skip to main content

Title: Excess demand prediction for bike sharing systems
One of the most crucial elements for the long-term success of shared transportation systems (bikes, cars etc.) is their ubiquitous availability. To achieve this, and avoid having stations with no available vehicle, service operators rely on rebalancing . While different operators have different approaches to this functionality, overall it requires a demand-supply analysis of the various stations. While trip data can be used for this task, the existing methods in the literature only capture the observed demand and supply rates. However, the excess demand rates (e.g., how many customers attempted to rent a bike from an empty station) are not recorded in these data, but they are important for the in-depth understanding of the systems’ demand patterns that ultimately can inform operations like rebalancing. In this work we propose a method to estimate the excess demand and supply rates from trip and station availability data. Key to our approach is identifying what we term as excess demand pulse (EDP) in availability data as a signal for the existence of excess demand. We then proceed to build a Skellam regression model that is able to predict the difference between the total demand and supply at a given station during a specific more » time period. Our experiments with real data further validate the accuracy of our proposed method. « less
Authors:
;
Editors:
Chiabaut, Nicolas
Award ID(s):
1739413
Publication Date:
NSF-PAR ID:
10295474
Journal Name:
PLOS ONE
Volume:
16
Issue:
6
Page Range or eLocation-ID:
e0252894
ISSN:
1932-6203
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract
    Excessive phosphorus (P) applications to croplands can contribute to eutrophication of surface waters through surface runoff and subsurface (leaching) losses. We analyzed leaching losses of total dissolved P (TDP) from no-till corn, hybrid poplar (Populus nigra X P. maximowiczii), switchgrass (Panicum virgatum), miscanthus (Miscanthus giganteus), native grasses, and restored prairie, all planted in 2008 on former cropland in Michigan, USA. All crops except corn (13 kg P ha−1 year−1) were grown without P fertilization. Biomass was harvested at the end of each growing season except for poplar. Soil water at 1.2 m depth was sampled weekly to biweekly for TDP determination during March–November 2009–2016More>>
  2. Hydropower is the largest renewable energy source for electricity generation in the world, with numerous benefits in terms of: environment protection (near-zero air pollution and climate impact), cost-effectiveness (long-term use, without significant impacts of market fluctuation), and reliability (quickly respond to surge in demand). However, the effectiveness of hydropower plants is affected by multiple factors such as reservoir capacity, rainfall, temperature and fluctuating electricity demand, and particularly their complicated relationships, which make the prediction/recommendation of station operational output a difficult challenge. In this paper, we present DeepHydro, a novel stochastic method for modeling multivariate time series (e.g., water inflow/outflow andmore »temperature) and forecasting power generation of hydropower stations. DeepHydro captures temporal dependencies in co-evolving time series with a new conditioned latent recurrent neural networks, which not only considers the hidden states of observations but also preserves the uncertainty of latent variables. We introduce a generative network parameterized on a continuous normalizing flow to approximate the complex posterior distribution of multivariate time series data, and further use neural ordinary differential equations to estimate the continuous-time dynamics of the latent variables constituting the observable data. This allows our model to deal with the discrete observations in the context of continuous dynamic systems, while being robust to the noise. We conduct extensive experiments on real-world datasets from a large power generation company consisting of cascade hydropower stations. The experimental results demonstrate that the proposed method can effectively predict the power production and significantly outperform the possible candidate baseline approaches.« less
  3. Abstract

    Water supply infrastructure planning in groundwater-dependent regions is often challenged by uncertainty in future groundwater resource availability. Many major aquifer systems face long-term water table decline due to unsustainable withdrawals. However, many regions, especially those in the developing world, have a scarcity of groundwater data. This creates large uncertainties in groundwater resource predictions and decisions about whether to develop alternative supply sources. Developing infrastructure too soon can lead to unnecessary and expensive irreversible investments, but waiting too long can threaten water supply reliability. This study develops an adaptive infrastructure planning framework that applies Bayesian learning on groundwater observations tomore »assess opportunities to learn about groundwater availability in the future and adapt infrastructure plans. This approach allows planners in data scarce regions to assess under what conditions a flexible infrastructure planning approach, in which initial plans are made but infrastructure development is deferred, can mitigate the risk of overbuilding infrastructure while maintaining water supply reliability in the face of uncertainty. This framework connects engineering options analysis from infrastructure planning to groundwater resources modeling. We demonstrate a proof-of-concept on a desalination planning case for the city of Riyadh, Saudi Arabia, where poor characterization of a fossil aquifer creates uncertainty in how long current groundwater resources can reliably supply demand. We find that a flexible planning approach reduces the risk of over-building infrastructure compared to a traditional static planning approach by 40% with minimal reliability risk (<1%). This striking result may be explained by the slow-evolving nature of groundwater decline, which provides time for planners to react, in contrast to more sudden risks such as flooding where tradeoffs between cost and reliability risk are heightened. This Bayesian approach shows promise for many civil infrastructure domains by providing a method to quantify learning in environmental modeling and assess the effectiveness of adaptive planning.

    « less
  4. BACKGROUND The availability of nitrogen (N) to plants and microbes has a major influence on the structure and function of ecosystems. Because N is an essential component of plant proteins, low N availability constrains the growth of plants and herbivores. To increase N availability, humans apply large amounts of fertilizer to agricultural systems. Losses from these systems, combined with atmospheric deposition of fossil fuel combustion products, introduce copious quantities of reactive N into ecosystems. The negative consequences of these anthropogenic N inputs—such as ecosystem eutrophication and reductions in terrestrial and aquatic biodiversity—are well documented. Yet although N availability is increasingmore »in many locations, reactive N inputs are not evenly distributed globally. Furthermore, experiments and theory also suggest that global change factors such as elevated atmospheric CO 2 , rising temperatures, and altered precipitation and disturbance regimes can reduce the availability of N to plants and microbes in many terrestrial ecosystems. This can occur through increases in biotic demand for N or reductions in its supply to organisms. Reductions in N availability can be observed via several metrics, including lowered nitrogen concentrations ([N]) and isotope ratios (δ 15 N) in plant tissue, reduced rates of N mineralization, and reduced terrestrial N export to aquatic systems. However, a comprehensive synthesis of N availability metrics, outside of experimental settings and capable of revealing large-scale trends, has not yet been carried out. ADVANCES A growing body of observations confirms that N availability is declining in many nonagricultural ecosystems worldwide. Studies have demonstrated declining wood δ 15 N in forests across the continental US, declining foliar [N] in European forests, declining foliar [N] and δ 15 N in North American grasslands, and declining [N] in pollen from the US and southern Canada. This evidence is consistent with observed global-scale declines in foliar δ 15 N and [N] since 1980. Long-term monitoring of soil-based N availability indicators in unmanipulated systems is rare. However, forest studies in the northeast US have demonstrated decades-long decreases in soil N cycling and N exports to air and water, even in the face of elevated atmospheric N deposition. Collectively, these studies suggest a sustained decline in N availability across a range of terrestrial ecosystems, dating at least as far back as the early 20th century. Elevated atmospheric CO 2 levels are likely a main driver of declines in N availability. Terrestrial plants are now uniformly exposed to ~50% more of this essential resource than they were just 150 years ago, and experimentally exposing plants to elevated CO 2 often reduces foliar [N] as well as plant-available soil N. In addition, globally-rising temperatures may raise soil N supply in some systems but may also increase N losses and lead to lower foliar [N]. Changes in other ecosystem drivers—such as local climate patterns, N deposition rates, and disturbance regimes—individually affect smaller areas but may have important cumulative effects on global N availability. OUTLOOK Given the importance of N to ecosystem functioning, a decline in available N is likely to have far-reaching consequences. Reduced N availability likely constrains the response of plants to elevated CO 2 and the ability of ecosystems to sequester carbon. Because herbivore growth and reproduction scale with protein intake, declining foliar [N] may be contributing to widely reported declines in insect populations and may be negatively affecting the growth of grazing livestock and herbivorous wild mammals. Spatial and temporal patterns in N availability are not yet fully understood, particularly outside of Europe and North America. Developments in remote sensing, accompanied by additional historical reconstructions of N availability from tree rings, herbarium specimens, and sediments, will show how N availability trajectories vary among ecosystems. Such assessment and monitoring efforts need to be complemented by further experimental and theoretical investigations into the causes of declining N availability, its implications for global carbon sequestration, and how its effects propagate through food webs. Responses will need to involve reducing N demand via lowering atmospheric CO 2 concentrations, and/or increasing N supply. Successfully mitigating and adapting to declining N availability will require a broader understanding that this phenomenon is occurring alongside the more widely recognized issue of anthropogenic eutrophication. Intercalibration of isotopic records from leaves, tree rings, and lake sediments suggests that N availability in many terrestrial ecosystems has steadily declined since the beginning of the industrial era. Reductions in N availability may affect many aspects of ecosystem functioning, including carbon sequestration and herbivore nutrition. Shaded areas indicate 80% prediction intervals; marker size is proportional to the number of measurements in each annual mean. Isotope data: (tree ring) K. K. McLauchlan et al. , Sci. Rep. 7 , 7856 (2017); (lake sediment) G. W. Holtgrieve et al. , Science 334 , 1545–1548 (2011); (foliar) J. M. Craine et al. , Nat. Ecol. Evol. 2 , 1735–1744 (2018)« less
  5. The problem of traffic prediction is paramount in a plethora of applications, ranging from individual trip planning to urban planning. Existing work mainly focuses on traffic prediction on road networks. Yet, public transportation contributes a significant portion to overall human mobility and passenger volume. For example, the Washington, DC metro has on average 600,000 passengers on a weekday. In this work, we address the problem of modeling, classifying and predicting such passenger volume in public transportation systems. We study the case of the Washington, DC metro exploring fare card data, and specifically passenger in- and outflow at stations. To reducemore »dimensionality of the data, we apply principal component analysis to extract latent features for different stations and for different calendar days. Our unsupervised clustering results demonstrate that these latent features are highly discriminative. They allow us to derive different station types (residential, commercial, and mixed) and to effectively classify and identify the passenger flow of “unknown” stations. Finally, we also show that this classification can be applied to predict the passenger volume at stations. By learning latent features of stations for some time, we are able to predict the flow for the following hours. Extensive experimentation using a baseline neural network and two naïve periodicity approaches shows the considerable accuracy improvement when using the latent feature based approach.« less