and smoking status, may be adequate in predicting their postoperative QALYs after one year. Understanding these factors can help identify individuals who require more personalized and intensive support before, during, and after surgery.Graphical

Dynamic modeling of pesticide residue in proso millet under multiple application situations

Proso millet (Panicum miliaceum L.) is a cereal crop with potential resistance to drought and heat stress, making it a promising alternative crop for regions with hot and dry climates. Because of its importance, it is crucial to investigate pesticide residues in proso millet and assess their potential risks to the environment and human health to protect it from insects or pathogens. This study aimed to develop a model for predicting pesticide residues in proso millet using dynamiCROP. The field trials consisted of four plots, with each plot containing three replicates of 10 m2. The applications of pesticides were conducted two or three times for each pesticide. The residual concentrations of the pesticides in the millet grains were quantitatively analyzed using gas and liquid chromatography-tandem mass spectrometry. The dynamiCROP simulation model, which calculates the residual kinetics of pesticides in plant-environment systems, was employed for predicting pesticide residues in proso millet. Crop-specific, environment-specific, and pesticide-specific parameters were utilized to optimize the model. Half-lives of pesticides in grain of proso millet, which were needed to input for dynamiCROP, were estimated using a modified first-order equation. Proso millet-specific parameters were obtained from previous studies. The accuracy of the dynamiCROP model was assessed using statistical criteria, including the coefficient of correlation (R), coefficient of determination (R2), mean absolute error (MAE), relative root mean square error (RRMSE), and root mean square logarithmic error (RMSLE). The model was then validated using additional field trial data, which showed that it could accurately predict pesticide residues in proso millet grain under different environmental conditions. The results demonstrated the accuracy of the model in predicting pesticide residues in proso millet after multiple applications.

Fractional norm regularization using inverse perturbation

A computation technique, known as inverse perturbation-fractional norm regularization (IP-FNR), is proposed in this wok for a sparse signal recovery problem. The objective function of this method is derived using a general ℓp norm, when p is a positive fractional number. Numerical examples are conducted for both noiseless and noisy cases. Performance of the proposed approach in terms of root-mean-square relative error (RMSRE), mean normalized squared error, standard deviation mean, occupied memory during the computation, and computational time is compared to several previous methods. It is found that in the noiseless case, the IP-FNR method significantly outperforms the former fixed-point algorithms for a certain range of the norm exponent p, provided that the perturbation parameter and the regularization multiplier are properly chosen. In the noisy case, at the expense of computational time, the IP-FNR approach provides noticeably lower RMSRE when the signal-to-noise ratio or the sparsity ratio is high and the compression ratio is quite low.

A Dynamic Concentration-Dependent Analytical I,–V Model for LG-GFET Biosensor

In the past few years, liquid-gated graphene field-effect transistors (LG-GFETs) have been widely used in biological detection due to their unique advantages. An accurate transistor model is the basis of biological detection circuit design, however, the reported GFET models are mainly focusing on solid-gated GFETs. Therefore, it is essential to conduct the research on LG-GFET model. In this article, an improved <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textit{I}$</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">$\textit{V}$</tex-math> </inline-formula> model of LG-GFET is presented based on Fregonese’s model. An improved electric double-layer capacitor model is proposed for LG-GFET. Then, the relationship among iron concentration, bias voltages, and current is studied comprehensively. Furthermore, the drain current response change with time is taken into account and the dynamic concentration-dependent model is established. To verify the accuracy of the proposed model, LG-GFET is simulated in TCAD software and fabricated to perform the measurement. The simulation results and measurement results are compared with the model results, respectively. These results show that the relative root-mean-square error (RMSE) to both simulation and measurement results is less than 5.7%. It is revealed that the proposed model can be applied to biological detection and achieve high accuracy.

P13: “Linearizing the Heart”: Application of an Autoencoder Network to Identify Koopman Embeddings in Hemodynamic Signals

System linearization helps researchers to understand and predict the behavior of complex systems like the cardiovascular system. This understanding is essential for developing medical devices or physiological cardiac control algorithms. Aim of this study was to use a neural network approach to obtain a linearized model of the cardiovascular system dynamics. An autoencoder network was used to learn Koopman embeddings from a dataset of simulated heartbeats obtained from a highly nonlinear lumped-parameter model of the human cardiovascular system. The dataset contained 18 hemodynamic signals of 800 separate heartbeats generated using varying initial conditions and included volumes, pressures, and flows of the heart chambers and the systemic circulation. All data were z-normalized, and the network was trained using the Adam optimizer. The decoder and encoder comprised 5 layers, both with progressively increasing/decreasing numbers of nodes (27-211). The latent space had the same number of dimensions as the input comprising 18 hemodynamic signals. An auxiliary network with 4 layers (28 nodes each) operating on the latent space was used to identify the Koopman operator. The results showed that, although the eigenvalues of the Koopman operator were allowed to vary, they remained about constant for all heartbeats, indicating the convergence towards a linear representation of the system’s dynamics. The overall average prediction error quantified as relative RMSE for 100 unseen heartbeats, given only the initial condition, was 5.4%, showing a good capture of the system’s dynamics. The results are consistent with previous work on Koopman linearization, adding to the growing body of evidence supporting the utility of this approach. Using autoencoders to learn Koopman embeddings from simulated heartbeats and thus identify a linear representation of the cardiovascular system’s dynamics is novel. This promising approach could be particularly useful for the development of physiological cardiac control algorithms.

Quantitative Representation of Water Quality Biotoxicity by Algal Photosynthetic Inhibition.

The method based on the photosynthetic inhibition effect of algae offers the advantages of swift response and straightforward measurement. Nonetheless, this effect is influenced by both the environment and the state of the algae themselves. Additionally, a single parameter is vulnerable to uncertainties, rendering the measurement accuracy and stability inadequate. This paper employed currently utilized photosynthetic fluorescence parameters, including Fv/Fm(maximum photochemical quantum yield), Performance Indicator (PIabs), Comprehensive Parameter Index (CPI) and Performance Index of Comprehensive Toxicity Effect (PIcte), as quantitative toxicity characteristic parameters. The paper compared the univariate curve fitting results with the multivariate data-driven model results and investigated the effectiveness of Back Propagation(BP) Neural Network and Support Vector Machine for Regression (SVR) models to enhance the accuracy and stability of toxicity detection. Using Dichlorophenyl Dimethylurea (DCMU) samples as an example, the mean Relative Root Mean Square Error (RRMSE) corresponding to the optimal parameter PIcte for the dose-effect curve fitting was 1.246 in the concentration range of 1.25-200 µg/L. On the other hand, the mean RRMSEs corresponding to the results of the BP neural network and SVR models were 0.506 and 0.474, respectively. Notably, BP neural network exhibited excellent prediction accuracy in the medium-high concentration range of 7.5-200 µg/L, with a mean RRSME of only 0.056. Regarding the stability of the results, the mean Relative Standard Deviation (RSD) of the univariate dose-effect curve results was 15.1% within the concentration range of 50-200 µg/L. In contrast, the mean RSDs for both BP neural network and SVR results were less than 5%. In the concentration range of 1.25-200 µg/L, the mean RSDs were 6.1% and 16.5%, with the BP neural network performing well. The experimental results of Atrazine were analyzed to further validate the effectiveness of the BP neural network in improving the accuracy and stability of results. These findings provided valuable insights for the development of biotoxicity detection by using the algae photosynthetic inhibition method.

RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network

Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and efficient rice production. In this study, we mainly focus on the precise counting of rice plants in paddy field and design a novel deep learning network, RPNet, consisting of four modules: feature encoder, attention block, initial density map generator, and attention map generator. Additionally, we propose a novel loss function called RPloss. This loss function considers the magnitude relationship between different sub-loss functions and ensures the validity of the designed network. To verify the proposed method, we conducted experiments on our recently presented URC dataset, which is an unmanned aerial vehicle dataset that is quite challenged at counting rice plants. For experimental comparison, we chose some popular or recently proposed counting methods, namely MCNN, CSRNet, SANet, TasselNetV2, and FIDTM. In the experiment, the mean absolute error (MAE), root mean squared error (RMSE), relative MAE (rMAE) and relative RMSE (rRMSE) of the proposed RPNet were 8.3, 11.2, 1.2% and 1.6%, respectively, for the URC dataset. RPNet surpasses state-of-the-art methods in plant counting. To verify the universality of the proposed method, we conducted experiments on the well-know MTC and WED datasets. The final results on these datasets showed that our network achieved the best results compared with excellent previous approaches. The experiments showed that the proposed RPNet can be utilized to count rice plants in paddy fields and replace traditional methods.

Numerical Modelling of a Dam-Regulated River Network for Balancing Water Supply and Ecological Flow Downstream

Dam operation is regarded as an effective way to increase water, food, and energy security for society. However, with the increasing water demand and frequent extreme droughts, numerous rivers worldwide go through periods of water scarcity and water ecosystem deterioration to varying degrees. Balancing the water supply and ecological flow of the dam-regulated river network is essential in the context of river restoration. In this study, we proposed a hydrodynamic and water quality model of a dam-regulated river network balancing water supply and ecological flow using the Environmental Fluid Dynamics Code (EFDC). A section of Jinjiang watershed located in the southwestern of China was chosen as the study area. Firstly, the model was calibrated and validated. By comparing the simulated values with the measured values, the statistical analysis results showed that the relative root mean-squared error (RRMSE) values of water level, COD and NH3-N were 5.5–8.1%, 23.6% and 28.4%, respectively, indicating an adequate degree of agreement between simulation and observation. Based on the established model, dam operation schemes under a dry hydrologic scenario and emergency contamination scenario were formulated to ensure the requirement of ecological water flow and water quality simultaneously. For the dry hydrologic scenario, the ecological water requirement could be satisfied through the dam operation. However, in an emergency contamination scenario, regional water quality requirements cannot be met through dam operation. The dam operation only plays a role in controlling the scope of pollution. This study is expected to provide scientific support for dam-regulated river network management and downstream river ecosystem protection.

Predicting eucalyptus plantation growth and yield using Landsat imagery in Minas Gerais, Brazil

Remote sensing applications in forest inventories allow for a detailed view of areas with extensive forest cover while potentially lowering costs. In this context, the objective of this study was to propose a methodology for using Landsat data to predict and project eucalyptus forest growth and yield, as well as to analyze forest growth dynamics. Three scenarios with varying sample sizes were proposed to assess the possibility of cost savings. The estimation was performed using an artificial neural network (ANN) and the random forest (RF) algorithm. Wall-to-wall prediction and projection were used, and projection maps were used to calculate the mean and current monthly increments. The relative root mean square error (RRMSE) values for the wall-to-wall prediction and for the projection ranged from 7.9% to 14.5% and 6.8% to 11.8%, respectively. All of the estimated means fell within the forest inventory confidence intervals. The mean and current monthly increment values projected by the ANN model did not differ from those obtained by the continuous forest inventory. Considering that the sampling intensity of traditional continuous forest inventories normally is one plot every 10 ha, the methodology presented here can be used to reduce sampling intensity to one plot for every 83.3 ha, without significant loss of accuracy, which represents a relevant cost reduction.

Extraction of tree heights in mountainous natural forests from UAV leaf-on stereoscopic imagery based on approximation of ground surfaces

The application of high-resolution stereoscopic imagery acquired by Unmanned Aerial Vehicle (UAV) on the extraction of forest heights has grown rapidly in recent years. Most existing studies either required auxiliary terrain data, e.g., Digital Terrain Model (DTM) provided by lidar data, or focused on flat terrains. It is still a great challenge to extract tree heights in mountainous forests only using UAV leaf-on stereoscopic imagery. An algorithm referred to as AGAR (i.e., Approximation of Ground using Allometric Relationship) is proposed in this study to estimate individual heights of visible trees on UAV stereoscopic imagery in mountainous natural forests. The central idea of the AGAR algorithm is firstly to approximate the understory terrain elevations (i.e., DTM) based on attributes of tree crowns (e.g., crown area) and the iterative adjustment of allometric equation coefficients. Then individual tree heights are determined by differencing the elevation of crown tops with that of the approximated ground surface. The proposed algorithm was demonstrated at five sites with different terrain conditions by taking field measurements and ICESat-2 data as references, respectively. Results showed that the AGAR algorithm worked well on the estimation of tree heights at all sites. In contrast, the classical progressive triangulation filter (PTF) algorithm was susceptible to terrains and forest structures. The root mean square error (RMSE) and relative RMSE (rRMSE) of tree heights estimated by the PTF algorithm were 4.4 m ∼ 6.3 m and 32.6% ∼ 37.6%, respectively. They were decreased by the AGAR algorithm to 1.7 m ∼ 2.5 m and 12.6% ∼ 15.2%, respectively. The AGAR algorithm will substantially advance the application of UAV stereoscopic imagery on the extraction of tree heights in the absence of other available terrain data, and will also open new horizons for application of decimeter or even centimeter spaceborne stereoscopic imagery on forest vertical structures in the future.