Abstract. Long Short-Term Memory Networks (LSTMs) have been applied to daily discharge prediction with remarkable success. Many practical scenarios, however, require predictions at more granular timescales. For instance, accurate prediction of short but extreme flood peaks can make a life-saving difference, yet such peaks may escape the coarse temporal resolution of daily predictions. Naively training an LSTM on hourly data, however, entails very long input sequences that make learning hard and computationally expensive. In this study, we propose two Multi-Timescale LSTM (MTS-LSTM) architectures that jointly predict multiple timescales within one model, as they process long-past inputs at a single temporal resolution and branch out into each individual timescale for more recent input steps. We test these models on 516 basins across the continental United States and benchmark against the US National Water Model. Compared to naive prediction with a distinct LSTM per timescale, the multi-timescale architectures are computationally more efficient with no loss in accuracy. Beyond prediction quality, the multi-timescale LSTM can process different input variables at different timescales, which is especially relevant to operational applications where the lead time of meteorological forcings depends on their temporal resolution.

Dissolved Organic Matter (DOM) represents a mixture of organic molecules that vary due to different source materials and degree of processing. Characterizing how DOM composition evolves along the aquatic continuum can be difficult. Using a size-exclusion chromatography technique (LC-OCD), we assessed the variability in DOM composition from both surface and groundwaters across a number of Canadian ecozones (mean annual temperature spanning -10 to +6 C). A wide range in DOM concentration was found from 0.2 to 120 mg C/L. Proportions of different size-based groupings across ecozones were variable, yet similarities between specific water-body types, regardless of location, suggest commonality in the processes dictating the evolution of DOM composition. A principal-component analysis identified 70% of the variation in LC-OCD derived DOM compositions could be explained by the water-body type. We find that water-body type has a greater influence on DOM composition than differences in climate or surrounding vegetation.

Abstract. This paper presents hydrometeorological, glaciological and geospatial data of the Peyto Glacier Research Basin (PGRB) in the Canadian Rockies. Peyto Glacier has been of interest to glaciological and hydrological researchers since the 1960s, when it was chosen as one of five glacier basins in Canada for the study of mass and water balance during the International Hydrological Decade (IHD, 1965–1974). Intensive studies of the glacier and observations of the glacier mass balance continued after the IHD, when the initial seasonal meteorological stations were discontinued, then restarted as continuous stations in the late 1980s. The corresponding hydrometric observations were discontinued in 1977 and restarted in 2013. Data sets presented in this paper include: high resolution, co-registered DEMs derived from original air photos and LiDAR surveys; hourly off-glacier meteorological data recorded from 1987 to present; precipitation data from nearby Bow Summit; and long-term hydrological and glaciological model forcing datasets derived from bias-corrected reanalysis products. These data are crucial for studying climate change and variability in the basin, and to understanding the hydrological responses of the basin to both glacier and climate change. The comprehensive data set for the PGRB is a valuable and exceptionally long-standing testament to the impacts of climate change on the cryosphere in the high mountain environment. The dataset is publicly available from Federated Research Data Repository at https://doi.org/10.20383/101.0259 (Pradhananga et al., 2020).

Abstract. Thirty-year simulations of seasonal snow cover in 22 physically based models driven with bias-corrected meteorological reanalyses are examined at four sites with long records of snow observations. Annual snow cover durations differ widely between models but interannual variations are strongly correlated because of the common driving data. No significant trends are observed in starting dates for seasonal snow cover, but there are significant trends towards snow cover ending earlier at two of the sites in observations and most of the models. A simplified model with just two parameters controlling solar radiation and sensible heat contributions to snowmelt spans the ranges of snow cover durations and trends. This model predicts that sites where snow persists beyond annual peaks in solar radiation and air temperature will experience rapid decreases in snow cover duration with warming as snow begins to melt earlier and at times of year with more energy available for melting.

Abstract. The interaction of mountain terrain with meteorological processes causes substantial temporal and spatial variability in snow accumulation and ablation. Processes impacted by complex terrain include large-scale orographic enhancement of snowfall, small-scale processes such as gravitational and wind-induced transport of snow, and variability in the radiative balance such as through terrain shadowing. In this study, a multi-scale modeling approach is proposed to simulate the temporal and spatial evolution of high mountain snowpacks using the Canadian Hydrological Model (CHM), a multi-scale, spatially distributed modelling framework. CHM permits a variable spatial resolution by using the efficient terrain representation by unstructured triangular meshes. The model simulates processes such as radiation shadowing and irradiance to slopes, blowing snow redistribution and sublimation, avalanching, forest canopy interception and sublimation and snowpack melt. Short-term, km-scale atmospheric forecasts from Environment and Climate Change Canada's Global Environmental Multiscale Model through its High Resolution Deterministic Prediction System (HRDPS) drive CHM, and were downscaled to the unstructured mesh scale using process-based procedures. In particular, a new wind downscaling strategy combines meso-scale HRDPS outputs and micro-scale pre-computed wind fields to allow for blowing snow calculations. HRDPS-CHM was applied to simulate snow conditions down to 50-m resolution during winter 2017/2018 in a domain around the Kananaskis Valley (~1000 km2) in the Canadian Rockies. Simulations were evaluated using high-resolution airborne Light Detection and Ranging (LiDAR) snow depth data and snow persistence indexes derived from remotely sensed imagery. Results included model falsifications and showed that both blowing snow and gravitational snow redistribution need to be simulated to capture the snowpack variability and the evolution of snow depth and persistence with elevation across the region. Accumulation of wind-blown snow on leeward slopes and associated snow-cover persistence were underestimated in a CHM simulation driven by wind fields that did not capture leeside flow recirculation and associated wind speed decreases. A terrain-based metric helped to identify these lee-side areas and improved the wind field and the associated snow redistribution. An overestimation of snow redistribution from windward to leeward slopes and subsequent avalanching was still found. The results of this study highlight the need for further improvements of snowdrift-permitting models for large-scale applications, in particular the representation of subgrid topographic effects on snow transport.

Abstract. Floods cause large damages, especially if they affect large regions. Assessments of current, local and regional flood hazards and their future changes often involve the use of hydrologic models. However, uncertainties in simulated floods can be considerable and yield unreliable hazard and climate change impact assessments. A reliable hydrologic model ideally reproduces both local flood characteristics and spatial aspects of flooding, which is, however, not guaranteed especially when using standard model calibration metrics. In this paper we investigate how flood timing, magnitude and spatial variability are represented by an ensemble of hydrological models when calibrated on streamflow using the Kling–Gupta efficiency metric, an increasingly common metric of hydrologic model performance. We compare how four well-known models (SAC, HBV, VIC, and mHM) represent (1) flood characteristics and their spatial patterns; and (2) how they translate changes in meteorologic variables that trigger floods into changes in flood magnitudes. Our results show that both the modeling of local and spatial flood characteristics is challenging. They further show that changes in precipitation and temperature are not necessarily well translated to changes in flood flow, which makes local and regional flood hazard assessments even more difficult for future conditions. We conclude that models calibrated on integrated metrics such as the Kling–Gupta efficiency alone have limited reliability in flood hazard assessments, in particular in regional and future assessments, and suggest the development of alternative process-based and spatial evaluation metrics.

Abstract. Land models are increasingly used in terrestrial hydrology due to their process-oriented representation of water and energy fluxes. Land models can be set up at a range of spatial configurations, often ranging from grid sizes of 0.02 to 2 degrees (approximately 2 to 200 km) and applied at sub-daily temporal resolutions for simulation of energy fluxes. A priori specification of the grid size of the land models typically is derived from forcing resolutions, modeling objectives, available geo-spatial data and computational resources. Typically, the choice of model configuration and grid size is based on modeling convenience and is rarely examined for adequate physical representation in the context of modeling. The variability of the inputs and parameters, forcings, soil types, and vegetation covers, are masked or aggregated based on the a priori chosen grid size. In this study, we propose an alternative to directly set up a land model based on the concept of Group Response Unit (GRU). Each GRU is a unique combination of land cover, soil type, and other desired geographical features that has hydrological significance, such as elevation zone, slope, and aspect. Computational units are defined as GRUs that are forced at a specific forcing resolution; therefore, each computational unit has a unique combination of specific geo-spatial data and forcings. We set up the Variable Infiltration Capacity (VIC) model, based on the GRU concept (VIC-GRU). Utilizing this model setup and its advantages we try to answer the following questions: (1) how well a model configuration simulates an output variable, such as streamflow, for range of computational units, (2) how well a model configuration with fewer computational units, coarser forcing resolution and less geo-spatial information, reproduces a model set up with more computational units, finer forcing resolution and more geo-spatial information, and finally (3) how uncertain the model structure and parameters are for the land model. Our results, although case dependent, show that the models may similarly reproduce output with a lower number of computational units in the context of modeling (streamflow for example). Our results also show that a model configuration with a lower number of computational units may reproduce the simulations from a model configuration with more computational units. Similarly, this can assist faster parameter identification and model diagnostic suites, such as sensitivity and uncertainty, on a less computationally expensive model setup. Finally, we encourage the land model community to adopt flexible approaches that will provide a better understanding of accuracy-performance tradeoff in land models.

Abstract. Northwestern Alaska has been highly affected by changing climatic patterns with new temperature and precipitation maxima over the recent years. In particular, the Baldwin and northern Seward peninsulas are characterized by an abundance of thermokarst lakes that are highly dynamic and prone to lake drainage, like many other regions at the southern margins of continuous permafrost. We used Sentinel-1 synthetic aperture radar (SAR) and Planet CubeSat optical remote sensing data to analyze recently observed widespread lake drainage. We then used synoptic weather data, climate model outputs and lake-ice growth simulations to analyze potential drivers and future pathways of lake drainage in this region. Following the warmest and wettest winter on record in 2017/2018, 192 lakes were identified to have completely or partially drained in early summer 2018, which exceeded the average drainage rate by a factor of ~ 10 and doubled the rates of the previous extreme lake drainage years of 2005 and 2006. The combination of abundant rain- and snowfall and extremely warm mean annual air temperatures (MAAT), close to 0 °C, may have led to the destabilization of permafrost around the lake margins. Rapid snow melt and high amounts of excess meltwater further promoted rapid lateral breaching at lake shores and consequently sudden drainage of some of the largest lakes of the study region that likely persisted for millenia. We hypothesize that permafrost destabilization and lake drainage will accelerate and become the dominant drivers of landscape change in this region. Recent MAAT are already within the range of predictions by UAF SNAP ensemble climate predictions in scenario RCP6.0 for 2100. With MAAT in 2019 exceeding 0 °C at the nearby Kotzebue, Alaska climate station for the first time since continuous recording started in 1949, permafrost aggradation in drained lake basins will become less likely after drainage, strongly decreasing the potential for freeze-locking carbon sequestered in lake sediments, signifying a prominent regime shift in ice-rich permafrost lowland regions.

Abstract Background Through their support of local agriculture, relationships, and healthy diets, farmers’ markets can contribute to a sustainable food system. Markets like the Yellowknife Farmers Market (YKFM) are social spaces that support local food, yet the COVID-19 pandemic has forced changes to their current model. This paper explores the potential of online marketplaces to contribute to a resilient, sustainable food system and the barriers to making this transition for the YKFM. Methods In 2019, a collaborative mixed-method evaluation was initiated by the YKFM and university partners in the Northwest Territories (NWT), Canada. The co-created evaluation plan included two patron surveys, a vendor survey and vendor interviews. The evaluation began with an in-person Rapid Market Assessment dot survey and questionnaire of market patrons from two YKFM dates prior to the pandemic. Due to COVID-19, we determined it was not a good time to conduct the vendor survey and interviews. Ongoing engagement with the market facilitated an assessment of the COVID-19 response. Results For the patron surveys, 59 dot survey and 31 questionnaire participants were recruited. The top motivators for attendance were eating dinner, atmosphere, and supporting local businesses, and most patrons attended as couples and spent over half of their time talking to others. The YKFM did not move online, citing concerns about meeting produce demand, incongruence between the online model and market strengths, low dependency on the YKFM by vendors, and potential challenges for patrons using new technology. Conclusions NWT food strategies rely on farmers’ markets to nurture a local food system. Online markets can support local food by facilitating purchases and knowledge-sharing, yet they do not replicate the open-air or social experience. Challenges to the online transition reflect the survey findings and current food context in the NWT. While online adaptation does not fit into the YKFM plan today, online markets may prove useful as a complementary strategy for future emerging stressors to enhance the resiliency of local systems.

Hydrologic-Land Surface Models (H-LSMs) have been progressively developed to a stage where they represent the dominant hydrological processes for a variety of hydrological regimes and include a range of water management practices, and are increasingly used to simulate water storages and fluxes of large basins under changing environmental conditions across the globe. However, efforts for comprehensive evaluation of the utility of H-LSMs in large, regulated watersheds have been limited. In this study, we evaluated the capability of a Canadian H-LSM, called MESH, in the highly regulated Saskatchewan River Basin (SaskRB), Canada, under the constraint of significant precipitation uncertainty. A comprehensive analysis of the MESH model performance was carried out in two steps. First, the reliability of multiple precipitation products was evaluated against climate station observations and based on their performance in simulating streamflow across the basin when forcing the MESH model with a default parameterization. Second, a state-of-the-art multi-criteria calibration approach was applied, using various observational information including streamflow, storage and fluxes for calibration and validation. The first analysis shows that the quality of precipitation products had a direct and immediate impact on simulation performance for the basin headwaters but effects were dampened when going downstream. The subsequent analyses show that the MESH model was able to capture observed responses of multiple fluxes and storage across the basin using a global multi-station calibration method. Despite poorer performance in some basins, the global parameterization generally achieved better model performance than a default model parameterization. Validation using storage anomaly and evapotranspiration generally showed strong correlation with observations, but revealed potential deficiencies in the simulation of storage anomaly over open water areas. Keywords: Precipitation Uncertainty, Hydrologic-Land Surface Models, multi-criteria calibration, storage and fluxes validation, Saskatchewan River Basin, Canada

Wet alpine meadow ecosystems generally act as a significant carbon sink due to their higher rate of photosynthesis than the rate of decomposition. However, it remains unclear whether the low decomposition rate is determined by low temperatures or by nearly-saturated soil conditions. Using five years of measurements from two sites on the Tibetan Plateau with significantly different soil water conditions, we showed that compared to the dry site (which had a deep water table), the much larger carbon sink at the site with a shallow groundwater was mainly caused by the inhibiting effects of the nearly-saturated soil condition on soil respiration rather than by the low temperature. The findings suggested that thawing of frozen soil may partially slow down soil carbon decomposition through increasing soil water. We highlights that a warming-induced shrinking cryosphere may largely affect the carbon dynamics of wet and cold ecosystems through changes in soil hydrology.

Abstract. Probabilistic methods are very useful to estimate the spatial variability in meteorological conditions (e.g., spatial patterns of precipitation and temperature across large domains). In ensemble probabilistic methods, equally plausible ensemble members are used to approximate the probability distribution, hence uncertainty, of a spatially distributed meteorological variable conditioned on the available information. The ensemble can be used to evaluate the impact of the uncertainties in a myriad of applications. This study develops the Ensemble Meteorological Dataset for North America (EMDNA). EMDNA has 100 members with daily precipitation amount, mean daily temperature, and daily temperature range at 0.1° spatial resolution from 1979 to 2018, derived from a fusion of station observations and reanalysis model outputs. The station data used in EMDNA are from a serially complete dataset for North America (SCDNA) that fills gaps in precipitation and temperature measurements using multiple strategies. Outputs from three reanalysis products are regridded, corrected, and merged using the Bayesian Model Averaging. Optimal Interpolation (OI) is used to merge station- and reanalysis-based estimates. EMDNA estimates are generated based on OI estimates and spatiotemporally correlated random fields. Evaluation results show that (1) the merged reanalysis estimates outperform raw reanalysis estimates, particularly in high latitudes and mountainous regions; (2) the OI estimates are more accurate than the reanalysis and station-based regression estimates, with the most notable improvement for precipitation occurring in sparsely gauged regions; and (3) EMDNA estimates exhibit good performance according to the diagrams and metrics used for probabilistic evaluation. We also discuss the limitations of the current framework and highlight that persistent efforts are needed to further develop probabilistic methods and ensemble datasets. Overall, EMDNA is expected to be useful for hydrological and meteorological applications in North America. The whole dataset and a teaser dataset (a small subset of EMDNA for easy download and preview) are available at https://doi.org/10.20383/101.0275 (Tang et al., 2020a).

Abstract. The verification of models in general is a non-trivial task and can, due to epistemological and practical reasons, never be considered as complete. As a consequence, a model may yield correct results for the wrong reasons, i.e. by a different chain of processes than found in observations. While in the atmospheric sciences guidelines and strategies exist to maximize the chances that models are correct for the right reasons, these are mostly applicable to full-physics models, such as numerical weather prediction models. The Intermediate Complexity Atmospheric Research (ICAR) model is an atmospheric model employing linear mountain wave theory to represent the wind field. In this wind field atmospheric quantities, such as temperature and moisture are advected and a microphysics scheme is applied to represent the formation of clouds and precipitation. This study conducts an in-depth process-based evaluation of ICAR, employing idealized simulations to increase the understanding of the model and develop recommendations to maximize the probability that its results are correct for the right reasons. To contrast the obtained results from the linear-theory-based ICAR model to a full-physics model, idealized simulations with the Weather Research and Forecasting (WRF) model are conducted. The impact of the developed recommendations is then demonstrated with a case study for the South Island of New Zealand. The results of this investigation suggest three modifications to improve different aspects of ICAR simulations. The representation of the wind field within the domain improves when the dry and the moist Brunt-Väisälä frequencies are calculated in accordance to linear mountain wave theory from the unperturbed base state rather than from the time-dependent perturbed atmosphere. Imposing boundary conditions at the upper boundary different to the standard zero gradient boundary condition is shown to reduce errors in the potential temperature and water vapor fields. Furthermore, the results show that there is a lowest possible model top elevation that should not be undercut to avoid influences of the model top on cloud and precipitation processes within the domain. The method to determine the lowest model top elevation is applied to both the idealized simulations as well as the real terrain case study. Notable differences between the ICAR and WRF simulations are observed across all investigated quantities such as the wind field, water vapor and hydrometeor distributions, and the distribution of precipitation. The case study indicates a large shift in the precipitation maximum for the ICAR simulation employing the developed recommendations in contrast to an unmodified version of ICAR. The cause for the shift is found in influences of the model top on cloud formation and precipitation processes in the ICAR simulations. Furthermore, the results show that when model skill is evaluated from statistical metrics based on comparisons to surface observations only, such analysis may not reflect the skill of the model in capturing atmospheric processes such as gravity waves and cloud formation.

Abstract. The snowpack over the Mediterranean mountains constitutes a key water resource for the downstream populations. However, its dynamics have not been studied in detail yet in many areas, mostly because of the scarcity of snowpack observations. In this work, we present a characterization of the snowpack over the two mountain ranges of Lebanon. To obtain the necessary snowpack information, we have developed a 1 km regional scale snow reanalysis (ICAR_assim) covering the period 2010–2017. ICAR_assim was developed by means of ensemble-based data assimilation of MODIS fractional snow-covered area (fSCA) through the energy and mass balance model the Flexible Snow Model (FSM2), using the Particle Batch Smoother (PBS). The meteorological forcing data was obtained by a regional atmospheric simulation developed through the Intermediate Complexity Atmospheric Research model (ICAR) nested inside a coarser regional simulation developed by the Weather Research and Forecasting model (WRF). The boundary and initial conditions of WRF were provided by the ERA5 atmospheric reanalysis. ICAR_assim showed very good agreement with MODIS gap-filled snow products, with a spatial correlation of R = 0.98 in the snow probability (P(snow)), and a temporal correlation of R = 0.88 in the day of peak snow water equivalent (SWE)Similarly, ICAR_assim has shown a correlation with the seasonal mean SWE of R = 0.75 compared with in-situ observations from Automatic Weather Stations (AWS). The results highlight the high temporal variability of the snowpack in the Lebanon ranges, with differences between Mount Lebanon and Anti-Lebanon that cannot be only explained by its hypsography been Anti-Lebanon in the rain shadow of Mount Lebanon. The maximum fresh water stored in the snowpack is in the middle elevations approximately between 2200 and 2500 m. a.s.l. Thus, the resilience to further warming is low for the snow water resources of Lebanon due to the proximity of the snowpack to the zero isotherm.

Abstract. The Snow Ensemble Uncertainty Project (SEUP) is an effort to establish a baseline characterization of snow water equivalent (SWE) uncertainty across North America with the goal of informing global snow observational needs. An ensemble-based modeling approach, encompassing a suite of current operational models, is used to assess the uncertainty in SWE and total snow storage (SWS) estimation over North America during the 2009&ndashl2017 period. The highest modeled SWE uncertainty is observed in mountainous regions, likely due to the relatively deep snow, forcing uncertainties, and variability between the different models in resolving the snow processes over complex terrain. This highlights a need for high-resolution observations in mountains to capture the high spatial SWE variability. The greatest SWS is found in Tundra regions where even though the spatiotemporal variability in modeled SWE is low, there is considerable uncertainty in the SWS estimates due to the large areal extent over which those estimates are spread. This highlights the need for high accuracy in snow estimations across the Tundra. In mid-latitude boreal forests, large uncertainties in both SWE and SWS indicate that vegetation-snow impacts are a critical area where focused improvements to modeled snow estimation efforts need to be made. Finally, the SEUP results indicate that SWE uncertainty is driving runoff uncertainty and measurements may be beneficial in reducing uncertainty in SWE and runoff, during the melt season at high latitudes (e.g., Tundra and Taiga regions) and in the Western mountain regions, whereas observations at (or near) peak SWE accumulation are more helpful over the mid-latitudes.

Abstract. The European Alps stretch over a range of climate zones, which affect the spatial distribution of snow. Previous analyses of station observations of snow were confined to regional analyses. Here, we present an Alpine wide analysis of snow depth from six Alpine countries: Austria, France, Germany, Italy, Slovenia, and Switzerland; including altogether more than 2000 stations. Using a principal component analysis and k-means clustering, we identified five main modes of variability and five regions, which match the climatic forcing zones: north and high Alpine, northeast, northwest, southeast and southwest. Linear trends of mean monthly snow depth between 1971 to 2019 showed decreases in snow depth for 87 % of the stations. December to February trends were on average −1.1 cm decade−1 (min, max: −10.8, 4.4; elevation range 0–1000 m), −2.5 (−25.1, 4.4; 1000–2000 m) and −0.1 (−23.3, 9.9; 2000–3000 m), with stronger trends in March to May: −0.6 (−10.9, 1.0; 0–1000 m), −4.6 (−28.1, 4.1; 1000–2000 m) and −7.6 (−28.3, 10.5; 2000–3000 m). However, regional trends differed substantially, which challenges the notion of generalizing results from one Alpine region to another or to the whole Alps. This study presents an analysis of station snow depth series with the most comprehensive spatial coverage in the European Alps to date.

<p>Soil heterotrophic respiration has been considered as a key source of CO<sub>2</sub> flux into the atmosphere and thus plays an important role in global warming. Although the relationship between soil heterotrophic respiration and soil water content has been frequently studied both theoretically and experimentally, model development has thus far been empirically based. Empirical models are often limited to the specific condition of their case studies and cannot be used as a general platform for modeling. Moreover, it is difficult to extend the empirical models by theoretically defined affinities to any desired degree of accuracy. As a result, it is of high priority to develop process-based models that are able to describe the mechanisms behind this phenomenon with more deterministic terms.</p><p>Here we present a mechanistic, mathematically-driven model that is based on the common geometry of a pore in porous media. Assuming that the aerobic respiration of bacteria requires oxygen as an electron acceptor and dissolved organic carbon (DOC) as a substrate, the CO<sub>2</sub> fluxes are considered a function of the bioavailable fraction of both DOC and oxygen. In this modeling approach, the availability of oxygen is controlled by its penetration into the aquatic phase through the interface between air and water. DOC on the other hand is only available to a section of the soil that is in contact with water. As the water saturation in the pore changes, it dynamically and kinematically impacts these interfaces through which the mass transfer of nutrients occurs, and therefore the CO<sub>2</sub> fluxes are directly controlled by water content. We showcased the model applicability on several case studies and illustrated the model capability in simulating the observed microbial respiration rates versus the soil water contents. Furthermore, we showed the model potential to accept additional physically-motivated parameters in order to explain respiration rates in frozen soils or at different temperatures.</p>

Abstract. Despite the high historical losses attributed to flood events, Canadian flood mitigation efforts have been hindered by a dearth of current, accessible flood extent/risk models and maps. Such resources often entail large datasets and high computational requirements. This study presents a novel, computationally efficient flood inundation modeling framework (InundatEd) using the height above the nearest drainage-based solution for Manning's equation, implemented in a big-data discrete global grid systems-based architecture with a web-GIS platform. Specifically, this study aimed to develop, present, and validate InundatEd through binary classification comparisons to known flood extents. The framework is divided into multiple swappable modules including GIS pre-processing; regional regression; inundation model; and web-GIS visualization. Extent testing and processing speed results indicate the value of a DGGS-based architecture alongside a simple conceptual inundation model and a dynamic user interface.