Explore the vast range of titles available.

Road discrepancies such as potholes and road cracks are often present in our day-to-day commuting and travel. The cost of damage repairs caused by potholes has always been a concern for owners of any type of vehicle. Thus, an early detection processes can contribute to the swift response of road maintenance services and the prevention of pothole related accidents. In this paper, automatic detection of potholes is performed using the computer vision model library, You Look Only Once version 3, also known as Yolo v3. Light and weather during driving naturally affect our ability to observe road damage. Such adverse conditions also negatively influence the performance of visual object detectors. The aim of this work was to examine the effect adverse conditions have on pothole detection. The basic design of this study is therefore composed of two main parts: (1) dataset creation and data processing, and (2) dataset experiments using Yolo v3. Additionally, Sparse R-CNN was incorporated into our experiments. For this purpose, a dataset consisting of subsets of images recorded under different light and weather was developed. To the best of our knowledge, there exists no detailed analysis of pothole detection performance under adverse conditions. Despite the existence of newer libraries, Yolo v3 is still a competitive architecture that provides good results with lower hardware requirements.

The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high‐resolution (∼37 km2) differentiable models (a type of hybrid model): one with implicit, unit‐hydrograph‐style routing and another with explicit Muskingum‐Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and process‐based equations to provide a structural backbone, which were trained simultaneously (“end‐to‐end”) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily Nash‐Sutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long‐standing modeling challenge. The Muskingum‐Cunge version further improved performance for basins >10,000 km2. Overall, our results show how neural‐network‐based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next‐generation NWM. We also provide a CONUS‐scale hydrologic data set for further evaluation and use. Key Points High‐resolution differentiable models offer substantial and widespread improvements for CONUS streamflow prediction accuracy With a differentiable routing model, we produced a seamlessly discretized streamflow product across approximately 180,000 CONUS river reaches Multiscale training can resolve spatial heterogeneity and improve peak flow, while explicit routing enables large‐river simulations

In the US Corn Belt, a recent doubling in commodity prices has created incentives for landowners to convert grassland to corn and soybean cropping. Here, we use land cover data from the National Agricultural Statistics Service Cropland Data Layer to assess grassland conversion from 2006 to 2011 in the Western Corn Belt (WCB): five states including North Dakota, South Dakota, Nebraska, Minnesota, and Iowa. Our analysis identifies areas with elevated rates of grass-to-corn/soy conversion (1.0–5.4% annually). Across the WCB, we found a net decline in grass-dominated land cover totaling nearly 530,000 ha. With respect to agronomic attributes of lands undergoing grassland conversion, corn/soy production is expanding onto marginal lands characterized by high erosion risk and vulnerability to drought. Grassland conversion is also concentrated in close proximity to wetlands, posing a threat to waterfowl breeding in the Prairie Pothole Region. Longer-term land cover trends from North Dakota and Iowa indicate that recent grassland conversion represents a persistent shift in land use rather than short-term variability in crop rotation patterns. Our results show that the WCB is rapidly moving down a pathway of increased corn and soybean cultivation. As a result, the window of opportunity for realizing the benefits of a biofuel industry based on perennial bioenergy crops, rather than corn ethanol and soy biodiesel, may be closing in the WCB.

Grasslands, and the depressional wetlands that exist throughout them, are endangered ecosystems that face both climate and land-use change pressures. Tens of millions of dollars are invested annually to manage the existing fragments of these ecosystems to serve as critical breeding habitat for migratory birds. The North American Prairie Pothole Region (PPR) contains millions of depressional wetlands that produce between 50% and 80% of the continent’s waterfowl population. Previous modeling efforts suggested that climate change would result in a shift of suitable waterfowl breeding habitat from the central to the southeast portion of the PPR, an area where over half of the depressional wetlands have been drained. The implications of these projections suggest a massive investment in wetland restoration in the southeastern PPR would be needed to sustain waterfowl populations at harvestable levels. We revisited these modeled results indicating how future climate may impact the distribution of waterfowl-breeding habitat using up-to-date climate model projections and a newly developed model for simulating prairie-pothole wetland hydrology. We also presented changes to the number of “May ponds,” a metric used by the U.S. Fish and Wildlife Service to estimate waterfowl breeding populations and establish harvest regulations. Based on the output of 32 climate models and two emission scenarios, we found no evidence that the distribution of May ponds would shift in the future. However, our results projected a 12% decrease to 1% increase in May pond numbers when comparing the most recent climate period (1989–2018) to the end of the 21st century (2070–2099). When combined, our results suggest areas in the PPR that currently support the highest densities of intact wetland basins, and thus support the largest numbers of breeding-duck pairs, will likely also be the places most critical to maintaining continental waterfowl populations in an uncertain future.

In pothole‐dominated catchments, such as those in the Prairie Pothole Region (PPR), potholes strongly influence catchment hydrologic behavior through complex and dynamic fill–spill–connection mechanisms. This complexity—combined with the predominance of ungauged catchments and the lack of high‐resolution pothole inventories—poses challenges for both traditional hydrologic models and purely data‐driven deep learning approaches. To address this, we developed the δHBV‐Pot model within a differentiable modeling framework (δ). This physics‐informed deep learning model integrates the conceptual HBV model with a probabilistic algorithm that emulates the aggregate effects of pothole fill–spill–connection processes. Applied to 98 PPR catchments, δHBV‐Pot achieves stronger predictive accuracy and physical realism than a purely data‐driven Long Short‐Term Memory (LSTM) model and two conceptual hydrologic models. The PPR‐scale regional δHBV‐Pot model successfully simulates hydrologic behavior for the majority of pseudo‐ungauged (test) catchments withheld during model development, effectively regionalizing (a) high‐flow magnitude and interannual variability, (b) intra‐annual flashiness of high‐flow and normal flow conditions, and (c) interannual variability in pothole water storage dynamics. Moreover, the model identifies vulnerable catchments with large high‐flow magnitude and variability—even in the absence of streamflow data—and delineates catchments with varying temporal variability in pothole water storage without requiring detailed pothole inventories. Our findings highlight the value of combining conceptual hydrology with data‐driven deep learning models in pothole‐dominated regions. This integrated approach enables the regionalization of high‐flow and pothole storage characteristics to ungauged catchments, providing critical insights for vulnerability assessment and the design of sustainable water and ecological management strategies in pothole‐dominated landscapes.

Depressional wetlands of the extensive U.S. and Canadian Prairie Pothole Region afford numerous ecosystem processes that maintain healthy watershed functioning. However, these wetlands have been lost at a prodigious rate over past decades due to drainage for development, climate effects, and other causes. Options for management entities to protect the existing wetlands, and their functions, may focus on conserving wetlands based on spatial location vis-à-vis a floodplain or on size limitations (e.g., permitting smaller wetlands to be destroyed but not larger wetlands). Yet the effects of such management practices and the concomitant loss of depressional wetlands on watershed-scale hydrological, biogeochemical, and ecological functions are largely unknown. Using a hydrological model, we analyzed how different loss scenarios by wetland size and proximal location to the stream network affected watershed storage (i.e., inundation patterns and residence times), connectivity (i.e., streamflow contributing areas), and export (i.e., streamflow) in a large watershed in the Prairie Pothole Region of North Dakota, USA. Depressional wetlands store consequential amounts of precipitation and snowmelt. The loss of smaller depressional wetlands (< 3.0 ha) substantially decreased landscape-scale inundation heterogeneity, total inundated area, and hydrological residence times. Larger wetlands act as hydrologic “gatekeepers,” preventing surface runoff from reaching the stream network, and their modeled loss had a greater effect on streamflow due to changes in watershed connectivity and storage characteristics of larger wetlands. The wetland management scenario based on stream proximity (i.e., protecting wetlands 30 m and ~450 m from the stream) alone resulted in considerable landscape heterogeneity loss and decreased inundated area and residence times. With more snowmelt and precipitation available for runoff with wetland losses, contributing area increased across all loss scenarios. We additionally found that depressional wetlands attenuated peak flows; the probability of increased downstream flooding from wetland loss was also consistent across all loss scenarios. It is evident from this study that optimizing wetland management for one end goal (e.g., protection of large depressional wetlands for flood attenuation) over another (e.g., protecting of small depressional wetlands for biodiversity) may come at a cost for overall watershed hydrological, biogeochemical, and ecological resilience, functioning, and integrity.

Recent work has suggested that a tradeoff exists between habitat area and habitat heterogeneity, with a moderate amount of heterogeneity supporting greatest species richness. Support for this unimodal relationship has been mixed and has differed among habitats and taxa. We examined the relationship between habitat heterogeneity and species richness after accounting for habitat area in glacially formed wetlands in the Prairie Pothole Region in the United States at both local and landscape scales. We tested for area–habitat heterogeneity tradeoffs in wetland bird species richness, the richness of groups of similar species, and in species' abundances. We then identified the habitat relationships for individual species and the relative importance of wetland area vs. habitat heterogeneity and other wetland characteristics. We found that habitat area was the primary driver of species richness and abundance. Additional variation in richness and abundance could be explained by habitat heterogeneity or other wetland and landscape characteristics. Overall avian species richness responded unimodally to habitat heterogeneity, suggesting an area–heterogeneity tradeoff. Group richness and abundance metrics showed either unimodal or linear relationships with habitat heterogeneity. Habitat heterogeneity indices at local and landscape scales were important for some, but not all, species and avian groups. Both abundance of individual species and species richness of most avian groups were higher on publicly owned wetlands than on privately owned wetlands, on restored wetlands than natural wetlands, and on permanent wetlands than on wetlands of other classes. However, we found that all wetlands examined, regardless of ownership, restoration status, and wetland class, supported wetland-obligate birds. Thus, protection of all wetland types contributes to species conservation. Our results support conventional wisdom that protection of large wetlands is a priority but also indicate that maintaining habitat heterogeneity will enhance biodiversity and support higher populations of individual species.

Land-use practices can alter shallow groundwater and salinity, further impacting greenhouse gas (GHG) emissions, particularly in the hydrologically dynamic riparian zones of wetlands. Emissions of CO₂, CH₄, and N₂O were estimated in soil cores collected from two prairie pothole region (PPR) sites with three adjacent land-use practices (i. e., annual crop = AC, pasture = PA, and short rotation willow = SRW) and treated with declining water table depths (2 to 26 cm), and salinity (S0 = control, S1 = 6 mS cm⁻¹, and S2 = 12 mS cm⁻¹) in a microcosm experiment. Land-use practices significantly (p < 0.001) affected GHG emissions in soils from both sites in the order of PA > AC = SRW. Compared to the control, emissions of CO₂ and CH₄ were significantly lower under higher salinity treatments (i.e., S1 and S2), while N₂O was significantly higher (p < 0.05). Emissions under declining groundwater table depths were significantly (p < 0.001) variable and specific to each gas, indicating the impacts of shifted soil moisture regime. Overall, the CO₂ and CH₄ emissions increased up to week four and then decreased with declining water table depths, whereas N₂O emission increased up to a maximum at week six. The soils from SRW had considerably lower global warming potential compared to AC and PA. Groundwater salinity in soils from contrasting land-use in the PPR has significant impacts on GHG emissions with potential for crucial climate feedback; however, the magnitude and direction of the impacts depend on hydrology.

Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed.

Wetland managers and policy makers need to make decisions based on a sound scientific understanding of hydrological and ecological functions of wetlands. This article presents an overview of the hydrology of prairie wetlands intended for managers, policy makers, and researchers new to this field (e.g., graduate students), and a quantitative conceptual framework for understanding the hydrological functions of prairie wetlands and their responses to changes in climate and land use. The existence of prairie wetlands in the semi-arid environment of the Prairie-Pothole Region (PPR) depends on the lateral inputs of runoff water from their catchments because mean annual potential evaporation exceeds precipitation in the PPR. Therefore, it is critically important to consider wetlands and catchments as highly integrated hydrological units. The water balance of individual wetlands is strongly influenced by runoff from the catchment and the exchange of groundwater between the central pond and its moist margin. Land-use practices in the catchment have a sensitive effect on runoff and hence the water balance. Surface and subsurface storage and connectivity among individual wetlands controls the diversity of pond permanence within a wetland complex, resulting in a variety of eco-hydrological functionalities necessary for maintaining the integrity of prairie-wetland ecosystems.