Stacking Method Research Articles

Predicting Landslide Using Machine Learning Techniques

In mountainous areas prone to landslides, it’s crucial to map out where these hazardous events are likely to occur to mitigate risks effectively. This study focuses employing an integrated approach to assess landslide susceptibility using Random Forest (RF), Stacking, Vote, AdaBoostM1, and Bagging. 13 factors influencing landslide occurrence are identified for modeling purposes. To evaluate and compare the models’ performance, multiple statistical methods are employed. The analysis highlights the effectiveness of employing machine learning models, Random Forest (RF), Stacking, Bagging, and Vote methods. The results demonstrate the efficiency of the models in accurately predicting landslide susceptibility. The study suggests that similar hybrid models can be effectively utilized in other sensitive regions with comparable geo-environmental conditions for landslide susceptibility studies. By integrating various techniques and leveraging ensemble algorithms, these models offer improved accuracy and reliability in assessing landslide hazards. This comprehensive approach provides valuable insights for disaster management and risk reduction efforts in landslideprone areas worldwide.

Improving diabetes disease patients classification using stacking ensemble method with PIMA and local healthcare data

Diabetes mellitus, a chronic metabolic disorder, continues to be a major public health issue around the world. It is estimated that one in every two diabetics is undiagnosed. Early diagnosis and management of diabetes can also prevent or delay the onset of complications. With the help of a variety of machine learning and deep learning models, stacking algorithms, and other techniques, our study's goal is to detect diseases early. In this study, we propose two stacking-based models for diabetes disease classification using a combination of the PIMA Indian diabetes dataset, simulated data, and additional data collected from a local healthcare facility. We use both the classical and deep neural network stacking ensemble methods to combine the predictions of multiple classification models and improve classification accuracy and robustness. In the evaluation protocol, we used both the train-test and cross-validation (CV) techniques to validate our proposed model. The highest accuracy is obtained by stacking ensemble with three NN architectures, resulting in an accuracy of 95.50 %, precision of 94 %, recall of 97 %, and f1-score of 96 % using 5-fold CV on simulation study. The stacked accuracy obtained from ML algorithms for the Pima Indian Diabetes dataset is 75.03 % using the train-test split protocol, while the accuracy obtained from the CV protocol is 77.10 % on the stacked model. The range of performance scores that outperformed the CV protocol 2.23 %–12 %. Our proposed method achieves a high accuracy range from 92 % to 95 %, precision, recall, and F1-score ranges from 88 % to 96 % using classical and deep neural network (NN)-based stacking method on the primary dataset. The proposed dataset and ensemble method could be useful in the early detection and treatment of diabetes, as well as in the advancement of machine learning and data analysis techniques in the healthcare industry.

CTA-Net: A gaze estimation network based on dual feature aggregation and attention cross fusion

Recent work has demonstrated the Transformer model is effective for computer vision tasks. However, the global self-attention mechanism utilized in Transformer models does not adequately consider the local structure and details of images, which may result in the loss of information and local details, causing decreased estimation accuracy in gaze estimation tasks when compared to convolution or sequential stacking methods. To address this issue, we propose a parallel CNNs-Transformer aggregation network (CTA-Net) for gaze estimation, which fully leverages the advantages of the Transformer model in modeling global context while the convolutional neural networks (CNNs) model in retaining local details. Specifically, Transformer and ResNet are deployed to extract facial and eye information, respectively. Additionally, an attention cross fusion (ACFusion) Block is embedded with CNN branch, which decomposes features in space and channels to supplement lost features, suppress noise, and help extract eye features more effectively. Finally, a dual-feature aggregation (DFA) module is proposed to effectively fuse the output features of both branches with the help feature a selection mechanism and a residual structure. Experimental results on the MPIIGaze and Gaze360 datasets demonstrate that our CTA-Net achieves state-of-the-art results.

TCS-Fall: Cross-individual fall detection system based on channel state information and time-continuous stack method.

Falls pose a serious health risk for the elderly, particular for those who are living alone. The utilization of WiFi-based fall detection, employing Channel State Information (CSI), emerges as a promising solution due to its non-intrusive nature and privacy preservation. Despite these advantages, the challenge lies in optimizing cross-individual performance for CSI-based methods. This study aimed to develop a resilient real-time fall detection system across individuals utilizing CSI, named TCS-Fall. This method was designed to offer continuous monitoring of activities over an extended timeframe, ensuring accurate and prompt detection of falls. Extensive CSI data on 1800 falls and 2400 daily activities was collected from 20 volunteers. The grouped coefficient of variation of CSI amplitudes were utilized as input features. These features capture signal fluctuations and are input to a convolutional neural network classifier. Cross-individual performance was extensively evaluated using various train/test participant splits. Additionally, a user-friendly CSI data collection and detection tool was developed using PyQT. To achieve real-time performance, data parsing and pre-processing computations were optimized using Numba's just-in-time compilation. The proposed TCS-Fall method achieved excellent performance in cross-individual fall detection. On the test set, AUC reached 0.999, no error warning ratio score reached 0. 955 and correct warning ratio score reached of 0.975 when trained with data from only two volunteers. Performance can be further improved to 1.00 when 10 volunteers were included in training data. The optimized data parsing/pre-processing achieved over 20× speedup compared to previous method. The PyQT tool parsed and detected the fall within 100 ms. TCS-Fall method enables excellent real-time cross-individual fall detection utilizing WiFi CSI, promising swift alerts and timely assistance to elderly. Additionally, the optimized data processing led to a significant speedup. These results highlight the potential of our approach in enhancing real-time fall detection systems.

Recent progress in emerging two-dimensional organic-inorganic van der Waals heterojunctions.

Two-dimensional (2D) materials have attracted significant attention in recent decades due to their exceptional optoelectronic properties. Among them, to meet the growing demand for multifunctional applications, 2D organic-inorganic van der Waals (vdW) heterojunctions have become increasingly popular in the development of optoelectronic devices. These heterojunctions demonstrate impressive capability to synergistically combine the favourable characteristics of organic and inorganic materials, thereby offering a wide range of advantages. Also, they enable the creation of innovative device structures and introduce novel functionalities in existing 2D materials, avoiding the need for lattice matching in different material systems. Presently, researchers are actively working on improving the performance of devices based on 2D organic-inorganic vdW heterojunctions by focusing on enhancing the quality of 2D materials, precise stacking methods, energy band regulation, and material selection. Therefore, this review presents a thorough examination of the emerging 2D organic-inorganic vdW heterojunctions, including their classification, fabrication, and corresponding devices. Additionally, this review offers profound and comprehensive insight into the challenges in this field to inspire future research directions. It is expected to propel researchers to harness the extraordinary capabilities of 2D organic-inorganic vdW heterojunctions for a wider range of applications by further advancing the understanding of their fundamental properties, expanding the range of available materials, and exploring novel device architectures. The ongoing research and development in this field hold potential to unlock captivating advancements and foster practical applications across diverse industries.

MAMMOTH-Subaru. III. Lyα Halo Identified by Stacking ∼3300 Lyα Emitters at z = 2.2–2.3

In this paper, we present a Lyα halo (LAH) identified by stacking ∼3300 Lyα emitters (LAEs) at z = 2.2–2.3. We carry out imaging observations and data reduction with Subaru/Hyper Suprime-Cam. Our total survey area is ∼12 deg2 and the imaging depths are 25.5–27.0 mag. Using the imaging data, we select 1240 and 2101 LAE candidates at z = 2.2 and 2.3, respectively. We carry out spectroscopic observations of our LAE candidates and data reduction with Magellan/IMACS to estimate the contamination rate of our LAE candidates. We find that the contamination rate of our sample is low (8%). We stack our LAE candidates with a median stacking method to identify the LAH at z = 2. We show that our LAH is detected until ∼100 kpc at the 2σ significance level and likely extended to ∼200 kpc at a surface brightness level of ∼10−20 erg s−1 cm−2 arcsec−2. Compared to those of previous studies, our LAH is brighter at radii of ∼25–100 kpc, which is not likely caused by the contamination in our sample but by the different redshifts, fields, and selection methods instead. To investigate how central galaxies affect surrounding LAHs, we divide our LAEs into subsamples based on the Lyα luminosity (L Lyα ), rest-frame Lyα equivalent width (EW0), and UV magnitude (M uv). We stack the subsamples and find that higher L Lyα , smaller EW0, and brighter M uv cause more extended halos. Our results suggest that more massive LAEs generally have more extended LAHs.

Industrial analysis of gyro stability and precision assembly

Abstract Gyro is a new type of widely used micro-inertial sensor, which can realize high-precision, small-size, and anti-interference angular velocity measurement and is widely used in aerospace, platform drilling, autonomous driving, wearable devices, and cell phones. The study first analyzes the influence of the angle of control torque on the stability of the gyro and deduces the relationship between the gyro rotational inertia, spin angular velocity, feed angular velocity, and stability. Then, through the research of industrial gyro products research status, the factors affecting the precision of the gyro elaborated on the key technologies that need to be broken through in the process of gyro precision assembly and combined with the sequential stacking method to realize the gyro in the industrial close assembly. The results show that both the shape factor and scale factor are the influencing factors of gyro stability. The shape and position error of each part, as well as the coupling of the error, cause the uneven force on the motor shaft, the local stress concentration, and, therefore, local deformation, which ultimately leads to the offset of the motor shaft center, and the influence of the shape and position coupling error on the assembly precision of the gyro.

Research on Numerical Weather Prediction Wind Speed Correction Based on Stacking Ensemble Learning Algorithm

The transportation of wind fields plays a crucial role in the dispersion and distribution of air pollutants, and accurate wind speed prediction is essential for assessing pollutant concentrations. In this study, we constructed a Stacking ensemble learning model using three models, namely Random Forest, LightGBM, and XGBoost, as base learners, and the LASSO regression model as the meta-learner to optimize wind speed data forecasting for Zhengzhou City’s urban area using WRF. Firstly, based on Pearson correlation coefficients, we selected meteorological variables that have a significant impact on near-surface wind speed and derived historical lagged features. Bayesian TPE was utilized for hyperparameter tuning and model building. Finally, the performance of the trained model was evaluated by comparing it with ground observation data. The results showed that compared to the WRF model, Random Forest, LightGBM, and XGBoost effectively reduced forecast errors and significantly improved wind speed predictions. Both LightGBM and XGBoost demonstrated similar performance in the correction models across the 11 stations and outperformed Random Forest. The Stacking method integrated the advantages of the base learners and exhibited improvement capabilities over individual models, highlighting the potential of machine learning in enhancing localized and accurate weather forecasting.

Arabic Idioms Detection by Utilizing Deep Learning and Transformer-based Models

Arabic language resources and natural language processing technologies have seen significant advancements in recent years. The detection of idiomatic expressions is a crucial problem in Arabic natural language processing. Unfortunately, there have been few advancements in this field due to the scarcity of datasets and computational models that still struggle to handle Arabic idiomatic phrases. Although idioms have significance in Arabic because of their distinctive relation to history and cultural knowledge, they also offer a language tool for conveying concepts and thoughts that may diverge from their literal interpretation. Hence, to accurately detect their incongruent language, a model requires the ability to interpret the idioms’ contextual meaning. To tackle this issue, this study entails comprehensive work on detecting Arabic idiomatic and literal statements. For that, we introduce a large Arabic idiomatic and literal statements. The dataset includes idioms from several Arabic idiomatic platforms balanced with literal statements from titles in news platforms with similar keywords found in the idioms. This study adopts four deep learning models, namely, CNN, LSTM, Bi-LSTM, and GRU trained with word embeddings, FastText and Skip-Gram Word2Vec, and three transformer-based models, BERT, RoBERTa, and DistilBERT were compiled and assessed via empirical evaluations. Our experiments demonstrated that transformer-based models outperformed deep learning models trained by word embedding to detect Arabic idioms and literal statements, reaching 97% in favor of DistilBERT. We also enhanced the accuracy through the ensemble stacking method, boosting it by 0.8 points. Furthermore, we propose a novel Arabic idiom interpreter that offers simple explanations for selected idiomatic contents within the literal text. Our work enriches the challenge of detecting incongruities found in similar figurative genres, specifically in the rich morphological language, Arabic.

StackER: a novel SMILES-based stacked approach for the accelerated and efficient discovery of ERα and ERβ antagonists

The role of estrogen receptors (ERs) in breast cancer is of great importance in both clinical practice and scientific exploration. However, around 15–30% of those affected do not see benefits from the usual treatments owing to the innate resistance mechanisms, while 30–40% will gain resistance through treatments. In order to address this problem and facilitate community-wide efforts, machine learning (ML)-based approaches are considered one of the most cost-effective and large-scale identification methods. Herein, we propose a new SMILES-based stacked approach, termed StackER, for the accelerated and efficient identification of ERα and ERβ inhibitors. In StackER, we first established an up-to-date dataset consisting of 1,996 and 1,207 compounds for ERα and ERβ, respectively. Using the up-to-date dataset, StackER explored a wide range of different SMILES-based feature descriptors and ML algorithms in order to generate probabilistic features (PFs). Finally, the selected PFs derived from the two-step feature selection strategy were used for the development of an efficient stacked model. Both cross-validation and independent tests showed that StackER surpassed several conventional ML classifiers and the existing method in precisely predicting ERα and ERβ inhibitors. Remarkably, StackER achieved MCC values of 0.829–0.847 and 0.712–0.786 in terms of the cross-validation and independent tests, respectively, which were 5.92–8.29 and 1.59–3.45% higher than the existing method. In addition, StackER was applied to determine useful features for being ERα and ERβ inhibitors and identify FDA-approved drugs as potential ERα inhibitors in efforts to facilitate drug repurposing. This innovative stacked method is anticipated to facilitate community-wide efforts in efficiently narrowing down ER inhibitor screening.

Machine Learning-Based Qualitative Identification of Four-Phase Fluid in Reservoir.

The identification of fluid types has always been the focus of oil and gas field exploration and development research. At this stage, a large amount of CO2 has been found in many basins during exploration and development, which greatly affects the accuracy of reservoir understanding and evaluation, so it is very important to accurately identify the fluid type of the CO2-bearing reservoirs. However, methods utilizing multiple logging data are greatly affected by physical changes in the formation, resulting in methods that are only applicable to the area and layer under study, are poorly generalized, and require multiple instruments and experimental support. Existing nuclear logging methods that primarily utilize logging curve stacking and intersection map methods fail to take full advantage of logging. In this study, taking advantage of the fact that the neutron gamma technique of nuclear logging measurement can provide multiparameter information with the characteristics of machine learning to deal with multidimensional data, comparing the classification results of different ware learning methods under different classification strategies and selecting a method of identifying fluids in logging while drilling was based on the idea of dichotomy and the use of the support vector machine as a meta-model. This solved the problem of identifying fluids in the CO2-bearing reservoirs, providing new ideas for the design and fabrication of logging instruments. These instruments can assist with the exploration and development of oil and gas fields and has a broad application prospect in CO2-EOR and CCUS.

Deep learning-based burned forest areas mapping via Sentinel-2 imagery: a comparative study.

In order to evaluate the effects of forest fires on the dynamics of the function and structure of ecosystems, it is necessary to determine burned forest areas with high accuracy, effectively, economically, and practically using satellite images. Extraction of burned forest areas utilizing high-resolution satellite images and image classification algorithms and assessing the successfulness of varied classification algorithms has become a prominent research field. This study aims to indicate on the capability of the deep learning-based Stacked Autoencoders method for the burned forest areas mapping from Sentinel-2 satellite images. The Stacked Autoencoders, used in this study as an unsupervised learning method, were compared qualitatively and quantitatively with frequently used supervised learning algorithms (k-Nearest Neighbors (k-NN), Subspaced k-NN, Support Vector Machines, Random Forest, Bagged Decision Tree, Naive Bayes, Linear Discriminant Analysis) on two distinct burnt forest zones. By selecting burned forest zones with contrasting structural characteristics from one another, an objective assessment was achieved. Manually digitized burned areas from Sentinel-2 satellite images were utilized for accuracy assessment. For comparison, different classification performance and quality metrics (Overall Accuracy, Mean Squared Error, Correlation Coefficient, Structural Similarity Index Measure, Peak Signal-to-Noise Ratio, Universal Image Quality Index, and KAPPA metrics) were used. In addition, whether the Stacked Autoencoders method produces consistent results was examined through boxplots. In terms of both quantitative and qualitative analysis, the Stacked Autoencoders method showed the highest accuracy values.

Braiding Three‐Dimensional Paper‐Based Microfluidic Devices

AbstractThree‐dimensional paper‐based microfluidic devices have shown great potential in various applications, including point‐of‐care diagnostics, environmental monitoring, and tissue engineering. However, their fabrication is still limited to stacking and origami methods. Inspired by the art of bamboo braiding in China, we developed a novel fabrication technique based on the braiding concept to create three‐dimensional paper‐based microfluidic devices with PDMS‐impregnated paper substrate as the building units. The resulting three‐dimensional paper device brings unique advantages, including compactness, facile disassembly, and real‐time flow visualization. The multiplexed glucose analysis with a braided device integrated with 16‐switchable valves for flow control was further fabricated to demonstrate the device‘s applicability. We envision braiding‐based fabrication technology opening new possibilities and bringing broad applications for three‐dimensional paper microfluidic devices.

Establishment and validation of a prediction nomogram for heart failure risk in patients with acute myocardial infarction during hospitalization

BackgroundAcute myocardial infarction (AMI) with consequent heart failure is one of the leading causes of death in humans. The aim of this study was to develop a prediction model to identify heart failure risk in patients with AMI during hospitalization.MethodsThe data on hospitalized patients with AMI were retrospectively collected and divided randomly into modeling and validation groups at a ratio of 7:3. In the modeling group, the independent risk factors for heart failure during hospitalization were obtained to establish a logistic prediction model, and a nomogram was constructed. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the predictive performance and clinical value. Machine learning models with stacking method were also constructed and compared to logistic model.ResultsA total of 1875 patients with AMI were enrolled in this study, with a heart failure rate of 5.1% during hospitalization. The independent risk factors for heart failure were age, heart rate, systolic blood pressure, troponin T, left ventricular ejection fraction and pro-brain natriuretic peptide levels. The area under the curve (AUC) of the model in modeling group and validation group were 0.829 and 0.846, respectively. The calibration curve showed high prediction accuracy and the DCA curve showed good clinical value. The AUC value of the ensemble model by the stacking method in the validation group were 0.821, comparable to logistic prediction model.ConclusionsThis model, combining laboratory and clinical factors, has good efficacy in predicting heart failure during hospitalization in AMI patients.

Multi-master event waveform stacking microseismic location method based on time-frequency transformation

Waveform stacking is frequently employed in the analysis of microseismic data due to its adaptability, effectiveness, and noise immunity. However, the low signal-to-noise ratio and inaccurate velocity model have a considerable negative impact on the waveform stacking location method's performance. A time-frequency transform-based characteristic function and the addition of a multi-master event method to waveform stacking location are presented as solutions to the aforementioned issues. In this paper, non-smooth statistical features of characteristic function are extracted and enhanced using time-frequency transform. Based on the two-pair double-difference method, multi-master events are introduced and a reference criterion for selecting the master events is proposed. Experiments with simulated and actual microseismic data show that the conversion of time-domain signals into time-frequency signals by wavelet transform can enhance the peak capacity of the signal and reduce the background noise, enhancing the imaging resolution. The introduction of multi-master events not only reduces the sensitivity of the waveform stacking method to velocity error but also improves the clustering effect of the master event method.

Fault diagnosis of brushless DC motor based on Stack Sparse Autoencoder

Because of their simple structure, long service life, high efficiency, etc., brushless DC (BLDC) motors have been widely applied in many fields. In some applications, high requirements for BLDC continuous use of motors, so often to BLDC running state monitoring of motors, realizes the early fault diagnosis, to improve the reliability, safety, and prolonged use. To solve this problem, a BLDC fault diagnosis method based on Fast Fourier Transform (FFT), Stacked Sparse Auto-encoder (SSAE), and soft classifier was proposed. In the laboratory, a BLDC model R-3525 was used as the experimental equipment, and the data of 9 kinds of fault conditions such as bearing damage, cage damage, inner and outer ring damage, and the normal condition of the motor were collected. The collected data are transformed into 28 × 28 two-dimensional data sets by FFT. The feature expressions of various faults are adaptively learned from many data, and the intelligent diagnosis of the motor is realized by the feature function expression. The experimental results demonstrate that, in comparison to the single neural network approach, the stacked method can significantly enhance the precision of fault classification and achieve fault diagnosis for brushless DC motors. This method carries valuable implications for other varieties of BLDC motors.

Comparative Evaluation of Masson's Trichrome and Picrosirius Red Staining for Digital Collagen Quantification Using ImageJ in Rabbit Wound Healing Research

The therapeutic potential of Pluronic F127 (PF127) hydrogel loaded with adipose-derived stromal vascular fraction (AdSVF), mesenchymal stem cells (AdMSC), and conditioned media (AdMSC-CM) for repairing full-thickness skin wounds was evaluated using a rabbit model. The rabbits were randomly divided into eight groups with six animals each and treatment was given as per the predetermined protocol (3 doses at one-week interval): Group A (Control), Group B (AdSVF), Group C (AdMSC), Group D (AdMSC-CM), Group E (PF127), Group F (AdSVF + PF127), Group G (AdMSC + PF127), and Group H (AdMSC-CM + PF127). Skin tissue samples were collected from the healing wounds on day 28 for staining and collagen quantification. Collagen density (Area %) was quantified using tissue sections stained with Masson's Trichrome (MT) and Picrosirius Red (PSR) stain using the Colour Deconvolution plugin of ImageJ and RGB stack method, respectively. These techniques function based on separating different colour channels in the stained tissue sections to isolate the collagen fibers and then quantifying them through thresholding and image analysis. Across the treatment groups, both staining methods generally showed a trend of increased collagen density compared to the control group. For most groups, PSR staining consistently indicated slightly lower collagen densities than MT staining. However, the overall trends were similar in both staining. The comparison between PSR and MT staining methods revealed that both techniques effectively assess collagen density in healing wounds. However, there were subtle differences in the absolute values obtained, with PSR staining tending to yield slightly lower collagen density measurements than MT. These differences can be attributed to the distinct mechanisms of these staining methods. Therefore, both staining methods can digitally quantify collagen density in wound healing research.

A stacked ensemble method based on TCN and convolutional bi-directional GRU with multiple time windows for remaining useful life estimation

With the widespread popularity of sensors, time-series data of engine degradation processes have been widely applied for remaining useful life (RUL) prediction. As a result, the large-dimensional, large-scale, and multi-state data characteristics of degraded data make accurate prediction very challenging. To overcome this issue, this paper proposes a stacked integration method based on temporal convolutional network (TCN) and convolutional bi-directional gate recurrent unit (CNN-Bi-GRU) with multiple time windows for RUL prediction, which has smaller ensemble dimensions and stronger reliability and adaptability. In the proposed model, the TCN model can well overcome the limitations of large amounts of data which leads to the problem of difficulty in learning temporal relationships; CNN-Bi-GRU model is used to extract important features to solve the problem of high-dimensional data. In addition, the multi-time window method is used to enhance the adaptability of the method and increase the information obtained by the model. Compared with the popular prediction methods, the prediction results of the proposed ensemble model have been improved by about 20 % on average on data sets. In addition, on the N-CMAPSS data set with larger data volume and more diverse states, the proposed model also achieves an average improvement of about 10% over comparison methods. It shows that the proposed method enhances the reliability and applicability of prediction.

Performance of Common Scene Stacking Atmospheric Correction on Nonlinear InSAR Deformation Retrieval

Atmospheric Phase Screen (APS) is a major noise that suppresses the accuracy of InSAR deformation time series products. Several correction methods have been developed to perform APS reduction in the InSAR analysis, in which an algorithm called Common Scene Stacking (CSS) method draws wide attention in the community as the method was supposed to effectively separate atmospheric contributions without any external data. CSS was initially proposed for solving linearly interseismic deformation. Whether CSS can be applied in nonlinear deformation cases remains unsolved. In this study, we first conduct a series of data simulations including variable elastic deformation components and also propose an iterative strategy to address the inherent weak edge constraint issues in CSS under different deformation conditions. The results show that signal-to-noise ratio (SNR) is a key parameter affecting the performance of CSS in APS separation. For example, the recovery rate of deformation can generally be greater than 80% from datasets with SNR greater than 10 dB. Our results imply that CSS can favor further improvement of InSAR measurement accuracy. The proposed method in this study was applied to assessing deformation history across the 2020 Mw 5.7 Dingjie earthquake, in which logarithmic postseismic deformation history and coseismic contribution can be successfully retrieved once.

Factors affecting diffusion of polar organic compounds in agarose hydrogel applied to control mass transfer in passive samplers.

Diffusive hydrogel-based passive sampler (HPS) based on diffusive gradients in thin films (DGT) is designed for monitoring polar organic contaminants in the aquatic environment. DGT technique controls the compound's overall uptake rate by adding a hydrogel layer of known thickness, which minimizes the importance of the resistive water boundary layer in the compound uptake process. In this work, we investigated several factors which may influence the diffusion of a range of aquatic contaminants in 1.5% agarose hydrogel. Diffusion in hydrogel was tested using the sheet stacking method. We demonstrated that a thin nylon netting incorporated into the diffusive hydrogel for mechanical strengthening does not significantly affect the diffusion of 11 perfluoroalkyl compounds. Further, we investigated the effect of pH in the range from 3 to 11 on the diffusion of a range of 39 aromatic amines (AAs)-36 aromatic, 2 aliphatic, and azobenzene in hydrogel. AAs were chosen as representatives of compounds with pH-dependent dissociation in water. Analysis of variance showed no significant difference in meandiffusion coefficient log D value at five pH values. The demonstration that the diffusion coefficient D and thus the sampling rate Rs are independent on pH simplifies the interpretation of data from field studies because we can neglect the influence of pH on the Rs. log D values (m2 s-1) of tested AAs ranged from to - 9.77 for 3,3'-dimethylbenzidine to - 9.19 for azobenzene. A negative correlation of log D with molar mass (log M) and molecular volume (log Vm) was observed (R = - 0.57 and - 0.56, respectively). The diffusion coefficient presents a critical parameter for the sampling rate estimation of HPS. Theoretical sampling rates Rs of AAs were calculated for a HPS using the average D values. TheoreticalRs values calculated for AAs at 22°C ranged from 29 mL day-1 for 3,3'-dimethylbenzidine to 106 mL day-1 for 2-aminopyridine. Our calculated values of Rs are in the same range as those already published for a range of low-molecular polar organic contaminants, which supports the possibility of deriving sampler performance parameters in the field from laboratory-derived diffusivity of analytes in hydrogel.