Usman T. Khan’s research while affiliated with New York University and other places

In refugee and internally displaced person settlements, hygienic water handling and free residual chlorine (FRC) are crucial for protecting water against recontamination after distribution up to the household point-of-consumption. We conducted a secondary analysis of water quality and water handling data collected in refugee camps in South Sudan, Jordan, and Rwanda using statistical and process-based modeling to explore how water handling practices affect FRC decay and household FRC outcomes. The two practices that consistently produced a significant effect on FRC decay and household FRC were storing water in direct sunlight and transferring water between containers during household storage. Samples stored in direct sunlight had 0.22–0.31 mg/L lower household FRC and had FRC decay rates between 2 and 3.7 times higher than samples stored in the shade, and samples that were transferred between containers had 0.031–0.51 mg/L lower household FRC and decay rates 1.65–3 times higher than non-transferred samples in sites in which the effect was significant, suggesting that humanitarian responders should aim to provide additional water storage containers to prevent water transferring in households and encourage water-users not to store water in direct sunlight. By contrast, the effect of the three recommended hygienic water handling behaviors (clean, covered containers and drawing by tap or pouring) was mixed or inconclusive. These inconclusive results were likely due to imbalanced or unreliable approaches to gathering the data, and we recommend that hygienic water handling practices that mechanistically provide a physical barrier against recontamination should always be promoted in humanitarian settings.

Deep learning models are increasingly being applied to streamflow forecasting problems. Their success is in part attributed to the large and hydrologically diverse datasets on which they are trained. However, common data selection methods fail to explicitly account for hydrological diversity contained within training data. In this research, clustering is used to characterise temporal and spatial diversity, in order to better understand the importance of hydrological diversity within regional training datasets. This study presents a novel, diversity-based resampling approach to creating hydrologically diverse datasets. First, the undersampling procedure is used to undersample temporal data, and is used to show how the amount of temporal data needed to train models can be halved without any loss in performance. Next, it is applied to reduce the number of basins in the training dataset. While basins cannot be omitted from training without some loss in performance, we show how hydrologically dissimilar basins are highly beneficial to model performance. This is shown empirically for Canadian basins; models trained to sets of basins separated by thousands of kilometres outperform models trained to localised clusters. We strongly recommend an approach to training data selection that encourages a broad representation of diverse hydrological processes.

Accurate flood susceptibility mapping (FSM) is critical for mitigating the environmental, social and economic consequences of floods. The influence of model generalizability onto new watersheds, and the impact of arbitrarily selecting a small subset of flooded and nonflooded locations are current major knowledge gaps in FSM research impacting predictive accuracy. As such, this study conducts an assessment of machine learning models – (i) an Artificial Neural Network - Synthetic Minority Oversampling Technique (ANN-SMOTE) hybrid ensemble with (ii) knowledge-based Analytical Hierarchy Process (AHP) and (iii) diversity-based Shannon Entropy approaches. The ANN-SMOTE, AHP and Entropy models were trained and tested on the Don River watershed in Ontario, Canada, with Overall Accuracy (OA) results of 0.549, 0.404 and 0.452, respectively. ANN-SMOTE’s predictive accuracy remained high when it was tested on four independent watersheds from southern Ontario, indicating strong generalization ability. To simulate the commonly used flood point inventory approach, the number of training samples was reduced by a factor of a 1000, which resulted in a 28% decrease in accuracy. The high performance and generalization potential of the ANN-SMOTE model demonstrate its utility and versatility for future FSM studies, and as a support tool in flood risk management decision making.

Waterborne illnesses are a leading public health concern in refugee and internally displaced person (IDP) settlements. Controlling the spread of these illnesses can be particularly challenging as pathogens can be introduced into previously-safe drinking water during the post-distribution period of collection, transport, and household storage. Free residual chlorine (FRC) is often used in these settlements to prevent recontamination of drinking water, and thus, it is critical that at least 0.2 mg/L of FRC is available up to the point-of-consumption. Chlorine decay models can be used to determine the chlorine dose required to maintain this residual; however, post-distribution FRC decay is highly uncertain due to many immeasurable factors that vary substantially from user to user within a site. Traditional deterministic FRC decay models are unable to quantify this uncertainty. Therefore, there is a need for improved modelling that quantifies uncertainty in FRC decay. Ensemble forecasting systems, which consist of collections of models as opposed to a single standalone model, can quantify this uncertainty by generating probabilistic forecasts of FRC. This study presents a novel use of ensemble techniques to generate probabilistic forecasts of FRC decay for the post-distribution period in refugee and IDP settlements. The two alternatives considered for determining the decay parameters for the ensembles were a resampling approach with least-squares regression and a quantile regression-based approach, both using six different FRC decay equations. These approaches were tested using a six-month operational water quality dataset collected from a refugee settlement in Bangladesh in 2019. The quantile regression-based ensembles produced more reliable forecasts, and better capture of observed values, as compared to resampling with least-squares. Of the FRC decay equations considered, the parallel first-order decay equation produced the least quantile error when compared to the other decay equations considered. This demonstrates that ensemble forecasting systems effectively quantify uncertainty when modelling post-distribution FRC decay. These findings can be used to develop improved FRC guidance for humanitarian responders working in refugee and IDP settlements.

Accurate prediction of the trajectories of material drifting on the ocean surface is critical for risk assessment and responses to environmental emergencies. Prediction of these trajectories is subject to uncertainty arising from a number of sources, with a primary source being uncertainty in the modelled ocean surface currents and winds used as input to the trajectory model. This article presents a fuzzy number-based algorithm for propagating uncertainty through a particle tracking scheme in a time- and space-varying velocity field. The performance of the algorithm was tested by applying it to idealized, analytical velocity fields and scoring the results against the analytical solution. Both epistemic and aleatoric uncertainty were considered and combined using a fractional Brownian motion model for temporal autocorrelation of the uncertainty. In the evaluation of the algorithm, sensitivity was quantified with respect to parameters such as timestep size, resolution of the forcing velocity field, spatial and temporal gradients in the forcing, and resolution of the applied uncertainty. Parameter values optimizing uncertainty representation and computational cost were identified. The applied uncertainty was found to evolve in agreement with classical relative dispersion relationships.

A boil water advisory (BWA) informs the public that there is an increased level of risk associated with their water and that they should boil it before consuming. Studies show that small communities in Canada are particularly likely to experience repeat and long-term BWAs. Climate change has led to changes in precipitation and temperature patterns, leading to region-specific impacts such as increased frequency, severity, or variance in floods, forest fires, droughts, freezing rain, and sea water intrusion. Academic and non-academic “grey” literature was reviewed to establish the most likely impacts of climate change on water treatment and infrastructure. Anonymized data from public drinking water systems in Canada was analyzed to determine the most common causes of BWAs between 2005 and 2020. Most BWAs reported were related to breakdowns/malfunctions along the distribution, though inadequate disinfection residual and turbidity or coliforms in the treated water were also common. Furthermore, statistical analysis of the data showed seasonal trends in some of these parameters. The results of this study suggest that increased precipitation, flooding, permafrost degradation, and forest fires are likely to have significant impacts on water safety in Canada. Highlights Climate change effects are expected to worsen many current water challenges. Climate change will disproportionately impact small, rural, and remote water utilities. Water distribution systems are the main source of water safety risk in Canada. Groundwater-supplied systems experience a disproportionate number of BWAs. Seasonal trends in BWA reasons provide opportunities for targeted mitigation.

Remote Sensing is launching a special issue entitled “Artificial Intelligence Applications in Remotely Sensed Hydrologic and Water Systems.” This issue aims to promote state-of-the-art data-driven and machine learning techniques such as deep learning, ensemble learning, and reinforcement learning, using remote sensing in water research spanning hydro-climatology, hydroinformatics, and hydro-meteorology. Applications of interest include, but not limited to, hazard monitoring, forecasting of extreme events, pollution analysis, mapping of renewables, surface water systems, sociotechnical analysis, hydroinformatics, environment and sustainable agriculture applications. Research featuring advances in statistical modeling approaches is also invited. Consideration will be also given to interdisciplinary methodologies in uncertainty analysis, state-estimation, model interpretability, system identification and relational mapping of remotely sensed systems. https://www.mdpi.com/journal/remotesensing/special_issues/AI_water