Nowcasting Model Research Articles

A Real-Time Spatiotemporal Machine Learning Framework for the Prediction of Nearshore Wave Conditions

Abstract The safe and successful operation of offshore infrastructure relies on a detailed awareness of ocean wave conditions. Ongoing growth in offshore wind energy is focused on very large-scale projects, deployed in ever more challenging environments. This inherently increases both cost and complexity and therefore the requirement for efficient operational planning. To support this, we propose a new machine learning framework for the short-term forecasting of ocean wave conditions to support critical decision-making associated with marine operations. Here, an attention-based long short-term memory (LSTM) neural network approach is used to learn the short-term temporal patterns from in situ observations. This is then integrated with an existing, low computational cost spatial nowcasting model to develop a complete framework for spatiotemporal forecasting. The framework addresses the challenge of filling gaps in the in situ observations and undertakes feature selection, with seasonal training datasets embedded. The full spatiotemporal forecasting system is demonstrated using a case study based on independent observation locations near the southwest coast of the United Kingdom. Results are validated against in situ data from two wave buoy locations within the domain and compared to operational physics-based wave forecasts from the Met Office (the United Kingdom’s national weather service). For these two example locations, the spatiotemporal forecast is found to have an accuracy of R2 = 0.9083 and 0.7409 in forecasting 1-h-ahead significant wave height and R2 = 0.8581 and 0.6978 in 12-h-ahead forecasts, respectively. Importantly, this represents respectable levels of accuracy, comparable to traditional physics-based forecast products, but requires only a fraction of the computational resources. Significance Statement Spectral wave models, based on modeling the underlying physics and physical processes, are traditionally used to generate wave forecasts but require significant computational cost. In this study, we propose a machine learning forecasting framework developed using both in situ buoy observations and a surrogate regional numerical wave model. The proposed framework is validated against in situ measurements at two renewable energy sites and found to have very similar 12-h forecasting errors when benchmarked against the Met Office’s physics-based forecasting model but requires far less computational power. The proposed framework is highly flexible and has the potential for offering a low-cost, low computational resource approach for the provision of short-term forecasts and can operate with other types of observations and other machine learning algorithms to improve the availability and accuracy of the prediction.

TSRC: A Deep Learning Model for Precipitation Short-Term Forecasting over China Using Radar Echo Data

Currently, most deep learning (DL)-based models for precipitation forecasting face two conspicuous issues: the smoothing effect in the precipitation field and the degenerate effect of forecasting precipitation intensity. Therefore, this study proposes “time series residual convolution (TSRC)”, a DL-based convolutional neural network for precipitation nowcasting over China with a lead time of 3 h. The core idea of TSRC is it compensates the current local cues with previous local cues during convolution processes, so more contextual information and less uncertain features would remain in deep networks. We use four years’ radar echo reflectivity data from 2017 to 2020 for model training and one year’s data from 2021 for model testing and compare it with two commonly used nowcasting models: optical flow model (OF) and UNet. Results show that TSRC obtains better forecasting performances than OF and UNet with a relatively high probability of detection (POD), low false alarm rate (FAR), small mean absolute error (MAE) and high structural similarity index (SSIM), especially at longer lead times. Meanwhile, the results of two case studies suggest that TSRC still introduces smoothing effects and slightly outperforms UNet at longer lead times. The most considerable result is that our model can forecast high-intensity radar echoes even for typhoon rainfall systems, suggesting that the degenerate effect of forecasting precipitation intensity can be improved by our model. Future works will focus on the combination of multi-source data and the design of the model’s architecture to gain further improvements in precipitation short-term forecasting.

Deep learning-based ensemble modeling of Vibrio parahaemolyticus concentration in marine environment

Vibrio parahaemolyticus(V.p) is a marine pathogenic bacterium that poses a high risk to human health and shellfish industry, yet an effective regional-scale nowcasting model for managing the risk remains lacking. This study presents the first regional-scale model for nowcasting the level of V.p in oysters in the marine environment by developing an ensemble modeling approach. The ensemble modeling approach involves the integration of genetic programming (GP) and deep artificial neural networks (DNN)-based modeling. The new approach was demonstrated by developing three GP-DNN ensemble models for predicting the V.p level in North Carolina, New Hampshire, and the combined region. Specifically, GP was employed to establish nonlinear functions between the V.p level and antecedent conditions of environmental variables. The nonlinear GP functions and current conditions of individual environmental variables were then utilized as inputs into a DNN model, forming a GP-DNN ensemble model. Modeling results indicated that the GP-DNN ensemble models were capable of predicting the V.p level with the correlation coefficient of 0.91, 0.90, and 0.80 for North Carolina, New Hampshire, and the combined region, respectively, demonstrating the impact of distinct environmental conditions in the local areas on accuracy of the combined regional-scale model. Sensitivity analysis results showed that sea surface temperature and sea surface salinity are the two most important environmental predictors for the abundance of V.p in oysters, followed by water level, pH, chlorophyll-a, and turbidity. The findings suggested that the GP-DNN ensemble models could be utilized as effective predictive tools for mitigating the V.p risk.

Combined assimilation of radar and lightning data for the short-term forecast of severe convection system

In this study, a lightning data assimilation (LDA) method adjusting dynamical fields was examined in the rapid cycle with Weather Research and Forecasting (WRF) model and WRF Data Assimilation (WRFDA). This method retrieves pseudo vertical velocity profiles from total lightning observations and promotes wind convergence over lightning regions. This newly developed LDA scheme is compared with radar data assimilation (RDA) that has been routinely applied in severe storm nowcasting models. Depending on whether the radar or lightning data is assimilated, four experiments were designed to evaluate the positive impacts of dynamical adjustment from LDA. Using a typical severe mesoscale convection system occurred in Beijing, we found that the effect of RDA and LDA are different. The assimilation of radar radial velocity mainly improves the forecast in a longer time, while assimilation of pseudo-vertical-velocity from lightning data mainly corrects intensity and location of the forecasted precipitation. When both radar and lightning data are assimilated, the small-scale wind convergence are promoted and contributes to the intensified updrafts. Thermal and water vapor fields are also adjusted indirectly. Consequently, the convective precipitation is significantly improved and the positive impacts from the combined assimilation scheme persisted over a longer period (at least 3 h). It can be concluded that a combined assimilation of convective data from multiple sources such as radar and lightning data enhance prominently the accuracy of short-term convection forecasts.

Know Before You Go: Data-Driven Beach Water Quality Forecasting.

Forecasting environmental hazards is critical in preventing or building resilience to their impacts on human communities and ecosystems. Environmental data science is an emerging field that can be harnessed for forecasting, yet more work is needed to develop methodologies that can leverage increasingly large and complex data sets for decision support. Here, we design a data-driven framework that can, for the first time, forecast bacterial standard exceedances at marine beaches with 3 days lead time. Using historical data sets collected at two California sites, we train nearly 400 forecast models using statistical and machine learning techniques and test forecasts against predictions from both a naive "persistence" model and a baseline nowcast model. Overall, forecast models are found to have similar sensitivities and specificities to the persistence model, but significantly higher areas under the ROC curve (a metric distinguishing a model's ability to effectively parse classes across decision thresholds), suggesting that forecasts can provide enhanced information beyond past observations alone. Forecast model performance at all lead times was similar to that of nowcast models. Together, results suggest that integrating the forecasting framework developed in this study into beach management programs can enable better public notification and aid in proactive pollution and health risk management.

Nowcasting domestic liquidity in the Philippines using machine learning algorithms

This study utilizes a number of algorithms used in machine learning to nowcast domestic liquidity growth in the Philippines. It employs regularization (i.e., Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net (ENET)) and tree-based (i.e., Random Forest, Gradient Boosted Trees) methods in order to support the BSP’s current suite of macroeconomic models used to forecast and analyze liquidity. Hence, this study evaluates the accuracy of time series models (e.g., Autoregressive, Dynamic Factor), regularization, and tree-based methods through an expanding window. The results indicate that Ridge Regression, LASSO, ENET, Random Forest, and Gradient Boosted Trees provide better estimates than the traditional time series models, with month-ahead nowcasts yielding lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Furthermore, regularization and tree-based methods facilitate the identification of macroeconomic indicators that are significant to specify parsimonious nowcasting models.

Enhanced automated meteorological observations at the Canadian Arctic Weather Science (CAWS) supersites

Abstract. The changing Arctic climate is creating increased economic, transportation, and recreational activities requiring reliable and relevant weather information. However, the Canadian Arctic is sparsely observed, and processes governing weather systems in the Arctic are not well understood. There is a recognized lack of meteorological data to characterize the Arctic atmosphere for operational forecasting and to support process studies, satellite calibration/validation, search and rescue operations (which are increasing in the region), high-impact weather (HIW) detection and prediction, and numerical weather prediction (NWP) model verification and evaluation. To address this need, Environment and Climate Change Canada commissioned two supersites, one in Iqaluit (63.74∘ N, 68.51∘ W) in September 2015 and the other in Whitehorse (60.71∘ N, 135.07∘ W) in November 2017 as part of the Canadian Arctic Weather Science (CAWS) project. The primary goals of CAWS are to provide enhanced meteorological observations in the Canadian Arctic for HIW nowcasting (short-range forecast) and NWP model verification, evaluation, and process studies and to provide recommendations on the optimal cost-effective observing system for the Canadian Arctic. Both sites are in provincial/territorial capitals and are economic hubs for the region; they also act as transportation gateways to the north and are in the path of several common Arctic storm tracks. The supersites are located at or next to major airports and existing Meteorological Service of Canada ground-based weather stations that provide standard meteorological surface observations and upper-air radiosonde observations; they are also uniquely situated in close proximity to frequent overpasses by polar-orbiting satellites. The suite of in situ and remote sensing instruments at each site is completely automated (no on-site operator) and operates continuously in all weather conditions, providing near-real-time data to operational weather forecasters, the public, and researchers via obrs.ca. The two sites have similar instruments, including mobile Doppler weather radars, multiple vertically profiling and/or scanning lidars (Doppler, ceilometer, water vapour), optical disdrometers, precipitation gauges in different shielded configurations, present weather sensors, fog monitoring devices, radiation flux sensors, and other meteorological instruments. Details on the two supersites, the suites of instruments deployed, the data collection methods, and example case studies of HIW events are discussed. CAWS data are publicly accessible via the Canadian Government Open Data Portal (https://doi.org/10.18164/ff771396-b22c-4bc3-844d-38fc697049e9, Mariani et al., 2022a, and https://doi.org/10.18164/d92ed3cf-4ba0-4473-beec-357ec45b0e78, Mariani et al., 2022b); this dataset is being used to improve our understanding of synoptic and fine-scale meteorological processes in the Arctic and sub-Arctic, including HIW detection and prediction and NWP verification, assimilation, and processes.

Forecasting changes of the magnetic field in the United Kingdom from L1 Lagrange solar wind measurements

Extreme space weather events can have large impacts on ground-based infrastructure important to technology-based societies. Machine learning techniques based on interplanetary observations have proven successful as a tool for forecasting global geomagnetic indices, however, few studies have examined local ground magnetic field perturbations. Nowcast and forecast models which predict the magnitude of the horizontal geomagnetic field, |BH|, and its time derivative, dBHdt, at ground level would be valuable for assessing the potential space weather hazard. We attempt to predict the variation of the magnetic field at the three United Kingdom observatories (Eskdalemuir, Hartland and Lerwick) driven by L1 solar wind parameters. The horizontal magnetic field component and its time derivative are predicted from solar wind plasma and interplanetary magnetic field observations using Long Short-Term Memory (LSTM) networks and hybrid Convolutional Neural Network-LSTM models. A 5-fold grid search cross-validation is used for tuning the hyperparameters in each model. Forecasts were made with 5, 15 and 30-min lead times. Models were trained and validated with geomagnetic storm-only data from 1997 to 2016; their outputs were evaluated with the 7–9th September 2017 storms. The forecast models are only able to predict the directly driven parts of geomagnetic storms (not the substorms) and LSTM models generally perform best. We find the |BH| 15- and 30-min forecasts at Lerwick and Eskdalemuir have some predictive power. The 5-min |BH| forecast as well as all the dBHdt models for Eskdalemuir and all the Hartland models were found to have little or no predictive power. This suggests that the machine learning models have better forecasting power at higher latitude (closer to the auroral zones), where the ground magnetic variation field is larger and during storm onset, which is directly driven by changes in the solar wind.

Design and evaluation of a community and impact‐based site‐specific early warning system (SS‐EWS): The SS‐EWS framework

AbstractThe recent extreme rainfall events in Spain such as the storm Gloria have highlighted the gaps in emergency communication, particularly the disconnect between the available impact‐based early warning systems (IBEWSs) and the steps communities take during emergencies. This paper presents a community‐centred framework named ‘site‐specific early warning system’ (SS‐EWS) to co‐design and co‐evaluate with communities an IBEWS for vulnerable locations within high‐risk areas. The components of the framework guide communities in identifying and evaluating local impacts; establishing impact and advisory tables; deriving impact‐based rainfall thresholds and warning levels; and configuring the SS‐EWS with radar‐based nowcasting and numerical weather prediction (NWP) models. A first implementation and evaluation of the SS‐EWS have been done for a public school, two ford crossings and the city of Terrassa, Spain. The SS‐EWS shows promising results in triggering location‐based or site‐specific warnings compatible with the reported impacts and proposing actions to reduce the local risk. Furthermore, the combination of NWP and radar‐based nowcasting improved the capacity of the SS‐EWS to monitor the evolution of the precipitation and capture highly intense rainfall. The SS‐EWS can be a straightforward and cost‐efficient complement for regional EWS to increase the preparedness of communities.

The ILO nowcasting model: Using high-frequency data to track the impact of the COVID-19 pandemic on labour markets1

The impact of the COVID-19 pandemic resulted in unprecedented labour market disruption, triggering the most severe global labour market crisis on record. The speed and depth of the crisis rendered labour force survey data unable to provide timely information. The ILO nowcasting model was designed to track the disruption in the world of work caused by the pandemic. This required: 1) filling data gaps, 2) increasing the timeliness of available data, and 3) focusing on an indicator that captured well the pandemic disruption: hours worked. The estimates obtained from the ILO nowcasting model have become the backbone of the empirical strategy behind the ILO Monitor on the World of Work publication series. The latest estimates corroborate that the pandemic induced very large declines in hours worked at an unprecedented speed. Furthermore, the recovery process has stalled, driven by a stagnant recovery in developing economies. The country-level input data and estimates of the ILO nowcasting model allow for complementary analysis, which was published in the ILO Monitor. The topics included the effects of COVID-19 testing and tracing, fiscal stimulus, and vaccination on labour market outcomes.

Ionospheric Kalman Filter Assimilation Based on Covariance Localization Technique

The data assimilation algorithm is a common algorithm in space weather research. Based on the GNSS data from the China Crustal Movement Observation Network (CMONOC) and the International Reference Ionospheric Model (IRI), a fast three-dimensional (3D) electron density nowcasting model for China and its adjacent regions was developed. Unlike the traditional Gaussian background covariance model, the error covariance of the IRI model, based on the IGS grid TEC data, is estimated in this work. Due to the large scale of the high-resolution covariance matrix, it cannot be stored and calculated directly on a personal computer. The covariance localization (CL) technique is introduced to sparse the covariance matrix while removing the pseudo-correlation of the covariance matrix. After localization, the covariance matrix can be converted into a sparse matrix for storage and calculation, which greatly reduces the computer memory requirement of the assimilation model and improves the calculation speed of the model. Based on this algorithm, a series of experiments were carried out in this work. The experimental results show that this algorithm can effectively assimilate the observed GNSS to the background field, make up for the temporal and spatial limitations of the observed data, and improve the accuracy of the ionospheric electron density nowcast. Compared with the digisonde observed foF2 (the critical frequency of the ionospheric F2 layer), the RMSE of the assimilation model is 0.44 MHz lower than that of the IRI model.

Rad-cGAN v1.0: Radar-based precipitation nowcasting model with conditional generative adversarial networks for multiple dam domains

Abstract. Numerical weather prediction models and probabilistic extrapolation methods using radar images have been widely used for precipitation nowcasting. Recently, machine-learning-based precipitation nowcasting models have also been actively developed for relatively short-term precipitation predictions. This study was aimed at developing a radar-based precipitation nowcasting model using an advanced machine-learning technique, conditional generative adversarial network (cGAN), which shows high performance in image generation tasks. The cGAN-based precipitation nowcasting model, named Rad-cGAN, developed in this study was trained with the radar reflectivity data of the Soyang-gang Dam basin in South Korea with a spatial domain of 128 × 128 pixels, spatial resolution of 1 km, and temporal resolution of 10 min. The model performance was evaluated using previously developed machine-learning-based precipitation nowcasting models, namely convolutional long short-term memory (ConvLSTM) and U-Net. In addition, Eulerian persistence model and pySTEPS, a radar-based deterministic nowcasting system, are used as baseline models. We demonstrated that Rad-cGAN outperformed reference models at 10 min lead time prediction for the Soyang-gang Dam basin based on verification metrics: Pearson correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), critical success index (CSI), and fraction skill scores (FSS) at an intensity threshold of 0.1, 1.0, and 5.0 mm h−1. However, unlike low rainfall intensity, the CSI at high rainfall intensity in Rad-cGAN deteriorated rapidly beyond the lead time of 10 min; however, ConvLSTM and baseline models maintained better performances. This observation was consistent with the FSS calculated at high rainfall intensity. These results were qualitatively evaluated using typhoon Soulik as an example, and through this, ConvLSTM maintained relatively higher precipitation than the other models. However, for the prediction of precipitation area, Rad-cGAN showed the best results, and the advantage of the cGAN method to reduce the blurring effect was confirmed through radially averaged power spectral density (PSD). We also demonstrated the successful implementation of the transfer learning technique to efficiently train the model with the data from other dam basins in South Korea, such as the Andong Dam and Chungju Dam basins. We used the pre-trained model, which was completely trained in the Soyang-gang Dam basin. Furthermore, we analyzed the amount of data to effectively develop the model for the new domain through the transfer learning strategies applying the pre-trained model using data for additional dam basins. This study confirmed that Rad-cGAN can be successfully applied to precipitation nowcasting with longer lead times and using the transfer learning approach showed good performance in dam basins other than the originally trained basin.

Pengembangan Sistem Peringatan Dini Cuaca Ekstrem Terintegrasi Berbasis Y-Model Webgis Development Methodology (Y-WDM)

The incidence of hydrometeorological disasters in Indonesia is in the largest percentage for the last 10 years. The development of an integrated extreme weather early warning system is one of the initial processes in a series of hydrometeorological disaster mitigation efforts. Data models, observation and remote sensing become the database in early warning of extreme weather, the officers who carry out early detection of hazards so that they have sufficient waiting time to prepare an effective emergency response plan. In this study, an early warning system was built by implementing the Y-Model WebGIS Development Methodology (YWDM) which is a combination of geographic information systems and web-based application development context. Spatial data processing is carried out using the python programming language, including radar and weather satellite data, surface observation, lightning detection, storm detection and identification, and nowcasting models. Web GIS visualization is built by using JavaScript and php programming language, database management managed using PostgreSQL. The results of the implementation are in the form of a SPACE (Spatial Based Extreme Weather Warning System) framework which Sidarma-Nowcast is a system within the framework. The development of this system shows an increase and the level of improvement in the process of producing and disseminating early warning information.

Sentimental wildfire: a social-physics machine learning model for wildfire nowcasting

The intensity of wildfires and wildfire season length is increasing due to climate change, causing a greater threat to the local population. Much of this population are increasingly adopting social media, and sites like Twitter are increasingly being used as a real-time human-sensor network during natural disasters; detecting, tracking and documenting events. The human-sensor concept is currently largely omitted by wildfire models, representing a potential loss of information. By including Twitter data as a source in our models, we aim to help disaster managers make more informed, socially driven decisions, by detecting and monitoring online social media sentiment over the course of a wildfire event. This paper implements machine learning in a wildfire prediction model, using social media and geophysical data sources with Sentiment Analysis to predict wildfire characteristics with high accuracy. We also use wildfire-specific attributes to predict online social dynamics, as this has been shown to be indicative of localised disaster severity. This may be useful for disaster management teams in identifying areas of immediate danger. We combine geophysical satellite data from the Global Fire Atlas with social data provided by Twitter. We perform data collection and subsequent analysis & visualisation, and compare regional differences in online social sentiment expression. Following this, we compare and contrast different machine learning models for predicting wildfire attributes. We demonstrate social media is a predictor of wildfire activity, and present models which accurately model wildfire attributes. This work develops the concept of the human sensor in the context of wildfires, using users’ Tweets as noisy subjective sentimental accounts of current localised conditions. This work contributes to the development of more socially conscious wildfire models, by incorporating social media data into wildfire prediction and modelling.

Adaptive precipitation nowcasting using deep learning and ensemble modeling

Accurate rainfall nowcasting is necessary for real-time flood management in urban areas. In this paper, some deep neural networks (DNNs) are developed for rainfall nowcasting with lead-time of 5 min. To increase the accuracy of the DNNs, their outputs are fused with the predictions of some numerical weather prediction (NWP) models using three ensemble models (i.e., bagging, random forest, and adaboost). The bias of NWPs is corrected using the quantile mapping technique. The ensemble models are compared with the DNNs and NWP models in terms of the accuracy of predictions. To reduce the run time of the proposed rainfall nowcasting models to be applicable for real-time urban flood management, they are executed using a parallel computing algorithm on the central processing unit (CPU) and graphics processing unit (GPU). To evaluate the efficiency of the proposed models, they were applied to the eastern drainage catchment (EDC) of Tehran city in Iran. More than 29,000 observed rainfall data were used for training and cross validating the proposed models. The results illustrated that the accuracy, coefficient of determination, of the ensemble models is at least 10% better than the DNNs in most rainfall events.

Towards the applicability of solar nowcasting: A practice on predictive PV power ramp-rate control

Solar forecasting has been widely adopted in modern power system operations to facilitate a reliable and continuous photovoltaic (PV) integration. Solar nowcasting, also known as intra-minute solar forecasting, is a new subdomain of solar forecasting. Nevertheless, despite the significant progress achieved in solar nowcasting over the last decade, one important aspect, that is, applicability—the value and operability of nowcasts in practical grid operations—is generally left out. To that end, this paper brings forth the applicability of solar nowcasting for the first time. Three time parameters involved in operational solar nowcasting are first identified, namely, forecast horizon, forecast resolution, and forecast model updating rate. Then paired with the state-of-the-art PV power ramp-rate control algorithm, i.e., predictive active power curtailment (PAPC), the effect of different time parameters is investigated, thus revealing the nowcasting applicability at large. Through four case studies and eight standardized deterministic and probabilistic solar nowcasting models, the applicability of solar nowcasting on PAPC is shown to be most characterized by the forecast horizon (up to a deviation of ramp smoothing rate around 12%, with smart persistence (SP) being the reference model), and least characterized by the forecast model updating rate (with a deviation of ramp smoothing rate less than 1% for SP). Moreover, the negatively-biased deterministic nowcasts and wider probabilistic nowcasts are found more applicable to PAPC. To promote solar nowcasting applicability on PAPC further, an outlook for future research is provided, from both a solar forecaster's and a system operator's viewpoints.

Learning from Precipitation Events in the Wider Domain to Improve the Performance of a Deep Learning–Based Precipitation Nowcasting Model

Abstract Deep learning models have been shown to perform well in terms of the radar-based precipitation nowcasting problem when compared with advection-based models. Yet, most of the existing literature has used locally trained models, and relatively little is known about how to construct deep learning–based nowcasting models applicable in wider domains. We conduct experiments for precipitation nowcasting using deep learning models spanning the region around Japan with the Japan Meteorological Agency radar precipitation dataset with 1-km spatial resolution and 5-min temporal resolution. We trained the model with radar data sampled from all over Japan, then applied transfer learning with regional data. Through this experiment, it is found that combining data from all over Japan is effective in improving the forecast performance of heavy precipitation with deep learning models. Significance Statement This paper proposes a methodological improvement for the problem of short-term rainfall forecasting (nowcasting) using deep learning. We trained deep learning models with data sampled from all over Japan, then applied transfer learning with regional data. We compared the performance metrics of several modeling approaches and demonstrated that learning from heavy precipitation examples collected from wider domains improves the performance significantly. This finding suggests that there are a lot of commonalities in the time evolution of rainfall patterns at different geographical locations, which could be exploited to improve the model’s performance. A future research topic could be to learn from a larger dataset, including precipitation datasets from other countries.

Smart flood resilience: harnessing community-scale big data for predictive flood risk monitoring, rapid impact assessment, and situational awareness

Smart resilience is the beneficial result of the collision course of the fields of data science and urban resilience to flooding. The objective of this study is to propose and demonstrate a smart flood resilience framework that leverages heterogeneous community-scale big data and infrastructure sensor data to enhance predictive risk monitoring and situational awareness. The smart flood resilience framework focuses on four core capabilities that could be augmented by the use of heterogeneous community-scale big data and analytics techniques: (1) predictive flood risk mapping; (2) automated rapid impact assessment; (3) predictive infrastructure failure prediction and monitoring; and (4) smart situational awareness capabilities. We demonstrate the components of these core capabilities of the smart flood resilience framework in the context of the 2017 Hurricane Harvey in Harris County, Texas. First, we present the use of flood sensors for the prediction of floodwater overflow in channel networks and inundation of co-located road networks. Second, we discuss the use of social media and machine learning techniques for assessing the impacts of floods on communities and sensing emotion signals to examine societal impacts. Third, we describe the use of high-resolution traffic data in network-theoretic models for nowcasting of flood propagation on road networks and the disrupted access to critical facilities, such as hospitals. Fourth, we introduce how location-based and credit card transaction data were used in spatial analyses to proactively evaluate the recovery of communities and the impacts of floods on businesses. These analyses show that the significance of core capabilities of the smart flood resilience framework in helping emergency managers, city planners, public officials, responders, and volunteers to better cope with the impacts of catastrophic flooding events.

Measuring tourism demand nowcasting performance using a monotonicity test

Tourism demand nowcasting is generally carried out using econometric models that incorporate either macroeconomic variables or search query data as explanatory variables. Nowcasting model accuracy is normally evaluated by traditional loss functions. This study proposes a novel statistical method, the monotonicity test, to assess whether the nowcasting errors obtained from the ordinary least squares, generalised dynamic factor model and generalised dynamic factor model combined with mixed data sampling model are monotonically decreasing when new data on explanatory variables become available, based on the mixed frequency data between 1 January 2011 and 31 December 2019. The results of the empirical analysis show that nowcasts generated results based on two data sources combined are superior to that based on a single data source. Compared with traditional loss functions, the monotonicity test leads to a more objective and convincing nowcasting model performance. This study is the first attempt to evaluate tourism demand nowcasting performance using a monotonicity test.

Improving the cloud initialization in WRF-Solar with enhanced short-range forecasting functionality: The MAD-WRF model

In spite of WRF-Solar being a numerical weather prediction (NWP) model specifically tailored for solar energy applications, the model lacks a specific cloud initialization component to improve short-range predictions. To overcome this limitation we have combined the fundamental concepts of the Multi-sensor Advection Diffusion nowCast (MADCast) model of using satellite observations to detect the clouds and advect and diffuse the clouds within a NWP model, with the better cloud–aerosol–radiation physics of WRF-Solar, into a new model referred to as MAD-WRF. The MAD-WRF cloud initialization combines a cloud parameterization that infers the presence of clouds based on relative humidity with observations of the cloud mask and cloud top/base height to provide a three-dimensional cloud analysis (liquid, ice, and snow hydrometeor content). During the forecasts, the hydrometeors can be advected and diffused with no microphysics, in what we refer to as the MAD-WRF passive mode. Alternatively, these passive hydrometeors can be integrated into the explicitly resolved hydrometeors during a nudging phase, designated the MAD-WRF active mode. In the nudging phase, there is a relaxation of the resolved hydrometeors towards the passive hydrometeors. Both modes aim to avoid an abrupt dissipation of clouds if the atmospheric environment is not adequate to support them. Both MAD-WRF active and passive modes as well as WRF-Solar have been run in a demonstration of MAD-WRF over the contiguous U.S., and results from these short-range forecasts (0–6 h) are presented here to illustrate the added value of MAD-WRF for global horizontal irradiance predictions. These results clearly illustrate the added value that MAD-WRF brings for short term irradiance predictions with the WRF-Solar model.