General Machine Learning Algorithms Research Articles

Bridging Hydrological Ensemble Simulation and Learning Using Deep Neural Operators

AbstractEnsemble‐based simulation and learning (ESnL) has long been used in hydrology for parameter inference, but computational demands of process‐based ESnL can be quite high. To address this issue, we propose a deep neural operator learning approach. Neural operators are generic machine learning algorithms that can learn functional mappings between infinite‐dimensional spaces, providing a highly flexible tool for scientific machine learning. Our approach is built upon DeepONet, a specific deep neural operator, and is designed to address several common problems in hydrology, namely, model parameter estimation, prediction at ungaged locations, and uncertainty quantification. Here we demonstrate the effectiveness of our DeepONet‐based workflow using an existing large model ensemble created for an eastern U.S. watershed that is instrumented with 10 streamflow gages. Results suggest DeepONet achieves high efficiency in learning an ML surrogate model from the model ensemble, with the modified Kling‐Gupta Efficiency exceeding 0.9 on holdout test sets. Parameter inference, carried out using the trained DeepONet surrogate model and genetic algorithm, also yields robust results. Additionally, we formulate and train a separate DeepONet model for physics‐informed, seq‐to‐seq streamflow forecasting, which further reduces biases in the pre‐trained DeepONet surrogate model. While this study focuses primarily on a single watershed, our approach is general and may be extended to enable learning from model ensembles across multiple basins or models. Thus, this research represents a significant contribution to the application of hybrid machine learning in hydrology.

Ensemble Conformalized Quantile Regression for Probabilistic Time Series Forecasting.

This article presents a novel probabilistic forecasting method called ensemble conformalized quantile regression (EnCQR). EnCQR constructs distribution-free and approximately marginally valid prediction intervals (PIs), which are suitable for nonstationary and heteroscedastic time series data. EnCQR can be applied on top of a generic forecasting model, including deep learning architectures. EnCQR exploits a bootstrap ensemble estimator, which enables the use of conformal predictors for time series by removing the requirement of data exchangeability. The ensemble learners are implemented as generic machine learning algorithms performing quantile regression (QR), which allow the length of the PIs to adapt to local variability in the data. In the experiments, we predict time series characterized by a different amount of heteroscedasticity. The results demonstrate that EnCQR outperforms models based only on QR or conformal prediction (CP), and it provides sharper, more informative, and valid PIs.

Monitoring human behaviour during pandemic — Attacks on healthcare personnel scenario

People exhibit all sorts of irrational behaviour during pandemics; occurrences during the Covid-19 pandemic also agree with this statement. Millions of people died during Covid-19 pandemic and people observed these deaths very closely. Therefore, it is highly probable that these deaths have a mental toll on people. One of the specific irrational incident types is - attacks on healthcare personnel (AoHP). These attacks include both verbal and physical abuse. Naturally, it is the duty of governing agencies to provide protection for these pandemic front-liners. In this work, we have explored the data related to AoHP incidents to fully understand the gravity of the situation. The current scenario is analysed through the utilization of data visualization techniques, thereby offering an insightful perspective. We have noticed that maximum cases are reported in India. In addition, civilians are mainly responsible for most occurrences. All things considered, we put forward an AoHP-type news detection mechanism, which is proposed through real experiments by applying several generic machine learning (ML) algorithms (Naive Bayes, Logistic Regression, Support Vector Machine, Extreme Gradient Boosting, Random Forest) and deep learning (DL) models (Artificial Neural Network, Long Short Term Memory, and Gated Recurrent Unit) over AoHP type news & reports for quick identification of occurrence, which would be helpful to alert the authorities. We have deployed four feature engineering techniques along with generic ML algorithms and pinpointed the most suitable one for our case. We declare Random Forest as the best fit for our purpose of classification, which achieved an F1-score of 97% in our experiments.

An attempt to augment performance of machine learning models in a pilot-scale urban wastewater treatment system

The challenge we face is striking a balance between ensuring the standards for wastewater treatment processes and minimizing energy consumption. As such, accurate predictive models become critical. With machine learning algorithms having the ability to discern relationships between inputs and outputs, broad interest has been shown in their applications in wastewater treatment. A key research focus is on effectively adjusting these generic machine learning algorithms to adapt to frequent fluctuations of water quality, inflow volume, and environmental variations. This study developed a Nonlinear Autoregressive neural network (NARX) model having an adaptive real-time updating module to predict the ammonium concentration in the treated effluent. The model has exhibited high predictive accuracy on the testing data, achieving an R2 value of 0.997. By incorporating an adaptive real-time updating module, the model's capability to predict effluent ammonium concentration on novel data sets has been significantly improved, with the R2 value for these predictions increasing from an initial 0.918 to a more refined range of 0.966 to 0.984. Our findings confirm that integrating real-time updating capabilities with machine learning algorithms substantially improves the stability and predictive performance of the models. These outcomes will prompt a broader integration of artificial intelligence in the domain of environmental engineering, which shall foster the implementation of more accurate and eco-friendly wastewater treatment strategies.

A simple and flexible bootstrap-based framework to quantify epistemic uncertainty of ground motion models by light gradient boosting machine

Ground motion models (GMM) incorporating proper epistemic uncertainty quantification are fundamental for seismic hazard analysis, structural seismic design, and earthquake risk management. However, this critical uncertainty has not been systematically addressed in recently prevalent machine learning (ML)-based GMMs. To rectify this gap, a straightforward and flexible framework based on bootstrapping is proposed for generic ML algorithms. Specifically, a group of datasets are generated through bootstrap resampling, each employed to develop an individual GMM. In the inference phase, the epistemic uncertainty is represented by the prediction samples from this ensemble of models. In case study, the Light Gradient Boosting Machine (LGBM), is applied to establish a GMM on the NGA-West2 database. Overfitting is mitigated by early-stopping, and its implications on uncertainty components and random-effect variability are thoroughly examined. Compared to artificial neural network (ANN) in literature, our work demonstrates a decrease in the standard deviation of inter- and intra-event variability by an average of 0.051 and 0.140, respectively. Moreover, our model adeptly captures the heteroscedasticity of epistemic uncertainty, particularly over different regions and within the range of the metadata with limited data. The significance of epistemic uncertainty is highlighted by its potential to diminish the statistical significance of seismic scaling effects at short-period pseudo spectral acceleration (PSA) for great events and at rock sites.

An evolutionary ensemble learning for diagnosing COVID-19 via cough signals

Objective The spread of the COVID-19 disease has caused great concern around the world and detecting the positive cases is crucial in curbing the pandemic. One of the symptoms of the disease is the dry cough it causes. It has previously been shown that cough signals can be used to identify a variety of diseases including tuberculosis, asthma, etc. In this paper, we proposed an algorithm to diagnose the COVID-19 disease via cough signals.Methods The proposed algorithm was an ensemble scheme that consists of a number of base learners, where each base learner used a different feature extractor method, including statistical approaches and convolutional neural networks (CNNs) for automatic feature extraction. Features were extracted from the raw signal and some transforms performed it, including Fourier, wavelet, Hilbert-Huang, and short-term Fourier transforms. The outputs of these base-learners were aggregated via a weighted voting scheme, with the weights optimised via an evolutionary paradigm. This paper also proposed a memetic algorithm for training the CNNs in the base-learners, which combined the speed of gradient descent (GD) algorithms and global search space coverage of the evolutionary algorithms.Results Experiments were performed on the proposed algorithm and different rival algorithms which included a number of CNN architectures in the literature and generic machine learning algorithms. The results suggested that the proposed algorithm achieves better performance compared to the existing algorithms in diagnosing COVID-19 via cough signals. Conclusion COVID-19 may be diagnosed via cough signals and CNNs may be employed to process these signals and it may be further improved by the optimization of CNN architecture.

The art of transfer learning: An adaptive and robust pipeline

Transfer learning is an essential tool for improving the performance of primary tasks by leveraging information from auxiliary data resources. In this work, we propose Adaptive Robust Transfer Learning (ART), a flexible pipeline of performing transfer learning with generic machine learning algorithms. We establish the nonasymptotic learning theory of ART, providing a provable theoretical guarantee for achieving adaptive transfer while preventing negative transfer. Additionally, we introduce an ART‐integrated‐aggregating machine that produces a single final model when multiple candidate algorithms are considered. We demonstrate the promising performance of ART through extensive empirical studies on regression, classification, and sparse learning. We further present a real‐data analysis for a mortality study.

WITHDRAWN: Visual System Development for Construction Project Management by Using Machine Learning Algorithm

Building management involves multiple data sources related to the whole building, so the visualization system can display relevant data information intuitively and improve the overall management level. Based on this, with the help of machine learning algorithm, this paper designs a visualization system of building management, which effectively improves the efficiency of building management. Firstly, this paper uses graph neural network algorithm to extract and transform the data of buildings. Through the continuous iterative process of summing the hidden vectors of adjacent nodes, more information about the building drawing is obtained, and the loss function of graph neural network is defined. In the early stage of building management, especially in the management of new buildings, there are few data available in the system model. Therefore, this paper adopts deep learning algorithm, which can effectively realize the feature analysis and data domain mapping of the original data by generating confrontation network. Finally, a data set with similar distribution features is generated to make up for the shortage of the original data. In the visualization research of construction project management, the analysis of building energy consumption is one of the main functions. Because of the high complexity of building energy consumption data and the variety of data, the recognition accuracy of general machine learning algorithms is low, visualization system is feasible in the construction project management, and more intuitively shows the building energy consumption and other related information, thereby assisting the building managers to improve the safety of the building system.

Classification and Prediction on Hypertension with Blood Pressure Determinants in a Deep Learning Algorithm.

Few studies classified and predicted hypertension using blood pressure (BP)-related determinants in a deep learning algorithm. The objective of this study is to develop a deep learning algorithm for the classification and prediction of hypertension with BP-related factors based on the Korean Genome and Epidemiology Study-Ansan and Ansung baseline survey. We also investigated whether energy intake adjustment is adequate for deep learning algorithms. We constructed a deep neural network (DNN) in which the number of hidden layers and the number of nodes in each hidden layer are experimentally selected, and we trained the DNN to diagnose hypertension using the dataset while varying the energy intake adjustment method in four ways. For comparison, we trained a decision tree in the same way. Experimental results showed that the DNN performs better than the decision tree in all aspects, such as having higher sensitivity, specificity, F1-score, and accuracy. In addition, we found that unlike general machine learning algorithms, including the decision tree, the DNNs perform best when energy intake is not adjusted. The result indicates that energy intake adjustment is not required when using a deep learning algorithm to classify and predict hypertension with BP-related factors.

Egg Freshness Prediction Model Using Real-Time Cold Chain Storage Condition Based on Transfer Learning.

Maintaining and monitoring the quality of eggs is a major concern during cold chain storage and transportation due to the variation of external environments, such as temperature or humidity. In this study, we proposed a deep learning-based Haugh unit (HU) prediction model which is a universal parameter to determine egg freshness using a non-destructively measured weight loss by transfer learning technique. The temperature and weight loss of eggs from a laboratory and real-time cold chain environment conditions are collected from ten different types of room temperature conditions. The data augmentation technique is applied to increase the number of the collected dataset. The convolutional neural network (CNN) and long short-term memory (LSTM) algorithm are stacked to make one deep learning model with hyperparameter optimization to increase HU value prediction performance. In addition, the general machine learning algorithms are applied to compare HU prediction results with the CNN-LSTM model. The source and target model for stacked CNN-LSTM used temperature and weight loss data, respectively. Predicting HU using only weight loss data, the target transfer learning CNN-LSTM showed RMSE value decreased from 6.62 to 2.02 compared to a random forest regressor, respectively. In addition, the MAE of HU prediction results for the target model decreased when the data augmentation technique was applied from 3.16 to 1.39. It is believed that monitoring egg freshness by predicting HU in a real-time cold chain environment can be implemented in real-life by using non-destructive weight loss parameters along with deep learning.

Secure tumor classification by shallow neural network using homomorphic encryption

BackgroundDisclosure of patients’ genetic information in the process of applying machine learning techniques for tumor classification hinders the privacy of personal information. Homomorphic Encryption (HE), which supports operations between encrypted data, can be used as one of the tools to perform such computation without information leakage, but it brings great challenges for directly applying general machine learning algorithms due to the limitations of operations supported by HE. In particular, non-polynomial activation functions, including softmax functions, are difficult to implement with HE and require a suitable approximation method to minimize the loss of accuracy. In the secure genome analysis competition called iDASH 2020, it is presented as a competition task that a multi-label tumor classification method that predicts the class of samples based on genetic information using HE.MethodsWe develop a secure multi-label tumor classification method using HE to ensure privacy during all the computations of the model inference process. Our solution is based on a 1-layer neural network with the softmax activation function model and uses the approximate HE scheme. We present an approximation method that enables softmax activation in the model using HE and a technique for efficiently encoding data to reduce computational costs. In addition, we propose a HE-friendly data filtering method to reduce the size of large-scale genetic data.ResultsWe aim to analyze the dataset from The Cancer Genome Atlas (TCGA) dataset, which consists of 3,622 samples from 11 types of cancers, genetic features from 25,128 genes. Our preprocessing method reduces the number of genes to 4,096 or less and achieves a microAUC value of 0.9882 (85% accuracy) with a 1-layer shallow neural network. Using our model, we successfully compute the tumor classification inference steps on the encrypted test data in 3.75 minutes. As a result of exceptionally high microAUC values, our solution was awarded co-first place in iDASH 2020 Track 1: “Secure multi-label Tumor classification using Homomorphic Encryption”.ConclusionsOur solution is the first result of implementing a neural network model with softmax activation using HE. Also, HE optimization methods presented in this work enable machine learning implementation using HE or other challenging HE applications.

Solving musculoskeletal biomechanics with machine learning.

Deep learning is a relatively new computational technique for the description of the musculoskeletal dynamics. The experimental relationships of muscle geometry in different postures are the high-dimensional spatial transformations that can be approximated by relatively simple functions, which opens the opportunity for machine learning (ML) applications. In this study, we challenged general ML algorithms with the problem of approximating the posture-dependent moment arm and muscle length relationships of the human arm and hand muscles. We used two types of algorithms, light gradient boosting machine (LGB) and fully connected artificial neural network (ANN) solving the wrapping kinematics of 33 muscles spanning up to six degrees of freedom (DOF) each for the arm and hand model with 18 DOFs. The input-output training and testing datasets, where joint angles were the input and the muscle length and moment arms were the output, were generated by our previous phenomenological model based on the autogenerated polynomial structures. Both models achieved a similar level of errors: ANN model errors were 0.08 ± 0.05% for muscle lengths and 0.53 ± 0.29% for moment arms, and LGB model made similar errors—0.18 ± 0.06% and 0.13 ± 0.07%, respectively. LGB model reached the training goal with only 103 samples, while ANN required 106 samples; however, LGB models were about 39 times slower than ANN models in the evaluation. The sufficient performance of developed models demonstrates the future applicability of ML for musculoskeletal transformations in a variety of applications, such as in advanced powered prosthetics.

Effective Procedure to Predict Rainfall Conditions using Hybrid Machine Learning Strategies

In the present information technology stream supports many natural disaster prediction schemes to save several people from disaster scenarios. In such case, rainfall prediction and analysis is the most important concern to take care as well as the prediction of high rainfall saves many individual's life and their assets. This kind of rainfall prediction schemes provides a facilitation to take respective precautions to avoid huge damages further. The rainfall predictions are categorized into two different variants such as Limited Period Rainfall Prediction and the long period Continuous Rainfall Prediction. Several past analysis and literatures provide accurate predictions for limited period rainfall but the major problem is to identify or predict the continuous long period rainfall. This kind of drawbacks leads many researchers to work on this domain and predict the rainfall status exactly for both limited period as well as long period continues rainfall. In this paper, a new hybrid machine learning strategy is implemented to predict the rainfall status exactly, in which the proposed methodology is named as Intense Neural Network Mining (INNM). This proposed approach of INNM analyze the rainfall prediction scenario based on two different machine learning logics such as Back Propagation Neural Network and the Rapid Miner. The general machine learning algorithms train the machine with respect to the dataset features and predict the result based on testing input. In this approach two different variants of machine learning principles are utilized to classify the resulting nature with better accuracy levels and cross-validations are providing best probabilistic results in outcome. And these two logics are integrated together to produce a new hybrid machine learning strategy to predict the rainfall status exactly and save human life against disasters. In this paper, a novel dataset is utilized from Regional Meteorological Centre Chennai to predict the rainfall summary in clear manner and the summarization of specific dataset is described on further sections. The proposed approach of INNM assures the resulting accuracy levels around 96.5% in prediction with lowest error ratio of 0.04% and the resulting portion of this paper provides a proper proof of this outcome in graphical manner.

Classification of Customer Reviews on E-commerce Platforms Based on Naive Bayesian Algorithm and Support Vector Machine

Customer reviews on e-commerce platforms contain valuable information, while sifting through them manually tends to dismay people because of the huge amount of data. Ideally, the identification classifier would analyze the emotional disposition of product reviews (positive, negative) and aggregate opinions about each of them. Previous literature has demonstrated extensive research conclusions on opinion extraction and semantic classification of product reviews on websites. However, analysis on the universality of machine learning algorithms in identifying the emotional tendency of different Chinese e-commerce reviews is not yet studied. This study uses a method, which is based on general machine learning algorithms, to classify feedbacks. Our classifier extracts Chinese word segmentation and text frequency for feature extraction and scoring, and implements the classification with methods of Naive Bayesian and Support Vector Machines. Experimental results on the Alibaba product review sentiment datasets show that our model based on two machine learning algorithms, though results in different performances, can provide suggestions on the selection of the identification classifier using a trade-off strategy and helps obtain fast and accurate classification on reviews of different categories.

Classification of EEG signals in epilepsy using a novel integrated TSK fuzzy system

The use of machine learning technology to recognize electrical signals of the brain is becoming increasingly popular. Compared with doctors’ manual judgment, machine learning methods are faster. However, only when its recognition accuracy reaches a high level can it be used in practice. Due to the difference in the data distributions of the training dataset and the test dataset and the lack of training samples, the classification accuracies of general machine learning algorithms are not satisfactory. In fact, among the many machine learning methods used to process epilepsy electroencephalogram (EEG) signals, most are black box methods; however, in medicine, methods with explanatory power are needed. In response to these three challenges, this paper proposes a novel technique based on domain adaptation learning, semi-supervised learning and a fuzzy system. In detail, we use domain adaptation learning to reduce deviation from the data distribution, semi-supervised learning to compensate for the lack of training samples, and the Takagi-Sugen-Kang (TSK) fuzzy system model to improve interpretability. Our experimental results show that the performance of the new method is better than those of most advanced epilepsy classification methods.

Efficient Generalized Boundary Detection Using a Sliding Information Distance

We present a general machine learning algorithm for boundary detection within general signals based on an efficient, accurate, and robust approximation of the universal normalized information distance. Our approach uses an adaptive sliding information distance (SLID) combined with a wavelet-based approach for peak identification to locate the boundaries. Special emphasis is placed on developing an adaptive formulation of SLID to handle general signals with multiple unknown and/or drifting section lengths. Although specialized algorithms may outperform SLID when domain knowledge is available, these algorithms are limited to specific applications and do not generalize. SLID excels in these cases. We demonstrate the versatility and efficacy of SLID on a variety of signal types, including synthetically generated sequences of tokens, binary executables for reverse engineering applications, and time series of seismic events.

Data-driven graph construction and graph learning: A review

Abstract A graph is one of important mathematical tools to describe ubiquitous relations. In the classical graph theory and some applications, graphs are generally provided in advance, or can at least be defined clearly. Thus, the main focus is to measure/analyze the graphs for mining informative patterns. However, for many real-world scenarios, the graph is often uncertain due to the fact that data associated with the vertices in the graph are high-dimensional, noisy, differently distributed, and even no clear definition. As a result, one needs to design or learn graphs from data prior to any analysis, which in turn affects the subsequent tasks. Therefore, constructing a high-quality graph has become an increasingly hot research problem, which inspired many graph construction methods being proposed in the past years. Since there has been no systematic summary on this topic, in this paper, we review the main-stream graph construction/learning methods involved in both general machine learning algorithms (including semi-supervised learning, clustering, manifold learning, and spectral kernel learning, etc.) and some specific applications (especially, the modeling and analysis of functional brain connectivity). Additionally, we introduce a matrix-regularized graph learning framework that can benefit to unify some existing graph construction models and develop new graph learning algorithms. Finally, we discuss several related topics and some promising research directions in this field.

Supervised machine learning using encrypted training data

Preservation of privacy in data mining and machine learning has emerged as an absolute prerequisite in many practical scenarios, especially when the processing of sensitive data is outsourced to an external third party. Currently, privacy preservation methods are mainly based on randomization and/or perturbation, secure multiparty computations and cryptographic methods. In this paper, we take advantage of the partial homomorphic property of some cryptosystems to train simple machine learning models with encrypted data. Our basic scenario has three parties: multiple Data Owners, which provide encrypted training examples; the Algorithm Owner (or Application), which processes them to adjust the parameters of its models; and a semi-trusted third party, which provides privacy and secure computation services to the Application in some operations not supported by the homomorphic cryptosystem. In particular, we focus on two issues: the use of multiple-key cryptosystems, and the impact of the quantization of real-valued input data required before encryption. In addition, we develop primitives based on the outsourcing of a reduced set of operations that allows to implement general machine learning algorithms using efficient dedicated hardware. As applications, we consider the training of classifiers using privacy-protected data and the tracking of a moving target using encrypted distance measurements.

Leveraging Saccades to Learn Smooth Pursuit: A Self-Organizing Motion Tracking Model Using Restricted Boltzmann Machines

In this paper, we propose a biologically-plausible model to explain the emergence of motion tracking behaviour in early development using unsupervised learning. The model's training is biased by a concept called retinal constancy, which measures how similar visual contents are between successive frames. This biasing is similar to a reward in reinforcement learning, but is less explicit, as it modulates the model's learning rate instead of being a learning signal itself. The model is a two-layer deep network. The first layer learns to encode visual motion, and the second layer learns to relate that motion to gaze movements, which it perceives and creates through bi-directional nodes. By randomly generating gaze movements to traverse the local visual space, desirable correlations are developed between visual motion and the appropriate gaze to nullify that motion such that maximal retinal constancy is achieved. Biologically, this is similar to using saccades to look around and learning from moments where a target and the saccade move together such that the image stays the same on the retina, and developing smooth pursuit behaviour to perform this action in the future. Restricted Boltzmann machines are used to implement this model because they can form a deep belief network, perform online learning, and act generatively. These properties all have biological equivalents and coincide with the biological plausibility of using saccades as leverage to learn smooth pursuit. This method is unique because it uses general machine learning algorithms, and their inherent generative properties, to learn from real-world data. It also implements a biological theory, uses motion instead of recognition via local searches, without temporal filtering, and learns in a fully unsupervised manner. Its tracking performance after being trained on real-world images with simulated motion is compared to its tracking performance after being trained on natural video. Results show that this model is able to successfully follow targets in natural video, despite partial occlusions, scale changes, and nonlinear motion.

SPATIOTEMPORAL DYNAMICS OF SURFACE WATER EXTENT FROM THREE DECADES OF SEASONALLY CONTINUOUS LANDSAT TIME SERIES AT SUBCONTINENTAL SCALE

Surface water is a critical resource in semi-arid areas. The Murray-Darling Basin (MDB) of Australia, one of the largest semi-arid basins in the world is aiming to set a worldwide example of how to balance multiple interests (i.e. environment, agriculture and urban use), but has suffered significant water shrinkages during the Millennium Drought (1999-2009), followed by extensive flooding. Baseline information and systematic quantification of surface water (SW) extent and flooding dynamics in space and time are needed for managing SW resources across the basin but are currently lacking. <br><br> To synoptically quantify changes in SW extent and flooding dynamics over MDB, we used seasonally continuous Landsat TM and ETM+ data (1986 – 2011) and generic machine learning algorithms. We further mapped flooded forest at a riparian forest site that experienced severe tree dieback due to changes in flooding regime. We used a stratified sampling design to assess the accuracy of the SW product across time. <br><br> Accuracy assessment yielded an overall classification accuracy of 99.94%, with producer’s and user’s accuracy of SW of 85.4% and 97.3%, respectively. Overall accuracy was the same for Landsat 5 and 7 data but user’s and producer’s accuracy of water were higher for Landsat 7 than 5 data and stable over time. <br><br> Our validated results document a rapid loss in SW bodies. The number, size, and total area of SW showed high seasonal variability with highest numbers in winter and lowest numbers in summer. SW extent per season per year showed high interannual and seasonal variability, with low seasonal variability during the Millennium Drought. <br><br> Examples of current uses of the new dataset will be presented and include (1) assessing ecosystem response to flooding with implications for environmental water releases, one of the largest investment in environment in Australia; (2) quantifying drivers of SW dynamics (e.g. climate, human activity); (3) quantifying changes in SW dynamics and connectivity for water dependent organisms; (4) assessing the impact of flooding on riparian vegetation health. The approach developed here is globally applicable, relevant to areas with competing water demands (e.g. Okavango River delta, Mekong River Basin). Future work should incorporate Landsat 8 and Sentinel-2 data for continued quantification of SW dynamics.