Maximum RMSE Research Articles

Assessment of CMIP6 models and multi-model averaging for temperature and precipitation over Iran

In this study, the performances of 40 Coupled Model Intercomparison Project Phase 6 are evaluated against observational data at synoptic stations in Iran using various evaluation criteria. The results reveal diverse model accuracy across different climate conditions and criteria, emphasizing particularly notable disparities in the nonstationarity R criterion compared to others. Although according to the ranking of the raw and bias-corrected outputs of CMIP6 GCMs for Iran, the NorESM2-MM, AWI-ESM-1-1-LR, and MPI-ESM1-2-LR models are consistently among the top six ranked models for precipitation in both raw and corrected outputs. For temperature, MPI-ESM1-2-LR, TaiESM1, INM-CM4-8, and IITM-ESM are consistently among the top six models for both the raw and bias-corrected outputs of CMIP6 GCMs. The Bias correction methods, including quantile mapping and linear scaling, integrated with Bayesian model averaging, were applied. While quantile mapping demonstrates superior performance and less disparity than linear scaling, it proves ineffective for correcting biases at stations with bias nonstationarity over time. The RMSE for monthly precipitation ranges from almost 0 to 200 mm, with a large RMSE value related to the high precipitation stations, and the monthly temperature exhibits a range of 0 to 4 °C. The use of a multi-model ensemble improves accuracy compared to individual models, resulting in a reduction in the differences between the minimum and maximum RMSE values from 178.6 to 91.0. Additionally, the range for mean absolute error decreases from 126.9 to 93.3, and the difference in the correlation coefficient narrows from 0.9 to 0.42. Averaging models after bias correction prevents significant fluctuations while maintaining higher accuracy, in contrast to the second method, which involves bias-correcting models after averaging.

Enhancing the state-of-charge estimation of lithium-ion batteries using a CNN-BiGRU and AUKF fusion model

Accurate estimation of lithium-ion batteries’ state of charge (SOC) is crucial for the safety of energy storage devices, preventing issues such as overcharging or discharging. This paper introduces a fusion model combining convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and adaptive unscented Kalman filter (AUKF). This method's advantage lies in integrating Kalman filtering with the benefits of neural networks, eliminating the need for complex hyperparameter tuning and battery model construction. Initially, CNN-BiGRU maps variables like voltage, current, and temperature to SOC for initial estimation. The AUKF algorithm then filters these SOC outputs, minimizing fluctuations and enhancing accuracy. This approach ultimately leads to precise and stable SOC estimates. To validate the model's effectiveness, lithium-ion battery datasets across various temperatures were extensively trained and tested. The CNN-BiGRU-AUKF model demonstrated consistent performance under these conditions, with a maximum MSE of 0.00011, MAE under 0.0092, Max AE around 0.02, and a maximum RMSE of 0.017. Compared to similar methods, the proposed approach demonstrates superior SOC estimation accuracy and computational efficiency. Additionally, the model's scalability was validated using training and testing data for SOC estimates from a different type of lithium battery.

Assessment of Low-Cost and Higher-End Soil Moisture Sensors across Various Moisture Ranges and Soil Textures.

The accuracy and unit cost of sensors are important factors for a continuous soil moisture monitoring system. This study compares the accuracy of four soil moisture sensors differing in unit costs in coarse-, fine-, and medium-textured soils. The sensor outputs were recorded for the VWC, ranging from 0% to 50%. Low-cost capacitive and resistive sensors were evaluated with and without the external 16-bit analog-to-digital converter ADS1115 to improve their performances without adding much cost. Without ADS1115, using only Arduino's built-in analog-to-digital converter, the low-cost sensors had a maximum RMSE of 4.79% (v/v) for resistive sensors and 3.78% for capacitive sensors in medium-textured soil. The addition of ADS1115 showed improved performance of the low-cost sensors, with a maximum RMSE of 2.64% for resistive sensors and 1.87% for capacitive sensors. The higher-end sensors had an RMSE of up to 1.8% for VH400 and up to 0.95% for the 5TM sensor. The RMSE differences between higher-end and low-cost sensors with the use of ADS1115 were not statistically significant.

A general unit hydrograph theory for water level and tidal range distributions in the Modaomen Estuary, China

Understanding the spatial distributions of river-tide dynamics in estuaries and their response to intensive human interventions is critical. However, the studies on the characteristics of the spatial distributions of water level and tidal range are insufficient, with inadequate direct established empirical formulas. In this study, we propose a general and analytical water level and tidal range distribution model based on the recently proposed General Unit Hydrograph (GUH) theory and apply it to the Modaomen Estuary in China. Due to the intensive human interventions, the evolution of river-tide dynamics in the Modaomen Estuary was divided into three distinct periods: Pre-human, Transitional and Post-human Periods. The results show that the water level increased at the SZ station, yet decreased at other stations, thereby reducing the maximum water level gradient by approximately 9.08 × 10−6 on average from the Pre-human to the Post-human Periods. The tidal range generally increased along the channel and the absolute value of the maximum tidal range gradient decreased by approximately 54 % on average. Correspondingly, the positions of both maximum water level gradient and minimum tidal range gradient generally move seaward by approximately 27.25 km and 0.34 km, respectively. Additionally, the spatial distributions of river-tide dynamics tended more linear after human interventions. The satisfactory correspondence of the model outputs with observations at the six gauging stations along the Modaomen Estuary (with maximum RMSE values being 0.05 m for the water level and 0.03 m for the tidal range, respectively) indicate that the newly proposed GUH model could serve as a simple tool to describe the spatial distributions of water level and tidal range in a specific channel together with their response to anthropogenic modifications, which is also particularly useful for the identification of regime shifts in river-tide dynamics and sustainable water resources management in other highly human-modified estuaries worldwide.

State of Health Estimation of Lithium-Ion Battery for Electric Vehicle Based on VMD-DBO-SVR Model

State-of-health (SOH) of lithium-ion batteries is an important indicator for measuring performance and remaining life. We propose an innovative prediction model that integrates variational mode decomposition (VMD), Dung Beetle optimizer (DBO), and support vector regression (SVR) algorithms. We extracted relevant features from the discharge characteristic curve and incremental capacity curve. We used Pearson and Spearman correlation coefficient methods for correlation analysis on the extracted health factors (HFs), selecting those that significantly impact SOH as input features. A DBO-SVR model was constructed to establish a nonlinear correlation between HFs and SOH, and the DBO algorithm was used to globally search and optimize the hyperparameters of the SVR model to improve its prediction accuracy. To reduce the impact of noise in battery signals on model performance, VMD technology was introduced to decompose battery signals into multiple intrinsic mode components, to extract useful features and remove noise to further improve prediction accuracy. The proposed method was validated using the NASA battery dataset and compared with other algorithm models. Results showed that the prediction model was significantly better than other models, with a maximum RMSE value of 0.84%, a maximum MAE value of 0.71%, and a stable prediction error value within 1%.

Dynamic Compressive Stress Relaxation Model of Tomato Fruit Based on Long Short-Term Memory Model.

Tomatoes are prone to mechanical damage due to improper gripping forces during automated harvest and postharvest processes. To reduce this damage, a dynamic viscoelastic model based on long short-term memory (LSTM) is proposed to fit the dynamic compression stress relaxation characteristics of the individual fruit. Furthermore, the classical stress relaxation models involved, the triple-element Maxwell and Caputo fractional derivative models, are compared with the LSTM model to validate its performance. Meanwhile, the LSTM and classical stress relaxation models are used to predict the stress relaxation characteristics of tomato fruit with different fruit sizes and compression positions. The results for the whole test dataset show that the LSTM model achieves a RMSE of 2.829×10-5 Mpa and a MAPE of 0.228%. It significantly outperforms the Caputo fractional derivative model by demonstrating a substantial enhancement with a 37% decrease in RMSE and a 36% reduction in MAPE. Further analysis of individual tomato fruit reveals the LSTM model's performance, with the minimum RMSE recorded at the septum position being 3.438×10-5 Mpa, 31% higher than the maximum RMSE at the locule position. Similarly, the lowest MAPE at the septum stands at 0.375%, outperforming the highest MAPE at the locule position by a significant margin of 90%. Moreover, the LSTM model consistently reports the smallest discrepancies between the predicted and observed values compared to classical stress relaxation models. This accuracy suggests that the LSTM model could effectively supplant classical stress relaxation models for predicting stress relaxation changes in individual tomato fruit.

Improvement in measurement of radiation based two-phase flowmeters independent of flow regime and scale thickness using ant colony optimization and GMDH

The formation of scales in pipes is one element that has a major impact on the efficiency of machinery used in the oil and gas sector. With the help of artificial intelligence, this new, non-invasive device was able to figure out the volume fraction of a two-phase flow by taking into account the thickness of the scale in the tested pipeline. The proposed design uses an isotope pair of barium-133 and cesium-137 as a dual-energy gamma generator. One detector records photons that are transmitted, and another detector records photons that are scattered. The signals from the detectors were simulated using the Monte Carlo N-Particle (MCNP) code, and then ten frequency and wavelet characteristics were extracted. To choose the best inputs from the collected features for computing the volume fraction, an ant colony optimization (ACO)-based method is applied. Six attributes, representing the optimal combination, were developed using this method. In order to forecast the volume percentage of two-phase flows independently of flow regime and scale thickness, we fed the characteristics introduced by ACO into a group method of data handling (GMDH) neural network. Volume fraction calculations had a maximum RMSE of 0.056, which is quite little compared to previous research. By using the ACO to choose the best characteristics, the current work has significantly increased its accuracy in identifying volume fractions.

Evaluation of 2D affine — hand-crafted detectors for feature-based TLS point cloud registration

Abstract The development of modern surveying methods, particularly, Terrestrial Laser Scanning (TLS), has found wide application in protecting and monitoring engineering and objects and sites of cultural heritage. For this reason, it is crucial that several factors a˛ecting the correctness of point cloud registration are considered, including the correctness of the distribution of control points (both signalised and natural), the quality of the process, and robustness analysis. The aim of this article is to evaluate the quality and correctness of TLS registration based on point clouds converted to raster form (in spherical mapping) and hand-crafted detectors. The expanded Structure-from-Motion (SfM) was used to detect the tie points for TLS registration and reliability assessment. The results demonstrated that affine detectors are useful in detecting a high number of key points (increased for point detectors by 8–12 times and for blob detectors by about 10–24 times), improving the quality and TLS registration completeness. For the registration accuracy of point cloud on signalised check points, the lower values can be noted for maximum RMSE errors for blob affine detectors than detectors and larger values for corner detectors and affine detectors (not more than 4 mm in the extreme cases, typically 2 mm). The commonly-applied target-based registration method yields similar results (di˛erences do not exceed – in extreme cases – 3.5 mm, typically less than 2 mm), proving that using affine detectors in the TLS registration process is and reasonable and can be recommended.

Investigating the Influence of Varied Particle Sizes on the Load-Bearing Properties of Arrester Bed Aggregates.

This study employs the discrete element method to investigate the influence of particle size on the load-bearing characteristics of aggregates, with a specific emphasis on the aggregates used in escape ramp arrester beds. This study utilises the log edge detection algorithm to introduce an innovative approach for modelling irregularly shaped pebbles, integrating their physical properties into a comprehensive discrete element model to enhance the accuracy and applicability of simulations involving such pebbles. Meticulous validation and parameter calibration (friction coefficient: 0.37, maximum RMSE: 3.43) confirm the accuracy of the simulations and facilitate an in-depth examination of the mechanical interactions between aggregate particles at macroscopic and microscopic scales. The findings reveal a significant relationship between the particle size and load-bearing capacity of aggregates. Smaller pebbles, which are more flexible under pressure, can be packed more densely, thereby improving the distribution of vertical forces and increasing the concentration of local stress. This enhancement substantially increases the overall load-bearing capacity of aggregates. These discoveries hold significant implications for engineering practices, particularly in the optimisation of safety for truck escape ramps and in identifying the ideal sizes of pebbles with irregular shapes.

Method and Validation of Coal Mine Gas Concentration Prediction by Integrating PSO Algorithm and LSTM Network

Gas concentration monitoring is an effective method for predicting gas disasters in mines. In response to the shortcomings of low efficiency and accuracy in conventional gas concentration prediction, a new method for gas concentration prediction based on Particle Swarm Optimization and Long Short-Term Memory Network (PSO-LSTM) is proposed. First, the principle of the PSO-LSTM fusion model is analyzed, and the PSO-LSTM gas concentration analysis and prediction model is constructed. Second, the gas concentration data are normalized and preprocessed. The PSO algorithm is utilized to optimize the training set of the LSTM model, facilitating the selection of the training data set for the LSTM model. Finally, the MAE, RMSE, and coefficient of determination R2 evaluation indicators are proposed to verify and analyze the prediction results. Gas concentration prediction comparison and verification research was conducted using gas concentration data measured in a mine as the sample data. The experimental results show that: (1) The maximum RMSE predicted using the PSO-LSTM model is 0.0029, and the minimum RMSE is 0.0010 when the sample size changes. This verifies the reliability of the prediction effect of the PSO-LSTM model. (2) The predictive performance of all models ranks as follows: PSO-LSTM > SVR-LSTM > LSTM > PSO-GRU. Comparative analysis with the LSTM model demonstrates that the PSO-LSTM model is more effective in predicting gas concentration, further confirming the superiority of this model in gas concentration prediction.

Lithium-ion battery SOH prediction based on VMD-PE and improved DBO optimized temporal convolutional network model

Accurately estimating the state of health (SOH) in lithium-ion batteries is crucial for optimizing performance, cost management, enhancing safety, extending lifespan, and promoting environmental sustainability. However, due to factors such as capacity regeneration, battery capacity degradation data exhibits nonlinear and non-stationary characteristics, making it challenging to accurately predict SOH. In order to improve prediction accuracy, this paper proposes a novel SOH prediction model based on VMD-PE-IDBO-TCN. Firstly, the variational mode decomposition-permutation entropy (VMD-PE) method is innovatively introduced to decompose the original battery SOH data and reorganize it into a series of subsequences, reducing the impact of non-stationary components on the prediction results. Moreover, temporal convolutional network (TCN) prediction models are used for each subsequence, and an improved dung beetle optimization (IDBO) algorithm is used to optimize the TCN parameters, where this IDBO algorithm incorporates SPM chaotic mapping, golden sine strategy, and adaptive Gaussian-Cauchy mixed mutation perturbation. The IDBO algorithm rapidly and accurately identifies the optimal parameter combination, significantly enhancing the predictive performance of the TCN model. Finally, the predicted values of each subsequence are superimposed to obtain the final prediction result. Two different lithium-ion battery datasets from NASA and CALCE are used for experimental validation. Experimental results show that the proposed model has higher prediction accuracy, with a maximum RMSE of only 0.0072 and a maximum MAPE of only 0.67 %, and has good adaptability to different types of batteries and batteries operating at high temperatures.

Configuration Optimization of Temperature–Humidity Sensors Based on Weighted Hilbert–Schmidt Independence Criterion in Chinese Solar Greenhouses

For cost-sensitive Chinese solar greenhouses (CSGs) with an uneven spatial distribution in temperature and humidity, there is a lack of effective strategies for sensor configuration that can reduce sensor usage while monitoring the microclimate precisely. A configuration strategy for integrated temperature–humidity sensors (THSs) based on the improved weighted Hilbert–Schmidt independence criterion (HSIC) is proposed in this paper. The data independence of the THSs in different sites was analyzed based on the improved HSIC, and the selection priority of the THSs was ranked based on the weighted independence of temperature and humidity. Then, according to different cost constraints and monitoring requirements, suitable THSs could be selected sequentially and constitute the monitoring solution. Compared with the original monitoring solution containing twenty-two THSs, the optimized solution used only four THSs (S6, S9 and H6, H5) under strict cost constraints, with a maximum RMSE of the temperature and relative humidity of 0.6 °C and 2.30%, as well as a maximum information gain rate (IGR) of 9.47% and 10.0%. If higher monitoring precision is required, we can increase the THS usage with a greater budget. The optimized solution with six THSs (S6, S9, S8 and H6, H5, H2) could further reduce the maximum RMSE of the temperature and relative humidity to 0.33 °C and 1.10% and the IGR to 6.9% and 8.7%. This indicated that the proposed strategy could use much fewer THSs to achieve accurate and comprehensive monitoring, which would provide efficient and low-cost solutions for CSG microclimate monitoring.

МОДЕЛИРОВАНИЕ ПОДТВЕРЖДЕНИЯ ДАННЫХ АЗН-В С КОРРЕКЦИЕЙ ТЕМПЕРАТУРЫ ПРИ ОЦЕНКЕ ВЫСОТЫ ПОЛЕТА НА МЕСТНЫХ ВОЗДУШНЫХ ЛИНИЯХ (ЧАСТЬ 2)

In the first part of the article, the author proposed a modified method for confirming the ADS-B data, which estimates and compares the aircraft flight altitude: barometric altitude (received from a barometric pressure altimeter) and geometric altitude (received from a GNSS receiver). In the presented work, application of the modified technique for confirming the ADS-B geometric altitude data is simulated. When simulating, real data were used which were received from the ADS-B ground station located at the Mezen aerodrome. Real values of pressure and temperature were used. The methodology takes into account the values of quality indicators of ADS-B data. For one flight on local airlines, an excess of the permissible interval was shown (GNSS data, according to the methodology, are not confirmed). The result obtained is consistent with the geometric vertical accuracy parameter GVA. To verify the modified method of the temperature determination according to geometric and barometric altitude, the obtained temperature data are compared with the values of the ECMWF forecasting model. The average RMSE value for 11 flights was 1.58 єС. For climbing aircraft the maximum RMSE value was 1.93 єС, for landing aircraft, maximum RMSE = 2.7°C.

Fast EIS acquisition method based on SSA-DNN prediction model

Electrochemical impedance spectroscopy (EIS) is an efficient and information-rich technique for detecting lithium-ion batteries. However, the measurement of EIS takes much time, and the lower the measurement frequency, the longer the measurement takes. To address this problem, this study innovatively proposes an EIS prediction method based on a sparrow search algorithm optimized deep neural network (SSA-DNN). The overall measurement time is reduced by extracting features from the medium-high frequency segments, where the EIS measurement is less time-consuming, and predicting the medium-low frequency segments that consume more measurement time. After evaluating the EIS prediction results at different cycling temperatures and states of charge (SOC), it is concluded that the EIS prediction method proposed in this paper has the advantages of fast measurement speed, high accuracy and applicability. Finally, the predicted EIS is used to estimate the state of health (SOH), and the distribution of relaxation time (DRT) is calculated. The results show that the proposed EIS prediction method has a maximum prediction RMSE of 29.15 mΩ, and the measurement time is reduced to 2.94 % of the original measurement time, which can be widely used in various scenarios based on EIS technology.

Stacking integrated learning model via ELM and GRU with mixture correntropy loss for robust state of health estimation of lithium-ion batteries

Accurate estimation of the state of health (SOH) is crucial for the safe and stable operation of lithium-ion batteries. However, since the labeled values may contain non-Gaussian noise which may lead to a decrease in the effectiveness of traditional data-driven based estimation methods. Therefore, a novel robust stacking integrated learning model (ILM) is proposed to enable accurate SOH estimation under non-Gaussian noises (or outliers) conditions. The mixture correntropy loss (MCL) is used in original extreme learning machine (ELM) and the gated recurrent unit (GRU) frameworks to develop novel robust learning models, i.e MCL-ELM and MCL-GRU, and they are used as the sub-models of the proposed ILM, which takes into account the generalization performance of the model and the overall trend of SOH over the time series. In addition, the entropy weighting method that can well reflect the differences between the sub-models is utilized to reduce the complexity of the stacked ILM. Furthermore, the local tangent space alignment is used to capture the local relationships between different loops to enhance the effectiveness of the extracted health features. Several numerical experiments are performed under different cases to validate the estimation effect of the proposed model by using two publicly available datasets, and the experimental results demonstrate that the maximum RMSE, MAE, and MAPE values of the proposed model are 1.391%, 0.932%, and 1.480%, respectively, under non-Gaussian noises conditions.

Parameter extraction of photovoltaic cells and modules by hybrid white shark optimizer and artificial rabbits optimization

This study presents the parameter extraction of photovoltaic (PV) cells and modules using a new hybrid metaheuristic algorithm developed based on the white shark optimizer (WSO) and the artificial rabbits optimization (ARO) algorithm. The accurate forecasting of economic benefits and the performance of PV based applications are heavily dependent upon the model accuracy of PV devices. Therefore, the main objective of this study is to obtain the most accurate model for the PV cells and modules that are commercially available in the market. For this purpose, the proposed hybrid algorithm (hWSO-ARO) is used for the modeling of two PV cells and six PV modules made by different manufacturers. A total of sixteen models for eight PV devices consisting of single diode (SDM) and double diode model (DDM) for each device have been developed. To verify the success, the results are compared against the results of seven different state-of-the-art algorithms. According to the results of 30 runs, the proposed algorithm has yielded the smallest objective function/root mean square error (RMSE) values in average, maximum, and minimum evaluation metrics. The hybrid algorithm achieves the best minimum average RMSE of 1.8354513E−04. It is then followed by the WSO algorithm with 1.8557680E−04 and with a difference of 1.11% and the ARO algorithm with 2.1286641E−04 and with a difference of 15.97%. Similarly, when the maximum RMSE metric is evaluated, the hybrid algorithm comes the first again with the lowest maximum RMSE of 2.0001806E−04. It is then followed by the WSO with 2.0897277E−04 and with a difference of 4.48% and again the ARO with 2.2591014E−04 and with a difference of 12.94%. When the last metric, the standard deviation, is analyzed, hWSO-ARO, out of 16 models, achieves the most minimum standard deviation of 3.6904635E−19. In addition, the Friedman rank test issues the highest rank to the hybrid algorithm. Moreover, the Wilcoxon rank test is producing results in favor of the proposed algorithm in 110 of 112 pairwise comparisons of algorithms and showing a 98.21% success rate. Later, a sensitivity analysis is performed using the datasheets values of the selected cells and modules. At every comparison, a perfect match is achieved between the calculated and the experimentally measured data. It is even maintained under variable irradiance and temperature conditions. In conclusion, it is demonstrated that the hybrid algorithm stands out in solving the PV parameter extraction problem with great success under all conditions and enables the development of the most accurate PV models with high computational accuracy.

Investigation on thermal performance analysis of a pouch Li-ion battery under various drive cycle profiles

Knowledge of accurate battery temperature is essential for enabling safe operation of batteries in electrified vehicles application under aggressive drive profiles. Thermal modelling of batteries based on mere joule heating term is usually unable to compensate for resulting inaccuracy due to neglecting entropic heat in batteries. Inclusion of entropic effect into the thermal model derived from simple experiments can help accurate estimate of battery temperature in early design stage. This paper presents a lumped thermal model incorporating entropic effect to predict transient thermal behaviors of pouch cell under various aggressive loads. Compared with experimental results simulation model can predict results with acceptable accuracy and minimal computing cost. The simulation results with these tested conditions are found in good agreement with experimental results with a maximum RMSE error of 0.15, 0.07, 0.29, and 0.26 respectively. This shows the inclusion of reversible heat in the enhancing thermal prediction performance of the proposed electro-thermal model is significant and is a fairly good candidate for a rapid electro-thermal simulation of Li-ion pouch type batteries.

Analysis of energy consumption prediction for office buildings based on GA-BP and BP algorithm

To gain building energy consumption information during the design phase, the variance analysis to identify significant factors affecting energy consumption in China cold-region office buildings are carried out in this study. Key factors are selected, and prediction models for energy consumption in cold-region office buildings are established using BP and GA-BP algorithms. Three prediction model evaluation indexes are introduced to evaluate the prediction accuracy of the models. The results show that the maximum RMSE of the BP neural network prediction model is 0.498, and the maximum MAPE is 0.797%. Furthermore, the GA algorithm is used to optimize the BP neural network, resulting in a prediction model with a maximum RMSE of 0.359 and a maximum MAPE of 0.289%. The prediction accuracy of the GA-BP algorithm is better than that of the BP algorithm.

Enhancing Solar-Induced Fluorescence Interpretation: Quantifying Fractional Sunlit Vegetation Cover Using Linear Spectral Unmixing

Solar-induced chlorophyll fluorescence (SIF) is closely related to plant photosynthetic activity and has been used in different studies as a proxy for vegetation health status. However, in order to use SIF as a relevant indicator of plant physiological stress, it is necessary to accurately quantify the amount of light absorbed by the photosynthetic plant pigments, called the absorbed photosynthetically active radiation (APAR). The ratio between fluorescence emission and light absorption (i.e., SIF and APAR) is known as the fluorescence quantum efficiency (FQE). In this work, simultaneous measurements of SIF and reflected radiance were performed both at the leaf and canopy levels for Salvia farinacea and Datura stramonium plants. With the aim of disentangling the proportion of sunlit and shaded absorbed PAR, an ad hoc experimental setup was designed to provide a wide range of fraction vegetation cover (FVC) canopy settings. A linear spectral unmixing method was proposed to estimate the contribution of soil, sunlit, and shaded vegetation from the total reflectance spectrum measured at the canopy level. Later, the retrieved sunlit FVC (FVCsunlit) was used to estimate the (dominant) green APAR flux, and this was combined with the integral of the spectrally resolved fluorescence to calculate the FQE. The results of this study demonstrated that under no-stress conditions and independently of the FVC, similar FQE values were observed when SIF was properly normalised by the green APAR flux. The results obtained showed that the reflectance spectra retrieved using a linear unmixing method had a maximum RMSE of less than 0.03 along the spectrum. The FVCsunlit evaluation showed an RMSE of 14% with an R2 of 0.84. Moreover, the FQE values obtained at the top of the canopy (TOC) were found statistically comparable to the reference values at the leaf level. These results support further efforts to improve the interpretation of fluorescence based on field spectroscopy and the further upscaling to imaging spectroscopy at airborne and satellite levels.

High-Precision and Robust SOC Estimation of LiFePO4 Blade Batteries Based on the BPNN-EKF Algorithm

The lithium iron phosphate (LiFePO4) blade battery is a long, rectangular-shaped cell that can be directly integrated into battery pack systems. It enhances volumetric power density, significantly reduces costs, and is widely utilized in electric vehicles. However, the flat open circuit voltage and significant polarization differences under wide operational temperatures are challenging for accurate voltage modeling of battery management systems (BMSs). In particular, inaccurate state of charge (SOC) estimation may cause overcharging and over-discharging risks. To accurately perceive the SOC of LiFePO4 blade batteries, a SOC estimation method based on the backpropagation neural network-extended Kalman filter (BPNN-EKF) algorithm is proposed. BPNN is a neural network model that utilizes the backpropagation algorithm to update model parameters, while EKF is an optimal estimation algorithm. Firstly, dynamic working condition tests, including the New European Driving Cycle (NEDC) and high-speed working (HSW) condition tests, are conducted under a wide temperature range (−25–43 °C). HSW conditions refer to a simulated operating condition that mimics the driving of an electric vehicle on a highway. The minimum voltage of the battery system is used as the output for training the BPNN model. We derive the Kalman gain by combining the BPNN output voltage. Additionally, the EKF algorithm is employed to correct the SOC value using voltage error information. Concerning long SOC calculation intervals, capacity errors, initial SOC errors, and current and voltage sampling errors, the maximum SOC estimation RMSE is 3.98% at −20 °C NEDC, 3.62% at 10 °C NEDC, and 1.68% at 35 °C HSW. The proposed algorithm can be applied to different temperatures and operations, demonstrating high robustness. This BPNN-EKF algorithm has the potential to be embedded in electric vehicle BMS systems for practical applications.