Explore the vast range of titles available.

The Shiyang River is an important ecological pillar in northwest China, sustaining Minqin oasis and its surrounding society. However, the basin has long been plagued by water scarcity and ecological fragility. Although the river classification is critical for understanding the complexity, diversity, and ecological functions of rivers, and the foundation of river management and watershed ecological restoration, it has not received adequate attention in this region. To obtain a deeper and comprehensive understanding of the Shiyang River, this study utilizes the Rosgen stream classification system to assess the river morphology, geomorphic features, and hydrologic processes. The results showed that seven first-level and fourteen second-level river types can be identified along 53 river sections of the Shiyang River. Further comparison analysis on the hydrologic parameters for each river type demonstrated a strong positive correlation between discharge and all river parameters. As discharge increased, channels with moderate to high width/depth ratios experienced significant lateral adjustments. A consistent channel gradient, coupled with higher discharge, facilitated the transition from single to multiple channels. Braiding tendencies were more pronounced in rivers where riverbeds were wider and shallower with higher stream power. Additionally, water-flow shear stress decreased with the increase in the width/depth ratio. This study offered critical insights into the Shiyang River’s forms and processes and for the river management and ecological restoration practices.

River science and management can be conducted at a range of spatiotemporal scales from reach to basin levels as long as the project goals and questions are matched correctly with the study design’s spatiotemporal scales and dependent variables. These project goals should also incorporate information on the hydrogeomorphically patchy nature of riverine macrosystems which is only partially predictable in type and location from a river’s headwaters to its terminus. This patchiness significantly affects a river’s habitat template, and thus community structure, ecosystem function, and responses to perturbations. Our manuscript is designed for use by senior administrators at government agencies through entry-level river scientists. It analyzes common challenges in project design and recommends solutions based partially on hierarchical analyses that combine geographic information systems and multivariate statistical analysis to enable self-emergence of a stream’s patchy structure. These approaches are useful at all spatial levels and can vary from primary reliance on geospatial techniques at the valley level to a greater dependence on field-based measurements and expert opinion at the reach level. Comparative uses of functional process zones (FPZs = valley-scale hydrogeomorphic patches), ecoregions, hydrologic unit codes, and reaches in project designs are discussed along with other comparative approaches for stream classification and analysis of species distributions (e.g., GAP analysis). Use of hierarchical classification of patch structure for sample stratification, reference site selection, ecosystem services, rehabilitation, and mitigation are briefly explored.

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference images. This is the first time that sequences of images are used directly for the classification of variable objects in astronomy. The second contribution of this work is the image simulation process. We generate synthetic image sequences which take into account the instrumental and observing conditions, obtaining a realistic, unevenly sampled, and variable noise set of movies for each astronomical object. The simulated data set is used to train our RCNN classifier. This approach allows us to generate data sets to train and test our RCNN model for different astronomical surveys and telescopes. Moreover, using a simulated data set is faster and more adaptable to different surveys and classification tasks. We aim to build a simulated data set whose distribution is close enough to the real data set, so that fine tuning could match the distributions. To test the RCNN classifier trained with the synthetic data set, we used real-world data from the High cadence Transient Survey (HiTS), obtaining an average recall of 85%, improved to 94% after performing fine tuning with 10 real samples per class. We compare the results of our RCNN model with those of a light curve random forest classifier. The proposed RCNN with fine tuning has a similar performance on the HiTS data set compared to the light curve random forest classifier, trained on an augmented training set with 10 real samples per class. The RCNN approach presents several advantages in an alert stream classification scenario, such as a reduction of the data pre-processing, faster online evaluation, and easier performance improvement using a few real data samples. The results obtained encourage us to use the proposed method for astronomical alert broker systems that will process alert streams generated by new telescopes such as the Large Synoptic Survey Telescope.

Hidden changes in the data stream are unknown to learning algorithms and are referred to in the literature as drifts of various types. The accuracy of the classifier may degrade due to the occurrence of drift in non-stationary data streams. In such situations, the classifier must detect significant data changes and adjust its predictions. This article aims to present a new method of drift detection based on analyzing changes in feature ranks across adjacent chunks of data. The proposed strategy involves determining the ranking of the most important feature and tracking its fluctuations within the chunks into which the input data stream is divided. Changes in feature rankings between adjacent chunks serve as symptoms of data drift. The Least Absolute Shrinkage and Selection Operator (LASSO) procedure was proposed as an efficient rank pointer. We compared well-known and popular drift detection algorithms, such as the Drift Detection Method (DDM), Early Drift Detection Method (EDDM), ADaptive WINdowing (ADWIN), and Principal Component Analysis Feature Drift Detection (PCA-FDD), with our approach in comparative studies. The tests were conducted on different artificial data streams (sudden, gradual, recurring, and incremental) as well as real data. Comparative studies were performed on both two-class and multi-class datasets. The experiments confirm that the proposed feature drift detection strategy produces valuable results.

We present a spatially hierarchical, hydrogeomorphological stream classification, based on data collected in Ireland and reflecting our hypothesis that local (site scale) stream physical habitat characteristics are related to the physical properties of the extended reach within which a site is located, and, in turn, to the physical character of the catchment. Using a top-down approach, data on catchment, reach and site-scale stream physical properties were collected for 42 Irish headwater streams. The summary catchment properties (rock type, topography, soil type and hydrology) were extracted from secondary sources. Reach-scale physical controls on stream hydrogeomorphology (planform, gradient, degree of confinement, bed material) were assembled mainly from secondary sources. Site-scale information on the stream physical habitat mosaic was collected by field survey. Data analysis identified six new ‘River Types’ for steep mountain streams that extend a pre-existing classification system developed for English streams and rivers. Five of the new types with sufficient replication were associated with ‘indicator’ habitats and characteristic habitat assemblages. The classification method is simple to apply and so it is suitable for operational use. We believe that it is applicable beyond Ireland and England to other areas of northern and western Europe with similar climate−landscape conditions.

Environmental streamflow management can improve the ecological health of streams by returning modified flows to more natural conditions. The Ecological Limits of Hydrologic Alteration (ELOHA) framework for developing regional environmental flow criteria has been implemented to reverse hydromodification across the heterogenous region of coastal southern California (So. CA) by focusing on two elements of the flow regime: streamflow permanence and flashiness. Within ELOHA, classification groups streams by hydrologic and geomorphic similarity to stratify flow–ecology relationships. Analogous grouping techniques are used by hydrologic modelers to facilitate streamflow prediction in ungaged basins (PUB) through regionalization. Most watersheds, including those needed for stream classification and environmental flow development, are ungaged. Furthermore, So. CA is a highly heterogeneous region spanning gradients of urbanization and flow permanence, which presents a challenge for regionalizing ungaged basins. In this study, we develop a novel classification technique for PUB modeling that uses an inductive approach to group perennial, intermittent, and ephemeral regional streams by modeled hydrologic similarity followed by deductively determining class membership with hydrologic model errors and watershed metrics. As a new type of classification, this hydrologic-model-based classification (HMC) prioritizes modeling accuracy, which in turn provides a means to improve model predictions in ungaged basins while complementing traditional classifications and improving environmental flow management. HMC is developed by calibrating a regional catalog of process-based rainfall–runoff models, quantifying the hydrologic reciprocity of calibrated parameters that would be unknown in ungaged basins and grouping sites according to hydrologic and physical similarity. HMC was applied to 25 USGS streamflow gages in the “South Coast” region of California and was compared to other hybrid PUB approaches combining inductive and deductive classification. Using an average cluster error metric, results show that HMC provided the most hydrologically similar groups according to calibrated parameter reciprocity. Hydrologic-model-based classification is relatively complex and time-consuming to implement, but it shows potential for simplifying ungaged basin management. This study demonstrates the benefits of thorough stream classification using multiple approaches and suggests that hydrologic-model-based classification has advantages for PUB and building the hydrologic foundation for environmental flow management.

Data collected over time often exhibit changes in distribution, or concept drift, caused by changes in factors relevant to the classification task, e.g. weather conditions. Incorporating all relevant factors into the model may be able to capture these changes, however, this is usually not practical. Data stream based methods, which instead explicitly detect concept drift, have been shown to retain performance under unknown changing conditions. These methods adapt to concept drift by training a model to classify each distinct data distribution. However, we hypothesize that existing methods do not robustly handle real-world tasks, leading to adaptation errors where context is misidentified. Adaptation errors may cause a system to use a model which does not fit the current data, reducing performance. We propose a novel repair algorithm to identify and correct errors in concept drift adaptation. Evaluation on synthetic data shows that our proposed AiRStream system has higher performance than baseline methods, while is also better at capturing the dynamics of the stream. Evaluation on an air quality inference task shows AiRStream provides increased real-world performance compared to eight baseline methods. A case study shows that AiRStream is able to build a robust model of environmental conditions over this task, allowing the adaptions made to concept drift to be analysed and related to changes in weather. We discovered a strong predictive link between the adaptions made by AiRStream and changes in meteorological conditions.

The future reliance on water supply and flood control reservoirs across the globe will continue to expand, especially under a variable climate. As the inventory of new potential dam sites is shrinking, construction of additional reservoirs is less likely compared to simultaneous flow and sediment management in existing reservoirs. One aspect of this sediment management is related to the control of upstream sediment sources. However, key research questions remain regarding upstream sediment loading rates. Highlighted in this article are research needs relative to measuring and predicting sediment transport rates and loading due to streambank and gully erosion within a watershed. For example, additional instream sediment transport and reservoir sedimentation rate measurements are needed across a range of watershed conditions, reservoir sizes, and geographical locations. More research is needed to understand the intricate linkage between upland practices and instream response. A need still exists to clarify the benefit of restoration or stabilization of a small reach within a channel system or maturing gully on total watershed sediment load. We need to better understand the intricate interactions between hydrological and erosion processes to improve prediction, location, and timing of streambank erosion and failure and gully formation. Also, improved process-based measurement and prediction techniques are needed that balance data requirements regarding cohesive soil erodibility and stability as compared to simpler topographic indices for gullies or stream classification systems. Such techniques will allow the research community to address the benefit of various conservation and/or stabilization practices at targeted locations within watersheds.

Many challenging real world problems involve multi-label data streams. Efficient methods exist for multi-label classification in non-streaming scenarios. However, learning in evolving streaming scenarios is more challenging, as classifiers must be able to deal with huge numbers of examples and to adapt to change using limited time and memory while being ready to predict at any point. This paper proposes a new experimental framework for learning and evaluating on multi-label data streams, and uses it to study the performance of various methods. From this study, we develop a multi-label Hoeffding tree with multi-label classifiers at the leaves. We show empirically that this method is well suited to this challenging task. Using our new framework, which allows us to generate realistic multi-label data streams with concept drift (as well as real data), we compare with a selection of baseline methods, as well as new learning methods from the literature, and show that our Hoeffding tree method achieves fast and more accurate performance.

Federated learning is an emerging collaborative learning paradigm of Machine learning involving distributed and heterogeneous clients. Enormous collections of continuously arriving heterogeneous data residing on distributed clients require federated adaptation of efficient mining algorithms to enable fair and high-quality predictions with privacy guarantees and minimal response delay. In this context, we propose a federated adaptation that mitigates discrimination embedded in the streaming data while handling concept drifts (FAC-Fed). We present a novel adaptive data augmentation method that mitigates client-side discrimination embedded in the data during optimization, resulting in an optimized and fair centralized server. Extensive experiments on a set of publicly available streaming and static datasets confirm the effectiveness of the proposed method. To the best of our knowledge, this work is the first attempt towards fairness-aware federated adaptation for stream classification, therefore, to prove the superiority of our proposed method over state-of-the-art, we compare the centralized version of our proposed method with three centralized stream classification baseline models (FABBOO, FAHT, CSMOTE). The experimental results show that our method outperforms the current methods in terms of both discrimination mitigation and predictive performance.