Urban transformations have profound societal impact on both individuals and communities at large. Accurately assessing these shifts is essential for understanding their underlying causes and ensuring sustainable urban planning. Traditional measurements often encounter constraints in spatial and temporal granularity, failing to capture real-time physical changes. While street view imagery, capturing the heartbeat of urban spaces in a pedestrian point of view, can add as a high-definition, up-to-date, and on-the-ground visual proxy of urban change. We curate the largest street view time series dataset to date, and propose an end-to-end change detection model to effectively capture physical alterations in the built environment at scale. We demonstrate the effectiveness of our proposed method by benchmark comparisons with previous literature and implementing it at the city-wide level. Our approach has the potential to supplement existing dataset and serve as a fine-grained and accurate assessment of urban change.

Remote sensing imagery, despite its broad applications in helping achieve Sustainable Development Goals and tackle climate change, has not yet benefited from the recent advancements of versatile, task-agnostic vision language models (VLMs). A key reason is that the large-scale, semantically diverse image-text dataset required for developing VLMs is still absent for remote sensing images. Unlike natural images, remote sensing images and their associated text descriptions cannot be efficiently collected from the public Internet at scale. In this work, we bridge this gap by using geo-coordinates to automatically connect open, unlabeled remote sensing images with rich semantics covered in OpenStreetMap, and thus construct SkyScript, a comprehensive vision-language dataset for remote sensing images, comprising 2.6 million image-text pairs covering 29K distinct semantic tags. With continual pre-training on this dataset, we obtain a VLM that surpasses baseline models with a 6.2% average accuracy gain in zero-shot scene classification across seven benchmark datasets. It also demonstrates the ability of zero-shot transfer for fine-grained object attribute classification and cross-modal retrieval. We hope this dataset can support the advancement of VLMs for various multi-modal tasks in remote sensing, such as open-vocabulary classification, retrieval, captioning, and text-to-image synthesis.

Vehicle damage localization and severity estimation is essential to post-accident assessments, with a traditional process taking an average of seven days and requiring substantial work from both customers and dealers. Towards improving this process, we propose an end-to-end system which inputs a set of user-acquired photographs of a vehicle after an accident and outputs a damage assessment report including the set of damaged parts and the type and size of the damage for each part. The system is composed of three deep learning modules: a model to identify whether a vehicle is present in the image, a model to localize the vehicle parts in the image, and a model to localize the damage in the image. We demonstrate the effectiveness of each module by evaluating them on labeled datasets containing images of vehicles after an accident, some collected by the OE (Original Equipment) Insured Fleet and some acquired by users of the OEM (Original Equipment Manufacturer) mobile application. We also describe how the modules fit together with a post-processing step to aggregate outputs between the different modules across multiple user-acquired views of the accident. Our approach demonstrates the potential for an accurate and automated vehicle damage estimation system to support a substantially more efficient vehicle damage assessment process.

Neighborhood gentrification plays a significant role in shaping the social and economic well-being of both individuals and communities at large. While some efforts have been made to detect gentrification in cities, existing approaches rely mainly on estimated measures from survey data, require substantial work of human labeling, and are limited in characterizing the neighborhood as a whole. We propose a novel approach to detecting neighborhood gentrification at a large-scale based on the physical appearance of neighborhoods by incorporating historical street-level visual data. We show the effectiveness of the proposed method by comparing results from our approach with gentrification measures from previous literature and case studies. Our approach has the potential to supplement existing indicators of gentrification and become a valid resource for urban researchers and policy makers.

Understanding intrinsic patterns and predicting spatiotemporal characteristics of cities require a comprehensive representation of urban neighborhoods. Existing works relied on either inter- or intra-region connectivities to generate neighborhood representations but failed to fully utilize the informative yet heterogeneous data within neighborhoods. In this work, we propose Urban2Vec, an unsupervised multi-modal framework which incorporates both street view imagery and point-of-interest (POI) data to learn neighborhood embeddings. Specifically, we use a convolutional neural network to extract visual features from street view images while preserving geospatial similarity. Furthermore, we model each POI as a bag-of-words containing its category, rating, and review information. Analog to document embedding in natural language processing, we establish the semantic similarity between neighborhood (“document”) and the words from its surrounding POIs in the vector space. By jointly encoding visual, textual, and geospatial information into the neighborhood representation, Urban2Vec can achieve performances better than baseline models and comparable to fully-supervised methods in downstream prediction tasks. Extensive experiments on three U.S. metropolitan areas also demonstrate the model interpretability, generalization capability, and its value in neighborhood similarity analysis.

Accurate electricity demand forecast plays a key role in sustainable power systems. It enables better decision making in the planning of electricity generation and distribution for many use cases. The electricity demand data can often be represented in a hierarchical structure. For example, the electricity consumption of a whole country could be disaggregated by states, cities, and households. Hierarchical forecasts require not only good prediction accuracy at each level of the hierarchy, but also the consistency between different levels. State-of-the-art hierarchical forecasting methods usually apply adjustments on the individual level forecasts to satisfy the aggregation constraints. However, the high-dimensionality of the unpenalized regression problem and the estimation errors in the high-dimensional error covariance matrix can lead to increased variability in the revised forecasts with poor prediction performance. In order to provide more robustness to estimation errors in the adjustments, we present a new hierarchical forecasting algorithm that computes sparse adjustments while still preserving the aggregation constraints. We formulate the problem as a high-dimensional penalized regression, which can be efficiently solved using cyclical coordinate descent methods. We also conduct experiments using a large-scale hierarchical electricity demand data. The results confirm the effectiveness of our approach compared to state-of-the-art hierarchical forecasting methods, in both the sparsity of the adjustments and the prediction accuracy. The proposed approach to hierarchical forecasting could be useful for energy generation including solar and wind energy, as well as numerous other applications.

The sixteen articles in this special section explore advances in communication technologies that have the potential for improving energy efficiency and realizing the smart grid vision. The articles tackle important challenges with respect to smart grid communications and include a wide range of topics such as electric load models, electric vehicle charging, models for demand response, power management optimization and storage, pricing, and security.

As a way to match peaks in demand to available supply in real-time on the power grid, energy utility companies employ Demand-Response (DR) strategies. With the recent deployment of advanced metering infrastructure collecting highly granular (sub-hourly) data on consumption from millions of users system operators may now understand how demand arises down to the individual level. In this paper we present an application of a dynamic model that describes residential users' thermally-sensitive consumption using hourly electricity and weather readings. We build rich profiles at individual and group levels that may be used to inform DR programs that focus on temperature-dependent consumption such as heating and cooling. We learn individual thermal profiles for a large user sample, and describe the seasonal and time-of-day distribution of thermal regimes. Finally, we build aggregate thermal profiles for geographically-homogeneous groups of different size. We argue that aggregation leads to regularity in temperature response of energy consumption, and characterize empirically the critical size of groups needed to achieve limiting regularity.

The drive towards more sustainable power supply systems has enabled significant growth of renewable generation. This in turn has pushed the rollout of demand response (DR) programs to address a larger population of consumers. Utilities are interested in enrolling small and medium sized customers that can provide demand curtailment during periods of shortfall in renewable production. It then becomes important to be able to target the right customers among the large population, since each enrollment has a cost. The availability of high resolution information about each consumers demand consumption can significantly change how such targeting is done. This paper develops a methodology for large scale targeting that combines data analytics and a scalable selection procedure. We propose an efficient customer selection method via stochastic knapsack problem solving and a simple response modeling in one example DR program. To cope with computation issues coming from the large size of data set, we design a novel approximate algorithm.

Truck weight data is used in many areas of transportation such as weight enforcement and pavement condition assessment. This paper describes a wireless sensor network (WSN) that estimates the weight of moving vehicles from pavement vibrations caused by vehicular motion. The WSN consists of: acceleration sensors that report pavement vibration; vehicle detection sensors that report a vehicle's arrival and departure times; and an access point (AP) that synchronizes all the sensors and records the sensor data. The paper also describes a novel algorithm that estimates a vehicle's weight from pavement vibration and vehicle detection data, and calculates pavement deflection in the process. A prototype of the system has been deployed near a conventional Weigh-In-Motion (WIM) system on I-80 W in Pinole, CA. Weights of 52 trucks at different speeds and loads were estimated by the system under different pavement temperatures and varying environmental conditions, adding to the challenges the system must overcome. The error in load estimates was less than 10% for gross weight and 15% for individual axle weights. Different states have different requirements for WIM but the system described here outperformed the nearby conventional WIM, and meets commonly used standards in United States. The system also opens up exciting new opportunities for WSNs in pavement engineering and intelligent transportation.

We propose a probabilistic formulation that enables sequential detection of multiple change points in a network setting. We present a class of sequential detection rules for functionals of change points, and prove their asymptotic optimality properties in terms of expected detection delay time. Drawing from graphical model formalism, the sequential detection rules can be implemented by a computationally efficient message-passing protocol which may scale up linearly in network size and in waiting time. The effectiveness of our exact and approximate inference algorithms are demonstrated by simulations.

The Internet has been evolving into a more heterogeneous internet work with diverse new applications imposing more stringent bandwidth and QoS requirements. Already such new applications such as YouTube, Hulu, and Netflix are consuming a large fraction of the total bandwidth. We argue that, in order to engineer future internets such that they can adequately cater to their increasingly diverse and complex set of applications while using resources efficiently, it is critical to be able to characterize the load that emerging and future applications place on the underlying network. In this paper, we investigate entropy as a metric for characterizing per-flow network traffic complexity. While previous work has analyzed aggregated network traffic, we focus on studying isolated traffic flows. Per-application flow characterization caters to the need of network control functions such as traffic scheduling and admission control at the edges of the network. Such control functions necessitate differentiating network traffic on a per-application basis. The "entropy fingerprints" that we get from our entropy estimator summarize many characteristics of each application's network traffic. Not only can we compare applications on the basis of peak entropy, but we can also categorize them based on a number of other properties of the fingerprints.

A system is described that measures the vehicle count and travel time in the links of a road network. The measurements require matching vehicle signatures recorded by a wireless magnetic sensor network. The matching algorithm is based on a statistical model of the signatures. The model itself is estimated from the data. The approach is first discussed for a single-lane road and extended to multiple-lane roads. The algorithm yields a correct matching rate of 75% for a false matching rate of 5% and reliably estimates the number of vehicles on each link and its travel-time distribution. The system is tested on a 0.9-mi-long segment of San Pablo Avenue, Albany, CA.

Monitoring its health by detecting its failed sensors is essential to the reliable functioning of any sensor network. This paper presents a distributed, online, sequential algorithm for detecting multiple faults in a sensor network. The algorithm works by detecting change points in the correlation statistics of neighboring sensors, requiring only neighbors to exchange information. The algorithm provides guarantees on detection delay and false alarm probability. This appears to be the first work to offer such guarantees for a multiple sensor network. Based on the performance guarantees, we compute a tradeoff between sensor node density, detection delay and energy consumption. We also address synchronization, finite storage and data quantization. We validate our approach with some example applications.

We consider the following problem of decentralized-statistical inference: given i.i.d. samples from an unknown distribution, estimate an arbitrary quantile subject to limits on the number of bits exchanged. We analyze a standard fusion-based architecture, in which each of m sensors transmits a single bit to the fusion center, which in turn is permitted to send some number k bits of feedback. Supposing that each of m sensors receives n observations, the mean-squared error of the optimal centralized protocol decays as O(1/nm). First, we describe the decentralized protocol based on k = m bits of feedback that is strongly consistent, and achieves the same asymptotic MSE as the centralized optimum. Second, we describe and analyze a decentralized protocol based on only a single bit (k = 1) of feedback. For step sizes independent of m, it achieves an asymptotic MSE of order O(1/nradicm), whereas for step sizes decaying as m-1/2, it achieves the same order of MSE - namely, O(1/nm) - as the centralized optimum. We discuss the tradeoffs between these different protocols

The concept of Riemannian geometries is used to construct induced homogeneous point sets on manifolds that are based on well-distributed point sets in unit cubes of an appropriately chosen Euclidean space. These well-distributed point sets in unit cubes are based on standard low-discrepancy sequences. The approach is algorithmic, that is, the methods developed in this article have been implemented and tested. Applications in image processing, graph theory and measurement-based exploration are presented.

The Makhoul Conjecture Challenge (Makhoul, 2000) has been published. To answer was the question whether or not the location of the peak of a digital stable all-pass filter lies in [0,2p-1], where p is the order of the all-pass filter. We construct numerous counter-examples, prove a new theorem stating that there is at least an upper bound on the order of p/sup 3/2/ for the location of the peak, and discuss the algebraic structure of all-pass filters and their impulse responses. The paper is heavily based on an experimental approach.