Search Results (29)

Micro-terrain recognition plays a crucial role in the planning, design, and safe operation of transmission lines. To achieve intelligent and automatic recognition of micro-terrain surrounding transmission lines, this paper proposes an improved semantic segmentation model based on UNet++. This model expands the single encoder into multiple encoders to accommodate the input of multi-source geographic features and introduces a gated fusion module (GFM) to effectively integrate the data from diverse sources. Additionally, the model incorporates a dual attention network (DA-Net) and a deep supervision strategy to enhance performance and robustness. The multi-source dataset used for the experiment includes the Digital Elevation Model (DEM), Elevation Coefficient of Variation (ECV), and profile curvature. The experimental results of the model comparison indicate that the improved model outperforms common semantic segmentation models in terms of multiple evaluation metrics, with pixel accuracy (PA) and intersection over union (IoU) reaching 92.26% and 85.63%, respectively. Notably, the performance in identifying the saddle and alpine watershed types has been enhanced significantly by the improved model. The ablation experiment results confirm that the introduced modules contribute to enhancing the model’s segmentation performance. Compared to the baseline network, the improved model enhances PA and IoU by 1.75% and 2.96%, respectively. Full article

An effective chip formation process is significant for an efficient metal-cutting process. Long continuous chips can lead to scratches on the machined surface, increasing the risk to operator safety and stability of the machining process. The use of chip grooves on cutting inserts allows for control of the chip formation and breaking process during machining. The shape of the rake surface and the design of the chip groove also affect the efficiency of the machining process. The article presents the use of 3D imaging to analyze changes in the selected chip groove shapes depending on the cutting depth a_p = 0.10, 0.25, and 0.50 mm and the angular location of the cutting insert relative to the machined surface of the workpiece (i.e., major cutting-edge angle K = 60° and K = 90°). The analysis methodology was based on the use of 3D image registration and surface shape modeling. In the analysis based on the 3D imaging presented, the novelty was the adaptation of methods typically used to map and model the terrain surface, which have not been used previously in cutting processes. The evaluation of the shape of the chip groove surface was carried out using, e.g., watershed maps and 3D surface maps. The obtained results indicated a significant influence of the cutting depth and major cutting-edge angle on the surface shape, profile, and length of the chip former; chip groove volume; and the theoretical contact area of the formed chip with the cutting insert. It was observed that for small depths of cut, i.e., a_p < 0.25 mm, the chip-curling process may be difficult due to the flattened shape of the rake surface. In addition, the influence of the convexity of the rake surface of the cutting insert on the chip formation process was demonstrated. The results of the experimental research that verified the conclusions are presented. The developed results may be useful in the process of selecting the parameters and conditions of the metal finishing through use of tools with a shaped rake surface. Full article

Landslide disasters pose a significant threat, with their highly destructive nature underscoring the critical importance of timely and accurate recognition for effective early warning systems and emergency response efforts. In recent years, substantial advancements have been made in the realm of landslide recognition (LR) based on remote sensing data, leveraging deep learning techniques. However, the intricate and varied environments in which landslides occur often present challenges in detecting subtle changes, especially when relying solely on optical remote sensing images. InSAR (Interferometric Synthetic Aperture Radar) technology emerges as a valuable tool for LR, providing more detailed ground deformation data and enhancing the theoretical foundation. To harness the slow deformation characteristics of landslides, we developed the FCADenseNet model. This model is designed to learn features and patterns within ground deformation data, with a specific focus on improving LR. A noteworthy aspect of our model is the integration of an attention mechanism, which considers various monitoring factors. This holistic approach enables the comprehensive detection of landslide disasters across entire watersheds, providing valuable information on landslide hazards. Our experimental results demonstrate the effectiveness of the FCADenseNet model, with an F1-score of 0.7611, which is 9.53% higher than that of FC_DenseNet. This study substantiates the feasibility and efficacy of combining InSAR with deep learning methods for LR. The insights gained from this research contribute to the advancement of regional landslide geological hazard monitoring, identification, and prevention strategies. Full article

Hydrology and meteorological data from relatively undisturbed watersheds aid in identifying effects on ecosystem services, tracking hydroclimatic trends, and reducing model uncertainties. Sustainable forest, water, and infrastructure management depends on assessing the impacts of extreme events and land use change on flooding, droughts, and biogeochemical processes. For example, global climate models predict more frequent high-intensity storms and longer dry periods for the southeastern USA. We summarized 17 years (2005–2021) of hydrometeorological data recorded in the 52 km², third-order Turkey Creek watershed at the Santee Experimental Forest (SEF), Southeastern Coastal Plain, USA. This is a non-tidal headwater system of the Charleston Harbor estuary. The study period included a wide range of weather conditions; annual precipitation (P) and potential evapotranspiration (PET) ranged from 994 mm and 1212 mm in 2007 to 2243 mm and 1063 in 2015, respectively. The annual runoff coefficient (ROC) varied from 0.09 in 2007 (with water table (WT) as deep as 2.4 m below surface) to 0.52 in 2015 (with frequently ponded WT conditions), with an average of 0.22. Although the average P (1470 mm) was 11% higher than the historic 1964–1976 average (1320 mm), no significant (α= 0.05) trend was found in the annual P (p = 0.11), ROC (p = 0.17) or runoff (p = 0.27). Runoff occurred on 76.4% of all days in the study period, exceeding 20 mm/day for 1.25% of all days, mostly due to intense storms in the summer and lower ET demand in the winter. No-flow conditions were common during most of the summer growing season. WT recharge occurred during water-surplus conditions, and storm-event base flow contributed 23–47% of the total runoff as estimated using a hydrograph separation method. Storm-event peak discharge in the Turkey Creek was dominated by shallow subsurface runoff and was correlated with 48 h precipitation totals. Estimated precipitation intensity–duration–frequency and flood frequency relationships were found to be larger than those found by NOAA for the 1893–2002 period (for durations ≥ 3 h), and by USGS regional frequencies (for ≥10-year return intervals), respectively, for the same location. We recommend an integrated analysis of these data together with available water quality data to (1) assess the impacts of rising tides on the hydroperiod and biogeochemical processes in riparian forests of the estuary headwaters, (2) validate rainfall–runoff models including watershed scale models to assess land use and climate change on hydrology and water quality, and (3) inform watershed restoration goals, strategies, and infrastructure design in coastal watersheds. Full article

Existing surface inlets behind terraces and water and sediment control basins (WASCoBs) were replaced with alternative tile intakes (ATIs) in agricultural fields of southeast Iowa. These ATIs consisted of a buried column of gravel atop woodchips. Computational, experimental, and field methods were used to design and evaluate the ATIs’ capacity to reduce sediment and nutrient export. Single-storm simulations using the Watershed Erosion Prediction Project (WEPP) provided boundary conditions for permeameter experiments that yielded a hydraulic conductivity for the layered gravel–woodchip configuration of 4.59 cm/s ± 0.36 cm/s. Additionally, a proportional amount of sediment was retained in the permeameter (42%) compared to the amount that settled on the permeameter surface (58%). Event monitoring of field-installed ATIs during three growing seasons measured a sediment trapping efficiency of 86 ± 12% that led to deposition rates of 5.44 ± 3.77 cm/yr, quantified with ²¹⁰Pb profiles. Percent reduction values were 43% for nitrate and 17% for ortho-phosphate. Finally, long-term continuous-storm modeling using the WEPP suggested that these ATIs could withstand at least 75 25-year events before clogging. Modeling using the Agricultural Conservation Planning Framework suggested watershed-scale load reductions of 1.6% for NO₃ and 1.4% for total P for ATIs draining 6.8% of the modeled watershed. Using ATIs in conjunction with WASCOBs and terraces, or as standalone practices, can be a cost-effective means for keeping sediment and nutrients in the landscape. Full article

The sediment transport process in watersheds is an important research component of geomorphology and surface dynamics. Previous work has inferred the spatial distribution of the sediment transport rate (STR) by the flow direction algorithm and measured topographic variation; however, the simple application of the flow direction algorithm contributes to mass non-conservation during a simulation. This study designs an improved flow direction algorithm for a sediment transport process simulation by judging the mass conservation situation in the simulation process. The specific implementation is to evaluate the existence of negative values for the STR; if they exist, the negative values of the STR are reset to stop the propagation of the negative values downstream. Experiments are conducted to improve the classical D8, MFD–se, and MFD–md flow algorithms in this paper, and the experimental results show that the method in this paper can effectively improve the simulation effect of STR. The STR simulations of the three models, D8, MFD–se, and MFD–md, improved by 1.26%, 4.17%, and 4.54%, respectively. Moreover, the MFD–se model is more suitable for the simulation of the STR when comparing the three models. The improved flow algorithm can be used to simulate the STR, sediment content, and pollutant migration in watersheds, providing a new method for the fine-grained characterization of surface processes in watersheds. Full article

Oblique photography technology based on UAV (unmanned aerial vehicle) provides an effective means for the rapid, real-scene 3D reconstruction of geographical objects on a watershed scale. However, existing research cannot achieve the automatic and high-precision reconstruction of water regions due to the sensitivity of water surface patterns to wind and waves, reflections of objects on the shore, etc. To solve this problem, a novel rapid reconstruction scheme for water regions in 3D models of oblique photography is proposed in this paper. It extracts the boundaries of water regions firstly using a designed eight-neighborhood traversal algorithm, and then reconstructs the triangulated irregular network (TIN) of water regions. Afterwards, the corresponding texture images of water regions are intelligently selected and processed using a designed method based on coordinate matching, image stitching and clipping. Finally, the processed texture images are mapped to the obtained TIN, and the real information about water regions can be reconstructed, visualized and integrated into the original real-scene 3D environment. Experimental results have shown that the proposed scheme can rapidly and accurately reconstruct water regions in 3D models of oblique photography. The outcome of this work can refine the current technical system of 3D modeling by UAV oblique photography and expand its application in the construction of twin watershed, twin city, etc. Full article

Excess nutrients and suspended sediment exports from agricultural watersheds are significant sources of global water quality degradation. An improved understanding of surface water and groundwater pollutant loads is needed to advance practices and policies. A study was conducted in an agricultural-forested catchment of the mid-Atlantic region of the United States. Stream water (SW) and shallow groundwater (SGW) samples were collected monthly between January 2020 and December 2021 from eight sub-catchment study sites. Samples were analyzed for nitrate (NO₃-N), nitrite (NO₂-N), total ammonia (NH₃-N), total nitrogen (TN-N), orthophosphate (PO₄³-P), and total phosphate (TP-P) concentrations using spectrophotometric methods. Total suspended solids concentrations (mg/L) were quantified gravimetrically and volumetrically to estimate mean particle diameter (MZ, µm), particle surface area (CS, m²/mL), sample skewness (Ski), and particle size distributions (sand/silt/clay%). Results showed significant (p < 0.05) differences in nutrient concentrations and suspended sediment characteristics between SW and SGW between study sites. Differences were attributed to source water type and sub-watershed location. Principal components analysis indicated seasonal effects on water quality in summer months and connected land use with TSS, TN-N, and TP-P concentrations. Study results emphasize the importance of SGW water quality metrics for non-point source loading predictions to inform management decisions in agro-forested watersheds. Full article

The design storm derived from intensity–duration–frequency (IDF) curves is the main input for hydrologic analysis or hydraulic design for flood control. The regions with higher flood risks due to extreme precipitation are often deficient in precipitation gauges. This study presents a detailed evaluation of IDF curves derived using IMERG Final half-hourly precipitation (V06), fitted with the widely used CDFs: Gumbel and MLE, Gumbel and MM, Pearson 3, and GEV. As benchmarks and following the same method, we also derived IDF curves using areal average gridded precipitation constructed from two dense gauges networks over (1) the WegenerNET Feldbach region in the Alpine forelands of Austria and (2) the gauge network of the Walnut Gulch Experimental Watershed, in a semiarid region of the United States. In both regions, the frequency analysis for return periods between 2 and 100 years was based on half-hourly rainfall and compared at a grid-scale with a spatial resolution of IMERG, 0.1° × 0.1° lat/lon. The impact of order in which the gridded gauge-based precipitation average is performed within an IMERG grid was evaluated by computing two different Annual Maximum Series (AMS). In one, the average was computed before obtaining the AMS (AB-AMS), and in the other, the average was computed after obtaining the AMS for each gauge grid (AA-AMS) within the IMERG grid. The evaluation revealed that IMERG AMS agrees better with AB-AMS than AA-AMS for the two study regions. Lastly, it was found that the use of Gumbel distribution in calculating IMERG IDF curves results in better agreement with the ground truth than the use of the other three distributions studied here. The outcomes should provide valuable knowledge for the application of IMERG precipitation over regions with sparse gauges. Full article

Change detection (CD) is one of the most important topics in remote sensing. In this paper, we propose a novel higher-order clique conditional random field model to unsupervised CD for remote sensing images (termed HOC²RF), by defining a higher-order clique potential. The clique potential, constructed based on a well-designed higher-order clique of image objects, takes the interaction between the neighboring objects in both feature and location spaces into account. HOC²RF consists of five principle steps: (1) Two difference images with complementary change information are produced by change vector analysis and using the spectral correlation mapper, which describe changes from the perspective of the vector magnitude and angle, respectively. (2) The fuzzy partition matrix of each difference image is calculated by fuzzy clustering, and the fused partition matrix is obtained by fusing the calculated partition matrices with evidence theory. (3) An object-level map is created by segmenting the difference images with an adaptive morphological reconstruction based watershed algorithm. (4) The energy function of the proposed HOC²RF, composed of unary, pairwise, and higher-order clique potentials, is computed based on the difference images, the fusion partition matrix, and the object-level map. (5) The energy function is minimized by the graph cut algorithm to achieve the binary CD map. The proposed HOC²RF CD approach combines the complementary change information extracted from the perspectives of vector magnitude and angle, and synthetically exploits the pixel-level and object-level spatial correlation of images. The main contributions of this article include: (1) proposing the idea of using the interaction between neighboring objects in both feature and location spaces to enhance the CD performance; and (2) presenting a method to construct a higher-order clique of objects, developing a higher-order clique potential function, and proposing a novel CD method HOC²RF. In the experiments on three real remote sensing images, the Kappa coefficient/overall accuracy values of the proposed HOC²RF are 0.9655/0.9967, 0.9518/0.9910, and 0.7845/0.9651, respectively, which are superior to some state-of-the-art CD methods. The experimental results confirm the effectiveness of the proposed method. Full article

In recent years, a remarkable effort has been made to recover the connectivity for fish in the rivers of Catalonia, mainly through the construction of new fish ladders, or river connectors. However, evaluating the effectiveness of new fish ladders is not yet a common practice, although knowing how it works is a key aspect of improving the design of new river connectors in other infrastructures. For this reason, the Catalan Water Agency has launched a study to monitor the effectiveness of several recently built river connectors. A total of five fish ladders were selected in the rivers Anoia, Ripoll, Brugent, Llémena and Borró, placed in four different watersheds (Llobregat, Besós, Ter and Fluvià, respectively). These rivers have a similar hydrology (average river discharge inferior to 1 m³/s), and a similar potential fish assemblage (Barbus haasi or B. meridionalis, Squaliuslaietanus, Anguilla anguilla, and in some cases Salaria fluviatilis). Several exotic species are also present in some of these rivers: Gambusia holbrooki, Lepomis gibbosus, Phoxinus sp., Barbatula sp. During 2021, between two and three monitoring campaigns (spring, summer, fall) were carried out. The methodology used consisted first in the installation of permanent traps at the top exit of ladders to obtain direct estimates of pass rate by species, and on comparative fish sampling on each side of the barrier. Additionally, regular monitoring of several hydraulic variables (water velocity, draft, and elevation) was performed at a selection of internal points on each ladder. Finally, the expected mobility per species was also estimated using the package Fishmove (Radinger, 2013), to compare it with experimental estimations and determine the efficiency of ladders. The results demonstrate the effectiveness of the evaluated ladders, at least for some of the species present. Among native species, barbels (B. haasi and B. meridionalis) showed the highest rates of passage. Some exotic species were also able to occasionally use the ladders. The efficiency of the ladders is mostly high but decreases when there are internal points with excessive speeds, or other failures with respect to the optimal design. Full article

Sign language recognition is one of the most challenging applications in machine learning and human-computer interaction. Many researchers have developed classification models for different sign languages such as English, Arabic, Japanese, and Bengali; however, no significant research has been done on the general-shape performance for different datasets. Most research work has achieved satisfactory performance with a small dataset. These models may fail to replicate the same performance for evaluating different and larger datasets. In this context, this paper proposes a novel method for recognizing Bengali sign language (BSL) alphabets to overcome the issue of generalization. The proposed method has been evaluated with three benchmark datasets such as ‘38 BdSL’, ‘KU-BdSL’, and ‘Ishara-Lipi’. Here, three steps are followed to achieve the goal: segmentation, augmentation, and Convolutional neural network (CNN) based classification. Firstly, a concatenated segmentation approach with YCbCr, HSV and watershed algorithm was designed to accurately identify gesture signs. Secondly, seven image augmentation techniques are selected to increase the training data size without changing the semantic meaning. Finally, the CNN-based model called BenSignNet was applied to extract the features and classify purposes. The performance accuracy of the model achieved 94.00%, 99.60%, and 99.60% for the BdSL Alphabet, KU-BdSL, and Ishara-Lipi datasets, respectively. Experimental findings confirmed that our proposed method achieved a higher recognition rate than the conventional ones and accomplished a generalization property in all datasets for the BSL domain. Full article

First flush is a phenomenon in stormwater runoff that has been considered a topic of great interest in the field of nonpoint source pollution. Despite several attempts to define the first flush quantitively, the specified characteristics of the phenomenon vary among sources. To address these uncertainties, a bibliometric and comprehensive review on published articles related to first flush was conducted. A corpus of 403 research articles was obtained from the Scopus database, which was then parsed using the CorText Manager for the bibliometric analysis. The study examined quantitative definitions of first flush from various sources; climate and topographic characteristics of monitoring and experimental sites where the studies on first flush were performed; the sample collection methods applied; the first flush values obtained on the studies and how it influenced the nonpoint source pollution in urban watersheds. A network map, two contingency matrices, and a Sankey diagram were created to visualize the relationship of significant keywords related to first flush, as well as their co-occurrences with journals, countries, and years. It was found that the strength of the first flush effect could vary depending on the geographical location of the site, climatic conditions, and the pollutants being analyzed. Therefore, initial rainfall monitoring, runoff sampling, and water quality testing were seen as critical steps in characterizing the first flush in urban catchments. Furthermore, the characterization of first flush was found to be significant to the selection of best management practices and design of low-impact development (LID) technologies for stormwater runoff management and nonpoint source pollution control. Full article

Suspended sediment is an important constituent of freshwater ecosystems that supports biogeochemical, geomorphological, and ecological processes. Current knowledge of suspended sediment is largely based on surface water studies; however, improved understanding of surface and in situ groundwater suspended sediment processes will improve pollutant loading estimates and watershed remediation strategies. A study was conducted in a representative mixed-use, agro-forested catchment of the Chesapeake Bay Watershed of the northeast, USA, utilizing an experimental watershed study design, including eight nested sub-catchments. Stream water and shallow groundwater grab samples were collected monthly from January 2020 to December 2020 (n = 192). Water samples were analyzed for suspended sediment using gravimetric (mg/L) and laser particle diffraction (µm) analytical methods. Results showed that shallow groundwater contained significantly higher (p < 0.001) total suspended solid concentrations and smaller particle sizes, relative to stream water. Differences were attributed to variability between sites in terms of soil composition, land use/land cover, and surficial geology, and also the shallow groundwater sampling method used. Results hold important implications for pollutant transport estimates and biogeochemical modeling in agro-forested watersheds. Continued work is needed to improve shallow groundwater suspended sediment characterization (i.e., mass and particle sizes) and the utility of this information for strategies that are designed to meet water quality goals. Full article

Best management practices (BMP) are defined in the United States Clean Water Act (CWA) as practices or measures that have been demonstrated to be successful in protecting a given water resource from nonpoint source pollution. Unfortunately, the greatest majority of BMPs remain unvalidated in terms of demonstrations of success. Further, there is not a broadly accepted or standardized process of BMP implementation and monitoring methods. Conceivably, if standardized BMP validations were a possibility, practices would be much more transferrable, comparable, and prescriptive. The purpose of this brief communication is to present a generalized yet integrated and customizable BMP decision-making process to encourage decision makers to more deliberately work towards the establishment of standardized approaches to BMP monitoring and validation in mixed-use and/or municipal watersheds. Decision-making processes and challenges to BMP implementation and monitoring are presented that should be considered to advance the practice(s) of BMP implementation. Acceptance of standard approaches may result in more organized and transferrable BMP implementation policies and increased confidence in the responsible use of taxpayer dollars through broad acceptance of methods that yield predictable and replicable results. Full article