Search

This article explores the intertwining connections among artificial intelligence, machine learning, digital transformation, and computational sustainability, detailing how these elements jointly empower citizens within a smart city framework. As technological advancement accelerates, smart cities harness these innovations to improve residents' quality of life. Artificial intelligence and machine learning act as data analysis powerhouses, making urban living more personalized, efficient, and automated, and are pivotal in managing complex urban infrastructures, anticipating societal requirements, and averting potential crises. Digital transformation transforms city operations by weaving digital technology into every facet of urban life, enhancing value delivery to citizens. Computational sustainability, a fundamental goal for smart cities, harnesses artificial intelligence, machine learning, and digital resources to forge more environmentally responsible cities, minimize ecological impact, and nurture sustainable development. The synergy of these technologies empowers residents to make well-informed choices, actively engage in their communities, and adopt sustainable lifestyles. This discussion illuminates the mechanisms and implications of these interconnections for future urban existence, ultimately focusing on empowering citizens in smart cities. [ABSTRACT FROM AUTHOR]

This paper offers three contributions to the burgeoning movements of AI for Social Good (AI4SG) and AI and the United Nations Sustainable Development Goals (SDGs). First, we introduce the SDG-Intense Evaluation framework (SDGIE) that aims to situate variegated automated/AI models in a larger ecosystem of computational approaches to advance the SDGs. To foster knowledge collaboration for solving complex social and environmental problems encompassed by the SDGs, the SDGIE framework details a benchmark structure of data-algorithm-output to effectively standardize AI approaches to the SDGs. Second, as a specific instantiation of the SDGIE framework, the SDG Impact Intensity Model (SDGIIM) is theoretically and operationally established. SDGIIM embeds expert decision-making and SDG keyword banks in textual data processing to determine overall SDG "impact intensity." Ideally, SDGIIM can be applied to textual data sets from any sector or discipline: academia, business, government, non-profit, civil society, etc. Third, the SDGIIM instantiation is applied to the specific domain of academic journal rating systems as a case study. Traditionally, academic journals have been evaluated on loosely conceived and empirically shaky notions of 'quality.' Aligned with the trend of AI4SG and broader calls to action, 'impact' is rapidly becoming the primary normative consideration for assessing academic journals. We hypothesize and demonstrate that SDGIIM is capable of producing evaluations aligned with experts' expectations of SDG impact intensity; the consistent analysis and rating of textual data sets that embody the SDGs with varying degrees of meaning and, ultimately, promote positive impact on the actual material conditions of the world. [ABSTRACT FROM AUTHOR]

We study the problem of placing wildlife crossings, such as green bridges, over human-made obstacles to challenge habitat fragmentation. The main task herein is, given a graph describing habitats or routes of wildlife animals and possibilities of building green bridges, to find a low-cost placement of green bridges that connects the habitats. We develop three problem models for this task and study them from a computational complexity and parameterized algorithmics perspective. [ABSTRACT FROM AUTHOR]

The scarcity of potable water is a critical challenge in many regions around the world. Previous studies have shown that knowledge of device-level water usage can lead to significant conservation. Although there is considerable interest in determining discriminative features via sparse coding for water disaggregation to separate whole-house consumption into its component appliances, existing methods lack a mechanism for fitting coefficient distributions and are thus unable to accurately discriminate parallel devices’ consumption. This article proposes a Bayesian discriminative sparse coding model, referred to as Virtual Metering (VM), for this disaggregation task. Mixture-of-Gammas is employed for the prior distribution of coefficients, contributing two benefits: (i) guaranteeing the coefficients’ sparseness and non-negativity, and (ii) capturing the distribution of active coefficients. The resulting method effectively adapts the bases to aggregated consumption to facilitate discriminative learning in the proposed model, and devices’ shape features are formalized and incorporated into Bayesian sparse coding to direct the learning of basis functions. Compact Gibbs Sampling (CGS) is developed to accelerate the inference process by utilizing the sparse structure of coefficients. The empirical results obtained from applying the new model to large-scale real and synthetic datasets revealed that VM significantly outperformed the benchmark methods. [ABSTRACT FROM AUTHOR]

In this article, we address the interrelated challenges of predicting user comfort and using this to reduce energy consumption in smart heating, ventilation, and air conditioning (HVAC) systems. At present, such systems use simple models of user comfort when deciding on a set-point temperature. Being built using broad population statistics, these models generally fail to represent individual users’ preferences, resulting in poor estimates of the users’ preferred temperatures. To address this issue, we propose the Bayesian Comfort Model (BCM). This personalised thermal comfort model uses a Bayesian network to learn from a user’s feedback, allowing it to adapt to the users’ individual preferences over time. We further propose an alternative to the ASHRAE 7-point scale used to assess user comfort. Using this model, we create an optimal HVAC control algorithm that minimizes energy consumption while preserving user comfort. Through an empirical evaluation based on the ASHRAE RP-884 dataset and data collected in a separate deployment by us, we show that our model is consistently 13.2% to 25.8% more accurate than current models and how using our alternative comfort scale can increase our model’s accuracy. Through simulations we show that using this model, our HVAC control algorithm can reduce energy consumption by 7.3% to 13.5% while decreasing user discomfort by 24.8% simultaneously. [ABSTRACT FROM AUTHOR]

Spatial management of invasive species is more likely to be successful when multiple locations are treated simultaneously. However, selecting the best locations to act is difficult due to the many options available at any time., We design a near-optimal policy for applying multiple actions simultaneously for faster invasive species control within a network. Our method uses a recent optimisation tool, the graph-based Markov decision process (GMDP). Since the policy can be difficult to interpret, we extracted a simpler policy using classification trees. We applied our approach to the eradication of invasive mosquitofish Gambusia holbrooki from the habitat of the red-finned blue-eye Scaturiginichthys vermeilipinnis, a critically endangered fish with a global population that is restricted to seven artesian springs in Queensland, Australia., The policy returned by the GMDP was to manage springs occupied by mosquitofish and their connected neighbours, unless the neighbours were occupied by red-finned blue-eyes., Simultaneous management resulted in rapid declines in simulated mosquitofish occupancy even if eradication effectiveness was low; however, the cost of simultaneous eradication was high and sustained eradication effort was necessary to maintain low mosquitofish occupancy., Synthesis and applications. Our paper finds a near-optimal, multi-action control policy to remove an invasive species from a multi-species spatial network. We introduce the graph-based Markov decision process and apply it to a real case study - eradication of invasive mosquitofish from the habitat of the red-finned blue-eye. We find that the graph-based Markov decision process can generate policies for networks with extremely large state spaces; however, it works best when nodes have fewer than five neighbours. We conclude that simultaneous eradications are effective for rapid control of invasive species; however, managers should consider the cost and time required for an effective eradication program. [ABSTRACT FROM AUTHOR]

Artificial intelligence techniques have been successfully applied to control dynamic systems looking for an optimal control. Among those techniques, reinforcement learning has been shown as particularly effective at reducing the dimensionality of some real problems and solving control problems by learning from experience. The use of thermal energy storage active systems in the building sector is identified as suitable option to reduce their energy demand for heating and cooling. However, these systems might be expensive and require appropriate control strategies in order to improve the performance of the building. In this paper a ventilated facade with PCM is controlled using a reinforcement learning algorithm. The ventilated facade uses mechanical ventilation during nighttime to solidify the PCM and releases this cold stored to the inner environment during the peak demand period. It is crucial to decide correctly the schedule of charge and discharge process of the PCM according to the weather and indoor conditions. An experimentally validated numerical model is used to test the performance of the control algorithm under different weather conditions. Important improvements on the energy savings due to the use of control strategies were found and supported by the data under the different tested climatic conditions. [ABSTRACT FROM AUTHOR]

A large fraction of the current environmental crisis derives from the large rates of human-driven biodiversity loss. Biodiversity conservation questions human practices towards biodiversity and, therefore, largely conflicts with ordinary societal aspirations. Decisions on the location of protected areas, one of the most convincing conservation tools, reflect such a competitive endeavor. Operations Research (OR) brings a set of analytical models and tools capable of resolving the conflicting interests between ecology and economy. Recent technological advances have boosted the size and variety of data available to planners, thus challenging conventional approaches bounded on optimized solutions. New models and methods are needed to use such a massive amount of data in integrative schemes addressing a large variety of concerns. This study provides an overview on the past, present and future challenges that characterize spatial conservation models supported by OR. We discuss the progress of OR models and methods in spatial conservation planning and how those models may be optimized through sophisticated algorithms and computational tools. Moreover, we anticipate possible panoramas of modern spatial conservation studies supported by OR and we explore possible avenues for the design of optimized interdisciplinary collaborative platforms in the era of Big Data, through consortia where distinct players with different motivations and services meet. By enlarging the spatial, temporal, taxonomic and societal horizons of biodiversity conservation, planners navigate around multiple socioecological/environmental equilibria and are able to decide on cost-effective strategies to improve biodiversity persistence under complex environments. [Display omitted] • Decision support models for effective biodiversity conservation are required. • Operations Research empowers decision making recurring to robust methods and theory. • Major challenges exist to the use of Operations Research in conservation planning. • A new generation of models need to integrate large datasets and high complexity. • Allying quantitative models with large empirical knowledge turns decisions successful. [ABSTRACT FROM AUTHOR]

Non-intrusive appliance load monitoring is the process of disaggregating a household's total electricity consumption into its contributing appliances. In this paper we propose an unsupervised training method for non-intrusive monitoring which, unlike existing supervised approaches, does not require training data to be collected by sub-metering individual appliances, nor does it require appliances to be manually labelled for the households in which disaggregation is performed. Instead, we propose an approach which combines a one-off supervised learning process over existing labelled appliance data sets, with an unsupervised learning method over unlabelled household aggregate data. First, we propose an approach which uses the Tracebase data set to build probabilistic appliance models which generalise to previously unseen households, which we empirically evaluate through cross validation. Second, we use the Reference Energy Disaggregation Data set to evaluate the accuracy with which these general models can be tuned to the appliances within a specific household using only aggregate data. Our empirical evaluation demonstrates that general appliance models can be constructed using data from only a small number of appliances (typically 3–6 appliances), and furthermore that 28–99% of the remaining behaviour which is specific to a single household can be learned using only aggregate data from existing smart meters. [ABSTRACT FROM AUTHOR]

Abstract: In a world where resources are scarce and urban areas consume the vast majority of these resources, it is vital to make cities greener and more sustainable. A smart city is a city in which information and communications technology are merged with traditional infrastructures, coordinated and integrated using new digital technologies. The increasing amount of waste generated, and the collection and treatment of waste poses a major challenge to modern urban planning in general, and to smart cities in particular. To cope with this problem, automated vacuum waste collection (AVWC) uses air suction on a closed network of underground pipes to transport waste from the drop off points scattered throughout the city to a central collection point, reducing greenhouse gas emissions and the inconveniences of conventional methods (odours, noise, etc.). Since a significant part of the cost of operating AVWC systems is energy consumption, we have developed a model with the aim of applying constraint programming technology to schedule the daily emptying sequences of the drop off points in such a way that energy consumption is minimized. In this paper we describe how the problem of deciding the drop off points that should be emptied at a given time can be modeled as a constraint integer programming (CIP) problem. Moreover, we report on experiments using real data from AVWC systems installed in different cities that provide empirical evidence that CIP offers a suitable technology for reducing energy consumption in AVWC. [Copyright &y& Elsevier]

This paper presents a proper orthogonal decomposition (POD)-based reduced-order modeling framework to improve spatial resolution of measured temperature data in an air-cooled data center. This data-driven approach is applied on transient air temperature data, acquired at the exhaust of a server simulator rack. Temperature data is collected by a distributed thermocouple network at 1 Hz sampling frequency following a step impulse in the rack heat load. The input data are organized in a 2-D array, comprising transient temperature signals measured at various spatial locations. Because its computational time scales logarithmically with the input size, the proposed POD-based approach is potentially useful as an efficient tool for handling large transient data sets. With spatial location being the parameter for the input data matrix, the proposed approach is suitable for rapid synthesis of transient temperature data at new spatial locations. The comparison between POD-based local air temperature predictions and corresponding data indicates a maximum prediction uncertainty of 3.2%, and root mean square prediction uncertainty of 1.9%. [ABSTRACT FROM AUTHOR]

We consider a dynamic Nash game among firms harvesting a renewable resource (e.g., in a fishery) and propose a differential variational inequality (DVI) framework for modeling and solving such a game. We suppose the firms compete over demand as well as over regulated harvest effort that we interpret as a sustainability constraint on the fleet's aggregate harvest effort. We suppose each firm is based in a home market that is not protected by trade barriers implying that each firm can sell its catch in any of the markets. Within this setting, we consider how harvest effort, catch, and sustainability of the resource are affected by the length of the planning horizon of the firms. We show results that contrast myopic planning versus long-term perspectives. To derive solutions for this game, we propose a DVI framework that is converted to a fixed-point problem. This allows us to employ a computationally efficient algorithm for the solution of the game. [ABSTRACT FROM AUTHOR]

Spatiotemporal planning involves making choices at multiple locations in space over some planning horizon to maximize utility and satisfy various constraints. In Forest Ecosystem Management, the problem is to choose actions for thousands of locations each year including harvesting, treating trees for fire or pests, or doing nothing. The utility models could place value on sale of lumber, ecosystem sustainability or employment levels and incorporate legal and logistical constraints on actions such as avoiding large contiguous areas of clearcutting. Simulators developed by forestry researchers provide detailed dynamics but are generally inaccesible black boxes. We model spatiotemporal planning as a factored Markov decision process and present a policy gradient planning algorithm to optimize a stochastic spatial policy using simulated dynamics. It is common in environmental and resource planning to have actions at different locations be spatially interelated; this makes representation and planning challenging. We define a global spatial policy in terms of interacting local policies defining distributions over actions at each location conditioned on actions at nearby locations. Markov chain Monte Carlo simulation is used to sample landscape policies and estimate their gradients. Evaluation is carried out on a forestry planning problem with 1,880 locations using a variety of value models and constraints. [ABSTRACT FROM AUTHOR]

Abstract: We develop methods for conservation resource allocation, to help with decisions about targeting of protection, habitat management, maintenance and restoration or biodiversity offsetting. We construct a framework, where conservation actions have different responses for different biodiversity features in different environments, and in which uncertainty in responses and the time perspective are explicitly considered. Costs of actions in different environments are also accounted for. Costs can be defined as constants, functions of time or as functions of the total area in which an action is performed. We optimize the combination of actions to maximize conservation value given uncertain responses, limited resources, different robustness requirements and limits to the area in which different actions can be undertaken. Accounting for the uncertainty in responses to actions or accounting for time can change the optimal combination of actions. We can account for both negative consequences of uncertainty (robustness analysis) and positive aspects of uncertainty (opportunity analysis). To allow for the complexity of the analysis above and to significantly reduce data demands, we have omitted an explicit spatial structure from these analyses. Nevertheless, we describe approaches that account for spatial considerations, for example, by using the present methods in combination with software that is intended for the spatial analysis of static biodiversity pattern. The proposed analyses have been implemented in a software package called RobOff, which will be made freely, publicly available. Thereby it is possible for the first time to effectively find solutions to a significant set of conservation resource allocation problems. These analyses can assist conservation scientists and managers in decision making based on quantitative analysis. [Copyright &y& Elsevier]

Abstract: Wildlife corridors connect areas of biological significance to mitigate the negative ecological impacts of habitat fragmentation. In this article we formalize the optimal corridor design as a connected subgraph problem, which maximizes the amount of suitable habitat in a fully connected parcel network linking core habitat areas, subject to a constraint on the funds available for land acquisition. To solve this challenging computational problem, we propose a hybrid approach that combines graph algorithms with Mixed Integer Programming-based optimization. We apply this technique to the design of corridors for grizzly bears in the U.S. Northern Rockies, illustrating the underlying computational complexities by varying the granularity of the parcels available for acquisition. The approach that is introduced is general and can be applied to other species or other similar problems, such as those occurring in social networks. [Copyright &y& Elsevier]

Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The “rawness” of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid. [ABSTRACT FROM PUBLISHER]