Savitzky-Golay Filter Research Articles

Enhancing pressure transient analysis in reservoir characterization through deep learning neural networks

Deep learning neural networks exhibit remarkable efficiency in numerous tasks within machine learning applications across various disciplines, including reservoir engineering. Traditional pressure transient analysis (PTA) methodologies, however, are challenged by limitations such as human error in accurately estimating critical reservoir parameters like permeability and wellbore damage (skin). In this study, we evaluate the efficiency and accuracy of various machine learning models in pressure transient analysis (PTA) tasks. Our investigation initially focused on integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance the precision in estimating reservoir parameters and identifying reservoir models. However, through comprehensive testing and validation using simulated well-test data and out-of-distribution samples, we discovered that tree-based models, specifically XGBoost and Random Forest, exhibit superior performance, particularly in generalization tasks. These models outperform CNN-LSTM and 1D-CNN models, demonstrating enhanced robustness and accuracy in handling diverse and unseen data, thereby addressing traditional challenges in pressure transient analysis more effectively. Moreover, Savitzky–Golay Filters were used to handle the noise problems of data, and this method proved effective for data with noise levels up to a standard deviation of 2. Compared with other models, the XGBoost model has a better performance in reservoir model identification with an out-of-distribution accuracy of 92%. On the other hand, Random Forest showed a remarkable result in the task of reservoir parameter estimation, especially for the permeability and skin with out-of-distribution R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2$$\\end{document} of 98% and 97%, respectively. The findings of this study can help for a better understanding of the different deep learning models and their applications in pressure transient analysis. Specifically, the superior performance of the tree-based models in overcoming traditional pressure transient analysis challenges demonstrates their potential to enhance reservoir characterization predictions. Employing these advanced machine learning techniques can significantly reduce human error, increase the accuracy of parameter estimation, and improve the analysis process, thereby aiding strategic decision-making in reservoir management

Smoothing of the Noisy Lithium-ion Battery Surface Temperature Data Based on Savitzky–Golay (SG) Filter

As the charging current and surrounding temperatures rise concurrently in an electric vehicle's (EV) battery pack, the battery temperature increases abruptly beyond safe limits. The battery is susceptible to triggering thermal runaway at higher temperatures, leading to battery damage and even an explosion. The control system depends on these measurement data from the sensors to prevent dangerous situations and maximize the performance and cycle life of batteries. However, traditional noisy temperature measurement sensors in a real application, such as thermistors and thermocouples, are extensively used. In this paper, the experimental setup, the heat pipe-based battery thermal management system (BTMS) was designed and experimented with high input power. The battery was sandwiched with heat pipes, and heated at 30, 40, 50, and 60 W. The Savitzky-Golay filter technique is applied to the noisy temperature data of the surface temperature of the lithium-ion batteries (LIBs) used to estimate the condition of the battery. According to this study, the start-up time parameter in battery thermal management can be controlled by the Savitzky-Golay filter. This will attenuate random temperature fluctuations of battery temperature noise and avoid the cooling system from being falsely triggered. The results are measured by the signal-to-noise (SNR) to demonstrate the ability of the Savitzky-Golay filter to eliminate noise

Authentication of the shelf-life of NPH injectable insulins samples using NIR and MS spectral fingerprints

Insulin is essential for regulating glucose levels, and its hormonal deficiency leads to diabetes. Treatment involves the use of different types of insulin tailored to individual needs. Properly stored and transported Neutral Protamine Hagedorn (NPH) insulin remains effective and stable, highlighting the importance of quality control to ensure its efficacy and patient safety. This study aims to develop an analytical method to evaluate the shelf-life of NPH injectable insulin samples while preserving packaging integrity. The approach consisted of analyzing intact insulin samples, with and without expired shelf-life dates, using near-infrared spectroscopy (NIR) obtained from two instruments: a benchtop and a portable device. These measurements were coupled with chemometric methods, specifically single-class classification algorithms. The classifiers considered were Data Driven-Soft Independent Modeling of Class Analogy (DD-SIMCA) and One-Class Partial Least Squares (OC-PLS). For benchtop NIR, the DD-SIMCA method, with Savitzky-Golay smoothing preprocessing (41-point window) and baseline offset (BO), achieved excellent results, reaching 100% sensitivity, specificity, and efficiency in both training and test sets. As for portable NIR, the most effective methods were DD-SIMCA and OC-PLS, using datasets preprocessed with Savitzky-Golay smoothing with first derivative, second-order polynomial (SGD-1st-2nd), and 9-point windows combined with Standard Normal Variate (SNV), and Savitzky-Golay smoothing filters (SGS) using second-order polynomial and 7-point windows combined with baseline offset (BO) and Multiplicative Scattering Correction (MSC). The results were corroborated by mass spectrometry, correlating the structural changes of degraded insulin with NIR data. The proposed methodology is a promising tool for non-destructive, rapid, and cost-effective authentication of the preservation state of NPH insulin, aligning with green chemistry principles and allowing for in-situ evaluation, thereby preserving medication integrity.

Innovative strategies for protein content determination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning algorithms through short-wave infrared imaging

In this study, we explored the application of Short-Wave Infrared (SWIR) hyperspectral imaging combined with Competitive Adaptive Reweighted Sampling (CARS) and advanced regression models for the non-destructive assessment of protein content in dried laver. Utilizing a spectral range of 900–1700 nm, we aimed to refine the quality control process by selecting informative wavelengths through CARS and applying various preprocessing techniques (standard normal variate [SNV], Savitzky-Golay filtering [SG], Orthogonal Signal Correction [OSC], and StandardScaler [SS]) to enhance the model's accuracy. The SNV-OSC-StandardScaler- Support vector regression (SVR) model trained on CARS-selected wavelengths significantly outperformed the other configurations, achieving a prediction determination coefficient (Rp2) of 0.9673, root mean square error of prediction of 0.4043, and residual predictive deviation of 5.533. These results highlight SWIR hyperspectral imaging's potential as a rapid and precise tool for assessing dried laver quality, aiding food industry quality control and dried laver market growth.

Long-term annual mapping and spatial-temporal dynamic analysis of winter wheat in Shandong Province based on spatial-temporal data fusion (2000-2022).

Winter wheat, as one of the world's key staple crops, plays a crucial role in ensuring food security and shaping international food trade policies. However, there has been a relative scarcity of high-resolution, long time-series winter wheat maps over the past few decades. This study utilized Landsat and Sentinel-2 data to produce maps depicting winter wheat distribution in Google Earth Engine (GEE). We further analyzed the comprehensive spatial-temporal dynamics of winter wheat cultivation in Shandong Province, China. The gap filling and Savitzky-Golay filter method (GF-SG) was applied to address temporal discontinuities in the Landsat NDVI (Normalized Difference Vegetation Index) time series. Six features based on phenological characteristics were used to distinguish winter wheat from other land cover types. The resulting maps spanned from 2000 to 2022, featuring a 30-m resolution from 2000 to 2017 and an improved 10-m resolution from 2018 to 2022. The overall accuracy of these maps ranged from 80.5 to 93.3%, with Kappa coefficients ranging from 71.3 to 909% and F1 scores from 84.2 to 96.9%. Over the analyzed period, the area dedicated to winter wheat cultivation experienced a decline from 2000 to 2011. However, a notable shift occurred with an increase in winter wheat acreage observed from 2014 to 2017 and a subsequent rise from 2018 to 2022. This research highlights the viability of using satellite observation data for the long-term mapping and monitoring of winter wheat. The proposed methodology has long-term implications for extending this mapping and monitoring approach to other similar areas.

Pre-trained Bi-LSTM model for automated classification of ventricular arrhythmias using 1-D and 2-D ECG

Number of cardiac conditions have been associated with abnormal heartbeat (arrhythmia) such as ventricular fibrillation (Vfib), ventricular flutter (Vfl), and ventricular tachycardia (Vta). This is a difficult and essential job for timely clinical assessment and identification of these potentially life-threatening heart arrhythmias. With the aid of a one-dimensional electrocardiogram (ECG) signal and its associated two-dimensional image, the suggested method provides a strategy for the detection of time-frequency interpretation (Vfib, Vfl, and Vta). A four-stage cascaded Savitzky-Golay (SG) filter is used after a 2-stage median filter to preprocess the ECG signal. This technique employs z-score normalisation after brief (2 sec) ECG readings. The classification of these ECG segments (1-D) and associated time-frequency representation pictures (2-D) was explored separately using a bi-directional long short-term memory-based network. Eight distinct categorization scenarios were examined, and then an average accuracy of 99.67% for 1-D ECG and 99.87% for 2-D ECG signal was attained.

Advanced Low-Pass Filters for Signal Processing: A Comparative Study on Gaussian, Mittag-Leffler, and Savitzky-Golay Filters

Advanced Low-Pass Filters for Signal Processing: A Comparative Study on Gaussian, Mittag-Leffler, and Savitzky-Golay Filters

Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials

Key Message Optimized phenomic selection in durum wheat uses near-infrared spectra, feature engineering and parameter tuning. Our study reports improvements in predictive ability and emphasizes customized preprocessing for different traits and models.The success of plant breeding programs depends on efficient selection decisions. Phenomic selection has been proposed as a tool to predict phenotype performance based on near-infrared spectra (NIRS) to support selection decisions. In this study, we test the performance of phenomic selection in multi-environmental trials from our durum wheat breeding program for three breeding scenarios and use feature engineering as well as parameter tuning to improve the phenomic prediction ability. In addition, we investigate the influence of genotype and environment on the phenomic prediction ability for agronomic and quality traits. Preprocessing, based on a grid search over the Savitzky–Golay filter parameters based on 756,000 genotype best linear unbiased estimate (BLUE) computations, improved the phenomic prediction ability by up to 1500% (0.02–0.3). Furthermore, we show that preprocessing should be optimized depending on the dataset, trait, and model used for prediction. The phenomic prediction scenarios in our durum breeding program resulted in low-to-moderate prediction abilities with the highest and most stable prediction results when predicting new genotypes in the same environment as used for model training. This is consistent with the finding that NIRS capture both the genotype and genotype-by-environment (G×E)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(G\ imes E)$$\\end{document} interaction variance.

Artificial Neural Network Models for Solution Concentration Measurement during Cooling Crystallization of Ceritinib

The development of a quantitative in-line UV spectroscopic method for monitoring of solute concentration during the crystallization process of the active pharmaceutical ingredient (API), ceritinib is described. The method is based on artificial neural networks (ANN). A seeded cooling crystallization process of ceritinib from tetrahydrofuran was studied as a model system. The model was constructed from collected ATR-UV spectra and temperature records within the metastable zone. The collected spectra were preprocessed with the first derivative using the Savitzky-Golay filter. ANN models with different architectures were created and the optimal architecture was chosen based on the root mean square error of prediction (RMSEP) criterion. In addition, ANN models were compared with the models obtained by the linear partial least squares regression (PLSR). Due to the nonlinear relationship in the data set, ANN models predict the solution concentration with higher accuracy compared to linear models. The developed models were successfully used in real-time solution concentration measurement during ceritinib crystallization along with a supersaturation control module developed in-house.

Field validation of NDVI to identify crop phenological signatures

Purpose and MethodsCrop identification using remotely sensed imagery provides useful information to make management decisions about land use and crop health. This research used phonecams to acquire the Normalized Difference Vegetation Index (NDVI) of various crops for three crop seasons. NDVI time series from Sentinel (L121-L192) images was also acquired using Google Earth Engine (GEE) for the same period. The resolution of satellite data is low therefore gap filling and smoothening filters were applied to the time series data. The comparison of data from satellite images and phenocam provides useful insight into crop phenology. The results show that NDVI is generally underestimated when compared to phenocam data. The Savitzky-Golay (SG) and some other gap filling and smoothening methods are applied to NDVI time series based on satellite images. The smoothened NDVI curves are statistically compared with daily NDVI series based on phenocam images as a reference.ResultsThe SG method has performed better than other methods like moving average. Furthermore, polynomial order has been found to be the most sensitive parameter in applying SG filter in GEE. Sentinel (L121-L192) image was used to identify wheat during the year 2022–2023 in Sargodha district where experimental fields were located. The Random Forest Machine Leaning algorithm was used in GEE as a classifier.ConclusionThe classification accuracy has been found 97% using this algorithm which suggests its usefulness in applying to other areas with similar agro-climatic characteristics.

Comparative analysis of filtering methods for measurement data from complex well configurations

This article presents a comparative analysis of various filtering methods for synthetic measurements that simulate data from well test analysis (WTA). The main objective of this work is to identify the most effective filtering methods for noisy WTA data, with the aim of preserving useful information and facilitating the subsequent interpretation of the results. The initial dataset consisted of 200 synthetic pressure drawdown (PDD) and pressure buildup (PBU) curves with varying levels of artificially introduced noise. Both classical filtering methods (Kalman filter, Savitzky–Golay filter, one-dimensional Gaussian filtering) and numerical methods based on neural networks (autoencoders) and machine learning (support vector machines) were considered for data filtering. The comparative analysis demonstrated that the performance of different filtering methods depends on the type of curve (PDD or PBU) and the well characteristics. The best results in terms of signal-to-noise ratio (SNR) and root mean square error (RMSE) were achieved using modern autoencoder-based methods. The conclusion is that the choice of an optimal filtering method requires a detailed analysis of the specific problem and the characteristics of the input data. A combination of different filtering methods is proposed to improve the quality of processing and interpretation of WTA data for complex well designs. The obtained results have practical significance, as they can simplify the segmentation of PDD and PBU curves, which is necessary for the correct identification of various operating periods of the well during the investigation process.

Enhanced Epileptic Seizure Detection through Wavelet-Based Analysis of EEG Signal Processing

Epilepsy affects millions worldwide, making timely seizure detection crucial for effective treatment and enhanced well-being. Electroencephalogram (EEG) analysis offers a non-intrusive solution, but its visual interpretation is prone to errors and requires a lot of time. Many existing works focus solely on achieving competitive levels of accuracy without considering processing speed or the computational complexity of their models. This study aimed to develop an automated technique for identifying epileptic seizures in EEG data through analysis methods. The efforts have been primarily focused on achieving high accuracy results by operating exclusively within a narrow frequency band of the signal, while also aiming to minimize computational complexity. In this article, a new automated approach is presented for seizure detection by combining signal processing and machine learning techniques. The proposed method comprises four stages: (1) Preprocessing: Savitzky–Golay filter to remove the background noise. (2) Decomposition: discrete wavelet transform (DWT) to extract spontaneous alpha and beta frequency bands. (3) Feature extraction: six features (mean, standard deviation, skewness, kurtosis, energy, and entropy) are computed for each frequency band. (4) Classification: a support vector machine (SVM) method classifies signals as normal or containing a seizure. The method was assessed using two publicly available EEG datasets. For the alpha band, the highest achieved accuracy was 92.82%, and for the beta band it was 90.55%, which demonstrates adequate capability in both bands for accurate seizure detection. Furthermore, the obtained low computational cost suggests a potentially valuable application in real-time assessment scenarios. The obtained results indicate its capacity as a valuable instrument for diagnosing epilepsy and monitoring patients. Further research is necessary for clinical validation and potential real-time deployment.

Forecasting operation of a chiller plant facility using data-driven models

In recent years, data-driven models have enabled accurate prediction of chiller power consumption and chiller coefficient of performance (COP). This study evaluates the usage of time series Extreme Gradient Boosting (XGBoost) models to predict chiller power consumption and chiller COP of a water-cooled chiller plant. The 10-second measured data used in this study are from the Intelligent Building Agents Laboratory (IBAL), which includes two water-cooled chillers. Preprocessing, data selection, noise analysis, and data smoothing methods influence the accuracy of these data-driven predictions. The data intervals were changed to 30 s, 60 s, and 180 s using down-sampling and averaging strategies to investigate the impact of data preprocessing methods and data resolutions on the accuracy of chiller COP and power consumption models. To overcome the effect of noise on the accuracy of the models of chiller power consumption and COP, two data smoothing methods, the moving average window strategy and the Savitzky-Golay (SG) filter, are applied. The results show that both methods improve the predictions compared to the baseline, with the SG filter slightly outperforming the moving average. Particularly, the mean absolute percentage error of the chiller COP and power consumption models improved from 4.8 to 4.9 for the baseline to 1.9 and 2.3 with the SG filter, respectively. Overall, this study provides a practical guide to developing XGBoost data-driven chiller power consumption and COP prediction models.

Constrained path planning for manned–unmanned rotorcraft teaming in emergency medical service missions

This paper investigates the path-planning problem applied to an innovative Unmanned Air Vehicle teaming with a helicopter to increase safety during Helicopter Emergency Medical Services operations. The unmanned vehicle, a drone that optionally can be launched from the helicopter, has the mission to explore the area of operation to determine the meteorological and environmental conditions and to detect physical obstacles. It is initially found that the combination of probabilistically optimal Rapidly-exploring Random Tree (RRT∗\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{*}$$\\end{document}) as the global planner and of Bidirectional Rapidly-exploring Random Tree (BiRRT) as the local planner provides a nearly optimal global path and a rapid replanning in case new obstacles are detected. Adopting a Savitzky–Golay filter in an optional post-processing phase enables trajectory smoothing, thus improving its practicability. The feasibility of the identified trajectory for a rigid-body helicopter model is assessed by computing a first estimate of attitude, forces, control inputs, and rotor power from the trajectory points and curvature. This assessment shows that the RRT∗\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{*}$$\\end{document} used as a local planner provides replanned trajectories more feasible than BiRRT with comparable computational times.

Lithium battery state of health estimation using real-world vehicle data and an interpretable hybrid framework

Accurate point estimation and uncertainty estimation of the state of health (SOH) of battery systems are crucial for alleviating user range anxiety and preventing battery safety incidents. On top of approximately 28 million real-world electric vehicle operation data samples, this paper embeds the categorical boosting algorithm as the base learner of the natural gradient boosting, proposing a novel interpretable N-CatBoost hybrid framework to achieve precise point estimation and uncertainty estimation of the battery SOH. Deep charging segments are selected to calculate the initial capacity, and the nonlinear decay trend of the capacity is derived through the Savitzky-Golay filter. Based on the influencing factors of capacity degradation, health features characterizing battery aging are extracted from electric vehicle data as model inputs. The model's hyperparameters are optimized using the particle swarm optimization algorithm, and it is compared with seven other popular machine learning algorithms. The results indicate that the proposed N-CatBoost model achieves the highest estimation accuracy, with mean absolute percentage error and root mean square error of 0.817 % and 1.156 Ah, respectively. In addition, the Shapley additive explanation method is utilized to make the model interpretable, providing full transparency of all predicted values. More importantly, the developed N-CatBoost model can achieve uncertainty estimation of its predictions, with 100 % of the actual capacity values successfully falling within the model's 99 % prediction interval. Therefore, the proposed N-CatBoost model is a reliable and effective method with great potential for deployment on the cloud side for the SOH estimation of batteries in large-scale vehicles.

H2LWRF-PDR: An efficient indoor positioning algorithm using a single Wi-Fi access point and Pedestrian Dead Reckoning

Indoor localization is challenging in densely populated urban areas due to the multipath effect, attenuation, noise, and difficulty finding reliable Wi-Fi access points. In urban flats, multiple access points are not easily available or require infrastructure setup, which increases cost. To address the above issues, the article proposes a new algorithm called ‘H2LWRF-PDR’ based on Wi-Fi fingerprinting using a single access point with extended features. This algorithm is designed for static and moving objects. The proposed algorithm first converts the received signal strengths from a single access point into five statistical features used as fingerprints. Then, hierarchical clustering is applied to remove outliers from the fingerprints. Then, a random forest classifier is used to predict the cluster values. Finally, the lowess filters are used to smoothen the output values from the classifier. Furthermore, these outputs are combined with the proposed Pedestrian Dead Reckoning (PDR) algorithm. In the end, a Savitzky–Golay filter is utilized to remove the fluctuations in the trajectories. The proposed approach has been validated in urban flat and laboratory environments and compared with state-of-the-art localization algorithms. The proposed algorithm ‘H2LWRF-PDR’ showed 50% improvements in an urban flat dataset and at least 30% in the laboratory dataset.

Advancing short-term solar irradiance forecasting accuracy through a hybrid deep learning approach with Bayesian optimization

The optimization of solar energy integration into the power grid relies heavily on accurate forecasting of solar irradiance. In this study, a new approach for short-term solar irradiance forecasting is introduced. This method combines Bayesian Optimized Attention-Dilated Long Short-Term Memory and Savitzky-Golay filtering. The methodology is implemented to analyze data obtained from a solar irradiance probe situated in Douala, Cameroon. Initially, the unprocessed data is augmented by integrating distinctive solar irradiation variables, and the Savitzky-Golay filter with Bayesian Optimization is used to enhance its quality. Subsequently, multiple deep learning models, including Long Short-Term Memory, Bidirectional Long Short-Term Memory, Artificial Neural Networks, Bidirectional Long Short-Term Memory with Additive Attention Mechanism, and Bidirectional Long Short-Term Memory with Additive Attention Mechanism and Dilated Convolutional layers, are trained and evaluated. Out of all the models considered, the proposed approach, which combines the attention mechanism and dilated convolutional layers, demonstrates exceptional performance with the best convergence and accuracy in forecasting. Bayesian Optimization is further utilized to fine-tune the polynomial and window size of the Savitzky-Golay filter and optimize the hyperparameters of the deep learning models. The results show a Symmetric Mean Absolute Percentage Error of 0.6564, a Normalized Root Mean Square Error of 0.2250, and a Root Mean Square Error of 22.9445, surpassing previous studies in the literature. Empirical findings highlight the effectiveness of the proposed methodology in enhancing the accuracy of short-term solar irradiance forecasting. This research contributes to the field by introducing novel data pre-processing techniques, a hybrid deep learning architecture, and the development of a benchmark dataset. These advancements benefit both researchers and solar plant managers, improving solar irradiance forecasting capabilities.

Iron ore rock classification and mine remote sensing inversion based on spectroscopy and improved extreme learning machine

The classification of iron ore rock plays a crucial role in assisting the mine to develop scientifically sound mining strategies. Given the limitations of traditional manual identification and chemical techniques in terms of cost and detection time, it is crucial to develop an economical, high-precision, and efficient classification method for iron ore rocks. This paper takes an iron mine in Anshan as the research center and aims to establish an iron ore rock classification model by combining the improved extreme learning machine (ELM) with near-infrared spectra (NIRS). The NIRS of iron ore rock is denoised and feature extracted using the Savitzky–Golay filter and competitive adaptive reweighted sampling (CARS) methods, respectively. In this paper, we propose the IAdaBoost algorithm by introducing the sample similarity relationship into the weight-updating strategy of the AdaBoost integration algorithm. The weighted extreme learning machine (WELM) is adopted as the base learner for the IAdaBoost algorithm. Furthermore, we employ a multi-strategy improved gray wolf optimization (IGWO) algorithm to optimize the learning rate and the number of integrated base learners in the IAdaBoost algorithm. Consequently, we propose the IGWO-IAdaBoost-WELM model. Compared to other machine learning models, our proposed model performs better and can classify iron ore rocks consistently and efficiently. Meanwhile, we also used the model to invert the remote sensing images of the iron ore mining area, and the results show that the model can achieve fast, efficient, and large-scale iron ore rock classification, which provides an important reference for mining.

Inversion of Glycyrrhiza Chlorophyll Content Based on Hyperspectral Imagery

Glycyrrhiza is an important medicinal crop that has been extensively utilized in the food and medical sectors, yet studies on hyperspectral remote sensing monitoring of glycyrrhiza are currently scarce. This study analyzes glycyrrhiza hyperspectral images, extracts characteristic bands and vegetation indices, and constructs inversion models using different input features. The study obtained ground and unmanned aerial vehicle (UAV) hyperspectral images and chlorophyll content (called Soil and Plant Analyzer Development (SPAD) values) from sampling sites at three growth stages of glycyrrhiza (regreening, flowering, and maturity). Hyperspectral data were smoothed using the Savitzky–Golay filter, and the feature vegetation index was selected using the Pearson Correlation Coefficient (PCC) and Recursive Feature Elimination (RFE). Feature extraction was performed using Competitive Adaptive Reweighted Sampling (CARS), Genetic Algorithm (GA), and Successive Projections Algorithm (SPA). The SPAD values were then inverted using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), and the results were analyzed visually. The results indicate that in the ground glycyrrhiza inversion model, the GA-XGBoost model combination performed best during the regreening period, with R2, RMSE, and MAE values of 0.95, 0.967, and 0.825, respectively, showing improved model accuracy compared to full-spectrum methods. In the UAV glycyrrhiza inversion model, the CARS-PLSR combination algorithm yielded the best results during the maturity stage, with R2, RMSE, and MAE values of 0.83, 1.279, and 1.215, respectively. This study proposes a method combining feature selection techniques and machine learning algorithms that can provide a reference for rapid, nondestructive inversion of glycyrrhiza SPAD at different growth stages using hyperspectral sensors. This is significant for monitoring the growth of glycyrrhiza, managing fertilization, and advancing precision agriculture.

Travelling Ionospheric Disturbances detection: a statistical study of detrending techniques, induced period error and near real-time observables

Due to advances in remote sensing of the Earth's Ionosphere through Total Electron Content (TEC) estimates by Global Navigation Satellite System (GNSS) receivers, it is possible to detect and characterize Travelling Ionospheric Disturbances (TIDs) in both post-processing and, to some extent, in near real-time (NRT). A reliable and precise TEC filtering technique must be adopted to characterize waves accurately. Specifically, TEC detrending is widely adopted to extract the amplitude and period of the detected ionospheric waves from the background ionospheric conditions. Therefore, this study aims to understand and compare how different TEC detrending techniques and their settings impact the ability to extract such parameters. We highlight that the novel Fast Iterative Filtering (FIF) and the Savitzky-Golay filter (SGOLAY) techniques are the most reliable overall compared with moving average (MA), multi-order numerical difference (DD), polynomial detrending (POLY) and Finite Impulse response (FIR) band-pass filter (BUTF). Moreover, the impact of general algorithm settings on the extracted TID period is investigated, such as the Ionospheric Piercing Point (IPP) height and elevation cut-off angle, showing that such parameters drastically impact the retrieved period, especially for slower TIDs. Finally, due to the growing interest in real-time (RT) detection and classification of TIDs, the study proposes techniques for accurately estimating the TID amplitude in an NRT scenario. Such NRT techniques are then compared with the widely used post-processing products, such as the calibrated vertical TEC (vTEC), showing a difference that is mostly lower than the typical noise level of GNSS receivers (0.05 TECu).