Field Data Sets Research Articles

Development of data anomaly classification for structural health monitoring based on iterative trimmed loss minimization and human-in-the-loop learning

Huge amounts of data can be generated during long-term monitoring performed by structural health monitoring (SHM) and structural integrity management applications. Monitoring data can be corrupted, and the presence of abnormal data can distort information during signal processing, extract incorrect characteristics during system identification, produce false conclusions during damage detection, and ultimately lead to misjudgment of structural conditions during diagnosis and prognosis. Therefore, developing effective techniques to autonomously detect and classify anomalies becomes necessary and significant. Generally, conventional physics-based strategies can be straightforward, but their performance highly depends on prior knowledge of measurement. Recently, data-driven methods leveraging machine learning (ML) have been used to directly handle the task. This study proposes an ML-based classifier and improves it by incorporating the human-in-the-loop (HITL) learning. The classifier is built on a shallow neural network with high performance to address potential online or real-time applications for long-term monitoring. First, a field monitoring dataset is introduced, and various anomalies are defined to investigate the effectiveness. To further enhance the performance of the proposed classifier, the mislabels in the monitoring dataset are examined, and a correction technique is performed. Additionally, HITL ML is developed to overcome the disadvantages of the conventional correction technique. As a result, the proposed procedure can improve both the classifier and the field dataset, and the proposed classifier can now function as a fundamental component in achieving a continuous and autonomous SHM system.

2-D probabilistic inversion of MT data and uncertainty quantification using the Hamiltonian Monte Carlo method

SUMMARY Bayesian methods provide a valuable framework for rigorously quantifying the model uncertainty arising from the inherent non-uniqueness in the magnetotelluric (MT) inversion. However, widely used Markov chain Monte Carlo (MCMC) sampling approaches usually require a significant number of model samples for accurate uncertainty estimates, making their applications computationally challenging for 2-D or 3-D MT problems. In this study, we explore the applicability of the Hamiltonian Monte Carlo (HMC) method for 2-D probabilistic MT inversion. The HMC provides a mechanism for efficient exploration in high-dimensional model space by making use of gradient information of the posterior probability distribution, resulting in a substantial reduction in the number of samples needed for reliable uncertainty quantification compared to the conventional MCMC methods. Numerical examples with synthetic data demonstrate that the HMC method achieves rapid convergence to the posterior probability distribution of model parameters with a limited number of model samples, indicating the computational advantages of the HMC in high-dimensional model space. Finally, we applied the developed approach to the COPROD2 field data set. The statistical models derived from the HMC approach agree well with previous results obtained by 2-D deterministic inversions. Most importantly, the probabilistic inversion provides valuable quantitative model uncertainty information associated with the resistivity structures derived from the observed data, which facilitates model interpretation.

A dataset for fine-grained seed recognition

The research of plant seeds has always been a focus of agricultural and forestry research, and seed identification is an indispensable part of it. With the continuous application of artificial intelligence technology in the field of agriculture, seed identification through computer vision can effectively promote the development of agricultural and forestry wisdom. Data is the foundation of computer vision, but there is a lack of suitable datasets in the agricultural field. In this paper, a seed dataset named LZUPSD is established. A device based on mobile phones and macro lenses was established to acquire images. The dataset contains 4496 images of 88 different seeds. This dataset can not only be used as data for training deep learning models in the computer field, but also provide important data support for agricultural and forestry research. As an important resource in this field, this dataset plays a positive role in modernizing agriculture and forestry.

Deep learning‐based extraction of surface wave dispersion curves from seismic shot gathers

AbstractMulti‐channel analysis of surface waves is a seismic method employed to obtain useful information about shear‐wave velocities in the near surface. A fundamental step in this methodology is the extraction of dispersion curves from dispersion spectra, with the latter usually obtained by applying specific processing algorithms onto the recorded shot gathers. Although the extraction process can be automated to some extent, it usually requires extensive quality control, which can be arduous for large datasets. We present a novel approach that leverages deep learning to identify a direct mapping between seismic shot gathers and their associated dispersion curves (both fundamental and first higher order modes), therefore by‐passing the need to compute dispersion spectra. Given a site of interest, a set of 1D compressional and shear velocities and density models are created using prior knowledge of the local geology; pairs of seismic shot gathers and Rayleigh‐wave phase dispersion curves are then numerically modelled and used to train a simplified residual network. The proposed approach is shown to achieve high‐quality predictions of dispersion curves on a synthetic test dataset and is, ultimately, successfully deployed on a field dataset. Various uncertainty quantification and convolutional neural network visualization techniques are also presented to assess the quality of the inference process and better understand the underlying learning process of the network. The predicted dispersion curves are inverted for both the synthetic and field data; in the latter case, the resulting shear‐wave velocity model is plausible and consistent with prior geological knowledge of the area. Finally, a comparison between the manually picked fundamental modes with the predictions from our model allows for a benchmark of the performance of the proposed workflow.

Fingerprinting the geochemical signals of episodic arc activity in the Sierra Nevada batholith in space and time

Although subduction is a continuous process, arc system behavior is non-steady-state, leading to uncertainty surrounding the composite spatial and temporal evolution of transcrustal arc magma plumbing systems. This study integrates field, geochronologic, and geochemical data sets from the central Sierra Nevada arc section to investigate the extent to which spatial inheritance is recorded in arc geochemical compositions, and how these signals may be modified by dynamic arc behaviors through time, from arc-wide flare-ups, migration, and crustal thickening to regional magma focusing. Geochemical patterns across Mesozoic arc rocks characterize persistent spatial signals of inheritance, whereas geochemical trends during Cretaceous arc activity provide the temporal component of simultaneous dynamic processes. Distinct bulk-rock isotopic signals define each of the three Mesozoic magmatic flare-ups, which, during Cretaceous arc magmatism, is coupled with eastward arc migration. Additionally, Cretaceous magmatic and tectonic thickening doubled the thickness of arc crust, and magmatism was focused toward a central zone, culminating in the formation of the ∼1100 km2 Tuolumne Intrusive Complex. During magma focusing, temporal signals of magma mixing outweighed the previously pervasive signal of spatial inheritance. Distinct dynamic behaviors effectively primed the arc by the Late Cretaceous, generating transcrustal hot zones of increased magma mixing, recycling, long-term storage, and homogenization. Non-steady-state behavior in the Sierra Nevada resulted in mountain building and voluminous continental crust formation by transforming the physical, thermal, and chemical properties of the lithosphere over tens of millions of years.

Reactive Transport Modeling for Exploring the Potential of Water Quality Sensors to Estimate Hydrocarbon Levels in Groundwater

AbstractPetroleum products have contaminated groundwater with harmful organic compounds, such as benzene, toluene, ethylbenzene, and xylenes (BTEX). Collecting and analyzing polluted groundwater samples is expensive and undertaken infrequently. However, quick remedial action in case of unexpected events requires continuous monitoring. In‐situ water quality sensors (pH, EC, DO, ORP) may show correlations with the components of dissolved petroleum hydrocarbon (PHC) such as aromatics and non‐volatile mobile fractions. Correlations are prerequisite to ultimately develop real‐time prediction models. Since suitable field data sets are limited, we simulated the fate of hydrocarbons in groundwater under various realistic conditions using a reactive transport model as novel approach to explore when, where, and why correlations occur. A stationary oil source zone continuously dissolved at the top of a heterogeneous and shallow sandy aquifer over a two‐dimensional cross‐section. Our model considered transient conditions (fluctuating water table) and spatially uniform hydrogeochemical composition. We observed a strong correlation between PHCs and water quality sensors (rolling Spearman's correlation > |0.8|) at varying periods. These correlations are strongly affected by the location of observation wells, the aquifer's hydraulic conductivity, and the availability of calcite and oxide minerals, and other electron acceptors. DO and ORP are significant for the early detection of hydrocarbon contamination, whereas pH and EC are important features for the long‐term monitoring of hydrocarbons. Our findings lay the foundation for the subsequent development of a data analysis model to detect and estimate in real time PHC levels in groundwater using in‐situ water quality sensors.

DFSNet: A 3D Point Cloud Segmentation Network toward Trees Detection in an Orchard Scene.

In order to guide orchard management robots to realize some tasks in orchard production such as autonomic navigation and precision spraying, this research proposed a deep-learning network called dynamic fusion segmentation network (DFSNet). The network contains a local feature aggregation (LFA) layer and a dynamic fusion segmentation architecture. The LFA layer uses the positional encoders for initial transforming embedding, and progressively aggregates local patterns via the multi-stage hierarchy. The fusion segmentation module (Fus-Seg) can format point tags by learning a multi-embedding space, and the generated tags can further mine the point cloud features. At the experimental stage, significant segmentation results of the DFSNet were demonstrated on the dataset of orchard fields, achieving an accuracy rate of 89.43% and an mIoU rate of 74.05%. DFSNet outperforms other semantic segmentation networks, such as PointNet, PointNet++, D-PointNet++, DGCNN, and Point-NN, with improved accuracies over them by 11.73%, 3.76%, 2.36%, and 2.74%, respectively, and improved mIoUs over the these networks by 28.19%, 9.89%, 6.33%, 9.89, and 24.69%, respectively, on the all-scale dataset (simple-scale dataset + complex-scale dataset). The proposed DFSNet can capture more information from orchard scene point clouds and provide more accurate point cloud segmentation results, which are beneficial to the management of orchards.

Research on Wind Speed Prediction Method Based on Feature Fusion

Wind speed occupies a central position in the study of atmospheric circulation and climate change, playing a crucial role in the accuracy and reliability of meteorological forecasting models. The current meteorological observation network, especially in remote and mountainous areas, faces challenges due to insufficient data resulting from low station density. This limitation hampers a comprehensive understanding of wind field dynamics, subsequently affecting the performance of forecasting models. To enhance the performance of meteorological prediction models, this study adopts an innovative approach that combines boxplot difference indexing and feature-level fusion techniques to filter key predictive features and reduce information redundancy. Furthermore, by integrating spatial location information, the contribution of geographic data to wind field prediction is enhanced, improving the quality of the fused data and thereby increasing the accuracy of model predictions. Experimental comparisons demonstrate that the integrated wind field dataset, post feature fusion, achieves better results across various deep learning models.

Generative Adversarial Networks-based solution for improving medical data quality and insufficiency

As big data brings intelligent solutions and innovations to various fields, the goal of this research is to solve the problem of poor-quality and insufficient datasets in the medical field, to help poor areas can access to high quality and rich medical datasets as well. This study focuses on solving the current problem by utilizing variants of generative adversarial network, Super Resolution Generative Adversarial Network (SRGAN) and Deep Convolutional Generative Adversarial Network (DCGAN). In this study, OpenCV is employed to introduce fuzziness to the Brain Tumor MRI Dataset, resulting in a blurred dataset. Subsequently, the research utilizes both the unaltered and blurred datasets to train the SRGAN model, which is then applied to enhance the low-quality dataset through inpainting. Moving forward, the original dataset, low-quality dataset, and the improved dataset are each used independently to train the DCGAN model. In order to compare the difference between the produced image datasets and the real dataset, the FID Score is separately computed. The results of the study found that by training DCGAN with SRGAN repaired medical dataset, the naked eye can observe that the medical image dataset is significantly clearer and there is a reduction in Frchet Inception Distance (FID) Score. Therefore, by using SRGAN and DCGAN the current problem of low quality and small quantity of datasets in the medical field can be solved, which increase the potential possibilities of big data in artificial intelligence filed of medicine.

Atom-profile updating dictionary learning with nucleus sampling attention mechanism sparse coding for audio magnetotelluric denoising

Audio magnetotellurics (AMT), as a commonly used passive geophysical technique, provides outstanding metal ore exploration capabilities based on the resistivity structure of the earth. However, the accuracy of AMT in translating geoelectrical structures decreases when the data collected in mining areas are of poor quality and contain complex anthropogenic noise, leading to distorted apparent resistivity-phase curves and posing significant challenges for mineral exploration. To effectively denoise AMT data, we develop a new denoising method that combines atom-profile updating dictionary learning (APrU) with the nucleus sampling attention mechanism (NSAM) sparse coding. First, we use APrU to accurately learn the characteristics of the noise in the AMT data; then, we apply the updated dictionary to perform sparse coding on the AMT data by NSAM to obtain the noise; finally, we subtract the noise from the original AMT data to obtain the denoised data. Our experimental results suggest that the proposed method can learn an overcomplete dictionary via the to-be-processed AMT data, thereby enabling the sparse representation of the noise within the learned dictionary. We also demonstrate the efficacy of this method with a set of field data collected from the Lu-Zong mining area, and the attained denoised data faithfully restore the geoelectrical structures with heightened accuracy. The findings confirm that the proposed method realizes the unsupervised learning of the AMT data and allows us to achieve precise denoising performance.

Deep-unrolling architecture for image-domain least-squares migration

Deep-image prior (DIP) is a novel approach to solving ill-posed inverse problems whose solution is parameterized with an untrained deep neural network and cascaded with the forward modeling operator. A key component to the success of such a method is represented by the choice of the network architecture, which must act as a natural prior to the inverse problem at hand and provide a strong inductive bias toward the desired solution. Inspired by the close link between neural networks and iterative algorithms in classical optimization, we apply an unrolled version of the gradient descent (GD) algorithm as our DIP network architecture, denoted as the deep-unrolling (DU) architecture. Each layer of the unrolled network is comprised of two parts: the first part corresponds to the GD step of the data-fidelity term, whereas the second part, formed by a six-layer convolutional neural network (CNN), plays the role of a regularizer in the associated objective function. The developed DU architecture is applied to the problem of image-domain least-squares migration (IDLSM) to invert migrated seismic images for their underlying reflectivity and is denoted as DU-IDLSM. As such, the DU architecture parameterizes the reflectivity, and the input of each layer of the unrolled network is the reflectivity at the previous layer. Similar to the classical DIP approach, the parameters of the DU architecture are optimized in an unsupervised fashion by minimizing the data misfit function itself. Through experiments with a part of the Sigsbee2A model and a marine field data set, we test the effectiveness of the DU-IDLSM approach and highlight two key benefits. First, the DU architecture can effectively regularize the inversion process, resulting in reflectivity estimates with fewer artifacts and higher image resolution than those produced by conventional IDLSM approaches. Second, we indicate that by including dropout layers in the CNN architecture, DU-IDLSM can produce a qualitative measure of the uncertainty associated with the least-squares migration process.

Geographic network effects in a circular economy: A field data analysis of reusable packaging services

AbstractProduct–service systems (PSS) have the potential to align businesses’ financial incentives with environmental objectives. Conceptual and qualitative research on non‐ownership consumption suggests that such offerings benefit from dense local networks, which motivate system adoption and use. However, geographic network effects and their magnitude have not been examined with field data capturing revealed behavior. This paper leverages a large field dataset from a system for reusable take‐out food containers to evaluate the effect of increased geographic network density of participating restaurants on (a) the acquisition of new users and (b) the frequency of system use. Based on fixed effects Poisson panel models, this paper finds statistically significant and practically meaningful positive effects of increased geographic network density on acquiring new users. Notably, marginal effects of increased geographic network density on user acquisition diminish as networks get denser. In terms of frequency of use, no significant effects of geographic network density are identified. These results contribute to the literature on non‐ownership consumption by presenting nuanced field evidence of indirect, cross‐side network effects in PSS. Furthermore, findings encourage businesses and policymakers to promote PSS with dense local networks.

Prediction of Bedform Dimensions on Alluvial Bed in Unidirectional Flow

In this study, the bedform dimensions of an alluvial bed in a unidirectional flow were experimentally investigated. A series of flume experiments was conducted; 700 sets of flume and field data were used in developing formulae for predicting the bedform dimensions on alluvial beds in unidirectional flow. Bedform dimensions include the length and height of bedforms generated by the lower and upper flow regimes; the resistance coefficient for the flow in different flow regimes is introduced into the proposed formulae. The momentum boundary-layer thickness was introduced as an independent variable instead of the flow depth. Based on a large amount of flume and field data, the coefficients of each parameter were determined; four typical formulae were used to compare the accuracy of the proposed formulae. The experimental results show that the momentum boundary-layer thickness, hydraulic radius, and resistance coefficient for the flow in different regimes correlate well with the bedform dimensions. The calculation results show that the dimensionless particle size should not be ignored in the calculation of bedform dimensions. The bedform dimensions have an obvious trend of rapid increase with an increase in the ratio of flow depth to sand size (H/d). The bedform dimensions obtained using the van Rijn method and the Engelund and Hansen method did not represent the variation trend of the bedform length in the upper flow regime with an increase in H/d when H/d was greater than 103. The calculations using the proposed formulae are more accurate and reasonable than those in previous studies predicting the bedform height and length on an alluvial bed in a unidirectional flow.

A new method for the estimation of the Rayleigh wave group-velocity spectrum

S-wave velocity is commonly used to understand the characteristics of the subsurface, which can be retrieved by inverting the phase or group velocity in Rayleigh wave surveys. Now, many studies have shown the advantage of analyzing group velocity over phase velocity to obtain the S-wave velocity. However, previous methods often suffer from poor resolution in estimating group velocity. To improve the resolution of the group velocity and reduce uncertainty in extracting dispersion curves, we develop a new method for the estimation of the Rayleigh wave group-velocity spectrum based on the slant stack and an adaptive generalized S-transform (APST) with energy reassignment. This method incorporates the APST and the energy reassignment technique to enhance the time-frequency representation and then calculates the group velocity at each frequency using the slant stack. By conducting experiments with synthetic seismic records, it is evident that the new method has high resolution and accurate multimode group-velocity calculations. Furthermore, when applied to a field data set and a synthetic record with noise, the method shows better results and noise robustness. This confirms the superior performance of the method at generating high-resolution dispersion images of the group velocity compared with previous approaches. The method will become an efficient tool in Rayleigh wave exploration.

δ2H isotopic offsets in xylem water measurements under cryogenic vacuum distillation: Quantifying and correcting wood‐water hydrogen exchange influences

AbstractStable isotopes δ18O and δ2H are used to infer vegetation water sources. In some studies, significant xylem water δ2H offsets from potential source waters have been observed. The offsets appear to be more prevalent with cryogenic vacuum distillation (CVD) of plant water. Hypothesized mechanisms for these offsets include changes during plant water uptake and transport, and methodological problems. We propose that a large portion of the offsets are due to hydrogen isotope exchange between xylem water and non‐crystalline hydroxyl groups of wood cellulose and hemicellulose during CVD. We present a method for estimating the hypothesized isotopic exchange between wood tissues and water, which is the result of Rayleigh and equilibrium fractionation. To estimate the exchange, we use published wood properties for North American tree species and isotope chemical relationships as a function of moisture content, CVD temperature and water extraction efficiency. A simple model of exchange between xylem water and hydroxyl groups captures the range of observations in studies in which CVD and non‐CVD methods were compared. To evaluate the model, we compared observed δ2H offsets (sw‐excess) values from two field datasets (90°C, n = 364, and 170°C, n = 43) to δ2H offsets estimated with our chemical model. We found good agreement between observed and estimated δ2H offsets for samples extracted at 90°C (r2 = 0.69) but not for samples extracted at 170°C (r2 = 0.20). The offset may be eliminated by increasing the extraction temperature to 229°C or by adding a standard sufficient to raise the moisture content to >150%. A correction can also be approximated by applying a theoretical calculation based on the extraction temperature, moisture content and water extraction efficiency.

A Wavelet Extraction Method of Attenuation Media for Direct Acoustic Impedance Inversion in Depth Domain

The seismic image produced by pre-stack depth migration is more accurate and has clearer geological significance than the time image. However, the waveform of the depth-domain seismic image is affected not only by depth-dependent velocity variation but also by media attenuation, resulting in strong spectral variation of depth-domain seismic data. Therefore, depth-domain seismic inversion is still challenging. We propose a wavelet extraction method of attenuation media based on the generalized seismic wavelet, to address this issue. Then, the estimated depth-domain wavelets were applied to the direct acoustic impedance inversion. First, we investigated the effect of attenuation media on depth-domain source wavelets and derived an analytical formula for the depth-domain wavelets of attenuation media. Next, the time-domain generalized seismic wavelet was extended to the depth domain, which was utilized to study the feasibility of using the generalized seismic wavelet to characterize the seismic wavelet of the depth-domain attenuation media. Based on the orthogonal matching pursuit, we propose a method to extract the depth-domain generalized seismic wavelet directly from depth-domain seismic data. Finally, we applied this method to the depth-domain direct acoustic impedance inversion of a 3D field data example. Tests on the synthetic and 3D field datasets show that the proposed method can correctly extract the depth-domain seismic wavelet of attenuation media and attain direct inversion of the depth-domain acoustic impedance with high accuracy. Therefore, our method is effective and has robust potential in reservoir characterization, fluid prediction, and attribute extraction in the depth domain.

Automatic stack velocity picking using a semi‐supervised ensemble learning method

AbstractPicking stack velocity from seismic velocity spectra is a fundamental method in seismic stack velocity analysis. With the increase in the scale of seismic data acquisition, manual picking cannot achieve the required efficiency. Therefore, an automatic picking algorithm is urgently needed now. Despite some supervised deep learning–based picking approaches that have been proposed, they heavily rely on sufficient training samples and lack interpretability. In contrast, utilizing physical knowledge to develop semi‐data‐driven methods has the potential to efficiently solve this problem. Thus, we propose a semi‐supervised ensemble learning method to reduce the reliance on manually labelled data and improve interpretability by incorporating the interval velocity constraint. Semi‐supervised ensemble learning fuses the information of the estimated spectrum, nearby velocity spectra and few‐shot manual picking to recognize the velocity picking. Test results of both the synthetic and field datasets indicate that semi‐supervised ensemble learning achieves more reliable and precise picking than traditional clustering‐based techniques and the currently popular convolutional neural network method.

Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning

Robust quantification of vegetative biomass using satellite imagery using one or more forms of machine learning (ML) has hitherto been hindered by the extent and quality of training data. Here, we showcase how ML predictive models demonstrably improve when additional training data is used. We collated field datasets of pasture biomass obtained via destructive sampling, ‘C-Dax’ reflective measurements and rising plate meters (RPM) from ten livestock farms across four States in Australia. Remotely sensed data from the Sentinel-2 constellation was used to retrieve aboveground biomass using a novel machine learning paradigm hereafter termed “SPECTRA-FOR” (Spectral Pasture Estimation using Combined Techniques of Random-forest Algorithm for Features Optimisation and Retrieval). Using this framework, we show that the low temporal resolution of Sentinel-2 in high latitude regions with persistent cloud cover leads to extensive gaps between cloud-free images, hindering model performance and, thus, contemporaneous ability to forecast real-time pasture biomass. By leveraging the spectral consistency between Sentinel-2 and Planet Lab SuperDove to overcome this limitation, we used ten spectral bands of Sentinel-2, four bands of Sentinel-2 as a proxy for pre-2022 SuperDove (referred to as synthetic SuperDove or SSD), and the actual SuperDove (ASD), given that SuperDove imagery has a higher resolution and more frequent passage compared with Sentinel-2. Using their respective bands as input features to SPECRA-FOR, model performance for the ten bands of Sentinel-2 were R2 = 0.87, root mean squared error (RMSE) of 439 kg DM/ha and mean absolute error (MAE) of 255 kg DM/ha, while that for SSD increased to an R2 of 0.92, RMSE of 346 kg DM/ha and MAE = 208 kg DM/ha. The study revealed the importance of robust data mining, imagery harmonisation and model validation for accurate real-time modelling of pasture biomass with ML.

Real-Time Automated Geosteering Interpretation Combining Log Interpretation and 3D Horizon Tracking

Existing methods for estimating formation boundaries from well-log data only analyze the formation along the wellbore, failing to capture changes in the 3D formation structure around it. This paper presents a method for real-time 3D formation boundary interpretation using readily available well logs and seismic image data. In the proposed workflow, the mean formation boundary is estimated as a curve following the well path. 3D surfaces are then fitted through this boundary curve, aligning with the slopes and features in the seismic image data. The proposed method is tested on both synthetic and field datasets and illustrates the capabilities of accurate boundary estimation near the well path and precise representation of boundary shape changes further away from the well trajectory. With this fully automated geological interpretation workflow, human bias and interpretation uncertainty can be minimized. Subsurface conditions can be continually updated while drilling to optimize drilling decisions and further automate the geosteering process.

Check dam impact on sediment loads: example of the Guerbe River in the Swiss Alps – a catchment scale experiment

Abstract. The construction of check dams is a common practice around the world where the aim is to reduce the damage by flooding events through mountain streams. However, quantifying the effectiveness of such engineering structures has remained very challenging and requires well-selected case studies, since the outcome of such an evaluation depends on site-specific geometric, geologic and climatic conditions. Conventionally, the check dams' effectiveness has been estimated using information about how the bedload sediment flux in the stream changes after the check dams are constructed. A permanent lowering of the bedload flux not only points to a success in reducing the probability of sediment transport occurrence but also implies that the sediment input through the system is likely to decrease. Here, we applied a method for data acquisition and two different equations (Meyer-Peter–Müller and Recking approach) to estimate and compare the sediment transport in a mountain stream in Switzerland under engineered and non-engineered conditions. Whereas the first equation is derived from a classical approach that is based on flume experiment data with a slope of less than 0.02 m m−1, the second equation (Recking) has been derived based on a bedload field dataset comprising active mountain streams under steeper conditions. We selected the Guerbe (Gürbe) River situated in the Swiss Alps as a case study, which has been engineered since the end of the 19th century. This has resulted in more than 110 check dams along a ca. 5 km reach where sediment has continuously been supplied from adjacent hillslopes, primarily by landsliding. We measured the riverbed grain size, topographic gradients and river widths within selected segments along this reach. Additionally, a gauging station downstream of the reach engineered with check dams yielded information to calibrate the hydroclimatic situation for the study reach, thus offering ideal conditions for our catchment-scale experiment. Using the acquired data and the dataset about historical runoff covering the time interval between 2009 and 2021 and considering the current engineered conditions, we estimated a mean annual volume of transported bedload which ranges from 900 to 6000 m3 yr−1. We then envisaged possible channel geometries before the check dams were constructed. We inferred (1) higher energy gradients which we averaged over the length of several check dams and which we considered a proxy for the steeper river slope under natural conditions; (2) channel widths that are smaller than those measured today, thereby anticipating that the channel was more confined in the past; and (3) larger grain size percentiles, which we consider to be similar to the values measured from preserved landslides in the region. Using such potential non-engineered scenarios as constraints, the two equations both point towards a larger sediment flux compared to the engineered state, although the results of these equations differed significantly in magnitude. Whereas the Recking approach returned estimates where the bedload sediment flux is ca. 10 times larger in comparison with the current situation, the use of the Meyer-Peter–Müller equation predicts an increase of ca. 100 times in bedload fluxes for a state without check dams. These results suggest that the check dams in the Guerbe River are highly efficient not only in regulating sediment transport by decreasing the probability of high sediment flux occurrence during torrential conditions but also in stabilizing the channel bed by avoiding incision. The most likely consequence is a stabilization of the terrain around such structures by reducing the activation of landslides.