Search

In the context of a resilient energy system, accurate residential load forecasting has become a non-trivial requirement for ensuring effective management and planning strategy/policy development. Due to the highly stochastic nature of energy load profiles, it is difficult to predict accurately, and usually, predictions are error-prone. This paper explores the potential of Empirical Mode Decomposition (EMD) in simplifying the dynamics of complex demand profiles. The simplified components are then embedded within a deep learning model, specifically Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM), to forecast short-term residential loads. The novel modelling framework integrates Bayesian optimisation strategy, feature decomposition technique, feature engineering phase, and percentile-based bias correction algorithm to enhance model accuracy. The model is developed using a case-study residential dwelling located in Fintry (Scotland), and the model performance is assessed over four forecast horizons. The overall efficiency of framework is also investigated for three algorithms: random forest, gradient boosting decision trees (GBDT), and an LSTM network. While EMD and feature engineering were found to greatly improve prediction accuracy, the number of IMFs used was shown to significantly impact the model's performance and computational complexity. The model was tested on two further case studies from Fintry. • A novel forecasting framework is proposed for short-term energy demand prediction. • Multi-domain features are extracted to increase the accuracy. • Utilising empirical mode decomposition to enhance framework performance. • Exhibit strong forecasting capability without the additional computational cost. • Excellent forecasting accuracy and model robustness are validated using three households. [ABSTRACT FROM AUTHOR]

This paper presents a new data-driven modelling framework for forecasting probabilistic flood inundation maps for real-time applications. The proposed end-to-end (rainfall–inundation) method combines a suite of machine learning (ML) algorithms to forecast discharge and deliver probabilistic flood inundation maps with a 3 h lead time. To classify wet/dry cells, the method applies rainfall–discharge models based on random forest technique on top of classifiers based on multi-layer perceptron. The hybrid modelling framework was tested using two subsets of data created from an observed fluvial flood event in a small flood-prone town in the UK. The results showed that the model can effectively emulate the outcomes of a hydrodynamic model (Flood Modeller (FM)) with considerably high accuracy measured in terms of flood arrival time error and classification accuracy. The mean arrival time difference between the proposed model and the hydrodynamic model was 1 h 53 min. The classification accuracy was measured against a synthetic aperture radar image, producing accuracies of 88.22% and 86.58% for the proposed data-driven model and FM, respectively. The key features of the proposed modelling framework are that it is simple to implement, detects flooded cells effectively and substantially reduces computational time. [ABSTRACT FROM AUTHOR]

Load forecasting necessitates a significant amount of smart meter data. Several elements in this process, including device malfunctions and signal transmission issues, produce missing data gaps. Missing values in the dataset significantly influence the learning ability of machine learning algorithms, and they must be infilled before proceeding with any statistical analysis. This paper investigates the handling of missing values in demand data, and a new approach is developed for improving the performance of demand analytics, such as energy forecasting. The proposed model uses a transformer neural network to impute the missing values at various rates in the demand profile. Our model uses a k-means algorithm to fill in the missing values with proxy values in the dataset. The model is applied to two case-study residential house located in Cornwall and Fintry, United Kingdom. The developed algorithm is assessed for it potential for infilling missing values for three widely understood missing value scenarios: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). The proposed model's imputed outputs are compared to the original dataset to assess model performance. The performance of the framework is compared with a selection of widely used statistical and machine learning models. The proposed transformer model shows significant improvements over the common linear method in all three scenarios (with 30% missing values), with percentage improvements ranging from approximately 49.71% to 57.52% for Cornwall dataset. • A novel imputation framework is proposed for energy demand data. • Testing the model for infilling missing values with MCAR, MAR, MNAR scenarios • Evaluating the model performance in comparison with established benchmark approaches. • Utilising a transformer network to enhance data imputation performance. • Excellent imputation accuracy and model robustness are validated by two datasets. [ABSTRACT FROM AUTHOR]

This paper presents a systematic investigation into modelling capacities of three conventional data-driven modelling techniques, namely, wavelet-based artificial neural network (WANN), support vector regression (SVR) and deep belief network (DBN) for multi-step ahead stream flow forecasting. To evaluate the effectiveness of these modelling techniques, hydro-meteorological hourly datasets from three case-study rivers located in the UK have been used. A heuristic performance analysis of the modelling schemes has been conducted by systematically analysing the key statistics that measure magnitude, scatter and density of model errors. Finally, for each of the modelling techniques, the performance deterioration rate in time was estimated. The results show that the SVR model can forecast quite accurately up to one to two hours ahead but its performance deteriorates gradually from three hours onwards. Further it has been found that the WANN model performs better when the overall non-linearity of the system increases, whereas the DBN model appeared to show consistently poor predictive capabilities when compared to the other models presented herein. The authors conclude by stating that, for any selected model, it is possible to use an identical model structure for up to two steps ahead forecasting. Models need to be re-configured beyond that limit. [ABSTRACT FROM AUTHOR]

Typically, the analysis and design of fluvial flood defence schemes is based on a single N year extreme flow event using a single survey of the river channel and flood plains. Adopting this approach assumes that the channel capacity is identical for all subsequent N year events. If one assumes that the typical design life for a flood defence scheme is of the order of 50 years, then such an approach is flawed because river channel morphology, and hence flood conveyance, may change considerably over this time scale. Therefore, to provide a more robust estimate of future flood inundation, a sensitivity analysis of these changes should be undertaken. This paper proposes a modeling methodology that combines a stochastic model, for estimating streamflow throughout the design period, and a 1D sediment transport model (HEC-RAS), to enable this sensitivity to be included in flood inundation modeling and defence scheme design. The methodology is demonstrated through conceptual implementation to evaluate the change in water surface elevation (WSE) along an alluvial river (River Caldew, England) reach after 50 years of sediment transport. Changes in WSE are assessed when the reach is natural (no flood defences) and modified (with idealized flood defences). Results show that the construction of the flood defence scheme does not alter the overall morphological pattern of the reach but can significantly increase (260%) local aggradation. Additionally, 50 years of morphological change have the potential to increase WSE such that high flows, previously confined within the channel, can overtop the banks and become flood events; and that, the standard freeboard levels of the flood defence scheme may be insufficient to prevent overtopping when morphological change is considered. The method can be considered as a semiquantitative modeling methodology to account for the sediment-related sensitivity of flood risk management; and provides valuable insights into the potential magnitude that this has on future flood inundation. [ABSTRACT FROM AUTHOR]

Estimation of daily streamflow time series is of paramount importance for the design and implementation of river engineering and management projects (e.g., restoration, sediment-transport modelling, hydropower). Traditionally, indirect approaches combining stochastic simulation of rainfall with hydrological rainfall-runoff models are used. However, these are limited by uncertainties in model calibration and computational expense. Thus, this paper demonstrates an alternative, direct approach, for stochastic modelling of daily streamflow data, specifically seeking to address wellknown deficiencies in model capability to capture extreme flow events in the simulated time series. Combinations of a hidden Markov model (HMM) with the generalised extreme value (HMM-GEV) and generalised Pareto (HMM-GP) distributions were tested for four hydrologically contrasting catchments in the UK (Rivers Dee, Falloch, Caldew and Lud), with results compared to recorded flow data and estimations obtained from a simpler autoregressive-moving-average (ARMA) model. Results show that the HMM-GP method is superior in performance over alternative approaches (relative mean absolute differences (RMAD) of <2% across all catchments), appropriately captures extreme events and is generically applicable across a range of hydrological regimes. In contrast, the ARMA model was unable to capture the flow regime successfully (average RMAD of 14% across all catchments). [ABSTRACT FROM AUTHOR]

Building energy use associated with non-domestic buildings accounts for approximately 19% of the total UK CO 2 emissions. Energy consumption in a non-domestic building is a complex issue due to a wide variety of uses and energy services and therefore the energy demand of individual buildings need to be understood. A pilot study was undertaken to analyse the relationship between the electrical energy demand profiles and user activities for a university building. To gain insight into how the building is used, operated and managed on a daily basis, an online questionnaire was distributed to staff and students as well as interviews conducted with key management personnel. Analysis was performed on the half-hourly electrical demand data for the case-study building to identify key trends and patterns in energy use. The shape and magnitude of energy demand profiles show a significant trend which does not seem to be strongly connected to occupancy patterns. It was found that the building was mostly controlled by a building management system (BMS) where building users have minimal access to the controls. However, it was interesting to find that the detailed information on the occupancy patterns could help the management team to redesign control strategies for optimum energy performance of the building. [ABSTRACT FROM AUTHOR]

Abstract: Climate change could substantially impact the performance of the buildings in providing thermal comfort to occupants. Recently launched UK climate projections (UKCP09), clearly indicate that all areas of the UK will get warmer in future with the possibility of more frequent and severe extreme events, such as heat waves. This study, as part of the Low Carbon Futures (LCF) Project, explores the consequent risk of overheating and the vulnerability of a building to extreme events. A simple statistical model proposed by the LCF project elsewhere has been employed to emulate the outputs of the dynamic building simulator (ESP-r) which cannot feasibly be used itself with thousands of available probabilistic climate database. Impact of climate change on the daily external and internal temperature profiles has been illustrated by means of 3D plots over the entire overheating period (May–October) and over 3000 equally probable future climates. Frequency of extreme heat events in changing climate and its impact on overheating issues for a virtual case study domestic house has been analyzed. Results are presented relative to a baseline climate (1961–1990) for three future timelines (2030s, 2050s, and 2080s) and three emission scenarios (Low, Medium, and High). [Copyright &y& Elsevier]

Abstract: The effect of projected climate change on building performance is currently a growing research area. Building designers and architects are becoming more concerned that buildings designed for the current climate might not provide adequate working and living environments in the coming decades. Advice is needed to guide how existing buildings might be adapted to cope with this future climate, as well as guidance for new building design to reduce the chances of the building failing in the future. The Low Carbon Futures Project, as part of the Adaptation and Resilience to Climate Change (ARCC) programme in the UK, is looking at methods of integrating the latest climate projections from the UK Climate Impact Programme (UKCIP) into building simulation procedures. The main obstacle to this objective is that these projections are probabilistic in nature; potentially thousands of equally-probably climate-years can be constructed that describe just a single scenario. The project is therefore developing a surrogate procedure that will use regression techniques to assimilate this breadth of climate information into the building simulation process. [Copyright &y& Elsevier]

Water is essential to all lifeforms including various ecological, geological, hydrological, and climatic processes/activities. With the changing climate, associated El Niño/Southern Oscillation (ENSO) events appear to stimulate highly uncertain patterns of precipitation (P) and evapotranspiration ( E V ) processes across the globe. Changes in P and E V patterns are highly sensitive to temperature (T) variation and thus also affect natural streamflow processes. This paper presents a novel suite of stochastic modelling approaches for associating streamflow sequences with climatic trends. The present work is built upon a stochastic modelling framework (HMM_GP) that integrates a hidden Markov model (HMM) with a generalised Pareto (GP) distribution for simulating synthetic flow sequences. The GP distribution within the HMM_GP model aims to improve the model's efficiency in effectively simulating extreme events. This paper further investigated the potential of generalised extreme value distribution (GEV) coupled with an HMM model within a regression-based scheme for associating the impacts of precipitation and evapotranspiration processes on streamflow. The statistical characteristic of the pioneering modelling schematic was thoroughly assessed for its suitability to generate and predict synthetic river flow sequences for a set of future climatic projections, specifically during ENSO events. The new modelling schematic can be adapted for a range of applications in hydrology, agriculture, and climate change. [ABSTRACT FROM AUTHOR]

• A CNN model is proposed to estimate flood water depths. • The model can predict water depths for over half of a million cells instantly. • The CNN can potentially be used as a surrogate model for real-time applications. • The benefit of using CNN over other ML methods for flood modelling is presented. Most of the two-dimensional (2D) hydraulic/hydrodynamic models are still computationally too demanding for real-time applications. In this paper, an innovative modelling approach based on a deep convolutional neural network (CNN) method is presented for rapid prediction of fluvial flood inundation. The CNN model is trained using outputs from a 2D hydraulic model (i.e. LISFLOOD-FP) to predict water depths. The pre-trained model is then applied to simulate the January 2005 and December 2015 floods in Carlisle, UK. The CNN predictions are compared favourably with the outputs produced by LISFLOOD-FP. The performance of the CNN model is further confirmed by benchmarking against a support vector regression (SVR) method. The results show that the CNN model outperforms SVR by a large margin. The CNN model is highly accurate in capturing flooded cells as indicated by several quantitative assessment matrices. The estimated error for reproducing maximum flood depth is 0–0.2 m for the 2005 event and 0–0.5 m for the 2015 event at over 99% of the cells covering the computational domain. The proposed CNN method offers great potential for real-time flood modelling/forecasting considering its simplicity, superior performance and computational efficiency. [ABSTRACT FROM AUTHOR]

Toxic heavy metals in soil negatively impact soil's physical, biological, and chemical characteristics, and also human wellbeing. The traditional approach of chemical analysis procedures for assessing soil toxicant element concentration is time-consuming and expensive. Due to accessibility, reliability, and rapidity at a high temporal and spatial resolution, hyperspectral remote sensing within the Vis-NIR region is an indispensable and widely used approach in today's world for monitoring broad regions and controlling soil arsenic (As) pollution in agricultural land. This study investigates the effectiveness of hyperspectral reflectance approaches in different regions for assessing soil As pollutants, as well as a basic review of space-borne earth observation hyperspectral sensors. Multivariate and various regression models were developed to avoid collinearity and improve prediction capabilities using spectral bands with the perfect correlation coefficients to access the soil As contamination in previous studies. This review highlights some of the most significant factors to consider when developing a remote sensing approach for soil As contamination in the future, as well as the potential limits of employing spectroscopy data. [ABSTRACT FROM AUTHOR]

Integrating renewable energy technologies into a decentralised smart grid presents the 'Duck Curve' challenge — the disparity between peak demand and solar photovoltaic (PV) yield. Smart grid operators still lack an effective solution to this problem, resulting in the need to maintain standby fossil fuel-fired plants. The COVID-19 pandemic-induced lockdowns necessitated a shift to remote work (work-from-home) and home-based education. The primary objective of this study was to explore mitigating strategies for the duck curve challenge by investigating this notable shift in behaviour by examining the effect of remote work and education on grid and decentralised solar PV electricity use in 100 households with battery energy storage in the southwest of the UK. This study examined 1-min granular grid electricity and decentralised solar energy consumption data for April–August 2019 and 2020. The findings revealed statistically significant disparities in energy demand. Notably, there was a 1.4—10% decrease in average electricity consumption from April to August 2020 (during and following the lockdown) compared to the corresponding months of 2019. Furthermore, household grid electricity consumption was reduced by 24—25%, while self-consumption from solar PV systems increased by 7—8% during the lockdown in April and May 2020 compared to 2019. This increase in self-consumption was particularly prominent in the morning and afternoon, possibly attributed to the growing prevalence of work-from-home and home-based education. The dynamic shifts in energy consumption patterns emphasised the role of decentralised solar PV energy in meeting the evolving needs of households during unprecedented societal changes. Additionally, remote work might unlock decentralised solar PV's potential in resolving the 'Duck Curve', urging further investigation into the implications for energy infrastructure and policy development. • Analysed 1-minutely grid and decentralised solar PV energy demand data from 100 houses in a southwestern UK city. • Average electricity consumption decreased by 1.4—10% in April—August 2020 compared to 2019. • Grid electricity consumption was reduced by 24—25%, and from solar PV self-consumption increased by 7—8%. • Increased solar PV self-consumption was prominent in the morning and afternoon. • Might unlock solar PV's potential of resolving the 'Duck Curve.' [ABSTRACT FROM AUTHOR]

Droughts cause critical and major risk to ecosystems, agriculture, and social life. While attempts have been made globally to understand drought characteristics, data scarcity in developing countries often challenges detailed analysis, including climatic, environmental, and social aspects. Therefore, this study developed a framework to investigate regional drought analysis (RDA) using regional drought intensity-duration-frequency (RD-IDF) curves and regional drought risk assessment (RDRA) based on the drought hazard indicator (DHI) and drought vulnerability indicator (DVI) for scarce data regions in Afghanistan. The drought characteristics were analyzed using the regional standardized-precipitation-index (SPI), and standardized precipitation-deficit distribution (SPDD). Further, L-moment statistics were used to classify different homogenous regions based on regional frequency analysis (RFA). The historical monthly precipitation data from 23 rainfall stations for the years 1970 to 2016 were collected from the Ministry of Water and Energy of Afghanistan. Based on the analysis performed, the area was classified into six homogeneous regions R-1, R-2, R-3, R-4, R-5, and R-6. The drought was very consistent—almost 50% of the years—irrespective of the homogeneous region classified. R-4, located in the northeast of the country, had a one-year extreme drought with high resiliency and low risk to drought compared to other regions. As R-1, R-3 and R-5 are located in the southwest, center and southeast parts of Afghanistan, they experience moderate drought with low resiliency and high drought risk due to long period of droughts. Moreover, the uniform distribution of precipitation deficit (Dm), was less in arid climate regions. In contrast, the semi-arid climate regions showed higher values of Dm. Furthermore, in the results in all the regions, the IDF curves showed a high drought intensity with increasing drought return periods. In contrast, the intensity significantly decreased when the time scale increased, and fewer were enhanced within the increasing drought return period. However, the outcome of this study may contain essential information for end users to make spatially advanced planning for drought effect mitigation in Afghanistan. [ABSTRACT FROM AUTHOR]

Abstract Rivers are among the ecosystems most sensitive to climate change. Whilst methods quantifying the impact and uncertainty of climate change on flow regime are well-established, the impact on hydroecological response is not well understood. Typically, investigative methods are qualitative in nature or follow quantitative methods of limited scope, whilst the effect of uncertainty is frequently minimised. This paper proposes a coupled hydrological and hydroecological modelling framework to assess the impact of climate change on hydroecological response quantitatively. The characterisation and reduction of modelling uncertainties was critical to the development of the framework. The ability of the framework is illustrated through application to a case study river, the River Nar, Norfolk, England, using the UKCP09 probabilistic climate projections (high emissions scenario, SRES A1F1). The results show that, by the 2050s, a reduction in instream biodiversity is virtually certain if future emissions follow the assumptions of SRES A1F1. Disruption to the natural low flow processes, essential to ecosystem functioning, is also indicated. These findings highlight the importance of the framework in water resources adaptation, particularly with respect to future environmental flows management. Highlights • We propose a modelling framework to assess hydroecological response to climate change. • Characterisation and reduction of uncertainty considered throughout. • Provides quantifiable measure of the uncertainty in the hydroecological projections. • Case study sees reduced instream biodiversity and disruption to flow processes. [ABSTRACT FROM AUTHOR]

Recent studies suggest that 80 % of the estimated 1.5 million private sewage systems (PSS) in the UK are working inefficiently, potentially threatening drinking water quality and human health, as well as providing a significant source of phosphorus (P) to freshwater bodies, increasing vulnerability to eutrophication. In this report we explore pro-environmental behaviours of PSS users that potentially offer significant reduction in both PSS system failure and P discharge by 1) reducing P input to the PSS by modifying domestic behaviour, and 2) reducing the risk of PSS failure by improving maintenance of the PSS. A detailed questionnaire of 156 PSS users in the catchment of Loch Leven, Scotland, UK, revealed 70 % of users feel responsible for maintaining their PSS, 46 % are potentially maintaining them ineffectively, nearly 30 % have poorly installed systems and 45 % report their PSS had, at some point, blocked or overflowed. Our results indicate that the most effective action to improve PSS operation would be to provide better guidance on low P lifestyles and correct PSS maintenance with an improvement in the provision of facilities to support these pro-environmental behaviours. [ABSTRACT FROM AUTHOR]

The condition of the soil environment is critical for human health and agricultural sustainability. As a result, the environmental and ecological issues impacting the soils throughout the world are receiving more attention. This research focuses on local site-specific studies in Cerrito Blanco, Matehuala municipality, San Luis Potosi, Mexico, and describes different types of GIS interpolation techniques, multivariate statistical analysis, and various contamination indices to investigate the relationship between predictive accuracy, levels of contamination risk, and soil toxic metal elements variation. Inductively coupled plasma optical emission spectroscopy (ICP-EOS) used to test 39 digested surface soil samples for significant toxic metals (Ag, Cd, Co, Cr, Li, and Ni) after suitable dilution with deionised water. According to the results, we found that only the mean value of cadmium (Cd) exceeded the permissible standard value. After evaluating the four types of interpolation techniques, the Inverse Distance Weighting (IDW) was determined to be the optimal interpolation model for assessing the spatial distribution patterns of toxic metal concentration in the research area. The calculated contamination risk indices showed no significant high contamination risk due to soil-borne toxic metals. These results provide a comprehensive analysis of the impact of past mining activities on toxic metal concentrations in non-cultivated surface soil. • The study addresses the research of different approaches of contamination assessment techniques to identify the toxic metal contaminations in the surface soil. • The study exploits the estimation of the contamination risk level of toxic heavy metals. • The study discusses GIS interpolation techniques as well as multivariate statistical analysis which were used for spatial distribution. [ABSTRACT FROM AUTHOR]

Freshwater biodiversity is a major determinant of ecosystem functionality and hence the provision of ecosystem services. Despite this, freshwater biodiversity is declining rapidly around the globe. Coupled with the impact of climate change, there are growing concerns about the long-term sustainability of our water resources. Methods investigating hydroecological response (flow~ecology) have, typically, been qualitative in nature or quantitative with limited scope, whilst the effect of uncertainty (e.g. parameter, structural, emissions scenario) is rarely considered. To address this research gap, the author's proposed a coupled hydrological and hydroecological modelling framework in an earlier work. The framework was developed using an English chalk stream, the River Nar, a SSSI in Norfolk, south-east England, where the coupled model was run for a single scenario (SRES A1FI) and 30-year time slice (2041-2070). Building on this, here we consider both change in river health over time (from the 2030s to the end of century) as well as the implications for ecosystem functionality. To this end, we consider the same case study river, eliminating the need for model calibration, thereby allowing the focus to be on the outputs. Probabilistic climate projections from the UKCP09 Weather Generator serve as input to the coupled model; specifically, the high emissions scenario. The results focus on the 99-100% probability, consistent with the IPCC's definition of a virtually certain outcome. The LIFE index served as the proxy for river health. Results showed that, from 2021 to the end-of- the century, inter-annual variation in hydroecological response becomes more heterogeneous. Over the IQR, this change is relatively gradually, with change at the tails indicating an almost complete loss of variability by the 2030s. The overall trend indicates an increased probability and magnitude of extreme responses, with less internal variability. This level of change has major implications for the structure of the macroinvertebrate community, and hence on ecosystem functionality. A functional matrix revealed that all functional flow preferences are only met at intermediate flows (LIFE 6-8). Under more extreme conditions, they are effectively 'knocked out'. Despite the limited range of the functional feeding groups on the baseline, the River Nar has been able to adapt to extreme events due to inter-annual variation. In the future, this variation is greatly reduced, raising real concerns over the resilience of the river ecosystem. Further, increases in duration of hydro-hazards as reported in other studies could exacerbate threats to an increasingly vulnerable riverine ecosystem. With manifest impacts of climate change in the river expected as early as the 2030s, the outlook for the River Nar is not promising. A large part of this low resilience may be attributed to the pressures on the river. The River Nar is not alone in this, overall, English chalk streams are in a poor state of health, largely for similar reasons. Therefore, our findings are likely to be more widely applicable to the 200+ chalk streams in England. However, this is not and should not be considered a foregone conclusion, as there remains the opportunity to intervene via improved river management. [ABSTRACT FROM AUTHOR]

A correction to the article "Assessing Pro-environmental Behaviour in Relation to the Management of Pollution from Private Sewage Systems" is presented.